case study and peer review

• Open access
• Published: 06 April 2016

How to review a case report

• Rakesh Garg 1 ,
• Shaheen E. Lakhan 2 &
• Ananda K. Dhanasekaran 3  

Journal of Medical Case Reports volume  10 , Article number:  88 ( 2016 ) Cite this article

70k Accesses

19 Citations

3 Altmetric

Metrics details

Peer Review reports

Introduction

Sharing individual patient experiences with clinical colleagues is an essential component of learning from each other. This sharing of information may be made global by reporting in a scientific journal. In medicine, patient management decisions are generally based on the evidence available for use of a particular investigation or technology [ 1 ]. The hierarchical rank of the evidence signifies the probability of bias. The higher up the hierarchy, the better its reliability and thus its clinical acceptance (Table  1 ). Though case reports remain lowest in the hierarchy of evidence, with meta-analysis representing the highest level, they nevertheless constitute important information with regard to rare events and may be considered as anecdotal evidence [ 2 ] (Table  1 ). Case reports may stimulate the generation of new hypotheses, and thus may support the emergence of new research.

The definition of a case report or a case series is not well defined in the literature and has been defined variously by different journals and authors. However, the basic definition of a case report is the detailed report of an individual including aspects like exposure, symptoms, signs, intervention, and outcome. It has been suggested that a report with more than four cases be called a case series and those with fewer than four a case report [ 3 ]. A case series is descriptive in design. Other authors describe “a collection of patients” as a case series and “a few patients” as a case report [ 4 ]. We suggest that should more than one case be reported, it may be defined as a case series—a concept proposed by other authors [ 5 ].

The importance of case reports

A case report may describe an unusual etiology, an unusual or unknown disorder, a challenging differential diagnosis, an unusual setting for care, information that can not be reproduced due to ethical reasons, unusual or puzzling clinical features, improved or unique technical procedures, unusual interactions, rare or novel adverse reactions to care, or new insight into the pathogenesis of disease [ 6 , 7 ]. In recent years, the publication of case reports has been given low priority by many high impact factor journals. However, the need for reporting such events remains. There are some journals dedicated purely to case reports, such as the Journal of Medical Case Reports , emphasizing their importance in modern literature. In the past, isolated case reports have led to significant advancements in patient care. For example, case reports concerning pulmonary hypertension and anorexic agents led to further trials and the identification of the mechanism and risk factors associated with these agents [ 2 , 8 ].

Reporting and publishing requirements

The reporting of cases varies for different journals. The authors need to follow the instructions for the intended publication. Owing to significant variability, it would be difficult to have uniform publication guidelines for case reports. A checklist called the CARE guidelines is useful for authors writing case reports [ 9 , 10 ]. However, it would be universally prudent to include a title, keywords, abstract, introduction, patient information, clinical findings, timeline, diagnostic assessment, therapeutic interventions, follow-up and outcomes, discussion, patient perspective, and informed consent.

Peer review process

The peer review process is an essential part of ethical and scientific writing. Peer review ultimately helps improve articles by providing valuable feedback to the author and helps editors make a decision regarding publication. The peer reviewer should provide unbiased, constructive feedback regarding the manuscript. They may also highlight the strengths and weaknesses of the report. When reviewing an article, it is prudent to read the entire manuscript first to understand the overall content and message. The reviewer than may read section-wise and provide comments to the authors and editorial team accordingly. The reviewer needs to consider the following important points when reviewing a case for possible publication [ 8 , 9 ] (summarized in Table  2 ).

Novelty remains the foremost important aspect of a case. The case report should introduce novel aspects of patient evaluation, investigation, treatment, or any other aspect related to patient care. The relevant information becomes a hypothesis generator for further study. The novelty may at times be balanced with some important information like severe adverse effects, even if they have been reported earlier. Reporting adverse events remains important so that information on cumulative adverse effects can be gathered globally, which helps in preparing a policy or guideline or a warning note for its use in patients. The data related to adverse effects include not only the impact but also the number of patients affected. This becomes more important for serious adverse effects. In the absence of an international registry for adverse effects, published case reports are important pieces of information. Owing to ethical concerns, formal evaluation may not be feasible in the format of prospective study.

Essential description

The case needs to have all essential details to allow a useful conclusion to emerge. For example, if a case is being reported for hemodynamic variability due to a drug, then the drug dose and timing along with timed vital signs need to be described.

Authenticity and genuineness

Honesty remains the most important basic principle of all publications. This remains a primary responsibility of the authors. However, if there is any doubt, reviewers may seek clarification. This doubt may result from some discordance in the case description. At times, a lack of correlation between the figures and description may act as “red flags.” For instance, authors may discuss a technique for dealing with a difficult airway, but the figure is of a normal-appearing airway. Another example would be where the data and figure do not correlate in a hemodynamic response related to a drug or a technique, with the graphical picture or screenshot of hemodynamics acting as an alert sign. Such cause for concern may be communicated in confidence to the editor.

Ethical or competing interests

Ethical issues need to be cautiously interpreted and communicated. The unethical use of a drug or device is not desirable and often unworthy of publication. This may relate to the route or dose of the drug administered. The off-label use of drugs where known side effects are greater than potential benefit needs to be discouraged and remains an example of unethical use. This use may be related to the drug dose, particularly when the drug dose exceeds the routine recommended dose, or to the route of administration. As an example, the maximal dose of acetaminophen (paracetamol) is 4g/day, and if an author reports exceeding this dose, it should be noted why a greater than recommended dose was used. Ultimately, the use of a drug or its route of administration needs to be justified in the manuscript. The reviewers need to serve as content experts regarding the drugs and other technologies used in the case. A literature search by the reviewer provides the data to comment on this aspect.

Competing interests (or conflicts of interest) are concerns that interfere or potentially interfere with presentation, review, or publication. They must be declared by the authors. Conflicts can relate to patient-related professional attributes (like the use of a particular procedure, drug, or instrument) being affected by some secondary gains (financial, non-financial, professional, personal). Financial conflict may be related to ownership, paid consultancy, patents, grants, honoraria, and gifts. Non-financial conflicts may be related to memberships, relationships, appearance as an expert witness, or personal convictions. At times, the conflict may be related to the author’s relationship with an organization or another person. A conflict may influence the interpretation of the outcome in an inappropriate and unscientific manner. Although conflicts may not be totally abolished, they must be disclosed when they reasonably exist. This disclosure should include information such as funding sources, present membership, and patents pending. Reviewers should cautiously interpret any potential bias regarding the outcome of the case based on the reported conflicts. This is essential for transparent reporting of research. At times, competing interests may be discovered by a reviewer and should be included in comments to the editorial team. Such conflicts may again be ascertained when the reviewer reviews the literature during the peer review process. The reviewer should also disclose their own conflicts related to the manuscript review when sending their report to the editorial team.

Impact on clinical practice

This is an important aspect for the final decision of whether to publish a case report. The main thrust or carry-home message needs to be emphasized clearly. It needs to be elaborated upon in concluding remarks.

Patient anonymity, consent, and ethical approval

When reviewing the manuscript of a case report, reviewers should ensure that the patient’s anonymity and confidentiality is protected. The reviewers should check that patient identifiers have been removed or masked from all aspects of the manuscript, whether in writing or within photograph. Identifiers can include things like the name of the patient, geographical location, date of birth, phone numbers, email of the patient, medical record numbers, or biometric identifiers. Utmost care needs to be taken to provide full anonymity for the patient.

Consent is required to participate in research, receive a certain treatment, and publish identifiable details. These consents are for different purposes and need to be explained separately to the patient. A patient’s consent to participate in the research or for use of the drug may not extend to consent for publication. All these aspects of consent must be explained to the patient, written explicitly in the patient’s own language, understood by the patient, and signed by the patient. For the purpose of the case, the patient must understand and consent for any new technique or drug (its dose, route, and timing) being used. In the case of a drug being used for a non-standard indication or route, consent for use must also be described. Patient consent is essential for the publication of a case if patient body parts are displayed in the article. This also includes any identifiers that can reveal the identity of the patient, such as the patient’s hospital identification number, address, and any other unique identifier. In situations where revealing the patient’s identity cannot be fully avoided, for example if the report requires an image of an identifiable body part like the face, then this should be explained to the patient, the image shown to them, and consent taken. Should the patient die, then consent must be obtained from next of kin or legal representative.

With case series, securing individual patient consent is advised and preferable. The authors may also need institutional review board (IRB) approval to publish a case series. IRBs can waive the need for consent if a study is conducted retrospectively and data are collected from patient notes for the purpose of research, usually in an anonymized way. However, wherever possible, individual patient consent is preferable, even for a retrospective study. Consent is mandatory for any prospective data collection for the purpose of publication as a case series. Consent and/or IRB approval must be disclosed in the case report and reasons for not obtaining individual consent may be described, if applicable.

There may be situations in which publishing patient details without their consent is justified, but this is a decision that should be made by the journal editor, who may decide to discuss the case with the Committee on Publication Ethics. Reviewers need to emphasize the issue to the editor when submitting their comments.

Manuscript writing

The CARE guidelines provide a framework that supports transparency and accuracy in the publication of case reports and the reporting of information from patient encounters. The acronym CARE was created from CA (the first two letters in “case”) and RE (the first two letters in “reports”). The initial CARE tools are the CARE checklist and the Case Report Writing Templates. These tools support the writing of case reports and provide data that inform clinical practice guidelines and provide early signals of effectiveness, harms, and cost [ 10 ].

The presentation of the case and its interpretation should be comprehensive and related. The various components of the manuscript should have sufficient information for understanding the key message of the case. The reviewer needs to comment on the relevant components of the manuscript. The reviewer should ascertain that the title of the case manuscript is relevant and includes keywords related to the case. The title should be short, descriptive, and interesting. The abstract should be brief, without any abbreviations, and include keywords. It is preferable to use Medical Subject Headings (MeSH) keywords. Reviewers must ensure that the introduction emphasizes the context of the case and describes the relevance and its importance in a concise and comprehensive manner. The case description should be complete and should follow basic rules of medical communication. The details regarding patient history, physical examination, investigations, differential diagnosis, management, and outcome should be described in chronological order. If repeated observations are present, then they may be tabulated. The use of graphs and figures helps the readers to better understand the case. Interpretation or inferences based on the outcomes should be avoided in this section and should be considered a part of the discussion. The discussion should highlight important aspects of the case, with its interpretation within the context of the available literature. References should be formatted as per the journal style. They should be complete and preferably of recent publications.

Reviewer responsibility

The reviewer’s remarks are essential not only for the editorial team but also for authors. A good peer review requires honesty, sincerity, and punctuality. Even if a manuscript is rejected, the authors should receive learning points from peer review commentary. The best way to review a manuscript is to read the manuscript in full for a gross overview and develop general comments. Thereafter, the reviewer should address each section of the manuscript separately and precisely. This may be done after a literature search if the reviewer needs to substantiate his/her commentary.

Constructive criticism

The reviewer’s remarks should be constructive to help the authors improve the manuscript for further consideration. If the manuscript is rejected, the authors should have a clear indication for the rejection. The remarks may be grouped as major and minor comments. Major comments likely suggest changes to the whole presentation, changing the primary aim of the case report, or adding images. Minor comments may include grammatical errors or getting references for a statement. The editorial team must be able to justify their decision on whether or not to accept an article for publication, often by citing peer review feedback. It is also good style to tabulate a list of the strengths and weaknesses of the manuscript.

Fixed time for review

Reviewer remarks should be submitted within a specified timeframe. If any delay is expected, it should be communicated to the editorial team. Reviewers should not rush to submit feedback without sufficient time to adequately review the paper and perform any necessary literature searches. Should a reviewer be unable to submit the review within the specified timeframe, they should reply to the review invitation to decline at their earliest convenience. If, after accepting a review invitation, the reviewer realizes they do not have time to perform the review, this must be communicated to the editorial team.

Conflict of interest

The reviewer’s conflicts of interest should be included along with the review. The conflicts may be related to the contents of the case, drugs, or devices pertaining to the case; the author(s); or the affiliated institution(s) of the author(s).

Lack of expertise

The reviewer may decline to review the manuscript if they think the topic is out of their area of expertise. If, after accepting an invitation to review, the reviewer realizes they are unable to review the manuscript owing to a lack of expertise in that particular field, they should disclose the fact to the editorial team.

Confidentiality

The reviewer should keep the manuscript confidential and should not use the contents of the unpublished manuscript in any form. Discussing the manuscript among colleagues or any scientific forum or meetings is inappropriate.

Review of revised manuscript

At times, a manuscript is sent for re-review to the reviewer. The reviewer should read the revised manuscript, the author’s response to the previous round of peer review, and the editorial comments. Sometimes, the authors may disagree with the reviewer’s remarks. This issue needs to be elaborated on and communicated with the editor. The reviewer should support their views with appropriate literature references. If the authors justify their reason for disagreeing with the viewer, then their argument should be considered evidence-based. However, if the reviewer still requests the revision, this may be politely communicated to the author and editor with justification for the same. In response to reviewers remarks, authors may not agree fully and provide certain suggestion in the form of clarification related to reviewers remarks. The reviewers should take these clarifications judiciously and comment accordingly with the intent of improving the manuscript further.

Peer reviewers have a significant role in the dissemination of scientific literature. They act as gatekeepers for science before it is released to society. Their sincerity and dedication is paramount to the success of any journal. The reviewers should follow a scientific and justifiable methodology for reviewing a case report for possible publication. Their comments should be constructive for the overall improvement of the manuscript and aid the editorial team in making a decision on publication. We hope this article will help reviewers to perform their important role in the best way possible. We send our best wishes to the reviewer community and, for those who are inspired to become reviewers after reading this article, our warm welcome to the reviewers’ club.

Burns PB, Rohrich RJ, Chung KC. The levels of evidence and their role in evidence-based medicine. Plast Reconstr Surg. 2011;128:305–10.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Green BN, Johnson CD. How to write a case report for publication. J Chiropr Med. 2006;5:72–82.

Article   PubMed   PubMed Central   Google Scholar  

Abu-Zidan FM, Abbas AK, Hefny AF. Clinical “case series”: a concept analysis. Afr Health Sci. 2012;12:557–62.

CAS   PubMed   PubMed Central   Google Scholar  

Porta M, editor. A dictionary of epidemiology/edited for the International Epidemiological Association. 5th ed. UK: Oxford University Press; 2008. p. 33.

Medical Research Council of South Africa. Evidence-based medicine. 2016. http://www.mrc.ac.za/healthsystems/sai.htm . Accessed on 1 Nov 2015.

Cohen H. How to write a patient case report. Am J Health-Syst Pharm. 2006;63:1888–92.

Article   PubMed   Google Scholar  

Roberts LW, Coverdale J, Edenharder K, Louie A. How to review a manuscript: a “down-to-earth” approach. Acad Psychiatry. 2004;28:81–7.

Rutowski JL, Cairone JV. How to review scientific manuscripts and clinical case reports for Journal of Oral Implantology. J Oral Implantol. 2009;35:310–4.

Article   Google Scholar  

Jabs DA. Improving the reporting of clinical case series. Am J Ophthalmol. 2005;139:900–5.

Gagnier JJ, Kienle G, Altman DG, Moher D, Sox H, Riley D; CARE Group. The CARE guidelines: consensus-based clinical case reporting guideline development. BMJ Case Reports. 2013; doi: 10.1136/bcr-2013-201554 .

Download references

Author information

Authors and affiliations.

Department of Anaesthesiology, Pain and Palliative Care, DR BRAIRCH, AIIMS, Ansari Nagar, New Delhi, 110029, India

Rakesh Garg

Neurology and Medical Education, California University of Science and Medicine - School of Medicine, Colton, CA, USA

Shaheen E. Lakhan

Sandwell & West Birmingham Hospitals, NHS Trust, Birmingham, UK

Ananda K. Dhanasekaran

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Rakesh Garg .

Additional information

Competing interests.

The authors declare that they have no competing interests.

Authors’ contributions

All authors read and approved the final manuscript.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License ( http://creativecommons.org/licenses/by/4.0/ ), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated.

Reprints and permissions

About this article

Cite this article.

Garg, R., Lakhan, S.E. & Dhanasekaran, A.K. How to review a case report. J Med Case Reports 10 , 88 (2016). https://doi.org/10.1186/s13256-016-0853-3

Download citation

Received : 27 August 2015

Accepted : 25 February 2016

Published : 06 April 2016

DOI : https://doi.org/10.1186/s13256-016-0853-3

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Journal of Medical Case Reports

ISSN: 1752-1947

• Submission enquiries: Access here and click Contact Us
• General enquiries: [email protected]

• Open access
• Published: 10 November 2020

Case study research for better evaluations of complex interventions: rationale and challenges

• Sara Paparini   ORCID: orcid.org/0000-0002-1909-2481 1 ,
• Judith Green 2 ,
• Chrysanthi Papoutsi 1 ,
• Jamie Murdoch 3 ,
• Mark Petticrew 4 ,
• Trish Greenhalgh 1 ,
• Benjamin Hanckel 5 &
• Sara Shaw 1  

BMC Medicine volume  18 , Article number:  301 ( 2020 ) Cite this article

17k Accesses

41 Citations

35 Altmetric

Metrics details

The need for better methods for evaluation in health research has been widely recognised. The ‘complexity turn’ has drawn attention to the limitations of relying on causal inference from randomised controlled trials alone for understanding whether, and under which conditions, interventions in complex systems improve health services or the public health, and what mechanisms might link interventions and outcomes. We argue that case study research—currently denigrated as poor evidence—is an under-utilised resource for not only providing evidence about context and transferability, but also for helping strengthen causal inferences when pathways between intervention and effects are likely to be non-linear.

Case study research, as an overall approach, is based on in-depth explorations of complex phenomena in their natural, or real-life, settings. Empirical case studies typically enable dynamic understanding of complex challenges and provide evidence about causal mechanisms and the necessary and sufficient conditions (contexts) for intervention implementation and effects. This is essential evidence not just for researchers concerned about internal and external validity, but also research users in policy and practice who need to know what the likely effects of complex programmes or interventions will be in their settings. The health sciences have much to learn from scholarship on case study methodology in the social sciences. However, there are multiple challenges in fully exploiting the potential learning from case study research. First are misconceptions that case study research can only provide exploratory or descriptive evidence. Second, there is little consensus about what a case study is, and considerable diversity in how empirical case studies are conducted and reported. Finally, as case study researchers typically (and appropriately) focus on thick description (that captures contextual detail), it can be challenging to identify the key messages related to intervention evaluation from case study reports.

Whilst the diversity of published case studies in health services and public health research is rich and productive, we recommend further clarity and specific methodological guidance for those reporting case study research for evaluation audiences.

Peer Review reports

The need for methodological development to address the most urgent challenges in health research has been well-documented. Many of the most pressing questions for public health research, where the focus is on system-level determinants [ 1 , 2 ], and for health services research, where provisions typically vary across sites and are provided through interlocking networks of services [ 3 ], require methodological approaches that can attend to complexity. The need for methodological advance has arisen, in part, as a result of the diminishing returns from randomised controlled trials (RCTs) where they have been used to answer questions about the effects of interventions in complex systems [ 4 , 5 , 6 ]. In conditions of complexity, there is limited value in maintaining the current orientation to experimental trial designs in the health sciences as providing ‘gold standard’ evidence of effect.

There are increasing calls for methodological pluralism [ 7 , 8 ], with the recognition that complex intervention and context are not easily or usefully separated (as is often the situation when using trial design), and that system interruptions may have effects that are not reducible to linear causal pathways between intervention and outcome. These calls are reflected in a shifting and contested discourse of trial design, seen with the emergence of realist [ 9 ], adaptive and hybrid (types 1, 2 and 3) [ 10 , 11 ] trials that blend studies of effectiveness with a close consideration of the contexts of implementation. Similarly, process evaluation has now become a core component of complex healthcare intervention trials, reflected in MRC guidance on how to explore implementation, causal mechanisms and context [ 12 ].

Evidence about the context of an intervention is crucial for questions of external validity. As Woolcock [ 4 ] notes, even if RCT designs are accepted as robust for maximising internal validity, questions of transferability (how well the intervention works in different contexts) and generalisability (how well the intervention can be scaled up) remain unanswered [ 5 , 13 ]. For research evidence to have impact on policy and systems organisation, and thus to improve population and patient health, there is an urgent need for better methods for strengthening external validity, including a better understanding of the relationship between intervention and context [ 14 ].

Policymakers, healthcare commissioners and other research users require credible evidence of relevance to their settings and populations [ 15 ], to perform what Rosengarten and Savransky [ 16 ] call ‘careful abstraction’ to the locales that matter for them. They also require robust evidence for understanding complex causal pathways. Case study research, currently under-utilised in public health and health services evaluation, can offer considerable potential for strengthening faith in both external and internal validity. For example, in an empirical case study of how the policy of free bus travel had specific health effects in London, UK, a quasi-experimental evaluation (led by JG) identified how important aspects of context (a good public transport system) and intervention (that it was universal) were necessary conditions for the observed effects, thus providing useful, actionable evidence for decision-makers in other contexts [ 17 ].

The overall approach of case study research is based on the in-depth exploration of complex phenomena in their natural, or ‘real-life’, settings. Empirical case studies typically enable dynamic understanding of complex challenges rather than restricting the focus on narrow problem delineations and simple fixes. Case study research is a diverse and somewhat contested field, with multiple definitions and perspectives grounded in different ways of viewing the world, and involving different combinations of methods. In this paper, we raise awareness of such plurality and highlight the contribution that case study research can make to the evaluation of complex system-level interventions. We review some of the challenges in exploiting the current evidence base from empirical case studies and conclude by recommending that further guidance and minimum reporting criteria for evaluation using case studies, appropriate for audiences in the health sciences, can enhance the take-up of evidence from case study research.

Case study research offers evidence about context, causal inference in complex systems and implementation

Well-conducted and described empirical case studies provide evidence on context, complexity and mechanisms for understanding how, where and why interventions have their observed effects. Recognition of the importance of context for understanding the relationships between interventions and outcomes is hardly new. In 1943, Canguilhem berated an over-reliance on experimental designs for determining universal physiological laws: ‘As if one could determine a phenomenon’s essence apart from its conditions! As if conditions were a mask or frame which changed neither the face nor the picture!’ ([ 18 ] p126). More recently, a concern with context has been expressed in health systems and public health research as part of what has been called the ‘complexity turn’ [ 1 ]: a recognition that many of the most enduring challenges for developing an evidence base require a consideration of system-level effects [ 1 ] and the conceptualisation of interventions as interruptions in systems [ 19 ].

The case study approach is widely recognised as offering an invaluable resource for understanding the dynamic and evolving influence of context on complex, system-level interventions [ 20 , 21 , 22 , 23 ]. Empirically, case studies can directly inform assessments of where, when, how and for whom interventions might be successfully implemented, by helping to specify the necessary and sufficient conditions under which interventions might have effects and to consolidate learning on how interdependencies, emergence and unpredictability can be managed to achieve and sustain desired effects. Case study research has the potential to address four objectives for improving research and reporting of context recently set out by guidance on taking account of context in population health research [ 24 ], that is to (1) improve the appropriateness of intervention development for specific contexts, (2) improve understanding of ‘how’ interventions work, (3) better understand how and why impacts vary across contexts and (4) ensure reports of intervention studies are most useful for decision-makers and researchers.

However, evaluations of complex healthcare interventions have arguably not exploited the full potential of case study research and can learn much from other disciplines. For evaluative research, exploratory case studies have had a traditional role of providing data on ‘process’, or initial ‘hypothesis-generating’ scoping, but might also have an increasing salience for explanatory aims. Across the social and political sciences, different kinds of case studies are undertaken to meet diverse aims (description, exploration or explanation) and across different scales (from small N qualitative studies that aim to elucidate processes, or provide thick description, to more systematic techniques designed for medium-to-large N cases).

Case studies with explanatory aims vary in terms of their positioning within mixed-methods projects, with designs including (but not restricted to) (1) single N of 1 studies of interventions in specific contexts, where the overall design is a case study that may incorporate one or more (randomised or not) comparisons over time and between variables within the case; (2) a series of cases conducted or synthesised to provide explanation from variations between cases; and (3) case studies of particular settings within RCT or quasi-experimental designs to explore variation in effects or implementation.

Detailed qualitative research (typically done as ‘case studies’ within process evaluations) provides evidence for the plausibility of mechanisms [ 25 ], offering theoretical generalisations for how interventions may function under different conditions. Although RCT designs reduce many threats to internal validity, the mechanisms of effect remain opaque, particularly when the causal pathways between ‘intervention’ and ‘effect’ are long and potentially non-linear: case study research has a more fundamental role here, in providing detailed observational evidence for causal claims [ 26 ] as well as producing a rich, nuanced picture of tensions and multiple perspectives [ 8 ].

Longitudinal or cross-case analysis may be best suited for evidence generation in system-level evaluative research. Turner [ 27 ], for instance, reflecting on the complex processes in major system change, has argued for the need for methods that integrate learning across cases, to develop theoretical knowledge that would enable inferences beyond the single case, and to develop generalisable theory about organisational and structural change in health systems. Qualitative Comparative Analysis (QCA) [ 28 ] is one such formal method for deriving causal claims, using set theory mathematics to integrate data from empirical case studies to answer questions about the configurations of causal pathways linking conditions to outcomes [ 29 , 30 ].

Nonetheless, the single N case study, too, provides opportunities for theoretical development [ 31 ], and theoretical generalisation or analytical refinement [ 32 ]. How ‘the case’ and ‘context’ are conceptualised is crucial here. Findings from the single case may seem to be confined to its intrinsic particularities in a specific and distinct context [ 33 ]. However, if such context is viewed as exemplifying wider social and political forces, the single case can be ‘telling’, rather than ‘typical’, and offer insight into a wider issue [ 34 ]. Internal comparisons within the case can offer rich possibilities for logical inferences about causation [ 17 ]. Further, case studies of any size can be used for theory testing through refutation [ 22 ]. The potential lies, then, in utilising the strengths and plurality of case study to support theory-driven research within different methodological paradigms.

Evaluation research in health has much to learn from a range of social sciences where case study methodology has been used to develop various kinds of causal inference. For instance, Gerring [ 35 ] expands on the within-case variations utilised to make causal claims. For Gerring [ 35 ], case studies come into their own with regard to invariant or strong causal claims (such as X is a necessary and/or sufficient condition for Y) rather than for probabilistic causal claims. For the latter (where experimental methods might have an advantage in estimating effect sizes), case studies offer evidence on mechanisms: from observations of X affecting Y, from process tracing or from pattern matching. Case studies also support the study of emergent causation, that is, the multiple interacting properties that account for particular and unexpected outcomes in complex systems, such as in healthcare [ 8 ].

Finally, efficacy (or beliefs about efficacy) is not the only contributor to intervention uptake, with a range of organisational and policy contingencies affecting whether an intervention is likely to be rolled out in practice. Case study research is, therefore, invaluable for learning about contextual contingencies and identifying the conditions necessary for interventions to become normalised (i.e. implemented routinely) in practice [ 36 ].

The challenges in exploiting evidence from case study research

At present, there are significant challenges in exploiting the benefits of case study research in evaluative health research, which relate to status, definition and reporting. Case study research has been marginalised at the bottom of an evidence hierarchy, seen to offer little by way of explanatory power, if nonetheless useful for adding descriptive data on process or providing useful illustrations for policymakers [ 37 ]. This is an opportune moment to revisit this low status. As health researchers are increasingly charged with evaluating ‘natural experiments’—the use of face masks in the response to the COVID-19 pandemic being a recent example [ 38 ]—rather than interventions that take place in settings that can be controlled, research approaches using methods to strengthen causal inference that does not require randomisation become more relevant.

A second challenge for improving the use of case study evidence in evaluative health research is that, as we have seen, what is meant by ‘case study’ varies widely, not only across but also within disciplines. There is indeed little consensus amongst methodologists as to how to define ‘a case study’. Definitions focus, variously, on small sample size or lack of control over the intervention (e.g. [ 39 ] p194), on in-depth study and context [ 40 , 41 ], on the logic of inference used [ 35 ] or on distinct research strategies which incorporate a number of methods to address questions of ‘how’ and ‘why’ [ 42 ]. Moreover, definitions developed for specific disciplines do not capture the range of ways in which case study research is carried out across disciplines. Multiple definitions of case study reflect the richness and diversity of the approach. However, evidence suggests that a lack of consensus across methodologists results in some of the limitations of published reports of empirical case studies [ 43 , 44 ]. Hyett and colleagues [ 43 ], for instance, reviewing reports in qualitative journals, found little match between methodological definitions of case study research and how authors used the term.

This raises the third challenge we identify that case study reports are typically not written in ways that are accessible or useful for the evaluation research community and policymakers. Case studies may not appear in journals widely read by those in the health sciences, either because space constraints preclude the reporting of rich, thick descriptions, or because of the reported lack of willingness of some biomedical journals to publish research that uses qualitative methods [ 45 ], signalling the persistence of the aforementioned evidence hierarchy. Where they do, however, the term ‘case study’ is used to indicate, interchangeably, a qualitative study, an N of 1 sample, or a multi-method, in-depth analysis of one example from a population of phenomena. Definitions of what constitutes the ‘case’ are frequently lacking and appear to be used as a synonym for the settings in which the research is conducted. Despite offering insights for evaluation, the primary aims may not have been evaluative, so the implications may not be explicitly drawn out. Indeed, some case study reports might properly be aiming for thick description without necessarily seeking to inform about context or causality.

Acknowledging plurality and developing guidance

We recognise that definitional and methodological plurality is not only inevitable, but also a necessary and creative reflection of the very different epistemological and disciplinary origins of health researchers, and the aims they have in doing and reporting case study research. Indeed, to provide some clarity, Thomas [ 46 ] has suggested a typology of subject/purpose/approach/process for classifying aims (e.g. evaluative or exploratory), sample rationale and selection and methods for data generation of case studies. We also recognise that the diversity of methods used in case study research, and the necessary focus on narrative reporting, does not lend itself to straightforward development of formal quality or reporting criteria.

Existing checklists for reporting case study research from the social sciences—for example Lincoln and Guba’s [ 47 ] and Stake’s [ 33 ]—are primarily orientated to the quality of narrative produced, and the extent to which they encapsulate thick description, rather than the more pragmatic issues of implications for intervention effects. Those designed for clinical settings, such as the CARE (CAse REports) guidelines, provide specific reporting guidelines for medical case reports about single, or small groups of patients [ 48 ], not for case study research.

The Design of Case Study Research in Health Care (DESCARTE) model [ 44 ] suggests a series of questions to be asked of a case study researcher (including clarity about the philosophy underpinning their research), study design (with a focus on case definition) and analysis (to improve process). The model resembles toolkits for enhancing the quality and robustness of qualitative and mixed-methods research reporting, and it is usefully open-ended and non-prescriptive. However, even if it does include some reflections on context, the model does not fully address aspects of context, logic and causal inference that are perhaps most relevant for evaluative research in health.

Hence, for evaluative research where the aim is to report empirical findings in ways that are intended to be pragmatically useful for health policy and practice, this may be an opportune time to consider how to best navigate plurality around what is (minimally) important to report when publishing empirical case studies, especially with regards to the complex relationships between context and interventions, information that case study research is well placed to provide.

The conventional scientific quest for certainty, predictability and linear causality (maximised in RCT designs) has to be augmented by the study of uncertainty, unpredictability and emergent causality [ 8 ] in complex systems. This will require methodological pluralism, and openness to broadening the evidence base to better understand both causality in and the transferability of system change intervention [ 14 , 20 , 23 , 25 ]. Case study research evidence is essential, yet is currently under exploited in the health sciences. If evaluative health research is to move beyond the current impasse on methods for understanding interventions as interruptions in complex systems, we need to consider in more detail how researchers can conduct and report empirical case studies which do aim to elucidate the contextual factors which interact with interventions to produce particular effects. To this end, supported by the UK’s Medical Research Council, we are embracing the challenge to develop guidance for case study researchers studying complex interventions. Following a meta-narrative review of the literature, we are planning a Delphi study to inform guidance that will, at minimum, cover the value of case study research for evaluating the interrelationship between context and complex system-level interventions; for situating and defining ‘the case’, and generalising from case studies; as well as provide specific guidance on conducting, analysing and reporting case study research. Our hope is that such guidance can support researchers evaluating interventions in complex systems to better exploit the diversity and richness of case study research.

Availability of data and materials

Not applicable (article based on existing available academic publications)

Abbreviations

Qualitative comparative analysis

Quasi-experimental design

Randomised controlled trial

Diez Roux AV. Complex systems thinking and current impasses in health disparities research. Am J Public Health. 2011;101(9):1627–34.

Article   Google Scholar  

Ogilvie D, Mitchell R, Mutrie N, M P, Platt S. Evaluating health effects of transport interventions: methodologic case study. Am J Prev Med 2006;31:118–126.

Walshe C. The evaluation of complex interventions in palliative care: an exploration of the potential of case study research strategies. Palliat Med. 2011;25(8):774–81.

Woolcock M. Using case studies to explore the external validity of ‘complex’ development interventions. Evaluation. 2013;19:229–48.

Cartwright N. Are RCTs the gold standard? BioSocieties. 2007;2(1):11–20.

Deaton A, Cartwright N. Understanding and misunderstanding randomized controlled trials. Soc Sci Med. 2018;210:2–21.

Salway S, Green J. Towards a critical complex systems approach to public health. Crit Public Health. 2017;27(5):523–4.

Greenhalgh T, Papoutsi C. Studying complexity in health services research: desperately seeking an overdue paradigm shift. BMC Med. 2018;16(1):95.

Bonell C, Warren E, Fletcher A. Realist trials and the testing of context-mechanism-outcome configurations: a response to Van Belle et al. Trials. 2016;17:478.

Pallmann P, Bedding AW, Choodari-Oskooei B. Adaptive designs in clinical trials: why use them, and how to run and report them. BMC Med. 2018;16:29.

Curran G, Bauer M, Mittman B, Pyne J, Stetler C. Effectiveness-implementation hybrid designs: combining elements of clinical effectiveness and implementation research to enhance public health impact. Med Care. 2012;50(3):217–26. https://doi.org/10.1097/MLR.0b013e3182408812 .

Moore GF, Audrey S, Barker M, Bond L, Bonell C, Hardeman W, et al. Process evaluation of complex interventions: Medical Research Council guidance. BMJ. 2015 [cited 2020 Jun 27];350. Available from: https://www.bmj.com/content/350/bmj.h1258 .

Evans RE, Craig P, Hoddinott P, Littlecott H, Moore L, Murphy S, et al. When and how do ‘effective’ interventions need to be adapted and/or re-evaluated in new contexts? The need for guidance. J Epidemiol Community Health. 2019;73(6):481–2.

Shoveller J. A critical examination of representations of context within research on population health interventions. Crit Public Health. 2016;26(5):487–500.

Treweek S, Zwarenstein M. Making trials matter: pragmatic and explanatory trials and the problem of applicability. Trials. 2009;10(1):37.

Rosengarten M, Savransky M. A careful biomedicine? Generalization and abstraction in RCTs. Crit Public Health. 2019;29(2):181–91.

Green J, Roberts H, Petticrew M, Steinbach R, Goodman A, Jones A, et al. Integrating quasi-experimental and inductive designs in evaluation: a case study of the impact of free bus travel on public health. Evaluation. 2015;21(4):391–406.

Canguilhem G. The normal and the pathological. New York: Zone Books; 1991. (1949).

Google Scholar  

Hawe P, Shiell A, Riley T. Theorising interventions as events in systems. Am J Community Psychol. 2009;43:267–76.

King G, Keohane RO, Verba S. Designing social inquiry: scientific inference in qualitative research: Princeton University Press; 1994.

Greenhalgh T, Robert G, Macfarlane F, Bate P, Kyriakidou O. Diffusion of innovations in service organizations: systematic review and recommendations. Milbank Q. 2004;82(4):581–629.

Yin R. Enhancing the quality of case studies in health services research. Health Serv Res. 1999;34(5 Pt 2):1209.

CAS   PubMed   PubMed Central   Google Scholar  

Raine R, Fitzpatrick R, Barratt H, Bevan G, Black N, Boaden R, et al. Challenges, solutions and future directions in the evaluation of service innovations in health care and public health. Health Serv Deliv Res. 2016 [cited 2020 Jun 30];4(16). Available from: https://www.journalslibrary.nihr.ac.uk/hsdr/hsdr04160#/abstract .

Craig P, Di Ruggiero E, Frohlich KL, E M, White M, Group CCGA. Taking account of context in population health intervention research: guidance for producers, users and funders of research. NIHR Evaluation, Trials and Studies Coordinating Centre; 2018.

Grant RL, Hood R. Complex systems, explanation and policy: implications of the crisis of replication for public health research. Crit Public Health. 2017;27(5):525–32.

Mahoney J. Strategies of causal inference in small-N analysis. Sociol Methods Res. 2000;4:387–424.

Turner S. Major system change: a management and organisational research perspective. In: Rosalind Raine, Ray Fitzpatrick, Helen Barratt, Gywn Bevan, Nick Black, Ruth Boaden, et al. Challenges, solutions and future directions in the evaluation of service innovations in health care and public health. Health Serv Deliv Res. 2016;4(16) 2016. https://doi.org/10.3310/hsdr04160.

Ragin CC. Using qualitative comparative analysis to study causal complexity. Health Serv Res. 1999;34(5 Pt 2):1225.

Hanckel B, Petticrew M, Thomas J, Green J. Protocol for a systematic review of the use of qualitative comparative analysis for evaluative questions in public health research. Syst Rev. 2019;8(1):252.

Schneider CQ, Wagemann C. Set-theoretic methods for the social sciences: a guide to qualitative comparative analysis: Cambridge University Press; 2012. 369 p.

Flyvbjerg B. Five misunderstandings about case-study research. Qual Inq. 2006;12:219–45.

Tsoukas H. Craving for generality and small-N studies: a Wittgensteinian approach towards the epistemology of the particular in organization and management studies. Sage Handb Organ Res Methods. 2009:285–301.

Stake RE. The art of case study research. London: Sage Publications Ltd; 1995.

Mitchell JC. Typicality and the case study. Ethnographic research: A guide to general conduct. Vol. 238241. 1984.

Gerring J. What is a case study and what is it good for? Am Polit Sci Rev. 2004;98(2):341–54.

May C, Mort M, Williams T, F M, Gask L. Health technology assessment in its local contexts: studies of telehealthcare. Soc Sci Med 2003;57:697–710.

McGill E. Trading quality for relevance: non-health decision-makers’ use of evidence on the social determinants of health. BMJ Open. 2015;5(4):007053.

Greenhalgh T. We can’t be 100% sure face masks work – but that shouldn’t stop us wearing them | Trish Greenhalgh. The Guardian. 2020 [cited 2020 Jun 27]; Available from: https://www.theguardian.com/commentisfree/2020/jun/05/face-masks-coronavirus .

Hammersley M. So, what are case studies? In: What’s wrong with ethnography? New York: Routledge; 1992.

Crowe S, Cresswell K, Robertson A, Huby G, Avery A, Sheikh A. The case study approach. BMC Med Res Methodol. 2011;11(1):100.

Luck L, Jackson D, Usher K. Case study: a bridge across the paradigms. Nurs Inq. 2006;13(2):103–9.

Yin RK. Case study research and applications: design and methods: Sage; 2017.

Hyett N, A K, Dickson-Swift V. Methodology or method? A critical review of qualitative case study reports. Int J Qual Stud Health Well-Being. 2014;9:23606.

Carolan CM, Forbat L, Smith A. Developing the DESCARTE model: the design of case study research in health care. Qual Health Res. 2016;26(5):626–39.

Greenhalgh T, Annandale E, Ashcroft R, Barlow J, Black N, Bleakley A, et al. An open letter to the BMJ editors on qualitative research. Bmj. 2016;352.

Thomas G. A typology for the case study in social science following a review of definition, discourse, and structure. Qual Inq. 2011;17(6):511–21.

Lincoln YS, Guba EG. Judging the quality of case study reports. Int J Qual Stud Educ. 1990;3(1):53–9.

Riley DS, Barber MS, Kienle GS, Aronson JK, Schoen-Angerer T, Tugwell P, et al. CARE guidelines for case reports: explanation and elaboration document. J Clin Epidemiol. 2017;89:218–35.

Download references

Acknowledgements

Not applicable

This work was funded by the Medical Research Council - MRC Award MR/S014632/1 HCS: Case study, Context and Complex interventions (TRIPLE C). SP was additionally funded by the University of Oxford's Higher Education Innovation Fund (HEIF).

Author information

Authors and affiliations.

Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, UK

Sara Paparini, Chrysanthi Papoutsi, Trish Greenhalgh & Sara Shaw

Wellcome Centre for Cultures & Environments of Health, University of Exeter, Exeter, UK

Judith Green

School of Health Sciences, University of East Anglia, Norwich, UK

Jamie Murdoch

Public Health, Environments and Society, London School of Hygiene & Tropical Medicin, London, UK

Mark Petticrew

Institute for Culture and Society, Western Sydney University, Penrith, Australia

Benjamin Hanckel

You can also search for this author in PubMed   Google Scholar

Contributions

JG, MP, SP, JM, TG, CP and SS drafted the initial paper; all authors contributed to the drafting of the final version, and read and approved the final manuscript.

Corresponding author

Correspondence to Sara Paparini .

Ethics declarations

Ethics approval and consent to participate, consent for publication, competing interests.

The authors declare that they have no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Paparini, S., Green, J., Papoutsi, C. et al. Case study research for better evaluations of complex interventions: rationale and challenges. BMC Med 18 , 301 (2020). https://doi.org/10.1186/s12916-020-01777-6

Download citation

Received : 03 July 2020

Accepted : 07 September 2020

Published : 10 November 2020

DOI : https://doi.org/10.1186/s12916-020-01777-6

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Qualitative
• Case studies
• Mixed-method
• Public health
• Health services research
• Interventions

BMC Medicine

ISSN: 1741-7015

• Submission enquiries: [email protected]
• General enquiries: [email protected]

OPINION article

Community case study article type: criteria for submission and peer review.

• 1 Department of Health Promotion and Behavior, College of Public Health, The University of Georgia, Athens, GA, USA
• 2 Department of Health Promotion and Community Health Sciences, Texas A&M Health Science Center School of Public Health, College Station, TX, USA
• 3 College of Social Work, University of South Carolina, Columbia, SC, USA

The Importance of Case Studies in Public Health Education and Promotion

Health programs and practices are often conceived and delivered by community-based practitioners to address specific community health education and promotion needs ( 1 ). Although, initially untested, such programs can provide important lessons for researchers and practitioners, alike. Given the growing emphasis on community-based participatory research (CBPR) approaches ( 2 ), it is especially important for researchers to build upon findings from CBPR studies, which can contribute to the development of evidence-based programs and practices for widespread dissemination ( 3 ).

While a community case study can take many forms ( 4 , 5 ), we are defining it as a description of, and reflection upon, a program or practice geared toward improving the health and functioning of a targeted population. We utilize the term “community” in contrast to “clinical” studies, but it is important to note that a community can be defined in terms of geographic boundaries as well as demographic characteristics, common settings, and/or affiliations.

Typically, a community case study documents a local experience about delivering services to meet an identified need. Community-based studies often rely on community engagement principles, which are not typically incorporated in the more traditional science-based approach to evidence-based program development (e.g., CBPR, action research, and community-engaged research). The community case study that documents early experiences can contribute to programmatic development as well as to the future development of evidence-based practice. This has been referred to as the “practice to science” approach to the development of evidence-based practices ( 6 ). The community case study can also represent activities at later development stages, for example, documenting the experience of implementing an evidence-based program or practice in a different context (e.g., different culture, different population, and different setting) from that in which it was first developed [“from science to practice” ( 6 )]. The lessons learned from such community case studies are essential for adaptation, replication, and eventual widespread dissemination and sustainability of innovations across a wide range of settings and populations.

Although case studies are a recognized form of research ( 5 ), the criteria for evaluating the quality of such efforts necessarily differs from empirical research articles where there is less attention to the local experience and context in which the intervention occurs, and more emphasis is given to the use of standardized research designs, measures, and analyses.

Key Components of a Community Case Study

Under this article type, Frontiers in Public Health Education and Promotion will accept a broad spectrum of manuscripts that describe interventions, including programs and services, which promote public health education, practice, research, and/or policy. Such public health interventions can be implemented at the behavioral, organizational, community, environmental, and/or policy level(s). Articles require a description of the nature of the problem being addressed and rationale for the proposed intervention, the context (setting and population) in which the intervention is being implemented, and sufficient detail to allow replication of key programmatic elements. Reflections about public health impact as well as what works and what does not work should be highlighted. Additionally, submissions will require a discussion section that shares practical implications, lessons learned for future applications, and acknowledgment of any conceptual or methodological constraints. Articles should not exceed 5,000 words and include a maximum of five tables/graphs. Evaluation criteria for this article type are outlined below:

We recommend that community case study article submissions address the following issues (if relevant).

□ What is the problem? Whom does it affect?

□ What are the gaps about what is known or done currently?

□ What is the setting? Who are the key stakeholders? Who is the target population or participants?

□ With whom did you work or collaborate? Are there any unique characteristics of the team who worked to implement the solution?

□ What is the solution described by this community case study?

□ Is this solution innovative/novel in terms of content, format, and/or delivery? If yes, why?

□ What are the essential elements of the solution? Could this community case study be replicated? Include sufficient detail that the reader would know if replication would be feasible in his/her own context.

□ What are the barriers and facilitators to the development, implementation, and/or dissemination of the intervention?

□ What are the major successes of the solution? What are the promising results to date? Include data and/or evaluation results, if available.

□ How does this improve public health education, practice, research, and/or policy? What are the broader implications of this work?

□ Recommendations for those who want to replicate this in other settings, populations, or over time.

Criteria for Review (Template for Review Editors to Complete for Each Manuscript)

Indicate what the community case study describes (check all that apply)

__an education effort

__a health promotion program

__a health promotion service

__an environmental change taking place in the community

__a technological change taking place in the community

__a policy change taking place in the community

__a community partnership

__others. Please specify: _____________________

__none of the above (i.e., inappropriately categorized for submission as a community case study article).

Indicate the target audience for the case study (check all that apply)

__educators

__community professionals

__health-care professionals

__lay public

__policy makers

__other. Please specify: _____________________

Mandatory Sections and Associated Criteria

A community case study article has the following mandatory sections: abstract, introduction, background and rationale, description of the case, methodological aspects (including targeted population and setting), discussion, and lessons learned/recommendations. Are all sections present?

• Is the abstract written in a clear and comprehensive way?

• Does the abstract reflect major conclusions articulated in the case study?

Introduction

• Does the introduction present the problem in an appropriate context?

• Other comments on introduction.

Background and Rationale

• Is the intent of the case study adequately described?

• Is a justification made for the innovation/novelty of proposed case in content, format, and/or delivery?

• Are the questions asked by the case study most essential to the success of the initiative?

• Other comments on background and rationale.

Essential Elements of the Intervention

• Is the intervention adequately described (e.g., development, previous findings if any, components, and format/design)?

• Is the intervention described in sufficient detail to understand the essential elements?

• Are the implementation procedures adequately described (e.g., how is the intervention being implemented in a particular setting, population, and/or partnerships; are any adaptations needed from prior work)?

• Are the target setting(s) and population(s) adequately described so that context for the case study is clearly understood?

• Is this a single community or multiple community study?

• Is there an overall conceptual model or framework for understanding the importance of the problem and selection of intervention elements?

• Is it clear whether the emphasis is on furthering knowledge about the process and/or outcome of the case study? If focus is on process, is there attention to key elements of implementation such as reach, reproducibility, scalability, or sustainability? If on outcomes, are the metrics of success (outcome indicators) clearly articulated?

• Is the generalizability of findings/lessons learned addressed?

• Other comments on methods.

• Are findings/lessons learned accurately reported from data presented?

• Is the level of detail of the results appropriate (too much, too little, or about right)?

• Is any essential information missing?

• Other comments on results.

• Are the reported findings/lessons learned summarized briefly and described within the context of what is currently known about the public health issue(s) or problem(s) being addressed?

• Does the article conclude with practical recommendations for others who might replicate this intervention/program (or similar interventions/programs)?

• Does the article conclude with applied recommendations for those in the field who might deliver this intervention/program (or similar interventions/programs) in their communities/settings?

• Does the case study contribute concrete recommendations for delivering and/or improving the intervention for future applications (directed toward educators, researchers, or practitioners, as appropriate)?

• Does the article address any conceptual or methodological limitations for future implementation, dissemination, and sustainability?

• Other comments on discussion.

• Are the conclusions justified?

• Overall, does the article contribute to building evidence-based practice and/or policy?

• Is prior work, if any, properly and fully cited?

Article Length

• A case study article should not exceed 5,000 words. Should any part of the article be shortened? If yes, please specify which part should be shortened.

• A case study article should not include more than five tables/figures. If there are more tables/figures included, please specify if you believe tables can be combined, condensed, or eliminated.

Language and Grammar

• Are the language and grammar correct?

• Should the paper be sent to an expert in English language and scientific writing?

Other Comments

• Please add any further comments you have regarding this manuscript.

Reviewer Ratings

• Significance of issue being addressed by the case study: scored out of a maximum of 10 points

• Description of essential elements of the case study: scored out of a maximum of 10 points

• Appropriateness of the context (population and setting) in addressing the public health issue/problem described in the case study: scored out of a maximum of 10 points

• Sufficient conceptual and methodological detail describing why and how the intervention was implemented: scored out of a maximum of 10 points

• Reflections on what worked and did not work in the design, implementation, and/or dissemination of the program: scored out of a maximum of 10 points

• Quality of the writing: scored out of a maximum of 10 points

• Quality of the figure(s) and table(s): scored out of a maximum of 10 points

• Significance of the findings/lessons learned: scored out of a maximum of 10 points

• Could this intervention be replicated by other educators, researchers, or practitioners?

Author Contributions

All authors were integral in formulating and drafting the manuscript and associated criteria.

Conflict of Interest Statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

1. Ory MG, Smith MLS, Howell D, Zollinger A, Quinn C, Swierc S, et al. The conversion of a practice-based lifestyle enhancement program into a formalized, testable program: from texercise classic to texercise select. Front Public Health (2015) 2 :291. doi: 10.3389/fpubh.2014.00291

PubMed Abstract | CrossRef Full Text | Google Scholar

2. Minkler M, Wallerstein N, editors. Community-Based Participatory Research for Health: From Process to Outcomes . John Wiley & Sons (2011).

Google Scholar

3. Ory MG, Smith ML. Research, practice, and policy perspectives on evidence-based programing for older adults. Front Public Health (2015) 3 :136. doi:10.3389/fpubh.2015.00136

CrossRef Full Text | Google Scholar

4. Soy SK. The Case Study as a Research Method. Unpublished Paper . Austin: University of Texas (1997).

5. Yin RK. Case Study Research: Design and Methods . Thousand Oaks, CA: Sage publications (2013).

6. Chen H, Levkoff S, Kleinman A. Contextual knowledge: from global aging to globalization. Can J Sociol (2014) 39 (2):141–58.

Keywords: case study, review criteria, article type, intervention, evaluation criteria

Citation: Smith ML, Levkoff SE and Ory MG (2016) Community Case Study Article Type: Criteria for Submission and Peer Review. Front. Public Health 4:56. doi: 10.3389/fpubh.2016.00056

Received: 06 November 2015; Accepted: 14 March 2016; Published: 14 April 2016

Reviewed by:

Copyright: © 2016 Smith, Levkoff and Ory. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Matthew Lee Smith, health@uga.edu

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

• Policy & Compliance
• Research Misconduct
• Integrity and Confidentiality in NIH Peer Review
• Taking Action – Case Studies In Research Integrity

Taking Action – Case Studies in Research Integrity

If you see something, say something. 

A series to raise awareness and inspire creative problem solving of the challenges in maintaining integrity in peer review

Learn more about  Integrity and Confidentiality in Peer Review (including this NIH Guide Notice ).

Case Studies

The following cases are anonymized, but based on real events.

The Seminar Trip

The stealth grant writer.

An NIH peer reviewer was approached by a well-known professional grant writing service to assist a client in preparing an NIH grant application. The service advertised phenomenal success in securing NIH funding for its clients. What would you do?

Sharing an Application Being Reviewed

Sharing an application with anyone who has not been officially designated to participate in the peer review process is a big no-no. And it is specifically prohibited by NIH peer review policy.

Review Integrity - Abuse of Power

What would you do if, as the Dean of Research at a major university, a group of students, postdocs, and junior faculty reported that they had been pressured into writing reviewer critiques for a senior faculty member?

Embellished Credentials in a Grant Application

What happens when the NIH discovers that an investigator has embellished his or her credentials in an NIH grant application? Or even fabricated credentials?

Undisclosed Conflict of Interest

What happens when it is discovered that one of the reviewers currently set to review an application, had been listed as one of the key personnel on an application with the same PI in another, recent study section?

Asking for Favorable Treatment

What happens when a former colleague contacts you, a reviewer, out of the blue to ask if the application on which he is a principal investigator could be treated favorably at the review meeting? Do you brush off the investigator and figure you will not let the contact influence your review of that application? Or do you instead immediately notify NIH?

This Application Feels Familiar

In this case study, we discuss how plagiarism in the grant application process is handled at NIH and remind the research community about the importance of maintaining confidentiality of the peer review process. 

Banned From Supervising, Can’t Go in Lab, but No Impact on NIH Funded Research?

Too often we hear from institutions that a PI has violated the institution’s policies and is no longer permitted to supervise students or staff, but there will be “no impact on NIH-funded work.” We have a problem with this response.

You Can Disagree, Without Being Disagreeable

Unfortunately, we are seeing a number of cases of uncivil behavior coming from individuals outside of NIH, directed at NIH extramural staff.

Double Double toil and Trouble

We discuss here what you and your institution should consider when submitting the same applications to multiple funders.

This page last updated on: November 28, 2023

• Bookmark & Share
• E-mail Updates
• Help Downloading Files
• Privacy Notice
• Accessibility
• National Institutes of Health (NIH), 9000 Rockville Pike, Bethesda, Maryland 20892
• NIH... Turning Discovery Into Health

Case Study: Apparent conflicts and priorities

ORI  Introduction  to RCR: Chapter 10. Peer Review    

• Should Dr. L. agree to do the review?
• If he is uncertain about his responsibilities, where can he get advice?
• Would the situation be different if he had been asked to review the student’s work for an
• appointment or promotion decision?

Email Updates

To read this content please select one of the options below:

Please note you do not have access to teaching notes, “being brave”: a case study of how an innovative peer review approach led to service improvement.

Journal of Integrated Care

ISSN : 1476-9018

Article publication date: 15 August 2016

The purpose of this paper is to report on the use of an innovative peer review approach to identifying and addressing the causes of inappropriate admissions from hospital to nursing homes in South Gloucestershire (SG). It explains the methodology that was developed, the findings of the peer review process and reflects on the effectiveness of the process.

Design/methodology/approach

The peer review consisted of two stages. The first stage involved a panel of local stakeholders carrying out an audit of a random selection of cases where people had been assessed as needing permanent nursing or residential care. From this four cases of inappropriate admissions were identified. Stage two involved an externally facilitated process with two peer challenge panels; one of local stakeholders and the other external experts. The two panels analysed the cases of inappropriate admissions, identified the system causes and suggested actions to tackle the issues which were fed back to an audience of local stakeholders.

The combination of case audit and peer review was successful in providing robust challenge to the processes in SG by identifying shortcomings in the system and suggesting actions to improve outcomes.

Research limitations/implications

The approach was taken in one Council area and therefore may not be replicable in another area.

Practical implications

The case study suggests that a peer review approach using both local and external peers, including providers, is an effective way to identify weaknesses in the health and social care processes. The insights offered by external peers and providers is helpful for councils in identifying where to focus resources and suggests that other areas should consider proactive adaptations to the peer review methodology that is offered as part of the LGA’s programme of sector-led improvement.

Social implications

The case study suggests that a peer review approach could have a positive impact on the quality of care and quality of life for older people who are admitted to hospital.

Originality/value

The case study offers an innovative and original use of the peer review approach in social care that can be shared with other councils and partners. The Southwest Improvement Board have identified it as of particular interest to other areas seeking to work with partners to identify and implement positive change.

• Partnership working
• Health and social care
• Interagency working
• Peer review
• Peer challenge

Mangan, C. , Pietroni, M. and Porter, D. (2016), "“Being brave”: A case study of how an innovative peer review approach led to service improvement", Journal of Integrated Care , Vol. 24 No. 4, pp. 201-213. https://doi.org/10.1108/JICA-06-2016-0021

Emerald Group Publishing Limited

Copyright © 2016, Emerald Group Publishing Limited

Related articles

We’re listening — tell us what you think, something didn’t work….

Report bugs here

All feedback is valuable

Please share your general feedback

Join us on our journey

Platform update page.

Visit emeraldpublishing.com/platformupdate to discover the latest news and updates

Questions & More Information

Answers to the most commonly asked questions here

• Open access
• Published: 26 April 2024

Clinician and staff experiences with frustrated patients during an electronic health record transition: a qualitative case study

• Sherry L. Ball 1 ,
• Bo Kim 2 , 3 ,
• Sarah L. Cutrona 4 , 5 ,
• Brianne K. Molloy-Paolillo 4 ,
• Ellen Ahlness 6 ,
• Megan Moldestad 6 ,
• George Sayre 6 , 7 &
• Seppo T. Rinne 2 , 8  

BMC Health Services Research volume  24 , Article number:  535 ( 2024 ) Cite this article

36 Accesses

Metrics details

Electronic health record (EHR) transitions are known to be highly disruptive, can drastically impact clinician and staff experiences, and may influence patients’ experiences using the electronic patient portal. Clinicians and staff can gain insights into patient experiences and be influenced by what they see and hear from patients. Through the lens of an emergency preparedness framework, we examined clinician and staff reactions to and perceptions of their patients’ experiences with the portal during an EHR transition at the Department of Veterans Affairs (VA).

This qualitative case study was situated within a larger multi-methods evaluation of the EHR transition. We conducted a total of 122 interviews with 30 clinicians and staff across disciplines at the initial VA EHR transition site before, immediately after, and up to 12 months after go-live (September 2020-November 2021). Interview transcripts were coded using a priori and emergent codes. The coded text segments relevant to patient experience and clinician interactions with patients were extracted and analyzed to identify themes. For each theme, recommendations were defined based on each stage of an emergency preparedness framework (mitigate, prepare, respond, recover).

In post-go-live interviews participants expressed concerns about the reliability of communicating with their patients via secure messaging within the new EHR portal. Participants felt ill-equipped to field patients’ questions and frustrations navigating the new portal. Participants learned that patients experienced difficulties learning to use and accessing the portal; when unsuccessful, some had difficulties obtaining medication refills via the portal and used the call center as an alternative. However, long telephone wait times provoked patients to walk into the clinic for care, often frustrated and without an appointment. Patients needing increased in-person attention heightened participants’ daily workload and their concern for patients’ well-being. Recommendations for each theme fit within a stage of the emergency preparedness framework.

Conclusions

Application of an emergency preparedness framework to EHR transitions could help address the concerns raised by the participants, (1) mitigating disruptions by identifying at-risk patients before the transition, (2) preparing end-users by disseminating patient-centered informational resources, (3) responding by building capacity for disrupted services, and (4) recovering by monitoring integrity of the new portal function.

Peer Review reports

Electronic health record (EHR) transitions present significant challenges for healthcare clinicians and staff. These transitions require adjustments in care delivery and may threaten care quality and value. It is critical that healthcare organizations undergoing these changes learn from others who have undergone similar transitions [ 1 , 2 ]. However, the current literature lacks adequate guidance on navigating EHR transitions, especially as they relate to how clinicians and staff interact with patients [ 3 ].

Embedded within EHRs, patient portals facilitate complete, accurate, timely, and unambiguous exchange of information between patients and healthcare workers [ 4 , 5 ]. These portals have become indispensable for completing routine out-of-office-visit tasks, such as medication refills, communicating laboratory results, and addressing patient questions [ 6 ]. In 2003, the VA launched their version of a patient portal, myHealtheVet [ 7 ] and by 2017 69% of Veterans enrolled in healthcare at the VA had registered to access the patient portal [ 8 ]. Similar to other electronic portals, this system allows Veterans to review test results, see upcoming appointments, and communicate privately and securely with their healthcare providers.

EHR transitions can introduce disruptions to patient portal communication that may compromise portal reliability, impacting patient and clinician satisfaction, patients’ active involvement in self-management, and ultimately health outcomes [ 9 ]. During an EHR transition, patients can expect reductions in access to care even when clinician capacity and IT support are increased. Patients will likely need for more assistance navigating the patient portal including and using the portal to communicate with their providers [ 10 ]. Staff must be prepared and understand how the changes in the EHR will affect patients and safeguards must be in place to monitor systems for potential risks to patient safety. Building the capacity to respond to emerging system glitches and identified changes must be included in any transition plan. Although portal disruptions are likely to occur when a new EHR is implemented, we know little about how these disruptions impact healthcare workers’ interactions and care delivery to patients [ 11 , 12 ].

Due to an urgency to raise awareness and promote resolution of these patient portal issues,, we utilized existing data from the first EHR transition site for the Department of Veterans Affairs (VA)’s enterprise-wide transition. We focused on end users’ responses to the question “How Veterans were affected by the transition?”. We used qualitative methods to begin to understand how provider and patient interactions were affected during and by the EHR transition. We explored the impact of the EHR transition on patients through healthcare workers’ vicarious and direct experiences with patients. Due to the high level of disruption in care delivery we draw on insights from an emergency preparedness framework [ 13 ] to generate a set of recommendations to improve healthcare workers’ experiences during EHR transitions. The emergency preparedness framework includes 4 phases of an iterative cycle that include: (1) building capacity to mitigate issues, (2) preparing for the inevitable onset of issues, (3) responding to issues as they emerge, and (4) strategies to recover from any damage incurred.

In early 2020, the VA embarked on an EHR transition from a homegrown, legacy EHR system, developed by VA clinicians and used since the 1990s, to a new commercial system by the Oracle-Cerner Corporation. The primary objectives of this transition were to standardize care and improve interoperability between VA Medical Centers nationwide and the Department of Defense (DoD). Spanning over a decade, this transition plan is scheduled to roll out to all VA medical centers and outpatient clinics.

In this manuscript, we present data from the Mann-Grandstaff VA Medical Center in Spokane, WA, VA’s first EHR transition site. The study uses qualitative methods with clinician and staff interviews as part of a larger multi-method evaluation of the EHR transition. Our overarching goal is to identify and share recommendations to improve VA’s EHR transition efforts; rather than be guided by a theoretical framework our study design including the interview guides [ 14 , 15 ] were based primarily on what was being experienced. An experienced team of ten qualitative methodologists and analysts conducted the study.

This evaluation was designated as non-research/quality improvement work by the VA Bedford Healthcare System Institutional Review Board deeming it exempt from needing an informed consent. Study materials, including interview guides with verbal consent procedures, were reviewed and approved by labor unions and by the VA Bedford Healthcare System Institutional Review Board; all methods were carried out in accordance with local and national VA guidelines and regulations.

Interview guides and an outline of the data collection plans were reviewed and approved by relevant national unions before beginning recruitment.

Recruitment

Recruitment began in July 2020, before the first site implemented the new EHR. Prior to collecting data, we met with site leadership to get buy-in and support for the study, understand local context, determine how the site was approaching the transition, and to obtain the names of clinicians and staff for potential interviews. All potential participants were invited by email to participate in a one-hour voluntary interview conducted on Microsoft Teams® about their experiences with this transition; we used snowball sampling during interviews to expand the pool of interviewees. Verbal permission for audio recording of interviews was obtained immediately prior to the interview. Interview participants were informed that they could skip any questions, pause or stop the recording, and stop the interview at any time and were invited to ask questions before beginning the interview.

Most participants were interviewed at multiple timepoints; these included pre-implementation interviews, brief check-ins, and post-implementation interviews (Table  1 ). At the end of the pre-implementation interview, participants were invited to participate in 3–4 additional, shorter (15–20 min), check-in interviews where information about any changes in the transition process, context, or experience could be discussed. Most initial interviewees, in addition to three new participants, participated in post-implementation interviews (35–60 min; approximately 2–3 months and 10–12 months after the implementation) to reflect on the entire transition process.

Data collection

Experienced qualitative interviewers included PhD trained qualitative methodologist and masters level qualitative analysts (JB, SB, AC, EK, MM, GS) conducted individual interviews with clinicians and staff, aligning to a semi-structured interview guide with follow-up probes using the participant’s words to elicit rich responses grounded in the data [ 16 ]. The guide was designed to inform ongoing efforts to improve the rollout of the new EHR. Six main categories were covered in our interview guides, including (1) attitudes toward the new software, (2) information communicated about the transition, (3) training and education, (4) resources, (5) prior experience with EHRs, and (6) prior experiences with EHR transitions. After piloting the interview guide with a clinician, initial interviews were completed between September and October 2020 and averaged  ∼  45 min in duration. Two-month and one-year post-implementation interview guides included an additional question, “Has the Cerner transition affected Vets?”; data presented here largely draw from responses to this question. Check-ins (October 2020– December 2020) took  ∼  15 min; two-month post-implementation interviews (December 2020– January 2021) and one-year post-implementation interviews (October 2020 - November 2021) took  ∼  45 min. Audio recordings of all interviews were professionally transcribed. To ensure consistency and relationship building, participants were scheduled with the same interviewer for the initial and subsequent interviews whenever feasible (i.e., check-ins and post-implementation interviews). Immediately following each interview, interviewers completed a debrief form where highlights and general reflections were noted.

Throughout the data collection process, interviewers met weekly with the entire qualitative team and the project principal investigators to discuss the recruitment process, interview guide development, and reflections on data collection. To provide timely feedback to leadership within the VA, a matrix analysis [ 17 ] was conducted concurrently with data collection using the following domains: training, roles, barriers, and facilitators. Based on these domains, the team developed categories and subcategories, which formed the foundation of an extensive codebook.

Data analysis

All interviewers also coded the data. We used inductive and deductive content analysis [ 18 ]. Interview transcripts were coded in ATLAS.ti qualitative data analysis software (version 9). A priori codes and categories (based on the overall larger project aims and interview guide questions) and emergent codes and categories were developed to capture concepts that did not fit existing codes or categories [ 18 ]. Codes related to patient experience and clinician interactions with patients were extracted and analyzed using qualitative content analysis to identify themes [ 18 ]. Themes were organized according to their fit within the discrete stages of an emergency preparedness framework to generate recommendations for future rollout. In total, we examined data from 111 interviews with 24 VA clinicians and staff (excluding the initial 11 stakeholder meetings (from the 122 total interviews) that were primarily for stakeholder engagement). We focused on participants’ responses related to their experiences interacting with patients during the EHR transition.

Exemplar quotes primarily came from participants’ responses to the question, “Has the Cerner transition affected Vets?” and addressed issues stemming from use of the patient portal. This included both clinicians’ direct experiences with the portal and indirect experiences when they heard from patients about disruptions when using the portal. We identified four themes related to clinicians’ and staff members’ reported experiences: (1) stress associated with the unreliability of routine portal functions and inaccurate migrated information; (2) concern about patients’ ability to learn to use a new portal (especially older patients and special populations); (3) frustration with apparent inadequate dissemination of patient informational materials along with their own lack of time and resources to educate patients on use of the new portal; and (4) burden of additional tasks on top of their daily workload when patients needed increased in-person attention due to issues with the portal.

Stress associated with the unreliability of routine portal functions and inaccurate migrated information

One participant described the portal changes as, “It’s our biggest stress, it’s the patients’ biggest stress… the vets are definitely frustrated; the clinicians are; so I would hope that would mean that behind the scenes somebody is working on it” (P5, check-in).

Participants expressed significant frustration when they encountered veterans who were suddenly unable to communicate with them using routine secure messaging. These experiences left them wondering whether messages sent to patients were received.

Those that use our secure messaging, which has now changed to My VA Health, or whatever it’s called, [have] difficulty navigating that. Some are able to get in and send the message. When we reply to them, they may or may not get the reply. Which I’ve actually asked one of our patients, ‘Did you get the reply that we took care of this?’ And he was like, ‘No, I did not (P11, 2-months post)

Participants learned that some patients were unable to send secure messages to their care team because the portal contained inaccurate or outdated appointment and primary site information.

I’ve heard people say that the appointments aren’t accurate in there… veterans who have said, ‘yeah, it shows I’m registered,’ and when they go into the new messaging system, it says they are part of a VA that they haven’t gone to in years, and that’s the only area they can message to, they can’t message to the [site] VA, even though that’s where they’ve actively being seen for a while now. (P20, 2-months post)

After the EHR transition, participants noted that obtaining medications through the portal, which was once a routine task, became unreliable. They expressed concern around patients’ ability to obtain their medications through the portal, primarily due to challenges with portal usability and incomplete migration of medication lists from the former to the new EHR.

I think it’s been negative, unfortunately. I try to stay optimistic when I talk to [patients], but they all seem to be all having continued difficulty with their medications, trying to properly reorder and get medications seems to still be a real hassle for them. (P17, one-year post) …the medications, their med list just didn’t transfer over into that list [preventing their ability to refill their medications]. (P13, 2-months post)

Concern about patients’ ability to learn to use a new portal

Clinicians and staff expressed concerns around veterans’ ability to access, learn, and navigate a new portal system. Clinicians noted that even veterans who were adept at using the prior electronic portal or other technologies also faced difficulties using the new portal.

They can’t figure out [the new portal], 99% of them that used to use our [old] portal, the electronic secure messaging or emailing between the team, they just can’t use [the new one]. It’s not functioning. (P13, one-year post) Apparently, there’s a link they have to click on to make the new format work for them, and that’s been confusing for them. But I still am having a lot of them tell me, I had somebody recently, who’s very tech savvy, and he couldn’t figure it out, just how to message us. I know they’re still really struggling with that. (P5, 2-months post) And it does seem like the My Vet [my VA Health, new portal], that used to be MyHealtheVet [prior portal], logging on and getting onto that still remains really challenging for a large number of veterans. Like they’re still just unable to do it. So, I do think that, I mean I want to say that there’s positive things, but really, I struggle (P17, one-year post)

Participants recognized difficulties with the new system and expressed empathy for the veterans struggling to access the portal.

I think that a lot of us, individually, that work here, I think we have more compassion for our veterans, because they’re coming in and they can’t even get onto their portal website. (P24, one-year post)

Participants acknowledged that learning a new system may be especially difficult for older veterans or those with less technology experience.

But, you know, veterans, the general population of them are older, in general. So, their technologic skills are limited, and they got used to a system and now they have to change to a new one. (P13, 2-months post) So, for our more elderly veterans who barely turn on the computer, they’re not getting to this new portal. (P8, check in) And you know, I do keep in mind that this is a group of people who aren’t always technologically advanced, so small things, when it’s not normal to them, stymie them.(P13, one-year post)

Concerns were heightened for veterans who were more dependent on the portal as a key element in their care due to specific challenges. One participant pointed out that there may be populations of patients with special circumstances who depend more heavily on the prior portal, MyHealtheVet.

I have veterans from [specific region], that’s the way they communicate. Hearing impaired people can’t hear on the phone, the robocall thing, it doesn’t work, so they use MyHealtheVet. Well, if that goes away, how is that being communicated to the veteran? Ok? (P18, Check-in)

Frustration with inadequate dissemination of information to veterans about EHR transition and use of new portal

Participants were concerned about poor information dissemination to patients about how to access the new portal. During medical encounters, participants often heard from patients about their frustrations accessing the new portal. Participants noted that they could only give their patients a phone number to call for help using the new system but otherwise lacked the knowledge and the time to help them resolve new portal issues. Some clinicians specifically mentioned feeling ill-equipped to handle their patients’ needs for assistance with the new portal. These experiences exacerbated clinician stress during the transition.

Our veterans were using the MyHealtheVet messaging portal, and when our new system went up, it transitioned to My VA Health, but that wasn’t really communicated to the veterans very well. So, what happened was they would go into their MyHealtheVet like they had been doing for all of these years, to go in and request their medications, and when they pulled it up it’d show that they were assigned to a clinician in [a different state], that they have no active medications. Everything was just messed up. And they didn’t know why because there was no alert or notification that things would be changing. (P8, check in) I field all-day frustration from the veterans. And I love my job, I’m not leaving here even as frustrated as I am, because I’m here for them, not to, I’m here to serve the veterans and I have to advocate for them, and I know it will get better, it can’t stay like this. But I constantly field their frustrations.… So, I give them the 1-800 number to a Cerner help desk that helps with that, and I’ve had multiple [instances of] feedback that it didn’t help. (P13, one-year post) And [the patients are] frequently asking me things about their medication [within the portal], when, you know, I can’t help them with that. So, I have to send them back up to the front desk to try to figure out their medications. (P17, one-year post)

Veteran frustration and the burden of additional tasks due to issues with the portal

Clinicians reported that veterans expressed frustration with alternatives to the portal, including long call center wait times. Some veterans chose to walk into the clinic without an appointment rather than wait on the phone. Clinicians noted an increase in walk-ins by frustrated veterans, which placed added workload on clinics that were not staffed to handle the increase in walk-ins.

It’s been kind of clunky also with trying to get that [new portal] transitioned. And then that’s created more walk-ins here, because one, the vets get frustrated with the phone part of it, and then MyHealtheVet (prior portal) not [working], so they end up walking [into the clinic without an appointment]. (P19, check-in) In terms of messages, they can’t necessarily find the clinician they want to message. We had a veteran who came in recently who wanted to talk to their Rheumatologist, and it’s like, yeah, I typed in their name, and nothing came up. So, they have to try calling or coming in. (P20, 2-months post)

In summary, participants described the new patient portal as a source of stress for both themselves and their patients.

In addition to their own direct experience using a new EHR to communicate with their patients, clinicians and staff can be affected by perceptions of their patients’ experiences during an EHR transition [ 19 ]. At this first VA site to transition to the new EHR, clinicians and staff shared their concerns about their patients’ experiences using the portal. They were particularly troubled by unreliability of the secure messaging system and challenges patients faced learning to use the new system without proper instruction. Moreover, clinicians were alarmed to hear about patients having to make in-person visits– especially unplanned (i.e., walk in) ones– due to challenges with the new portal. Each of these issues needs to be addressed to ensure veteran satisfaction. However, the only solution participants could offer to frustrated patients was the telephone number to the help desk, leaving them with no clear knowledge of a solution strategy or a timeline for resolution of the issues.

We propose applying emergency preparedness actions to future EHR rollouts: mitigate, prepare, respond, and recover (Fig.  1 ) [ 13 ]. By applying these actions, patient portal disruptions may be alleviated and patients’ communication with their clinicians and access to care can be maintained. For example, issues stemming from a disruption in the portal may be mitigated by first identifying and understanding which patients typically use the portal and how they use it. Sites can use this information to prepare for the transition by disseminating instructional materials to staff and patients on how to access the new portal, targeting the most common and critical portal uses. Sites can respond to any expected and emerging portal disruptions by increasing access to alternative mechanisms for tasks disrupted by and typically completed within the portal. After the transition, recovery can begin by testing and demonstrating the accuracy and reliability of functions in the new portal. These actions directly address reported clinician concerns and can help maintain patient-clinician communication, and access to care.

The emergency preparedness framework was applied. This framework includes 4 actions: (1) mitigate, (2) prepare, (3) respond, and (4) recover. These actions can be repeated. Recommendations for how each action (1–4) can be applied to a portal transition are included in each blue quadrant of the circle

Sites could mitigate issues by first understanding which patients will be most affected by the transition, such as those who rely heavily on secure messaging. Reliable use of secure messaging within the VA facilitates positive patient-clinician relationships by providing a mechanism for efficient between-visit communication [ 20 , 21 , 22 , 23 ]. During the EHR transition, clinicians and staff became concerned about the well-being of patients from whom they weren’t receiving messages and those who depended on the portal to complete certain tasks. Since secure messaging is often initiated by patients to clinicians [ 23 ], clinicians will likely be unaware that messages are being missed. Understanding how and which patients currently use the portal and anticipating potential portal needs is a first step toward mitigating potential issues.

Despite efforts to inform Veterans of the EHR transition and patient portal [ 24 ] including information sent to a Veteran by email, direct mail, postings on VA websites, and a town hall, our findings agree with those of Fix and colleagues [ 10 ] and suggest that many Veterans were unprepared for the transition. Our findings suggest that end users heard that more is needed to improve the dissemination of knowledge about the transition and how to navigate the new patient portal to both VA employees and the patients they serve.

Preparations for the transition should prioritize providing VA clinicians and staff with updated information and resources on how to access and use the new portal [ 25 ]. VA clinicians deliver quality care to veterans and many VA employees are proud to serve the nation’s veterans and willing to go the extra mile to support their patients’ needs [ 26 ]. In this study, participants expressed feeling unprepared to assist or even respond to their patients’ questions and concerns about using the new portal. This unpreparedness contributed to increased clinician and staff stress, as they felt ill-equipped to help their patients with portal issues. Such experiences can negatively affect the patient-clinician relationship. Preparing clinicians and patients about an upcoming transition, including technical support for clinicians and patients, may help minimize these potential issues [ 10 , 27 ]. Specialized training about an impending transition, along with detailed instructions on how to gain access to the new system, and a dedicated portal helpline may be necessary to help patients better navigate the transition [ 23 , 28 ].

In addition to a dedicated helpline, our recommendations include responding to potential changes in needed veteran services during the transition. In our study, participants observed more veteran walk-ins due to challenges with the patient portal. Health systems need to anticipate and address this demand by expanding access to in-person services and fortifying other communication channels. For example, sites could use nurses to staff a walk-in clinic to handle increases in walk-in traffic and increase call center capacity to handle increases in telephone calls [ 29 ]. Increased use of walk-in clinics have received heightened attention as a promising strategy for meeting healthcare demands during the COVID-19 pandemic [ 30 ] and can potentially be adapted for meeting care-related needs during an EHR transition. These strategies can fill a gap in communication between clinicians and their patients while patients are learning to access and navigate a new electronic portal.

Finally, there is a need for a recovery mechanism to restore confidence in the reliability of the EHR and the well-being of clinicians and staff. Healthcare workers are experiencing unprecedented levels of stress [ 31 ]. A plan must be in place to improve and monitor the accuracy of data migrated, populated, and processed within the new system [ 2 ]. Knowing that portal function is monitored could help ease clinician and staff concerns and mitigate stress related to the transition.

Limitations

This study has several limitations. First, data collection relied on voluntary participation, which may introduce self-selection response bias. Second, this work was completed at one VA medical center that was the first site in the larger enterprise-wide transition, and experiences at other VAs or healthcare systems might differ substantially. Third, we did not interview veterans and relied entirely on secondhand accounts of patient experiences with the patient portal. Future research should include interviews with veterans during the transition and compare veteran and VA employee experiences.

Despite a current delay in the deployment of the new EHR at additional VA medical centers, findings from this study offer timely lessons that can ensure clinicians and staff are equipped to navigate challenges during the transition. The strategies presented in this paper could help maintain patient-clinician communication and improve veteran experience. Guided by the emergency preparedness framework, recommended strategies to address issues presented here include alerting those patients most affected by the EHR transition, being prepared to address patients’ concerns, increasing staffing for the help desk and walk-in care clinics, and monitoring the accuracy and reliability of the portal to provide assurance to healthcare workers that patients’ needs are being met. These strategies can inform change management at other VA medical centers that will soon undergo EHR transition and may have implications for other healthcare systems undergoing patient portal changes. Further work is needed to directly examine the perspectives of veterans using the portals, as well as the perspectives of both staff and patients in the growing number of healthcare systems beyond VA that are preparing for an EHR-to-EHR transition.

Data availability

Deidentified data analyzed for this study are available from the corresponding author on reasonable request.

Abbreviations

Electronic health record

Department of Veterans Affairs

VA Medical Centers

Department of Defense

Huang C, Koppel R, McGreevey JD 3rd, Craven CK, Schreiber R. Transitions from one Electronic Health record to another: challenges, pitfalls, and recommendations. Appl Clin Inf. 2020;11(5):742–54.

Article   Google Scholar  

Penrod LE. Electronic Health Record Transition considerations. PM R. 2017;9(5S):S13–8.

Article   PubMed   Google Scholar  

Cogan AM, Haltom TM, Shimada SL, Davila JA, McGinn BP, Fix GM. Understanding patients’ experiences during transitions from one electronic health record to another: a scoping review. PEC Innov. 2024;4:100258. https://doi.org/10.1016/j.pecinn.2024.100258 . PMID: 38327990; PMCID: PMC10847675.

Article   PubMed   PubMed Central   Google Scholar  

Powell KR. Patient-perceived facilitators of and barriers to Electronic Portal Use: a systematic review. Comput Inf Nurs. 2017;35(11):565–73.

Google Scholar  

Wilson-Stronks A, Lee KK, Cordero CL, et al. One size does not fit all: meeting the Health Care needs of diverse populations. Oakbrook Terrace, IL: The Joint Commission; 2008.

Carini E, Villani L, Pezzullo AM, Gentili A, Barbara A, Ricciardi W, Boccia S. The Impact of Digital Patient Portals on Health outcomes, System Efficiency, and patient attitudes: updated systematic literature review. J Med Internet Res. 2021;23(9):e26189.

Home -. My HealtheVet - My HealtheVet (va.gov).

Nazi KM, Turvey CL, Klein DM, Hogan TP. A decade of veteran voices: examining patient Portal Enhancements through the Lens of user-centered design. J Med Internet Res. 2018;20(7):e10413. https://doi.org/10.2196/10413 .

Tapuria A, Porat T, Kalra D, Dsouza G, Xiaohui S, Curcin V. Impact of patient access to their electronic health record: systematic review. Inf Health Soc Care. 2021;46:2.

Fix GM, Haltom TM, Cogan AM, et al. Understanding patients’ preferences and experiences during an Electronic Health Record Transition. J GEN INTERN MED. 2023. https://doi.org/10.1007/s11606-023-08338-6 .

Monturo C, Brockway C, Ginev A. Electronic Health Record Transition: the patient experience. CIN: Computers Inf Nurs. 2022;40:1.

Tian D, Hoehner CM, Woeltje KF, Luong L, Lane MA. Disrupted and restored patient experience with transition to New Electronic Health Record System. J Patient Exp. 2021;18:8.

Emergency management programs for healthcare facilities. the four phases of emergency management. US Department of Homeland Security website: https://www.hsdl.org/?view&did=765520 . Accessed 28 Aug 2023.

Ahlness EA, Orlander J, Brunner J, Cutrona SL, Kim B, Molloy-Paolillo BK, Rinne ST, Rucci J, Sayre G, Anderson E. Everything’s so Role-Specific: VA Employee Perspectives’ on Electronic Health Record (EHR) transition implications for roles and responsibilities. J Gen Intern Med. 2023;38(Suppl 4):991–8. Epub 2023 Oct 5. PMID: 37798577; PMCID: PMC10593626.

Rucci JM, Ball S, Brunner J, Moldestad M, Cutrona SL, Sayre G, Rinne S. Like one long battle: employee perspectives of the simultaneous impact of COVID-19 and an Electronic Health Record Transition. J Gen Intern Med. 2023;38(Suppl 4):1040–8. https://doi.org/10.1007/s11606-023-08284-3 . Epub 2023 Oct 5. PMID: 37798583; PMCID: PMC10593661.

Sayre G, Young J. Beyond open-ended questions: purposeful interview guide development to elicit rich, trustworthy data [videorecording]. Seattle (WA): VA Health Services Research & Development HSR&D Cyberseminars; 2018.

Averill JB. Matrix analysis as a complementary analytic strategy in qualitative inquiry. Qual Health Res. 2002;12:6855–66.

Elo S, Kyngäs H. The qualitative content analysis process. J Adv Nurs. 2008;62:1107–15.

Haun JN, Lind JD, Shimada SL, Simon SR. Evaluating Secure Messaging from the veteran perspective: informing the adoption and sustained use of a patient-driven communication platform. Ann Anthropol Pract. 2013;372:57–74.

Kittler AF, Carlson GL, Harris C, Lippincott M, Pizziferri L, Volk LA, et al. Primary care physician attitudes toward using a secure web-based portal designed to facilitate electronic communication with patients. Inf Prim Care. 2004;123:129–38.

Shimada SL, Petrakis BA, Rothendler JA, Zirkle M, Zhao S, Feng H, Fix GM, Ozkaynak M, Martin T, Johnson SA, Tulu B, Gordon HS, Simon SR, Woods SS. An analysis of patient-provider secure messaging at two Veterans Health Administration medical centers: message content and resolution through secure messaging. J Am Med Inf Assoc. 2017;24:5.

Jha AK, Perlin JB, Kizer KW, Dudley RA. Effect of the transformation of the Veterans Affairs Health Care System on the quality of care. N Engl J Med. 2003;348:22.

McAlearney AS, Walker DM, Gaughan A, Moffatt-Bruce S, Huerta TR. Helping patients be better patients: a qualitative study of perceptions about Inpatient Portal Use. Telemed J E Health. 2020;26:9.

https://www.myhealth.va.gov/mhv-portal-web/transitioning-to-my-va-health-learn-more .

Beagley L. Educating patients: understanding barriers, learning styles, and teaching techniques. J Perianesth Nurs. 2011;26:5.

Moldestad M, Stryczek KC, Haverhals L, Kenney R, Lee M, Ball S, et al. Competing demands: Scheduling challenges in being veteran-centric in the setting of Health System initiatives to Improve Access. Mil Med. 2021;186:11–2.

Adusumalli J, Bhagra A, Vitek S, Clark SD, Chon TY. Stress management in staff supporting electronic health record transitions: a novel approach. Explore (NY). 2021;17:6.

Heponiemi T, Gluschkoff K, Vehko T, Kaihlanen AM, Saranto K, Nissinen S, et al. Electronic Health Record implementations and Insufficient Training Endanger nurses’ Well-being: cross-sectional survey study. J Med Internet Res. 2021;23:12e27096.

Laurant M, van der Biezen M, Wijers N, Watananirun K, Kontopantelis E, van Vught AJ. Nurses as substitutes for doctors in primary care. Cochrane Database Syst Rev. 201;7(7):CD001271.

Elnahal S, Kadakia KT, Gondi S, How, U.S. Health systems Can Build Capacity to Handle Demand Surges. Harvard Business Review. 2021. https://hbr.org/2021/10/how-u-s-health-systems-can-build-capacity-to-handle-demand-surges/ Accessed 25 Nov 2022.

George RE, Lowe WA. Well-being and uncertainty in health care practice. Clin Teach. 2019;16:4.

Download references

Acknowledgments

We acknowledge and thank members of the EMPIRIC Evaluation qualitative and supporting team for their contributions to this work including Ellen Ahlness, PhD, Julian Brunner, PhD, Adena Cohen-Bearak, MPH, M.Ed, Leah Cubanski, BA, Christine Firestone, Bo Kim, PhD, Megan Moldestad, MS, and Rachel Smith. We greatly appreciate the staff at the Mann-Grandstaff VA Medical Center and associated community-based outpatient clinics for generously sharing of their time and experiences participating in this study during this challenging time.

The “EHRM Partnership Integrating Rapid Cycle Evaluation to Improve Cerner Implementation (EMPIRIC)” (PEC 20–168) work was supported by funding from the US Department of Veterans Affairs, Veterans Health Administration, Health Services Research & Development Quality Enhancement Research Initiative (QUERI) (PEC 20–168). The findings and conclusions in this article are those of the authors and do not necessarily reflect the views of the Veterans Health Administration, Veterans Affairs, or any participating health agency or funder.

Author information

Authors and affiliations.

VA Northeast Ohio Healthcare System, 10701 East Blvd., Research Service 151, 44106, Cleveland, OH, USA

Sherry L. Ball

Center for Healthcare Organization and Implementation Research, VA Boston Healthcare System, Boston, MA, USA

Bo Kim & Seppo T. Rinne

Department of Psychiatry, Harvard Medical School, Boston, MA, USA

Center for Healthcare Organization and Implementation Research, VA Bedford Healthcare System, Bedford, MA, USA

Sarah L. Cutrona & Brianne K. Molloy-Paolillo

Division of Health Informatics & Implementation Science, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA, USA

Sarah L. Cutrona

Seattle-Denver Center of Innovation for Veteran-Centered and Value-Driven Care, VHA Puget Sound Health Care System, Seattle, WA, USA

Ellen Ahlness, Megan Moldestad & George Sayre

University of Washington School of Public Health, Seattle, WA, USA

George Sayre

Geisel School of Medicine at Dartmouth, Hannover, NH, USA

Seppo T. Rinne

You can also search for this author in PubMed   Google Scholar

Contributions

S.R. designed the larger study. G.S. was the qualitative methodologist who led the qualitative team. S.B., E.A., and M.M. created the interview guides and completed the interviews; Data analysis, data interpretation, and the initial manuscript draft were completed by S.B. and B.K. S.C. and B.M. worked with the qualitative team to finalize the analysis and edit and finalize the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Sherry L. Ball .

Ethics declarations

Ethics approval and consent to participate.

This evaluation was designated as non-research/quality improvement by the VA Bedford Healthcare System Institutional Review Board. All methods were carried out in accordance with local and national VA guidelines and regulations for quality improvement activities. This study included virtual interviews with participants via MS Teams. Employees volunteered to participate in interviews and verbal consent was obtained to record interviews. Study materials, including interview guides with verbal consent procedures, were reviewed and approved by labor unions and determined as non-research by the VA Bedford Healthcare System Institutional Review Board.

Consent for publication

Not applicable.

The findings and conclusions in this paper are those of the authors and do not necessarily represent the official position of the Department of Veterans Affairs.

Prior presentations

Ball S, Kim B, Moldestad M, Molloy-Paolillo B, Cubanski L, Cutrona S, Sayre G, and Rinne S. (2022, June). Electronic Health Record Transition: Providers’ Experiences with Frustrated Patients. Poster presentation at the 2022 AcademyHealth Annual Research Meeting. June 2022.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Ball, S.L., Kim, B., Cutrona, S.L. et al. Clinician and staff experiences with frustrated patients during an electronic health record transition: a qualitative case study. BMC Health Serv Res 24 , 535 (2024). https://doi.org/10.1186/s12913-024-10974-5

Download citation

Received : 29 August 2023

Accepted : 09 April 2024

Published : 26 April 2024

DOI : https://doi.org/10.1186/s12913-024-10974-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• EHR transition
• Patient experience
• Clinician experience
• Qualitative analysis

BMC Health Services Research

ISSN: 1472-6963

• General enquiries: [email protected]

• Open access
• Published: 18 April 2024

Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research

• James Shaw 1 , 13 ,
• Joseph Ali 2 , 3 ,
• Caesar A. Atuire 4 , 5 ,
• Phaik Yeong Cheah 6 ,
• Armando Guio Español 7 ,
• Judy Wawira Gichoya 8 ,
• Adrienne Hunt 9 ,
• Daudi Jjingo 10 ,
• Katherine Littler 9 ,
• Daniela Paolotti 11 &
• Effy Vayena 12  

BMC Medical Ethics volume  25 , Article number:  46 ( 2024 ) Cite this article

920 Accesses

6 Altmetric

Metrics details

The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice. In this paper we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022.

The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, research ethics committee members and other actors to engage with challenges and opportunities specifically related to research ethics. In 2022 the focus of the GFBR was “Ethics of AI in Global Health Research”. The forum consisted of 6 case study presentations, 16 governance presentations, and a series of small group and large group discussions. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. In this paper, we highlight central insights arising from GFBR 2022.

We describe the significance of four thematic insights arising from the forum: (1) Appropriateness of building AI, (2) Transferability of AI systems, (3) Accountability for AI decision-making and outcomes, and (4) Individual consent. We then describe eight recommendations for governance leaders to enhance the ethical governance of AI in global health research, addressing issues such as AI impact assessments, environmental values, and fair partnerships.

Conclusions

The 2022 Global Forum on Bioethics in Research illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

Peer Review reports

Introduction

The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice [ 1 , 2 , 3 ]. Beyond the growing number of AI applications being implemented in health care, capabilities of AI models such as Large Language Models (LLMs) expand the potential reach and significance of AI technologies across health-related fields [ 4 , 5 ]. Discussion about effective, ethical governance of AI technologies has spanned a range of governance approaches, including government regulation, organizational decision-making, professional self-regulation, and research ethics review [ 6 , 7 , 8 ]. In this paper, we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health research, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022. Although applications of AI for research, health care, and public health are diverse and advancing rapidly, the insights generated at the forum remain highly relevant from a global health perspective. After summarizing important context for work in this domain, we highlight categories of ethical issues emphasized at the forum for attention from a research ethics perspective internationally. We then outline strategies proposed for research, innovation, and governance to support more ethical AI for global health.

In this paper, we adopt the definition of AI systems provided by the Organization for Economic Cooperation and Development (OECD) as our starting point. Their definition states that an AI system is “a machine-based system that can, for a given set of human-defined objectives, make predictions, recommendations, or decisions influencing real or virtual environments. AI systems are designed to operate with varying levels of autonomy” [ 9 ]. The conceptualization of an algorithm as helping to constitute an AI system, along with hardware, other elements of software, and a particular context of use, illustrates the wide variety of ways in which AI can be applied. We have found it useful to differentiate applications of AI in research as those classified as “AI systems for discovery” and “AI systems for intervention”. An AI system for discovery is one that is intended to generate new knowledge, for example in drug discovery or public health research in which researchers are seeking potential targets for intervention, innovation, or further research. An AI system for intervention is one that directly contributes to enacting an intervention in a particular context, for example informing decision-making at the point of care or assisting with accuracy in a surgical procedure.

The mandate of the GFBR is to take a broad view of what constitutes research and its regulation in global health, with special attention to bioethics in Low- and Middle- Income Countries. AI as a group of technologies demands such a broad view. AI development for health occurs in a variety of environments, including universities and academic health sciences centers where research ethics review remains an important element of the governance of science and innovation internationally [ 10 , 11 ]. In these settings, research ethics committees (RECs; also known by different names such as Institutional Review Boards or IRBs) make decisions about the ethical appropriateness of projects proposed by researchers and other institutional members, ultimately determining whether a given project is allowed to proceed on ethical grounds [ 12 ].

However, research involving AI for health also takes place in large corporations and smaller scale start-ups, which in some jurisdictions fall outside the scope of research ethics regulation. In the domain of AI, the question of what constitutes research also becomes blurred. For example, is the development of an algorithm itself considered a part of the research process? Or only when that algorithm is tested under the formal constraints of a systematic research methodology? In this paper we take an inclusive view, in which AI development is included in the definition of research activity and within scope for our inquiry, regardless of the setting in which it takes place. This broad perspective characterizes the approach to “research ethics” we take in this paper, extending beyond the work of RECs to include the ethical analysis of the wide range of activities that constitute research as the generation of new knowledge and intervention in the world.

Ethical governance of AI in global health

The ethical governance of AI for global health has been widely discussed in recent years. The World Health Organization (WHO) released its guidelines on ethics and governance of AI for health in 2021, endorsing a set of six ethical principles and exploring the relevance of those principles through a variety of use cases. The WHO guidelines also provided an overview of AI governance, defining governance as covering “a range of steering and rule-making functions of governments and other decision-makers, including international health agencies, for the achievement of national health policy objectives conducive to universal health coverage.” (p. 81) The report usefully provided a series of recommendations related to governance of seven domains pertaining to AI for health: data, benefit sharing, the private sector, the public sector, regulation, policy observatories/model legislation, and global governance. The report acknowledges that much work is yet to be done to advance international cooperation on AI governance, especially related to prioritizing voices from Low- and Middle-Income Countries (LMICs) in global dialogue.

One important point emphasized in the WHO report that reinforces the broader literature on global governance of AI is the distribution of responsibility across a wide range of actors in the AI ecosystem. This is especially important to highlight when focused on research for global health, which is specifically about work that transcends national borders. Alami et al. (2020) discussed the unique risks raised by AI research in global health, ranging from the unavailability of data in many LMICs required to train locally relevant AI models to the capacity of health systems to absorb new AI technologies that demand the use of resources from elsewhere in the system. These observations illustrate the need to identify the unique issues posed by AI research for global health specifically, and the strategies that can be employed by all those implicated in AI governance to promote ethically responsible use of AI in global health research.

RECs and the regulation of research involving AI

RECs represent an important element of the governance of AI for global health research, and thus warrant further commentary as background to our paper. Despite the importance of RECs, foundational questions have been raised about their capabilities to accurately understand and address ethical issues raised by studies involving AI. Rahimzadeh et al. (2023) outlined how RECs in the United States are under-prepared to align with recent federal policy requiring that RECs review data sharing and management plans with attention to the unique ethical issues raised in AI research for health [ 13 ]. Similar research in South Africa identified variability in understanding of existing regulations and ethical issues associated with health-related big data sharing and management among research ethics committee members [ 14 , 15 ]. The effort to address harms accruing to groups or communities as opposed to individuals whose data are included in AI research has also been identified as a unique challenge for RECs [ 16 , 17 ]. Doerr and Meeder (2022) suggested that current regulatory frameworks for research ethics might actually prevent RECs from adequately addressing such issues, as they are deemed out of scope of REC review [ 16 ]. Furthermore, research in the United Kingdom and Canada has suggested that researchers using AI methods for health tend to distinguish between ethical issues and social impact of their research, adopting an overly narrow view of what constitutes ethical issues in their work [ 18 ].

The challenges for RECs in adequately addressing ethical issues in AI research for health care and public health exceed a straightforward survey of ethical considerations. As Ferretti et al. (2021) contend, some capabilities of RECs adequately cover certain issues in AI-based health research, such as the common occurrence of conflicts of interest where researchers who accept funds from commercial technology providers are implicitly incentivized to produce results that align with commercial interests [ 12 ]. However, some features of REC review require reform to adequately meet ethical needs. Ferretti et al. outlined weaknesses of RECs that are longstanding and those that are novel to AI-related projects, proposing a series of directions for development that are regulatory, procedural, and complementary to REC functionality. The work required on a global scale to update the REC function in response to the demands of research involving AI is substantial.

These issues take greater urgency in the context of global health [ 19 ]. Teixeira da Silva (2022) described the global practice of “ethics dumping”, where researchers from high income countries bring ethically contentious practices to RECs in low-income countries as a strategy to gain approval and move projects forward [ 20 ]. Although not yet systematically documented in AI research for health, risk of ethics dumping in AI research is high. Evidence is already emerging of practices of “health data colonialism”, in which AI researchers and developers from large organizations in high-income countries acquire data to build algorithms in LMICs to avoid stricter regulations [ 21 ]. This specific practice is part of a larger collection of practices that characterize health data colonialism, involving the broader exploitation of data and the populations they represent primarily for commercial gain [ 21 , 22 ]. As an additional complication, AI algorithms trained on data from high-income contexts are unlikely to apply in straightforward ways to LMIC settings [ 21 , 23 ]. In the context of global health, there is widespread acknowledgement about the need to not only enhance the knowledge base of REC members about AI-based methods internationally, but to acknowledge the broader shifts required to encourage their capabilities to more fully address these and other ethical issues associated with AI research for health [ 8 ].

Although RECs are an important part of the story of the ethical governance of AI for global health research, they are not the only part. The responsibilities of supra-national entities such as the World Health Organization, national governments, organizational leaders, commercial AI technology providers, health care professionals, and other groups continue to be worked out internationally. In this context of ongoing work, examining issues that demand attention and strategies to address them remains an urgent and valuable task.

The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, REC members and other actors to engage with challenges and opportunities specifically related to research ethics. Each year the GFBR meeting includes a series of case studies and keynotes presented in plenary format to an audience of approximately 100 people who have applied and been competitively selected to attend, along with small-group breakout discussions to advance thinking on related issues. The specific topic of the forum changes each year, with past topics including ethical issues in research with people living with mental health conditions (2021), genome editing (2019), and biobanking/data sharing (2018). The forum is intended to remain grounded in the practical challenges of engaging in research ethics, with special interest in low resource settings from a global health perspective. A post-meeting fellowship scheme is open to all LMIC participants, providing a unique opportunity to apply for funding to further explore and address the ethical challenges that are identified during the meeting.

In 2022, the focus of the GFBR was “Ethics of AI in Global Health Research”. The forum consisted of 6 case study presentations (both short and long form) reporting on specific initiatives related to research ethics and AI for health, and 16 governance presentations (both short and long form) reporting on actual approaches to governing AI in different country settings. A keynote presentation from Professor Effy Vayena addressed the topic of the broader context for AI ethics in a rapidly evolving field. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. The 2-day forum addressed a wide range of themes. The conference report provides a detailed overview of each of the specific topics addressed while a policy paper outlines the cross-cutting themes (both documents are available at the GFBR website: https://www.gfbr.global/past-meetings/16th-forum-cape-town-south-africa-29-30-november-2022/ ). As opposed to providing a detailed summary in this paper, we aim to briefly highlight central issues raised, solutions proposed, and the challenges facing the research ethics community in the years to come.

In this way, our primary aim in this paper is to present a synthesis of the challenges and opportunities raised at the GFBR meeting and in the planning process, followed by our reflections as a group of authors on their significance for governance leaders in the coming years. We acknowledge that the views represented at the meeting and in our results are a partial representation of the universe of views on this topic; however, the GFBR leadership invested a great deal of resources in convening a deeply diverse and thoughtful group of researchers and practitioners working on themes of bioethics related to AI for global health including those based in LMICs. We contend that it remains rare to convene such a strong group for an extended time and believe that many of the challenges and opportunities raised demand attention for more ethical futures of AI for health. Nonetheless, our results are primarily descriptive and are thus not explicitly grounded in a normative argument. We make effort in the Discussion section to contextualize our results by describing their significance and connecting them to broader efforts to reform global health research and practice.

Uniquely important ethical issues for AI in global health research

Presentations and group dialogue over the course of the forum raised several issues for consideration, and here we describe four overarching themes for the ethical governance of AI in global health research. Brief descriptions of each issue can be found in Table  1 . Reports referred to throughout the paper are available at the GFBR website provided above.

The first overarching thematic issue relates to the appropriateness of building AI technologies in response to health-related challenges in the first place. Case study presentations referred to initiatives where AI technologies were highly appropriate, such as in ear shape biometric identification to more accurately link electronic health care records to individual patients in Zambia (Alinani Simukanga). Although important ethical issues were raised with respect to privacy, trust, and community engagement in this initiative, the AI-based solution was appropriately matched to the challenge of accurately linking electronic records to specific patient identities. In contrast, forum participants raised questions about the appropriateness of an initiative using AI to improve the quality of handwashing practices in an acute care hospital in India (Niyoshi Shah), which led to gaming the algorithm. Overall, participants acknowledged the dangers of techno-solutionism, in which AI researchers and developers treat AI technologies as the most obvious solutions to problems that in actuality demand much more complex strategies to address [ 24 ]. However, forum participants agreed that RECs in different contexts have differing degrees of power to raise issues of the appropriateness of an AI-based intervention.

The second overarching thematic issue related to whether and how AI-based systems transfer from one national health context to another. One central issue raised by a number of case study presentations related to the challenges of validating an algorithm with data collected in a local environment. For example, one case study presentation described a project that would involve the collection of personally identifiable data for sensitive group identities, such as tribe, clan, or religion, in the jurisdictions involved (South Africa, Nigeria, Tanzania, Uganda and the US; Gakii Masunga). Doing so would enable the team to ensure that those groups were adequately represented in the dataset to ensure the resulting algorithm was not biased against specific community groups when deployed in that context. However, some members of these communities might desire to be represented in the dataset, whereas others might not, illustrating the need to balance autonomy and inclusivity. It was also widely recognized that collecting these data is an immense challenge, particularly when historically oppressive practices have led to a low-trust environment for international organizations and the technologies they produce. It is important to note that in some countries such as South Africa and Rwanda, it is illegal to collect information such as race and tribal identities, re-emphasizing the importance for cultural awareness and avoiding “one size fits all” solutions.

The third overarching thematic issue is related to understanding accountabilities for both the impacts of AI technologies and governance decision-making regarding their use. Where global health research involving AI leads to longer-term harms that might fall outside the usual scope of issues considered by a REC, who is to be held accountable, and how? This question was raised as one that requires much further attention, with law being mixed internationally regarding the mechanisms available to hold researchers, innovators, and their institutions accountable over the longer term. However, it was recognized in breakout group discussion that many jurisdictions are developing strong data protection regimes related specifically to international collaboration for research involving health data. For example, Kenya’s Data Protection Act requires that any internationally funded projects have a local principal investigator who will hold accountability for how data are shared and used [ 25 ]. The issue of research partnerships with commercial entities was raised by many participants in the context of accountability, pointing toward the urgent need for clear principles related to strategies for engagement with commercial technology companies in global health research.

The fourth and final overarching thematic issue raised here is that of consent. The issue of consent was framed by the widely shared recognition that models of individual, explicit consent might not produce a supportive environment for AI innovation that relies on the secondary uses of health-related datasets to build AI algorithms. Given this recognition, approaches such as community oversight of health data uses were suggested as a potential solution. However, the details of implementing such community oversight mechanisms require much further attention, particularly given the unique perspectives on health data in different country settings in global health research. Furthermore, some uses of health data do continue to require consent. One case study of South Africa, Nigeria, Kenya, Ethiopia and Uganda suggested that when health data are shared across borders, individual consent remains necessary when data is transferred from certain countries (Nezerith Cengiz). Broader clarity is necessary to support the ethical governance of health data uses for AI in global health research.

Recommendations for ethical governance of AI in global health research

Dialogue at the forum led to a range of suggestions for promoting ethical conduct of AI research for global health, related to the various roles of actors involved in the governance of AI research broadly defined. The strategies are written for actors we refer to as “governance leaders”, those people distributed throughout the AI for global health research ecosystem who are responsible for ensuring the ethical and socially responsible conduct of global health research involving AI (including researchers themselves). These include RECs, government regulators, health care leaders, health professionals, corporate social accountability officers, and others. Enacting these strategies would bolster the ethical governance of AI for global health more generally, enabling multiple actors to fulfill their roles related to governing research and development activities carried out across multiple organizations, including universities, academic health sciences centers, start-ups, and technology corporations. Specific suggestions are summarized in Table  2 .

First, forum participants suggested that governance leaders including RECs, should remain up to date on recent advances in the regulation of AI for health. Regulation of AI for health advances rapidly and takes on different forms in jurisdictions around the world. RECs play an important role in governance, but only a partial role; it was deemed important for RECs to acknowledge how they fit within a broader governance ecosystem in order to more effectively address the issues within their scope. Not only RECs but organizational leaders responsible for procurement, researchers, and commercial actors should all commit to efforts to remain up to date about the relevant approaches to regulating AI for health care and public health in jurisdictions internationally. In this way, governance can more adequately remain up to date with advances in regulation.

Second, forum participants suggested that governance leaders should focus on ethical governance of health data as a basis for ethical global health AI research. Health data are considered the foundation of AI development, being used to train AI algorithms for various uses [ 26 ]. By focusing on ethical governance of health data generation, sharing, and use, multiple actors will help to build an ethical foundation for AI development among global health researchers.

Third, forum participants believed that governance processes should incorporate AI impact assessments where appropriate. An AI impact assessment is the process of evaluating the potential effects, both positive and negative, of implementing an AI algorithm on individuals, society, and various stakeholders, generally over time frames specified in advance of implementation [ 27 ]. Although not all types of AI research in global health would warrant an AI impact assessment, this is especially relevant for those studies aiming to implement an AI system for intervention into health care or public health. Organizations such as RECs can use AI impact assessments to boost understanding of potential harms at the outset of a research project, encouraging researchers to more deeply consider potential harms in the development of their study.

Fourth, forum participants suggested that governance decisions should incorporate the use of environmental impact assessments, or at least the incorporation of environment values when assessing the potential impact of an AI system. An environmental impact assessment involves evaluating and anticipating the potential environmental effects of a proposed project to inform ethical decision-making that supports sustainability [ 28 ]. Although a relatively new consideration in research ethics conversations [ 29 ], the environmental impact of building technologies is a crucial consideration for the public health commitment to environmental sustainability. Governance leaders can use environmental impact assessments to boost understanding of potential environmental harms linked to AI research projects in global health over both the shorter and longer terms.

Fifth, forum participants suggested that governance leaders should require stronger transparency in the development of AI algorithms in global health research. Transparency was considered essential in the design and development of AI algorithms for global health to ensure ethical and accountable decision-making throughout the process. Furthermore, whether and how researchers have considered the unique contexts into which such algorithms may be deployed can be surfaced through stronger transparency, for example in describing what primary considerations were made at the outset of the project and which stakeholders were consulted along the way. Sharing information about data provenance and methods used in AI development will also enhance the trustworthiness of the AI-based research process.

Sixth, forum participants suggested that governance leaders can encourage or require community engagement at various points throughout an AI project. It was considered that engaging patients and communities is crucial in AI algorithm development to ensure that the technology aligns with community needs and values. However, participants acknowledged that this is not a straightforward process. Effective community engagement requires lengthy commitments to meeting with and hearing from diverse communities in a given setting, and demands a particular set of skills in communication and dialogue that are not possessed by all researchers. Encouraging AI researchers to begin this process early and build long-term partnerships with community members is a promising strategy to deepen community engagement in AI research for global health. One notable recommendation was that research funders have an opportunity to incentivize and enable community engagement with funds dedicated to these activities in AI research in global health.

Seventh, forum participants suggested that governance leaders can encourage researchers to build strong, fair partnerships between institutions and individuals across country settings. In a context of longstanding imbalances in geopolitical and economic power, fair partnerships in global health demand a priori commitments to share benefits related to advances in medical technologies, knowledge, and financial gains. Although enforcement of this point might be beyond the remit of RECs, commentary will encourage researchers to consider stronger, fairer partnerships in global health in the longer term.

Eighth, it became evident that it is necessary to explore new forms of regulatory experimentation given the complexity of regulating a technology of this nature. In addition, the health sector has a series of particularities that make it especially complicated to generate rules that have not been previously tested. Several participants highlighted the desire to promote spaces for experimentation such as regulatory sandboxes or innovation hubs in health. These spaces can have several benefits for addressing issues surrounding the regulation of AI in the health sector, such as: (i) increasing the capacities and knowledge of health authorities about this technology; (ii) identifying the major problems surrounding AI regulation in the health sector; (iii) establishing possibilities for exchange and learning with other authorities; (iv) promoting innovation and entrepreneurship in AI in health; and (vi) identifying the need to regulate AI in this sector and update other existing regulations.

Ninth and finally, forum participants believed that the capabilities of governance leaders need to evolve to better incorporate expertise related to AI in ways that make sense within a given jurisdiction. With respect to RECs, for example, it might not make sense for every REC to recruit a member with expertise in AI methods. Rather, it will make more sense in some jurisdictions to consult with members of the scientific community with expertise in AI when research protocols are submitted that demand such expertise. Furthermore, RECs and other approaches to research governance in jurisdictions around the world will need to evolve in order to adopt the suggestions outlined above, developing processes that apply specifically to the ethical governance of research using AI methods in global health.

Research involving the development and implementation of AI technologies continues to grow in global health, posing important challenges for ethical governance of AI in global health research around the world. In this paper we have summarized insights from the 2022 GFBR, focused specifically on issues in research ethics related to AI for global health research. We summarized four thematic challenges for governance related to AI in global health research and nine suggestions arising from presentations and dialogue at the forum. In this brief discussion section, we present an overarching observation about power imbalances that frames efforts to evolve the role of governance in global health research, and then outline two important opportunity areas as the field develops to meet the challenges of AI in global health research.

Dialogue about power is not unfamiliar in global health, especially given recent contributions exploring what it would mean to de-colonize global health research, funding, and practice [ 30 , 31 ]. Discussions of research ethics applied to AI research in global health contexts are deeply infused with power imbalances. The existing context of global health is one in which high-income countries primarily located in the “Global North” charitably invest in projects taking place primarily in the “Global South” while recouping knowledge, financial, and reputational benefits [ 32 ]. With respect to AI development in particular, recent examples of digital colonialism frame dialogue about global partnerships, raising attention to the role of large commercial entities and global financial capitalism in global health research [ 21 , 22 ]. Furthermore, the power of governance organizations such as RECs to intervene in the process of AI research in global health varies widely around the world, depending on the authorities assigned to them by domestic research governance policies. These observations frame the challenges outlined in our paper, highlighting the difficulties associated with making meaningful change in this field.

Despite these overarching challenges of the global health research context, there are clear strategies for progress in this domain. Firstly, AI innovation is rapidly evolving, which means approaches to the governance of AI for health are rapidly evolving too. Such rapid evolution presents an important opportunity for governance leaders to clarify their vision and influence over AI innovation in global health research, boosting the expertise, structure, and functionality required to meet the demands of research involving AI. Secondly, the research ethics community has strong international ties, linked to a global scholarly community that is committed to sharing insights and best practices around the world. This global community can be leveraged to coordinate efforts to produce advances in the capabilities and authorities of governance leaders to meaningfully govern AI research for global health given the challenges summarized in our paper.

Limitations

Our paper includes two specific limitations that we address explicitly here. First, it is still early in the lifetime of the development of applications of AI for use in global health, and as such, the global community has had limited opportunity to learn from experience. For example, there were many fewer case studies, which detail experiences with the actual implementation of an AI technology, submitted to GFBR 2022 for consideration than was expected. In contrast, there were many more governance reports submitted, which detail the processes and outputs of governance processes that anticipate the development and dissemination of AI technologies. This observation represents both a success and a challenge. It is a success that so many groups are engaging in anticipatory governance of AI technologies, exploring evidence of their likely impacts and governing technologies in novel and well-designed ways. It is a challenge that there is little experience to build upon of the successful implementation of AI technologies in ways that have limited harms while promoting innovation. Further experience with AI technologies in global health will contribute to revising and enhancing the challenges and recommendations we have outlined in our paper.

Second, global trends in the politics and economics of AI technologies are evolving rapidly. Although some nations are advancing detailed policy approaches to regulating AI more generally, including for uses in health care and public health, the impacts of corporate investments in AI and political responses related to governance remain to be seen. The excitement around large language models (LLMs) and large multimodal models (LMMs) has drawn deeper attention to the challenges of regulating AI in any general sense, opening dialogue about health sector-specific regulations. The direction of this global dialogue, strongly linked to high-profile corporate actors and multi-national governance institutions, will strongly influence the development of boundaries around what is possible for the ethical governance of AI for global health. We have written this paper at a point when these developments are proceeding rapidly, and as such, we acknowledge that our recommendations will need updating as the broader field evolves.

Ultimately, coordination and collaboration between many stakeholders in the research ethics ecosystem will be necessary to strengthen the ethical governance of AI in global health research. The 2022 GFBR illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

Data availability

All data and materials analyzed to produce this paper are available on the GFBR website: https://www.gfbr.global/past-meetings/16th-forum-cape-town-south-africa-29-30-november-2022/ .

Clark P, Kim J, Aphinyanaphongs Y, Marketing, Food US. Drug Administration Clearance of Artificial Intelligence and Machine Learning Enabled Software in and as Medical devices: a systematic review. JAMA Netw Open. 2023;6(7):e2321792–2321792.

Article   Google Scholar  

Potnis KC, Ross JS, Aneja S, Gross CP, Richman IB. Artificial intelligence in breast cancer screening: evaluation of FDA device regulation and future recommendations. JAMA Intern Med. 2022;182(12):1306–12.

Siala H, Wang Y. SHIFTing artificial intelligence to be responsible in healthcare: a systematic review. Soc Sci Med. 2022;296:114782.

Yang X, Chen A, PourNejatian N, Shin HC, Smith KE, Parisien C, et al. A large language model for electronic health records. NPJ Digit Med. 2022;5(1):194.

Meskó B, Topol EJ. The imperative for regulatory oversight of large language models (or generative AI) in healthcare. NPJ Digit Med. 2023;6(1):120.

Jobin A, Ienca M, Vayena E. The global landscape of AI ethics guidelines. Nat Mach Intell. 2019;1(9):389–99.

Minssen T, Vayena E, Cohen IG. The challenges for Regulating Medical Use of ChatGPT and other large Language models. JAMA. 2023.

Ho CWL, Malpani R. Scaling up the research ethics framework for healthcare machine learning as global health ethics and governance. Am J Bioeth. 2022;22(5):36–8.

Yeung K. Recommendation of the council on artificial intelligence (OECD). Int Leg Mater. 2020;59(1):27–34.

Maddox TM, Rumsfeld JS, Payne PR. Questions for artificial intelligence in health care. JAMA. 2019;321(1):31–2.

Dzau VJ, Balatbat CA, Ellaissi WF. Revisiting academic health sciences systems a decade later: discovery to health to population to society. Lancet. 2021;398(10318):2300–4.

Ferretti A, Ienca M, Sheehan M, Blasimme A, Dove ES, Farsides B, et al. Ethics review of big data research: what should stay and what should be reformed? BMC Med Ethics. 2021;22(1):1–13.

Rahimzadeh V, Serpico K, Gelinas L. Institutional review boards need new skills to review data sharing and management plans. Nat Med. 2023;1–3.

Kling S, Singh S, Burgess TL, Nair G. The role of an ethics advisory committee in data science research in sub-saharan Africa. South Afr J Sci. 2023;119(5–6):1–3.

Google Scholar  

Cengiz N, Kabanda SM, Esterhuizen TM, Moodley K. Exploring perspectives of research ethics committee members on the governance of big data in sub-saharan Africa. South Afr J Sci. 2023;119(5–6):1–9.

Doerr M, Meeder S. Big health data research and group harm: the scope of IRB review. Ethics Hum Res. 2022;44(4):34–8.

Ballantyne A, Stewart C. Big data and public-private partnerships in healthcare and research: the application of an ethics framework for big data in health and research. Asian Bioeth Rev. 2019;11(3):315–26.

Samuel G, Chubb J, Derrick G. Boundaries between research ethics and ethical research use in artificial intelligence health research. J Empir Res Hum Res Ethics. 2021;16(3):325–37.

Murphy K, Di Ruggiero E, Upshur R, Willison DJ, Malhotra N, Cai JC, et al. Artificial intelligence for good health: a scoping review of the ethics literature. BMC Med Ethics. 2021;22(1):1–17.

Teixeira da Silva JA. Handling ethics dumping and neo-colonial research: from the laboratory to the academic literature. J Bioethical Inq. 2022;19(3):433–43.

Ferryman K. The dangers of data colonialism in precision public health. Glob Policy. 2021;12:90–2.

Couldry N, Mejias UA. Data colonialism: rethinking big data’s relation to the contemporary subject. Telev New Media. 2019;20(4):336–49.

Organization WH. Ethics and governance of artificial intelligence for health: WHO guidance. 2021.

Metcalf J, Moss E. Owning ethics: corporate logics, silicon valley, and the institutionalization of ethics. Soc Res Int Q. 2019;86(2):449–76.

Data Protection Act - OFFICE OF THE DATA PROTECTION COMMISSIONER KENYA [Internet]. 2021 [cited 2023 Sep 30]. https://www.odpc.go.ke/dpa-act/ .

Sharon T, Lucivero F. Introduction to the special theme: the expansion of the health data ecosystem–rethinking data ethics and governance. Big Data & Society. Volume 6. London, England: SAGE Publications Sage UK; 2019. p. 2053951719852969.

Reisman D, Schultz J, Crawford K, Whittaker M. Algorithmic impact assessments: a practical Framework for Public Agency. AI Now. 2018.

Morgan RK. Environmental impact assessment: the state of the art. Impact Assess Proj Apprais. 2012;30(1):5–14.

Samuel G, Richie C. Reimagining research ethics to include environmental sustainability: a principled approach, including a case study of data-driven health research. J Med Ethics. 2023;49(6):428–33.

Kwete X, Tang K, Chen L, Ren R, Chen Q, Wu Z, et al. Decolonizing global health: what should be the target of this movement and where does it lead us? Glob Health Res Policy. 2022;7(1):3.

Abimbola S, Asthana S, Montenegro C, Guinto RR, Jumbam DT, Louskieter L, et al. Addressing power asymmetries in global health: imperatives in the wake of the COVID-19 pandemic. PLoS Med. 2021;18(4):e1003604.

Benatar S. Politics, power, poverty and global health: systems and frames. Int J Health Policy Manag. 2016;5(10):599.

Download references

Acknowledgements

We would like to acknowledge the outstanding contributions of the attendees of GFBR 2022 in Cape Town, South Africa. This paper is authored by members of the GFBR 2022 Planning Committee. We would like to acknowledge additional members Tamra Lysaght, National University of Singapore, and Niresh Bhagwandin, South African Medical Research Council, for their input during the planning stages and as reviewers of the applications to attend the Forum.

This work was supported by Wellcome [222525/Z/21/Z], the US National Institutes of Health, the UK Medical Research Council (part of UK Research and Innovation), and the South African Medical Research Council through funding to the Global Forum on Bioethics in Research.

Author information

Authors and affiliations.

Department of Physical Therapy, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada

Berman Institute of Bioethics, Johns Hopkins University, Baltimore, MD, USA

Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA

Department of Philosophy and Classics, University of Ghana, Legon-Accra, Ghana

Caesar A. Atuire

Centre for Tropical Medicine and Global Health, Nuffield Department of Medicine, University of Oxford, Oxford, UK

Mahidol Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand

Phaik Yeong Cheah

Berkman Klein Center, Harvard University, Bogotá, Colombia

Armando Guio Español

Department of Radiology and Informatics, Emory University School of Medicine, Atlanta, GA, USA

Judy Wawira Gichoya

Health Ethics & Governance Unit, Research for Health Department, Science Division, World Health Organization, Geneva, Switzerland

Adrienne Hunt & Katherine Littler

African Center of Excellence in Bioinformatics and Data Intensive Science, Infectious Diseases Institute, Makerere University, Kampala, Uganda

Daudi Jjingo

ISI Foundation, Turin, Italy

Daniela Paolotti

Department of Health Sciences and Technology, ETH Zurich, Zürich, Switzerland

Effy Vayena

Joint Centre for Bioethics, Dalla Lana School of Public Health, University of Toronto, Toronto, Canada

You can also search for this author in PubMed   Google Scholar

Contributions

JS led the writing, contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. JA contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. CA contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. PYC contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. AE contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. JWG contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. AH contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. DJ contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. KL contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. DP contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. EV contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper.

Corresponding author

Correspondence to James Shaw .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Shaw, J., Ali, J., Atuire, C.A. et al. Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research. BMC Med Ethics 25 , 46 (2024). https://doi.org/10.1186/s12910-024-01044-w

Download citation

Received : 31 October 2023

Accepted : 01 April 2024

Published : 18 April 2024

DOI : https://doi.org/10.1186/s12910-024-01044-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence
• Machine learning
• Research ethics
• Global health

BMC Medical Ethics

ISSN: 1472-6939

• General enquiries: [email protected]

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

482 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

• Open access
• Published: 22 April 2024

The influence of maternal prepregnancy weight and gestational weight gain on the umbilical cord blood metabolome: a case–control study

• Xianxian Yuan   ORCID: orcid.org/0000-0001-8762-8471 1 ,
• Yuru Ma 1 ,
• Jia Wang 2 ,
• Yan Zhao 1 ,
• Wei Zheng 1 ,
• Ruihua Yang 1 ,
• Lirui Zhang 1 ,
• Xin Yan 1 &
• Guanghui Li   ORCID: orcid.org/0000-0003-2290-1515 1  

BMC Pregnancy and Childbirth volume  24 , Article number:  297 ( 2024 ) Cite this article

128 Accesses

Metrics details

Maternal overweight/obesity and excessive gestational weight gain (GWG) are frequently reported to be risk factors for obesity and other metabolic disorders in offspring. Cord blood metabolites provide information on fetal nutritional and metabolic health and could provide an early window of detection of potential health issues among newborns. The aim of the study was to explore the impact of maternal prepregnancy overweight/obesity and excessive GWG on cord blood metabolic profiles.

A case control study including 33 pairs of mothers with prepregnancy overweight/obesity and their neonates, 30 pairs of mothers with excessive GWG and their neonates, and 32 control mother-neonate pairs. Untargeted metabolomic profiling of umbilical cord blood samples were performed using UHPLC‒MS/MS.

Forty-six metabolites exhibited a significant increase and 60 metabolites exhibited a significant reduction in umbilical cord blood from overweight and obese mothers compared with mothers with normal body weight. Steroid hormone biosynthesis and neuroactive ligand‒receptor interactions were the two top-ranking pathways enriched with these metabolites ( P  = 0.01 and 0.03, respectively). Compared with mothers with normal GWG, in mothers with excessive GWG, the levels of 63 metabolites were increased and those of 46 metabolites were decreased in umbilical cord blood. Biosynthesis of unsaturated fatty acids was the most altered pathway enriched with these metabolites ( P  < 0.01).

Conclusions

Prepregnancy overweight and obesity affected the fetal steroid hormone biosynthesis pathway, while excessive GWG affected fetal fatty acid metabolism. This emphasizes the importance of preconception weight loss and maintaining an appropriate GWG, which are beneficial for the long-term metabolic health of offspring.

Peer Review reports

The obesity epidemic is an important public health problem in developed and developing countries [ 1 ] and is associated with the emergence of chronic noncommunicable diseases, including type 2 diabetes mellitus (T2DM), hypertension, cardiovascular disease, nonalcoholic fatty liver disease (NAFLD), and cancer [ 2 , 3 , 4 ]. Maternal obesity is the most common metabolic disturbance in pregnancy, and the prevalence of obesity among women of childbearing age is 7.1% ~ 31.9% in some countries [ 5 ]. In China, the prevalence of overweight and obesity has also increased rapidly in the past four decades. Based on Chinese criteria, the latest national prevalence estimates for 2015–2019 were 34.3% for overweight and 16.4% for obesity in adults (≥ 18 years of age) [ 6 ].

Increasing evidence implicates overnutrition in utero as a major determinant of the health of offspring during childhood and adulthood, which is compatible with the developmental origins of health and disease (DOHaD) framework [ 7 ]. Maternal obesity and excessive gestational weight gain (GWG) are important risk factors for several adverse maternal outcomes, including gestational diabetes and hypertensive disorders, fetal death, and preterm birth [ 8 , 9 , 10 ]. More importantly, they have negative implications for offspring, both perinatally and later in life. Evidence from cohort studies focusing on offspring development confirms the relationship between maternal obesity/excessive GWG and offspring obesity programming [ 11 , 12 , 13 ]. Currently, there is no unified mechanism to explain the adverse outcomes associated with maternal obesity and excessive GWG, which may be the independent and interactive effects of the obese maternal phenotype itself and the diet associated with this phenotype. In addition to genetic and environmental factors, metabolic programming may also lead to the intergenerational transmission of obesity through epigenetic mechanisms.

Metabolomics, which reflects the metabolic phenotype of human subjects and animals, is the profiling of metabolites in biofluids, cells and tissues using high-throughput platforms, such as mass spectrometry. It has unique potential in identifying biomarkers for predicting occurrence, severity, and progression of diseases, as well as exploring underlying mechanistic abnormalities [ 14 , 15 ]. Umbilical cord metabolites can provide information about fetal nutritional and metabolic health, and may provide an early window for detection of potential health issues in newborns [ 16 ]. Previous studies have reported differences in umbilical cord metabolite profiles associated with maternal obesity [ 17 , 18 ]. However, the results were inconsistent due to differences in sample sizes, ethnicity and region, and mass spectrometry. In addition, most studies have not considered the difference in the effects of prepregnancy body mass index (BMI) and GWG on cord blood metabolites.

To investigate the relationship between early metabolic programming and the increased incidence of metabolic diseases in offspring, we studied the associations between elevated prepregnancy BMI/excessive GWG and umbilical cord metabolic profiles. Another purpose of this study was to explore whether there were differences in the effects of prepregnancy overweight/obesity and excessive GWG on cord blood metabolites.

Study population

This was a hospital-based, case control study that included singleton pregnant women who received prenatal care and delivered vaginally at Beijing Obstetrics and Gynecology Hospital, Capital Medical University, from January 2022 to March 2022. We selected 33 pregnant women with a prepregnancy BMI ≥ 24.0 kg/m 2 regardless of their gestational weight gain as the overweight/obese group, 30 pregnant women with a prepregnancy BMI of 18.5–23.9 kg/m 2 and a GWG > 14.0 kg as the excessive GWG group, and 32 pregnant women with a BMI of 18.5–23.9 kg/m 2 and a GWG of 8.0–14.0 kg as the control group. The ages of the three groups were matched (± 1.0 years), and the prepregnancy BMIs of the excessive GWG and control groups were matched (± 1.0 kg/m 2 ).

The inclusion criteria were women with singleton pregnancies, those aged between 20 and 45 years, those with full-term delivery (gestational age ≥ 37 weeks), those with a prepregnancy BMI ≥ 18.5 kg/m 2 , those without prepregnancy diabetes mellitus (DM) or hypertension, and those without gestational diabetes mellitus (GDM). The exclusion criteria were women with multiple pregnancies, those less than 20 years or more than 45 years old, those with a prepregnancy BMI < 18.5 kg/m 2 , those with prepregnancy DM, hypertension or GDM, and those without cord blood samples.

We classified pregnant women into BMI categories based on Chinese guidelines [ 19 ]: normal weight (prepregnancy BMI 18.5–23.9 kg/m 2 ), overweight (prepregnancy BMI 24.0–27.9 kg/m 2 ), and obese (prepregnancy BMI ≥ 28.0 kg/m 2 ). GWG guideline concordance was defined by the 2021 Chinese Nutrition Society recommendations according to prepregnancy BMI. The upper limits of GWG for normal weight, overweight, and obesity were 14.0 kg, 11.0 kg, and 9.0 kg, respectively.

Ethical approval and written informed consent were obtained from all participants. The study has been performed according to the Declaration of Helsinki, and the procedures have been approved by the ethics committees of Beijing Obstetrics and Gynecology Hospital, Capital Medical University (2021-KY-037).

Sample and data collection

Maternal and neonatal clinical data were collected from the electronic medical records system of Beijing Obstetrics and Gynecology Hospital. Maternal clinical characteristics included age, height, prepregnancy and predelivery weight, education level, smoking and drinking status during pregnancy, parity, conception method, comorbidities and complications of pregnancy, family history of DM and hypertension, gestational age, mode of delivery, and biochemical results during pregnancy. Prepregnancy BMI was calculated as prepregnancy weight in kilograms divided by the square of height in meters. GWG was determined by subtracting the prepregnancy weight in kilograms from the predelivery weight in kilograms. GDM was defined using the IAPDSG’s diagnostic criteria at 24 to 28 +6  weeks gestation and the fasting glucose and 1- and 2-h glucose concentrations at the time of the oral glucose tolerance test (OGTT). Neonatal clinical characteristics included sex, birth weight and length. Macrosomia was defined as a birth weight of 4,000 g or more [ 20 ]. Low birth weight (LBW) was defined as a birth weight less than 2,500 g [ 21 ].

Umbilical cord blood samples were obtained by trained midwives after clamping the cord at delivery. Whole blood samples were collected in EDTA tubes, refrigerated for < 24 h, and centrifuged at 2,000 r.p.m. at 4 ℃ for 10 min. Plasma aliquots were stored at -80 ℃ until shipment on dry ice to Novogene, Inc. (Beijing, China) for untargeted metabolomic analysis.

Untargeted metabolomic analyses

Ultrahigh-performance liquid chromatography tandem mass spectrometry (UHPLC‒MS/MS) analyses were performed using a Vanquish UHPLC system (Thermo Fisher, Germany) coupled with an Orbitrap Q Exactive™ HF mass spectrometer (Thermo Fisher, Germany) at Novogene Co., Ltd. (Beijing, China). Detailed descriptions of the sample preparation, mass spectrometry and automated metabolite identification procedures are described in the Supplementary materials .

Statistical analysis

Clinical data statistical analysis.

Quantitative data are shown as the mean ± standard deviation (SD) or median (interquartile range), and categorical data are presented as percentages. The Mann‒Whitney U test, chi-square test, and general linear repeated-measures model were used to assess the differences between the control and study groups when appropriate. A P value < 0.05 was considered statistically significant. All analyses were performed using Statistical Package of Social Sciences version 25.0 (SPSS 25.0) for Windows (SPSS Inc).

Umbilical cord metabolome statistical analysis

These metabolites were annotated using the Human Metabolome Database (HMDB) ( https://hmdb.ca/metabolites ), LIPIDMaps database ( http://www.lipidmaps.org/ ), and Kyoto Encylopaedia of Genes and Genomes (KEGG) database ( https://www.genome.jp/kegg/pathway.html ). Principal component analysis (PCA) and partial least-squares discriminant analysis (PLS-DA) were performed at metaX. We applied univariate analysis ( T test) to calculate the statistical significance ( P value). Metabolites with a variable importance for the projection (VIP) > 1, a P value < 0.05 and a fold change (FC) ≥ 2 or FC ≤ 0.5 were considered to be differential metabolites. A false discovery rate (FDR) control was implemented to correct for multiple comparisons. The q -value in the FDR control was defined as the FDR analog of the P -value. In this study, the q -value was set at 0.2. For clustering heatmaps, the data were normalized using z scores of the intensity areas of differential metabolites and were plotted by the Pheatmap package in R language.

The correlations among differential metabolites were analyzed by cor () in R language (method = Pearson). Statistically significant correlations among differential metabolites were calculated by cor.mtest () in R language. A P value < 0.05 was considered statistically significant, and correlation plots were plotted by the corrplot package in R language. The functions of these metabolites and metabolic pathways were studied using the KEGG database. The metabolic pathway enrichment analysis of differential metabolites was performed when the ratio was satisfied by x/n > y/N, and the metabolic pathway was considered significantly enriched when P  < 0.05.

Demographic characteristics of study participants

The demographic and clinical characteristics of the three population groups enrolled in the study are summarized in Table  1 . Mothers had no significant difference regarding their ages or gestational ages. Compared to the mothers in the excessive GWG and control groups, those in the prepregnancy overweight/obesity group had a significantly higher prepregnancy BMI (25.6 (24.5, 27.2) kg/m 2 ). However, there was no significant difference in prepregnancy BMI between mothers in the excessive GWG group (20.3 ± 1.2 kg/m 2 ) and mothers in the control group (20.6 ± 1.5 kg/m 2 ). Mothers in the excessive GWG group had the highest GWG (17.0 (15.5, 19.1) kg) among the three groups. The mean GWG of the mothers in the prepregnancy overweight/obesity group was 12.9 ± 3.8 kg, which was similar to that of the control group (11.8 ± 1.5 kg). It was noteworthy that among the 33 prepregnancy overweight/obese pregnant women, 20 of them had appropriate GWG, 1 had insufficient GWG, and 12 had excessive GWG. The proportion of mothers who underwent invitro fertilization and embryo transfer (IVF-ET) in the prepregnancy overweight/obesity group (15.2%) was significantly higher than that in the excessive GWG and control groups. There were no statistically significant differences in the proportions of pregnancy outcomes among the three groups, including preeclampsia, premature rupture of membranes, postpartum hemorrhage, macrosomia, and LBW. The babies in the three groups showed no significant difference regarding their birth weights or lengths.

The biochemical parameters of the mothers during pregnancy are shown in Table  2 . The levels of triglyceride (TG) and uric acid (UA) of mothers in the prepregnancy overweight/obesity group were significantly higher than those of the mothers in the excessive GWG and control groups in the first trimester. However, there was no significant difference in the blood glucose and lipid levels in the second and third trimesters of pregnancy among the three groups.

PCA and PLS-DA analysis of cord blood metabolites

Functional and taxonomic annotations of the identified metabolites included the HMDB classification annotations, LIPID MAPS classification annotations, and KEGG pathway annotations. Those cord blood metabolites included lipids and lipid-like molecules, organic acids and their derivatives, and organoheterocyclic compounds, which were mainly involved in metabolism. To better understand the structure of the cord blood metabolome in cases versus controls, we used unsupervised PCA to identify metabolites contributing the most to observed differences in the dataset. PCA did not clearly separate the three groups. We next used PLS-DA to identify metabolites that were predictive of case versus control status. PLS-DA clearly distinguished the cases from the controls (Fig.  1 ), the prepregnancy overweight/obesity group vs. the control group (R2Y = 0.82, Q2Y = 0.37; R2Y = 0.77, Q2Y = 0.13, respectively) (Fig.  1 A), and the excessive GWG group vs. the control group (R2Y = 0.76, Q2Y = 0.16; R2Y = 0.81, Q2Y = 0.41) (Fig.  1 B).

PLS-DA of identified cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (a) PLS-DA score. The horizontal coordinates are the score of the sample on the first principal component; the longitudinal coordinates are the score of the sample on the second principal component; R2Y represents the interpretation rate of the model, and Q2Y is used to evaluate the predictive ability of the PLS-DA model, and when R2Y is greater than Q2Y, it means that the model is well established. (b) PLS-DA valid. Horizontal coordinates represent the correlation between randomly grouped Y and the original group Y, and vertical coordinates represent the scores of R2 and Q2. (1) POS, positive metabolites; (2) NEG, negative metabolites

Maternal prepregnancy overweight/obesity

Screening differential metabolites according to a PLS-DA VIP > 1.0, a FC > 1.2 or < 0.833 and a P value < 0.05, a total of 106 cord blood metabolites (77 positive metabolites and 29 negative metabolites) differed between the prepregnancy overweight/obesity group and the control group. Compared with those in the control group, the levels of 46 metabolites (19 positive metabolites and 27 negative metabolites) were increased in the prepregnancy overweight/obesity group, among which octopamine was the metabolite with the largest increase, followed by (2S)-4-Oxo-2-phenyl-3,4-dihydro-2H-chromen-7-yl beta-D-glucopyranoside, N-tetradecanamide, stearamide, and methanandamide (Fig.  2 A). Compared with the control group, in the prepregnancy overweight/obesity group, there were 60 metabolites (58 positive metabolites and 2 negative metabolites) with reduced concentrations, among which senecionine was the metabolite with the largest decrease, followed by 3-(methylsulfonyl)-2H-chromen-2-one, methyl EudesMate, cuminaldehyde, and 2-(tert-butyl)-1,3-thiazolane-4-carboxylic acid (Fig.  2 A).

Stem plots of differential cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (1) positive metabolites; (2) negative metabolites. Notes: The color of the dot in the stem plots represents the upward and lower adjustment, the blue represents downward, and the red represents upward. The length of the rod represents the size of log2 (FC), and the size of the dot represents the size of the VIP value

A hierarchical analysis of the two groups of differential metabolites obtained was carried out, and the difference in metabolic expression patterns between the two groups and within the same comparison was obtained, which is shown in Fig.  3 . KEGG pathway analysis of differential cord blood metabolites associated with the prepregnancy overweight/obesity group versus the control group is shown in Table  3 and Fig.  4 A. The metabolite enrichment analysis revealed that steroid hormone biosynthesis ( P value = 0.01) and neuroactive ligand‒receptor interactions ( P value = 0.03) were the two pathways that were most altered between the prepregnancy overweight/obesity group and the control group. 19 metabolites were distributed in the pathway of steroid hormone biosynthesis, and 4 metabolites were distributed in the pathway of neuroactive ligand‒receptor interactions. In the steroid hormone biosynthesis pathway, the levels of corticosterone, 11-deoxycortisol, cortisol, testosterone, and 7α-hydroxytestosterone were decreased in the prepregnancy overweight/obesity group relative to those in the control group. In the neuroactive ligand‒receptor interaction pathway, the level of cortisol was decreased and the levels of trace amines were increased in the prepregnancy overweight/obesity group relative to the control group.

Clustering heat maps of differential cord blood metabolites of the three groups. A positive metabolites; B negative metabolites. Notes: Longitudinal clustering of samples and trans-verse clustering of metabolites. The shorter the clustering branches, the higher the similarity. Through horizontal comparison, we can see the relationship between groups of metabolite content clustering

KEGG enrichment scatterplots (a) and net (b) of differential cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (1) positive metabolites; (2) negative metabolites. Notes: (a) The horizontal co-ordinates in the figure are x/y (the number of differential metabolites in the corresponding metabolic pathway/the total number of total metabolites identified in this pathway). The value represents the enrichment degree of differential metabolites in the pathway. The color of the point rep-resents the P -value of the hypergeometric test, and the size of the point represents the number of differential metabolites in the corresponding pathway. (b) The red dot represents a metabolic pathway, the yellow dot represents a substance-related regulatory enzyme information, the green dot represents the background substance of a metabolic pathway, the purple dot represents the molecular module information of a class of substances, the blue dot represents a substance chemical reaction, and the green square represents the differential substance obtained by this comparison

Maternal excessive GWG

A total of 109 cord blood metabolites (52 positive metabolites and 57 negative metabolites) differed between the excessive GWG group and the control group. Compared with the control group, in the excessive GWG group, there were 63 metabolites (15 positive metabolites and 48 negative metabolites) with increased concentrations, among which 2-thio-acetyl MAGE was the metabolite with the largest increase, followed by PC (7:0/8:0), lysopc 16:2 (2 N isomer), MGMG (18:2), and thromboxane B2 (Fig.  2 B). Compared with the levels in the control group, the levels of 46 metabolites (37 positive metabolites and 9 negative metabolites) in the excessive GWG group were reduced, among which hippuric acid had the largest decrease, followed by 8-hydroxyquinoline, gamithromycin, 2-phenylglycine, and cefmetazole (Fig.  2 B).

A hierarchical analysis of differential metabolites obtained in the two groups was carried out, and the difference in metabolic expression patterns between the two groups and within the same comparison was obtained, which is shown in Fig.  3 . KEGG pathway analysis of the cord blood metabolites associated with the excessive GWG group versus the control group is shown in Table  4 and Fig.  4 B. The metabolite enrichment analysis revealed that biosynthesis of unsaturated fatty acids was the most altered pathway between the excessive GWG and control groups ( P value < 0.01). There were 13 metabolites distributed in the enriched pathway. The levels of docosapentaenoic acid (DPA), docosahexaenoic acid (DHA), arachidonic acid, adrenic acid, palmitic acid, stearic acid, behenic acid, lignoceric acid, and erucic acid were increased in the excessive GWG group relative to those in the control group.

Our present study found that both maternal prepregnancy overweight/obesity and excessive GWG could affect umbilical cord blood metabolites, and they had different effects on these metabolites. Regardless of their gestational weight gain, the umbilical cord blood of prepregnancy overweight and obese mothers had 46 metabolites increased and 60 metabolites decreased compared with the umbilical cord blood of mothers with normal body weight and appropriate GWG. Steroid hormone biosynthesis and neuroactive ligand‒receptor interactions were the two top-ranking pathways enriched with these metabolites. Compared with mothers with normal prepregnancy BMI and appropriate GWG, in mothers with normal prepregnancy BMI but excessive GWG, the levels of 63 metabolites were increased and those of 46 metabolites were decreased in umbilical cord blood. Biosynthesis of unsaturated fatty acids was the most altered pathway enriched with these metabolites.

There were many differential metabolites in the cord blood between the prepregnancy overweight/obesity group and the control group and between the excessive GWG group and the control group. However, the roles of most of these differential metabolites are unknown. The levels of stearamide and methanandamide were increased in the prepregnancy overweight/obesity group. Stearamide, also known as octadecanamide or kemamide S, belongs to the class of organic compounds known as carboximidic acids. Stearamide, which is increased in the serum of patients with hepatic cirrhosis and sepsis, may be associated with the systemic inflammatory state [ 22 , 23 ]. Methanandamide is a stable analog of anandamide that participates in energy balance mainly by activating cannabinoid receptors. Methanandamide dose-dependently inhibits and excites tension-sensitive gastric vagal afferents (GVAs), which play a role in appetite regulation [ 24 ]. In mice fed a high-fat diet, only an inhibitory effect of methanandamide was observed, and GVA responses to tension were dampened [ 24 , 25 ]. These changes may contribute to the development and/or maintenance of obesity. Moreover, methanandamide can produce dose-related hypothermia and attenuate cocaine-induced hyperthermia by a cannabinoid 1-dopamine D2 receptor mechanism [ 26 ].

Metabolomic pathway analysis of the cord blood metabolite features in the prepregnancy overweight and obesity group identified two filtered significant pathways: steroid hormone biosynthesis and neuroactive ligand‒receptor interaction pathways. In the steroid hormone biosynthesis pathway, the levels of several glucocorticoids (including corticosterone, 11-deoxycortisol, cortisol, testosterone, and 7α-hydroxytestosterone) were decreased in the prepregnancy overweight/obesity group. In addition to the physiological role of glucocorticoids in the healthy neuroendocrine development and maturation of fetuses and babies, glucocorticoids are essential to human health by regulating different physiological events in mature organs and tissues, such as glucose metabolism, lipid biosynthesis and distribution, food intake, thermogenesis, and mood and learning patterns [ 27 ]. Glucocorticoids have been considered as a link between adverse early-life conditions and the development of metabolic disorders in later life [ 28 , 29 , 30 ]. However, there is still much controversy regarding the role of maternal obesity in the fetal–steroid hormone biosynthesis pathway. Studies of maternal obesity animal models showed that corticosterone and cortisol levels were increased in the offspring of obese mothers [ 31 , 32 ]. A study reported by Satu M Kumpulainen et al. showed that young adults born to mothers with higher early pregnancy BMIs show lower average levels of diurnal cortisol, especially in the morning [ 33 ]. Laura I. Stirrat et al. found that increased maternal BMI was associated with lower maternal cortisol, corticosterone, and 11-dehydrocorticosterone levels. However, there were no associations between maternal BMI and glucocorticoid levels in the cord blood [ 34 ]. The differences in the study protocols of these previous studies may explain the mixed findings, such as cortisol measured from peripheral blood, cord blood or saliva; variation in measurement time points; the number of samples. Although the effect of maternal obesity on fetal steroid hormone levels is controversial, dysregulation of glucocorticoids may be a plausible mechanism by which maternal obesity can increase the risk of metabolic disorders and mental health disorders in offspring.

The effect of excessive GWG on umbilical cord blood metabolites is different from that of maternal overweight and obesity. Compared with the control group, in the excessive GWG group, the level of thromboxane B2 was increased and the level of hippuric acid was decreased. Thromboxane B2, which is important in the platelet release reaction, is a stable, physiologically active compound formed in vivo from prostaglandin endoperoxides. Hippuric acid is an acyl glycine formed from the conjugation of benzoic acid with glycine. Several studies have confirmed that both thromboxane B2 and hippuric acid levels are associated with diet. Dietary fatty acids affect platelet thromboxane production [ 35 , 36 , 37 ]. In our study, several fatty acids (e.g., palmitic acid, stearic acid, behenic acid, and lignoceric acid) in the excessive GWG group were also increased, which may have led to the increase in thromboxane B2 levels. Hippuric acid can be detected after the consumption of whole grains and anthocyanin-rich bilberries [ 38 , 39 ]. A healthy diet intervention increased the signals for hippuric acid to incorporate polyunsaturated fatty acids [ 38 ], and the low level of hippuric acid was associated with lower fruit-vegetable intakes [ 39 ]. Maternal overnutrition and unhealthy dietary patterns are the main reasons for excessive GWG [ 40 , 41 ]. Therefore, we speculated that the differences in thromboxane B2 and hippuric acid between the excessive GWG and control groups were associated with maternal diet during pregnancy. The effect of these differential metabolites on the long-term metabolic health of offspring after birth needs further study.

Metabolomic pathway analysis of the cord blood metabolite features in the excessive GWG group identified that biosynthesis of unsaturated fatty acids was the filtered significant pathway. The levels of several fatty acids in this pathway were increased in the excessive GWG group, including long-chain saturated fatty acids (e.g., palmitic acid (C 16:0), stearic acid (C 18:0), behenic acid (C 22:0), and lignoceric acid (C 23:0)), monounsaturated fatty acids (erucic acid), and polyunsaturated fatty acids (e.g., DPA, DHA, arachidonic acid, and adrenic acid). Because perinatal fatty acid status can be influenced by maternal dietary modifications or supplementation [ 42 ], we speculated that maternal diet during pregnancy caused the difference in umbilical cord blood fatty acids between the excessive GWG and control groups. A large body of evidence from mechanistic studies supports the potential of fatty acids to influence later obesity. However, the possible mechanisms and observed relationships are complex and related to the types and patterns of fatty acids [ 43 , 44 ]. Maternal dietary fatty acids have been found to induce hypothalamic inflammation, cause epigenetic changes, and alter the mechanisms of energy control in offspring [ 43 ]. Evidence from cell culture and rodent studies showed that polyunsaturated fatty acids might serve several complex roles in fetuses, including the stimulation and/or inhibition regulation of adipocyte differentiation [ 44 ]. The questions of whether lower n-6 long-chain polyunsaturated fatty acid levels or higher n-3 long-chain polyunsaturated fatty acid levels are of more relevance and whether the long-term effects differ with different offspring ages remain [ 44 ]. Although there is a biologically plausible case for the relevance of perinatal fatty acid status in later obesity risk, available data in humans suggest that the influence of achievable modification of perinatal n-3/n-6 status is not sufficient to influence offspring obesity risk in the general population [ 45 ]. Further studies seem justified to clarify the reasons.

The advantage of our present study is that we simultaneously analyzed the effects of prepregnancy overweight/obesity and excessive GWG on cord blood metabolites and explored their differences. In addition, to exclude the effect of hyperglycemia on cord blood metabolites, both women with prepregnancy diabetes mellitus and gestational diabetes mellitus were excluded from our study. The limitation of our study is that it was a single-center study with a small sample, especially in the prepregnancy overweight/obesity group. In the future, we can expand the sample size and conduct a subgroup analysis of the prepregnancy overweight/obesity group and analyze the differences in the effects of different degrees of obesity on cord blood metabolites. The prepregnancy overweight/obesity group can be further divided into an appropriate GWG group and an excessive GWG group, and the differences in the effects of these two groups on umbilical cord blood metabolites can be analyzed. Moreover, the dietary pattern of the pregnant woman could affect the production of cord blood metabolites. We did not investigate the dietary patterns of the mothers in this study, which is another limitation of this study. In future studies, we should investigate maternal dietary patterns as a very important confounding variable.

In conclusion, our present study confirmed that both prepregnancy overweight/obesity and excessive GWG could affect umbilical cord blood metabolites, and they had different effects on these metabolites. Prepregnancy overweight and obesity affected the fetal steroid hormone biosynthesis pathway, while normal prepregnancy body weight but excessive GWG affected fetal fatty acid metabolism. This emphasizes the importance of preconception weight loss and maintaining an appropriate GWG, which are beneficial for the long-term metabolic health of offspring.

Availability of data and materials

Data sets generated during the current study are not publicly available but will be available from the corresponding author at a reasonable request. Responses to the request for the raw data will be judged by a committee including XXY and GHL.

Abbreviations

Excessive gestational weight gain

Ultrahigh-performance liquid chromatography tandem mass spectrometry

Type 2 diabetes mellitus

Nonalcoholic fatty liver disease

The developmental origins of health and disease

Body mass index

Diabetes mellitus

Gestational diabetes mellitus

Oral glucose tolerance test

Low birth weight

Standard deviation

The Human Metabolome Database

Kyoto Encylopaedia of Genes and Genomes

Principal component analysis

Partial least-squares discriminant analysis

Importance for the projection

Fold change

Invitro fertilization and embryo transfer

Triglyceride

Docosapentaenoic acid

Docosahexaenoic acid

Gastric vagal afferents

Collaborators GBDO, Afshin A, Forouzanfar MH, Reitsma MB, Sur P, Estep K, Lee A, Marczak L, Mokdad AH, Moradi-Lakeh M, et al. Health effects of overweight and obesity in 195 countries over 25 years. N Engl J Med. 2017;377(1):13–27.

Article   Google Scholar  

Bjerregaard LG, Jensen BW, Angquist L, Osler M, Sorensen TIA, Baker JL. Change in overweight from childhood to early adulthood and risk of type 2 diabetes. N Engl J Med. 2018;378(14):1302–12.

Article   PubMed   Google Scholar  

Sharma V, Coleman S, Nixon J, Sharples L, Hamilton-Shield J, Rutter H, Bryant M. A systematic review and meta-analysis estimating the population prevalence of comorbidities in children and adolescents aged 5 to 18 years. Obes Rev. 2019;20(10):1341–9.

Article   PubMed   PubMed Central   Google Scholar  

Llewellyn A, Simmonds M, Owen CG, Woolacott N. Childhood obesity as a predictor of morbidity in adulthood: a systematic review and meta-analysis. Obes Rev. 2016;17(1):56–67.

Article   CAS   PubMed   Google Scholar  

Poston L, Caleyachetty R, Cnattingius S, Corvalan C, Uauy R, Herring S, Gillman MW. Preconceptional and maternal obesity: epidemiology and health consequences. Lancet Diabetes Endocrinol. 2016;4(12):1025–36.

Pan XF, Wang L, Pan A. Epidemiology and determinants of obesity in China. Lancet Diabetes Endocrinol. 2021;9(6):373–92.

Barker DJ. The developmental origins of adult disease. J Am Coll Nutr. 2004;23(6 Suppl):588S-595S.

LifeCycle Project-Maternal O, Childhood Outcomes Study G, Voerman E, Santos S, Inskip H, Amiano P, Barros H, Charles MA, Chatzi L, Chrousos GP, et al. Association of gestational weight gain with adverse maternal and infant outcomes. JAMA. 2019;321(17):1702–15.

Aune D, Saugstad OD, Henriksen T, Tonstad S. Maternal body mass index and the risk of fetal death, stillbirth, and infant death: a systematic review and meta-analysis. JAMA. 2014;311(15):1536–46.

Ukah UV, Bayrampour H, Sabr Y, Razaz N, Chan WS, Lim KI, Lisonkova S. Association between gestational weight gain and severe adverse birth outcomes in Washington State, US: a population-based retrospective cohort study, 2004–2013. PLoS Med. 2019;16(12):e1003009.

Starling AP, Brinton JT, Glueck DH, Shapiro AL, Harrod CS, Lynch AM, Siega-Riz AM, Dabelea D. Associations of maternal BMI and gestational weight gain with neonatal adiposity in the Healthy Start study. Am J Clin Nutr. 2015;101(2):302–9.

Voerman E, Santos S, Patro Golab B, Amiano P, Ballester F, Barros H, Bergstrom A, Charles MA, Chatzi L, Chevrier C, et al. Maternal body mass index, gestational weight gain, and the risk of overweight and obesity across childhood: an individual participant data meta-analysis. PLoS Med. 2019;16(2):e1002744.

Heslehurst N, Vieira R, Akhter Z, Bailey H, Slack E, Ngongalah L, Pemu A, Rankin J. The association between maternal body mass index and child obesity: a systematic review and meta-analysis. PLoS Med. 2019;16(6):e1002817.

Newgard CB. Metabolomics and metabolic diseases: where do we stand? Cell Metab. 2017;25(1):43–56.

Johnson CH, Ivanisevic J, Siuzdak G. Metabolomics: beyond biomarkers and towards mechanisms. Nat Rev Mol Cell Biol. 2016;17(7):451–9.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Hivert MF, Perng W, Watkins SM, Newgard CS, Kenny LC, Kristal BS, Patti ME, Isganaitis E, DeMeo DL, Oken E, et al. Metabolomics in the developmental origins of obesity and its cardiometabolic consequences. J Dev Orig Health Dis. 2015;6(2):65–78.

Schlueter RJ, Al-Akwaa FM, Benny PA, Gurary A, Xie G, Jia W, Chun SJ, Chern I, Garmire LX. Prepregnant obesity of mothers in a multiethnic cohort is associated with cord blood metabolomic changes in offspring. J Proteome Res. 2020;19(4):1361–74.

Shokry E, Marchioro L, Uhl O, Bermudez MG, Garcia-Santos JA, Segura MT, Campoy C, Koletzko B. Impact of maternal BMI and gestational diabetes mellitus on maternal and cord blood metabolome: results from the PREOBE cohort study. Acta Diabetol. 2019;56(4):421–30.

Chen C, Lu FC, Department of Disease Control Ministry of Health PRC. The guidelines for prevention and control of overweight and obesity in Chinese adults. Biomed Environ Sci. 2004;17(Suppl):1–36.

PubMed   Google Scholar  

The American College of Obstetricians and Gynecologists. Macrosomia: ACOG practice bulletin, number 216. Obstet Gynecol. 2020;135(1):e18–e35.

Goldenberg RL, Culhane JF. Low birth weight in the United States. Am J Clin Nutr. 2007;85(2):584S-590S.

Lian JS, Liu W, Hao SR, Guo YZ, Huang HJ, Chen DY, Xie Q, Pan XP, Xu W, Yuan WX, et al. A serum metabonomic study on the difference between alcohol- and HBV-induced liver cirrhosis by ultraperformance liquid chromatography coupled to mass spectrometry plus quadrupole time-of-flight mass spectrometry. Chin Med J (Engl). 2011;124(9):1367–73.

CAS   PubMed   Google Scholar  

Ding W, Xu S, Zhou B, Zhou R, Liu P, Hui X, Long Y, Su L. Dynamic plasma lipidomic analysis revealed cholesterol ester and amides associated with sepsis development in critically Ill patients after cardiovascular surgery with cardiopulmonary bypass. J Pers Med. 2022;12(11):1838.

Christie S, O’Rielly R, Li H, Nunez-Salces M, Wittert GA, Page AJ. Modulatory effect of methanandamide on gastric vagal afferent satiety signals depends on nutritional status. J Physiol. 2020;598(11):2169–82.

Christie S, O’Rielly R, Li H, Wittert GA, Page AJ. High fat diet induced obesity alters endocannabinoid and ghrelin mediated regulation of components of the endocannabinoid system in nodose ganglia. Peptides. 2020;131:170371.

Rasmussen BA, Kim E, Unterwald EM, Rawls SM. Methanandamide attenuates cocaine-induced hyperthermia in rats by a cannabinoid CB1-dopamine D2 receptor mechanism. Brain Res. 2009;1260:7–14.

Facchi JC, Lima TAL, Oliveira LR, Costermani HO, Miranda GDS, de Oliveira JC. Perinatal programming of metabolic diseases: the role of glucocorticoids. Metabolism. 2020;104:154047.

Reynolds RM, Walker BR, Syddall HE, Andrew R, Wood PJ, Whorwood CB, Phillips DI. Altered control of cortisol secretion in adult men with low birth weight and cardiovascular risk factors. J Clin Endocrinol Metab. 2001;86(1):245–50.

Valtat B, Dupuis C, Zenaty D, Singh-Estivalet A, Tronche F, Breant B, Blondeau B. Genetic evidence of the programming of beta cell mass and function by glucocorticoids in mice. Diabetologia. 2011;54(2):350–9.

Jia Y, Li R, Cong R, Yang X, Sun Q, Parvizi N, Zhao R. Maternal low-protein diet affects epigenetic regulation of hepatic mitochondrial DNA transcription in a sex-specific manner in newborn piglets associated with GR binding to its promoter. PLoS ONE. 2013;8(5):e63855.

Rodriguez JS, Rodriguez-Gonzalez GL, Reyes-Castro LA, Ibanez C, Ramirez A, Chavira R, Larrea F, Nathanielsz PW, Zambrano E. Maternal obesity in the rat programs male offspring exploratory, learning and motivation behavior: prevention by dietary intervention pre-gestation or in gestation. Int J Dev Neurosci. 2012;30(2):75–81.

Tuersunjiang N, Odhiambo JF, Long NM, Shasa DR, Nathanielsz PW, Ford SP. Diet reduction to requirements in obese/overfed ewes from early gestation prevents glucose/insulin dysregulation and returns fetal adiposity and organ development to control levels. Am J Physiol Endocrinol Metab. 2013;305(7):E868-878.

Kumpulainen SM, Heinonen K, Kaseva N, Andersson S, Lano A, Reynolds RM, Wolke D, Kajantie E, Eriksson JG, Raikkonen K. Maternal early pregnancy body mass index and diurnal salivary cortisol in young adult offspring. Psychoneuroendocrinology. 2019;104:89–99.

Stirrat LI, Just G, Homer NZM, Andrew R, Norman JE, Reynolds RM. Glucocorticoids are lower at delivery in maternal, but not cord blood of obese pregnancies. Sci Rep. 2017;7(1):10263.

Prisco D, Filippini M, Francalanci I, Paniccia R, Gensini GF, Serneri GG. Effect of n-3 fatty acid ethyl ester supplementation on fatty acid composition of the single platelet phospholipids and on platelet functions. Metabolism. 1995;44(5):562–9.

Kaapa P, Uhari M, Nikkari T, Viinikka L, Ylikorkala O. Dietary fatty acids and platelet thromboxane production in puerperal women and their offspring. Am J Obstet Gynecol. 1986;155(1):146–9.

Teng KT, Chang CY, Kanthimathi MS, Tan AT, Nesaretnam K. Effects of amount and type of dietary fats on postprandial lipemia and thrombogenic markers in individuals with metabolic syndrome. Atherosclerosis. 2015;242(1):281–7.

Hanhineva K, Lankinen MA, Pedret A, Schwab U, Kolehmainen M, Paananen J, de Mello V, Sola R, Lehtonen M, Poutanen K, et al. Nontargeted metabolite profiling discriminates diet-specific biomarkers for consumption of whole grains, fatty fish, and bilberries in a randomized controlled trial. J Nutr. 2015;145(1):7–17.

Brunelli L, Davin A, Sestito G, Mimmi MC, De Simone G, Balducci C, Pansarasa O, Forloni G, Cereda C, Pastorelli R, et al. Plasmatic hippuric acid as a hallmark of frailty in an Italian cohort: the mediation effect of fruit-vegetable intake. J Gerontol A Biol Sci Med Sci. 2021;76(12):2081–9.

Ferreira LB, Lobo CV, Miranda A, Carvalho BDC, Santos LCD. Dietary patterns during pregnancy and gestational weight gain: a systematic review. Rev Bras Ginecol Obstet. 2022;44(5):540–7.

Tielemans MJ, Garcia AH, Peralta Santos A, Bramer WM, Luksa N, Luvizotto MJ, Moreira E, Topi G, de Jonge EA, Visser TL, et al. Macronutrient composition and gestational weight gain: a systematic review. Am J Clin Nutr. 2016;103(1):83–99.

Lewis RM, Wadsack C, Desoye G. Placental fatty acid transfer. Curr Opin Clin Nutr Metab Care. 2018;21(2):78–82.

Cesar HC, Pisani LP. Fatty-acid-mediated hypothalamic inflammation and epigenetic programming. J Nutr Biochem. 2017;42:1–6.

Demmelmair H, Koletzko B. Perinatal polyunsaturated fatty acid status and obesity risk. Nutrients. 2021;13(11):3882.

Hauner H, Brunner S. Early fatty acid exposure and later obesity risk. Curr Opin Clin Nutr Metab Care. 2015;18(2):113–7.

Download references

Acknowledgements

The authors thank the study participants for their involvement and research assistants for their help conducting the study.

This research was funded by the Beijing Natural Science Foundation, grant number 7214231.

Author information

Authors and affiliations.

Division of Endocrinology and Metabolism, Department of Obstetrics, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing Maternal and Child Health Care Hospital, No. 251, Yaojiayuan Road, Chaoyang District, Beijing, 100026, China

Xianxian Yuan, Yuru Ma, Yan Zhao, Wei Zheng, Ruihua Yang, Lirui Zhang, Xin Yan & Guanghui Li

Department of Obstetrics and Gynecology, The Second Hospital of Jilin University, Changchun, 130041, Jilin, China

You can also search for this author in PubMed   Google Scholar

Contributions

XXY designed the study. XXY, WZ, LRZ and XY analyzed the data. YRM, JW, YZ and RHY took part in data collection and management. XXY wrote the manuscript. XXY and GHL reviewed the manuscript and contributed to manuscript revision. All authors contributed to the article and approved the submitted version. All authors reviewed the manuscript.

Corresponding author

Correspondence to Guanghui Li .

Ethics declarations

Ethics approval and consent to participate.

This study has been performed in accordance with the Declaration of Helsinki and has been approved by the ethics committee of Beijing Obstetrics and Gynecology Hospital, Capital Medical University (2021-KY-037). Informed consent was obtained from all subjects involved in the study to publish this paper. All methods were carried out in accordance with relevant guidelines and regulations in the declaration.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Yuan, X., Ma, Y., Wang, J. et al. The influence of maternal prepregnancy weight and gestational weight gain on the umbilical cord blood metabolome: a case–control study. BMC Pregnancy Childbirth 24 , 297 (2024). https://doi.org/10.1186/s12884-024-06507-x

Download citation

Received : 30 September 2023

Accepted : 11 April 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12884-024-06507-x

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Maternal obesity
• Gestational weight gain
• Offspring health
• Metabolites
• Umbilical cord blood

BMC Pregnancy and Childbirth

ISSN: 1471-2393

• Submission enquiries: [email protected]
• General enquiries: [email protected]

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List

Why training and specialization is needed for peer review: a case study of peer review for randomized controlled trials

Jigisha patel.

Biomed Central Ltd, Floor 6, 236 Gray’s Inn Road, London, WC1X 8HB UK

The purpose and effectiveness of peer review is currently a subject of hot debate, as is the need for greater openness and transparency in the conduct of clinical trials. Innovations in peer review have focused on the process of peer review rather than its quality.

The aims of peer review are poorly defined, with no evidence that it works and no established way to provide training. However, despite the lack of evidence for its effectiveness, evidence-based medicine, which directly informs patient care, depends on the system of peer review. The current system applies the same process to all fields of research and all study designs. While the volume of available health related information is vast, there is no consistent means for the lay person to judge its quality or trustworthiness. Some types of research, such as randomized controlled trials, may lend themselves to a more specialized form of peer review where training and ongoing appraisal and revalidation is provided to individuals who peer review randomized controlled trials. Any randomized controlled trial peer reviewed by such a trained peer reviewer could then have a searchable ‘quality assurance’ symbol attached to the published articles and any published peer reviewer reports, thereby providing some guidance to the lay person seeking to inform themselves about their own health or medical treatment.

Specialization, training and ongoing appraisal and revalidation in peer review, coupled with a quality assurance symbol for the lay person, could address some of the current limitations of peer review for randomized controlled trials.

A brief history of trial reporting and peer review

‘Better have them all removed now.’ That was the advice I received in the early 1990s when my pain free un-erupted wisdom teeth first came to the notice of a surgeon. He was emphatic that I would suffer complications in the future if I did not have all four teeth removed under a general anesthetic. This seemed drastic to me, but I was given the same advice by two health professionals and it was with trepidation that I questioned their advice. At the time, ‘Evidence-Based Medicine’ which proposed the use of scientific evidence to inform clinical decision making was still a novel idea [ 1 ] and the Cochrane Collaboration [ 2 ], aimed at facilitating up-to-date systematic reviews of randomized controlled trials, had recently been founded.

I decided to search for the evidence. My only source of information was a medical library where I could identify and photo-copy relevant looking articles or get copies via an ‘inter-library loan’. I did not find any useful information, but I decided against the procedure on the basis that the risk of a general anesthetic and a stay in hospital seemed to me to completely outweigh any benefit of having four perfectly healthy pain-free teeth removed.

A short time later, when I was a junior doctor, a subgroup analysis of the diabetic patients who took part in the original ‘4S study’ [ 3 ], reported that simvastatin treatment improved morbidity and mortality in patients with diabetes [ 4 ]. At the time, my peers and I took for granted that the editors of the journals where the studies were published must have chosen the best people qualified to peer review and the peer reviewers must have done a competent job. The reported findings were compelling enough to have a profound effect on the care received by patients with diabetes.

These experiences not only illustrate the barriers to information I faced as a patient, but the power of individual clinical trials to directly influence treatment decisions for individual patients and the blind faith I and my peers had in a system whereby publication in a peer reviewed journal gave the reported results the status of ‘the evidence’ and, therefore, the ‘Truth’.

While my faith in the publication process was naïve and misplaced, flaws in the way randomised controlled trials (RCTs) were conducted and reported were recognised and initiatives were underway address these concerns. These culminated in the CONSORT statement [ 5 ] which aims to specify in detail how randomised controlled trials should be reported to improve transparency and help peer reviewers and readers make informed judgements about clinical trials. Since then a number of reporting guidelines for other types of clinical studies have been developed [ 6 ].

While my faith in the publication process was naïve and misplaced, flaws in the way RCTs were conducted and reported were recognized and initiatives were underway to address these concerns. These culminated in the Consolidated Standards of Reporting Trials (CONSORT) statement [ 5 ] which aims to specify in detail how RCTs should be reported to improve transparency and help peer reviewers and readers make informed judgments about clinical trials. Since then a number of reporting guidelines for other types of clinical studies have been developed [ 6 ].

While reporting guidelines aimed to address how individual trials were reported, there were also concerns about how far only positive or favorable findings were published while those with less exciting, favorable or inclusive findings were not (publishing bias). In 2005, the International Committee of Medical Journal Editors (ICMJE) published a statement announcing that its member journals would adopt compulsory trial registration as journal policy [ 7 ]. The aim was to register the existence of all clinical trials so that they became part of the public record.

Recently, in light of ongoing concerns about publication bias and the suppression of unfavorable results, the All Trials campaign [ 8 ] was launched which calls for the registering of all clinical trials and availability of all data for treatments in current use.

Meanwhile, running parallel with this, the world of peer review, was undergoing a revolution. Most definitions of peer review include a description of a process of scrutiny by independent experts or peers in the same field [ 9 , 10 ]. For peer-review journals this process involves sending submitted manuscripts to two or more people deemed to be knowledgeable enough in the field of the manuscript to judge its suitability for publication in that journal.

Flaws with the common single blind peer review system (where the reviewers know who the authors are, but the authors do not know who the reviewers are) were recognized [ 11 ] and there were experiments with double blind peer review to attempt to address this as well as in open peer review where the identity of reviewers and authors is known to all. While closed peer review did not appear to improve the quality of peer review [ 12 ], open peer review did appear to be feasible without undermining the quality of peer reviewer reports [ 13 ] and was first adopted by the British Medical Journal ( BMJ ) in 1999 [ 14 ].

The novel idea of an ‘Open Access’ journal, where all published research is freely available without subscription, began to emerge and although it was met by ferocious opposition from publishers [ 15 ], BioMed Central [ 16 ], the first completely online open access publisher was founded in 2000, followed, in 2006, by the launch of PLoS One [ 17 ].

The number of peer reviewed journals has been increasing at a steady rate of 3.5% a year and almost all are now available online [ 18 ]. With online publishing flourishing and with technical advances that allow comments to be made and shared in real time on a global stage, the process of traditional peer review, which can be slow and laborious, has been criticized [ 19 ]. New models of peer review have emerged and include (Table  1 ): re-review opt out [ 20 ], post-publication peer review [ 21 ], decoupled peer review [ 22 - 24 ], portable peer review [ 25 ], and collaborative peer review [ 26 , 27 ].

Models of peer review

The impetus behind these recent initiatives has been to reduce delays for authors and reduce burden for reviewers. Their focus is on the process of peer review in terms of how and when it is done, rather than the substance and quality of peer review itself or expertise of the peer reviewer.

The problem with peer review in medicine

Recent innovations in peer review seem to be driven by biologists with medical research ‘tagging along’. However, systems which might help biological research to thrive, might not necessarily be appropriate for research that directly influences patient care. There is no agreement on who a ‘peer’ or what ‘peer review’ actually is [ 11 ]. It is not clear what peer review aims to achieve [ 28 ] and no evidence that peer review works [ 29 ]. Journal instructions for peer reviewers [ 30 ] and the criteria for eligibility to peer review are variable (Table  1 ). There has been little evaluation of any of the more recent innovations in peer review for any outcomes. Furthermore, the whole system is based on honesty and trust and, as a consequence, is not designed to detect fraud.

Despite this, peer review is still seen by researchers as important and necessary for scientific communication [ 31 ] and publication in a peer reviewed medical journal is still the only valid or legitimate route to disseminating clinical research. In 2006, Richard Smith of the BMJ commented that it was, ‘odd that science should be rooted in belief’ [ 11 ]. In the world of evidence based medicine, it is astonishing that the evidence on which medical treatment is based is itself based on such precarious foundations with so many untested assumptions. Today, a junior doctor still relies on faith in the peer review system when judging a clinical trial and a patient searching, ‘Should I have my wisdom teeth removed if they don’t hurt?’ would get more than a million results on Google (search date 12 May 2014) with no guidance on the relevance or trustworthiness of any of them, leaving them as much in the dark as I was when I first asked that question. The difference between now and then is that then, information was just not available or accessible, and now, there is so much information available of varying quality that it is impossible to make sense of it all without some specialist knowledge. For example, if the lay person knows what to search for (prophylactic extraction of third molar) and which sources they can trust (the Cochrane library), the relevant information can be found easily. According to a Cochrane review I found [ 32 ], there is no evidence either way of the benefit of having wisdom teeth removed if they are asymptomatic. I feel reassured I made the right decision all those years ago. However, not all clinical questions can be answered so easily or can afford the luxury of waiting for a Cochrane systematic review to be done. When there is no ready-made Cochrane review, a system that provides some sort of quality check for individual studies might serve as an important consideration for patients (and doctors) who need to weigh up, using the available evidence, the risks and benefits of a course of action and make definitive, time dependent, decisions that could be life changing.

A UK Parliamentary enquiry on peer review in 2011 [ 33 ] concluded that different types of peer review are suitable for different disciplines and encouraged increased recognition that peer-review quality is independent of journal business model. With this in mind, is there a need to redesign peer review specifically for clinical research and ensure that this is driven by the clinical community?

Training and specialization in peer review

With peer review as a vague and undefined process it is not surprising that in a survey of peer review conducted by Sense about Science, 56% of reviewers in a survey said there was a lack of guidance on how to review and 68% thought formal training would help [ 31 ]. Training and mentoring schemes for peer review have shown little impact [ 34 - 37 ] and even a decline in peer reviewer performance with time [ 38 ]. It may be that by the time a researcher has reached the stage in their career when they start to peer review, it is too late to teach peer review.

Although reporting guidelines have been available for two decades, many researchers and reviewers still do not understand what they are or the need for them. This is further compounded by inconsistent guidance from journals for authors on how to use reporting guidelines [ 30 ] and a lack of awareness of how they can improve the reporting of RCTs [ 39 ] and, thereby, aid peer review. There are misunderstandings about trial registration and even what constitutes an RCT. There is evidence that reviewers fail to detect deliberately introduced errors [ 34 , 37 ] and do not detect deficiencies in reporting methods, sometimes even suggesting inappropriate revisions [ 40 ]. Manuscripts reporting poorly conducted clinical research get published in peer reviewed journals and their findings inform systematic reviews, which in turn could also be poorly conducted and reported. These systematic reviews have the potential to inform clinical judgments.

The need for a concerted effort across disciplines to investigate the effects of peer review has been recognized [ 28 ], but before the effects can be investigated, the aims of peer review need to be defined. This is a daunting challenge if one aim, or a small number of aims, is intended to fulfill all peer review needs for all fields, specialties and study designs. A more manageable way may be to introduce specialization into peer review, so that specific fields can define the purpose and aims of peer review to suit their own needs and design training to meets those aims.

Since the methodology for conducting and reporting of RCTs has been defined by the CONSORT statement [ 41 ] which improves the reporting of RCTs [ 39 ] and, thereby, aids the peer review process, peer review of RCTs lends itself to such specialization. CONSORT could form the framework for the content of a training program and help to define the knowledge and skills that are needed by a given individual to appraise an RCT critically. Peer reviewers could be taught to spot fundamental flaws and be periodically evaluated to make sure they do, in the same way that any other knowledge or skill that affects patient care is.

Peer review of RCTs should be recognized as a professional skill in this way. Every RCT, and its peer review reports if made public, whether published online, on paper, open access or subscription only, with open or closed peer review, or peer reviewed before or after publication could then have a searchable ‘quality assurance’ symbol (like the ‘kite-mark’ used by the British Standards Institute [ 42 ]) or a word, so that readers know whether a study was reviewed by at least one appropriately trained and accredited expert. Such a system could accommodate all peer review models (Figure  1 ).

Interaction of trained RCT peer reviewers with existing peer review models. RCT, randomized controlled trial.

To achieve this, major organizations including medical schools, medical regulatory and accreditation organizations (such as the General Medical Council and Royal Colleges in the UK), funding bodies, publishers and journal editors and lay people need to come to a consensus on the definition, purpose, standards and training requirements of peer review of RCTs. Training should begin in medical schools and be ongoing.

By recognizing peer review as a professional skill with measurable standards which are separate from the journal, publisher or peer review model, peer review is separated from commercial considerations, peer reviewers get recognition for their work, and researchers, clinicians and patients get some indication of quality on which to base their judgments. Publishers and journals are then free to innovate while still maintaining consistency of peer review for RCTS, editors have clear criteria on which to base their choice of peer reviewer for a given manuscript and a baseline is set that allows for future research into the effectiveness of peer review per se and comparative studies on the effectiveness and quality of emerging innovations.

While innovations in trial reporting and the peer review process have increased transparency, there has been little progress in defining the aims and effects or improving the quality of peer review itself. There is a vast volume of health information available to the lay person with little or no guidance on its quality or trustworthiness.

Treatment decisions are based on evidence which is itself determined by a system for which there is no evidence of effectiveness. Innovations in peer review that specifically address the quality of peer review and the expertise of the peer reviewer and provide guidance for lay people seeking to inform themselves about their own health related decisions are urgently needed. Formal professional training for peer review of RCTs coupled with a means of identifying RCTs peer reviewed by such trained experts could address these needs.

The focus of this article has been on peer review of evidence-based medicine and RCTs in particular because the consequences of an ill-defined system of peer review are easily understandable by the scientist and the lay person alike. However, the purpose of peer review and a method of training and evaluating peer reviewers could be defined in a similar way for any other type of study design or any other field.

Acknowledgements

The author would like to acknowledge Elizabeth Moylan, Biology Editor at BioMed Central for her detailed comments and suggestions for this manuscript and the whole Biology and Medical Editors team at BioMed Central for their general advice and comments.

Abbreviations

Competing interests

The author is an employee of BioMed Central and Medical Editor of BMC Medicine . The views expressed in this article are entirely her own.

Authors' contributions

JP is the sole author of this article. She conceived the idea, researched the background and wrote the manuscript.

• Open access
• Published: 23 April 2024

Factors influencing the commissioning and implementation of health and social care interventions for people with dementia: commissioner and stakeholder perspectives

• Rachael Tucker   ORCID: orcid.org/0000-0001-8133-1909 1 ,
• Robert Vickers   ORCID: orcid.org/0000-0002-3031-2940 2 , 5 ,
• Emma J. Adams   ORCID: orcid.org/0000-0002-5444-6951 1 ,
• Clare Burgon   ORCID: orcid.org/0000-0002-4910-9969 2 ,
• Juliette Lock   ORCID: orcid.org/0000-0003-2028-6889 2 ,
• Sarah E. Goldberg   ORCID: orcid.org/0000-0001-5109-798X 1 ,
• John Gladman   ORCID: orcid.org/0000-0002-8506-7786 2 , 3 , 4 , 5 ,
• Tahir Masud   ORCID: orcid.org/0000-0003-1061-2898 3 ,
• Elizabeth Orton   ORCID: orcid.org/0000-0002-2531-8846 2 ,
• Stephen Timmons   ORCID: orcid.org/0000-0002-3731-1350 6 &
• Rowan H. Harwood   ORCID: orcid.org/0000-0002-4920-6718 1 , 3  

Archives of Public Health volume  82 , Article number:  54 ( 2024 ) Cite this article

157 Accesses

3 Altmetric

Metrics details

Despite several interventions demonstrating benefit to people living with dementia and their caregivers, few have been translated and implemented in routine clinical practice. There is limited evidence of the barriers and facilitators for commissioning and implementing health and social care interventions for people living with dementia. The aim of the current study was to explore the barriers and facilitators to commissioning and implementing health and social care interventions for people with dementia, using a dementia friendly exercise and physical activity-based intervention (PrAISED [Promoting Activity, Stability and Independence in Early Dementia and Mild Cognitive Impairment]) as a case study.

Qualitative semi-structured interviews were conducted with stakeholders from a range of backgrounds including individuals from health and social care, local government, the voluntary and community sector, universities, and research centres in England. The Consolidated Framework for Intervention Research (CFIR) was used to guide the design and analysis.

Fourteen participants took part, including commissioning managers, service managers, partnership managers, charity representatives, commercial research specialists, academics/researchers, and healthcare professionals. Data were represented in 33 constructs across the five CFIR domains. Participants identified a need for greater support for people diagnosed with dementia and their caregivers immediately post dementia diagnosis. Key barriers included cost/financing, the culture of commissioning, and available resources. Key facilitators included the adaptability of the intervention, cosmopolitanism/partnerships and connections, external policy and incentives, and the use of already existing (and untapped) workforces.

Several barriers and facilitators for commissioning and implementing health and social care interventions for people with dementia were identified which need to be addressed. Recommended actions to facilitate the commissioning and implementation of dementia friendly services are: 1) map out local needs, 2) evidence the intervention including effectiveness and cost-effectiveness, 3) create/utilise networks with stakeholders, and 4) plan required resources.

Peer Review reports

Introduction

Dementia is a progressive, neurodegenerative, life limiting condition associated with a range of symptoms including memory loss, declining executive function, and associated changes in behaviour and mood [ 5 ]. Over 55 million people live with dementia worldwide [ 43 ] and this is projected to increase to approximately 153 million by 2050 [ 37 ]. The global cost of dementia in 2019 amounted to US$ 1.3 trillion, with costs expected to exceed US$ 2.8 trillion by 2030 [ 43 ]. As the condition progresses, the amount of support required, and thus, care costs also increase [ 3 ]. Therefore, implementing interventions for dementia that focus on maintaining independence and slowing the rate of functional decline to prevent health and social care use and reduce this economic burden is important.

Translating research into practice

The research into practice gap is well documented. It takes an average of 17 years for innovations to be implemented into routine clinical practice [ 7 , 24 ]. Despite many non-pharmacological interventions for dementia demonstrating benefit, a small number are implemented in practice [ 24 ]. Thus, it is crucial to understand strategies that facilitate their implementation.

There is little evidence for translating dementia friendly exercise/physical activity interventions into practice. A systematic review by Groot Kormelinck et al. [ 27 ] identified barriers and facilitators for implementing complex interventions for residents with dementia living in long term care. In this review, only two interventions had an exercise or physical activity component [ 27 ], and due to its setting, may not have identified factors relevant to implementation across a range of health systems.

Commissioning in England’s National Health Service

The National Health Service (NHS) in England is a publicly funded health system providing universal access to healthcare based on clinical need, not ability to pay [ 20 ]. NHS commissioning is complex whereby different services may be specified and paid for by different commissioners, including nationally (NHS England) and locally (e.g. Primary Care Networks and local government). Services may be provided by the voluntary and community sector (VCS), primary and secondary care health services, and support organisations working interdependently [ 36 , 40 ]. However, social care in England is not universally funded, is commissioned by local government, provided by a range of providers, and is means tested [ 39 ]. Commissioning dementia services is therefore also complex [ 29 ]. Such complexities mean many people with dementia and their families are burdened with care costs and inadequate support [ 4 ].

The PrAISED programme

The Promoting Activity, Independence and Stability in Early Dementia and Mild Cognitive Impairment (PrAISED) programme is a complex intervention which aims to keep people living with dementia independent and healthier for longer [ 11 , 25 ]. PrAISED was developed by physiotherapists, occupational therapists, health psychologists, nurses, geriatricians, and carer representatives [ 11 ] and was tested in a feasibility study [ 25 ]. It is a 12-month exercise and activity-based programme consisting of progressive strength, balance and dual task exercises, functional activities and activities of daily living training, risk analysis, advice, and environmental assessment, all delivered using a motivational approach to support long-term participation in physical activity [ 11 ]. The effectiveness of the PrAISED intervention was studied in the PrAISED-2 multi-site, pragmatic, Randomised Controlled Trial (RCT), which took place between September 2018 and January 2023 [ 6 , 28 ]. Before the results of PrAISED-2 were available and in anticipation of an implementation phase, the current study aimed to explore the views of commissioners and stakeholders on this matter and to inform the commissioning and implementation of wider health and social care dementia interventions.

Given the complexities of commissioning, the current study aimed to identify barriers and facilitators for commissioning and implementing health and social care interventions for people with dementia, using a dementia-friendly exercise and physical activity-based intervention (PrAISED) as a case study and to provide recommendations for future implementation.

Ethical approval

The study received research governance approvals and ethical approval from the Bradford Leeds Research Ethics Committee (18/YH/0059; 236099).

Study design

The Consolidated Framework for Implementation Research (CFIR) [ 17 ] was used as a theoretical framework for the study, to guide the methods, such as the development of the topic guide, and for data analysis (see data analysis section). This framework was chosen as it is comprehensive and is commonly used in implementation research enabling comparisons with other studies. Qualitative, semi-structured interviews were used for data collection. Participants were asked to consider PrAISED in their answers, even if they had not been involved in the PrAISED RCT (see Table A1 in Appendix : interview topic guide).

Participant recruitment

Participants were stakeholders involved in the commissioning and delivery of dementia services. An introductory email was sent out to potential participants and/or contacts from pre-existing networks known to the research team. This included individuals working in the NHS/healthcare, social care, local authorities, the VCS, and other key stakeholder organisations concerned with commissioning, implementing, delivering, or promoting activity-based interventions for people with dementia and/or mild cognitive impairment. Participants were provided with an information sheet and a consent form which was completed prior to their interview. Two researchers (RT and RV) conducted the interviews, all of which were carried out, recorded, and transcribed using Microsoft Teams. Any identifiable information was removed from the transcripts and participants were assigned a participant number. A ‘snowball’ (chain-referral) sampling technique was employed to identify additional participants, who were contacted via email.

Data analysis

Data analysis was carried out using codebook thematic analysis [ 13 ]. This type of thematic analysis uses a structured approach with predetermined themes and codes, or a research framework, to guide the analysis [ 13 ]. This study used the CFIR [ 17 ] as a codebook, thus the transcripts were coded according to the CFIR constructs to identify the barriers and facilitators to commissioning and implementing health and social care interventions for people with dementia from the perspectives of the participants.

The CFIR was developed to consolidate published implementation theories into a consistent typology for use in evaluating implementation [ 17 ]. Since its publication in 2009, the CFIR has grown in recognition and is now used widely across mixed method, quantitative and qualitative studies [ 31 ]. The CFIR consists of five domains: intervention characteristics, outer setting, inner setting, characteristics of individuals involved, and process of implementation. Across these domains are 39 constructs, full details are available at Damschroder et al. [ 17 ] or https://cfirguide.org/ .

Approximately halfway through the data analysis, revised CFIR guidelines were published updating constructs and their definitions [ 18 ]. The methodological implications of this publication were considered collectively by the research team, and the team came to a consensus that the new/expanded constructs from the updated CFIR would be incorporated where relevant to the analysis. As per the updated CFIR framework, the research team worked collaboratively to define each domain in this study. The domains and their constructs used in this study are presented in Table  1 . Constructs that were added, revised or renamed after the publication of the updated CFIR are denoted by *.

Data analysis process

NVivo software version 13 [ 38 ] and a CFIR-approved pre-populated template [available at https://cfirguide.org/tools/tools-and-templates/ ] were used to analyse the data; additional constructs were added where appropriate.

Braun and Clarke’s [ 12 ] and Braun et al.’s [ 13 ] thematic analysis steps were amended and/or combined to reflect the methods used in this study (codebook thematic analysis), which had predetermined codes and themes determined by the CFIR framework. Data analysis followed these steps:

Familiarisation (repeatedly reading transcripts and making notes about content)

Preliminary coding (preliminary coding into relevant constructs as per the CFIR codebook [available at https://cfirguide.org/tools/tools-and-templates/ ] and documenting rationale for coding decisions

Revising and revisiting coding/theme development (data revisited to check interpretations and amend if needed as researchers became more familiar with the data)

Finalising codes/themes (codes finalised within the research team)

Producing the report

Although these steps are presented as a sequence, data analysis followed an iterative process, with each step being revisited and revised. The lead author (RT) acted as lead coder for this study. A second coder (RV) reviewed a third of the transcripts to act as a peer-checker and reviewer of coding decisions. To improve understanding and collaborative use of the CFIR framework, the lead coder, second coder and wider implementation study team met weekly to discuss coding decisions.

A total of 14 participants took part in interviews. Participants included commissioning managers ( n  = 4), service managers ( n  = 3), charity representatives ( n  = 1), partnership managers (responsible for developing and managing strategic partnerships between organisations) ( n  = 1), commercial research specialists ( n  = 1), academics/researchers ( n  = 2), and healthcare professionals ( n  = 2), working across a range of settings including universities, research centres, the VCS, health and social care, and local government. Interviews lasted between 25 and 68 min. Of the 40 constructs (39 original CFIR constructs, plus one from the updated CFIR [ 18 ]) (Table  1 ), six had no entries during the analysis. These were: two constructs from the innovation characteristics domain (relative advantage and trialability), one from the inner setting domain (learning climate), two from the individual characteristics domain (self-efficacy and individual identification with organisation), and one from the process domain (executing). The remaining constructs were used as codes and were representative of extracts from the interview transcripts. The most frequently coded constructs were 1) needs and resources of those served by the organisation (outer setting), 2) available resources (inner setting), and 3) cosmopolitanism/partnership and connections (outer setting). Table 2 shows the frequency of coding for each construct (though frequency does not necessarily reflect importance), along with their classification as a barrier, facilitator, or both.

As barriers and facilitators to the implementation of dementia friendly activity-based interventions were identified across all domains, this paper presents each domain and discusses barriers and facilitators within them, before presenting key meta-themes and considerations for the wider commissioning and implementation climate as part of the discussion.

Innovation characteristics

The innovation source, evidence strength and quality, adaptability, complexity, design quality and packaging, and cost, all represented barriers and facilitators. The PrAISED intervention was coproduced with patient and public representatives and healthcare professionals [ 11 ]. Interviewees suggested coproduction was integral to successful implementation as the individual tailoring was seen to enhance participation, and the involvement of healthcare professionals provided reassurance of its effect:

‘…the fact that it’s also being developed with health professionals is something that’s really quite to its favour, because I think we find that people really look for reassurance from medical professionals, so if they know it’s got that medical endorsement, I think for us would be really positive,’ Participant 2 (Activity Manager).

Another facilitator was the innovation’s ability to be adapted to suit local systems. Several participants suggested that implementation would be facilitated and/or would be more likely to be commissioned if the innovation could be embedded within existing services:

‘I think if it’s something that you can almost add on to an existing provision… so you do have some of that skilled workforce, you have that management structure around it… some of the concerns of commissioners is when you end up with lots of small and then potentially vulnerable services… it just helps because you know you've got that capability there that could be mobilised rather than if you're starting from scratch,’ Participant 1 (Commissioner).

Some suggested utilising day services and/or care homes to deliver an intervention like PrAISED would keep costs down, utilise already existing services and upskill existing staff.

Another facilitator was the potential to use other professionals to deliver PrAISED in practice. In the main trial, PrAISED was delivered by occupational therapists, physiotherapists, and rehabilitation support workers. Participants in the current study suggested other professionals, such as exercise instructors, could take on responsibility for delivering a dementia friendly, exercise-based intervention and would be qualified to do so (discussed in greater depth in the individual characteristics domain). Interestingly, this view differed from those of healthcare professionals interviewed as part of a pilot PrAISED service, who felt it was essential healthcare professionals delivered exercise interventions for people living with dementia [ 1 ]. It was suggested this potential adaptation had collateral benefits for cost, and could reduce the demand on the existing workforce, utilise an untapped workforce and improve collaborative working with the local community, for example, leisure centres.

Evidence was a significant factor and facilitator in the commissioning of an intervention like PrAISED:

‘It’s an area that you’ve got to have as much efficacy evidence as possible… that is what is going to determine the success,’ Participant 7 (Commercial Director).

‘If the evidence isn’t there to support it, then it's not going to be there ultimately,’ Participant 12 (Partnership Manager).

One strand of evidence that was particularly pertinent to successful commissioning was the intervention’s ability to deliver cost savings and where these would be visible, for example, in health as opposed to social care budgets. However, this was deemed difficult to evidence. Participants 13 and 14, both commissioning managers, described the importance of interventions delivering cost savings in influencing decisions and allocating funds:

‘If we can start to evidence that this is delaying or improving outcomes… that would help massively… It’s like that invest to save sort of thing, isn’t it? If we can really show some evidence around that… then I think that you've got more of a chance,’ Participant 13 (Commissioning Manager).

‘Delaying need for social care is a really big thing for us. So, if an organisation came and said look, we can prevent people hitting your services for a long time, that's a really big driver for us, and like promoting independence, so, even if people are using our services, they’re using them less and living at home longer,’ Participant 14 (Commissioning Manager).

Also, participants working outside of commissioning recognised how crucial evidence was to the decision-making process:

‘It’s also important to show that there’s evidence… certainly some people in commissioning are a bit swayed by evidence or are very sceptical about things unless there’s evidence,’ Participant 8 (Professor of Dementia Research).

Interestingly, participant 7 described how different ‘levels’ of evidence would be required, depending on the system of delivery. For example, lower-level evidence would be required if the intervention were to be self-funded, as it would be an ‘emotional purchase’ by family members and/or carers, whereas:

‘…if it’s a statutory service provision model [local authority or NHS], then the bar is higher in terms of the amount of certainty that they would need in order to commission it and that might be certainty around patient outcomes, deferred benefit, cost versus benefit, cost benefit analysis… with limited budgets and competing demands for resources, they want to put their bets on the horses that are going to get them the biggest returns. Otherwise, it might fall into that nice to have, but not essential, which is really hard,’ Participant 7 (Commercial Director).

Whilst evidence of RCT outcomes was mostly advocated, other forms of evidence, such as qualitative research, were also important:

‘… it’s about showing real life stories and the positive impact it can have on someone’s life… I think that's really powerful,’ Participant 6 (Sports Development Officer).

Outer setting

Most participants reported that there is a need for dementia friendly activity-based interventions. Participants recognised the benefits of physical activity, and many proactively promoted this. Some reported that there were vast amounts of initiatives which aimed to engage people with long term conditions in physical activity and exercise. However, importantly, these were mostly deemed unsuitable for people living with dementia:

‘You need to have sort of a specific understanding of their needs and what’s going to be most likely to support them into activity and help them to maintain that… often people with dementia, when we're talking to them about some of the services and support that we're providing, they find it a little bit harder to relate to some of the messaging and a bit harder to undertake some of the activities… they need to be communicated in a particular way and they need to take into consideration their ability level and just them as a whole person,’ Participant 2 (Activity Manager).

There were few dementia specific or dementia friendly services currently being provided, though participant 10 reported that there was ‘ an appetite definitely to improve the provision or enhance the provision or create the provision to start with .’ Participants described the post-diagnostic support as lacking, and at worst, absent:

‘We have a gap… the post-diagnostic offer to people with dementia is pretty woeful,’ Participant 8 (Professor of Dementia Research).

Participants described efforts in their organisation and/or local area to provide or promote dementia friendly interventions, such as dementia friendly swimming and golf. However, what was evident across the data was a need to map what was already available, and to evaluate the needs of the local population living with dementia, including marginalised and underserved communities. Participants attempted to address unmet need and deficits in specialist dementia knowledge through training and education for care home and day centre staff, and dementia specialist accreditation. Some described using roles such as social prescribing (referrals from healthcare professionals to local non-clinical services [e.g., volunteering, sports groups etc.] with the aim of holistically improving health and wellbeing [ 14 ]) to engage this population in exercise, and others created dementia hubs and strategies to support local priorities. Participants identified several barriers to engaging their local community of people living with dementia in physical activity. This included fear and anxiety, avoidance of activity perceived as risky, lacking support, poor awareness of available services, and lacking infrastructure and transport links, which were troublesome in rural areas.

Participants considered an intervention like PrAISED to be an important component in addressing the post-diagnostic support gap which could play an important role in preventing health and social care use. This was a particular concern in the face of exponential growth in the number of people living with dementia. For some, this underpinned the demand for services like PrAISED:

‘It is critical because we are very limited in the resources we have, so everything you can do to keep people at the lower levels of care for as long as possible are critical and keep people in their own homes wherever possible… anything that supports that kind of left shift to our demand management is really critical,’ Participant 1 (Commissioner).

Early support was deemed necessary to not only prevent health and social care consumption, but also to enhance quality of life and promote meaningful activity and engagement in all aspects of life.

A significant facilitator to providing dementia friendly services was collaborative working and the formation of partnerships and connections with other organisations and stakeholders. Participants were hopeful that health service organisational changes (to Integrated Care Systems (ICS) [ 16 ] would improve collaborative working and align commissioning priorities across health and social care in England. Despite optimism regarding these new partnerships, there was confusion surrounding the responsibilities of these groups and concerns that this would complicate the commissioning process. Additionally, competing priorities between organisations attempting to work cohesively posed a challenge.

Nonetheless, these partnerships were imperative to effective commissioning. Most participants emphasised the importance of the voluntary sector in the provision of dementia friendly services (if commissioned to do so). Many stakeholders had experience working with charities in the design, delivery and maintenance of dementia services and they advocated for their presence as specialists in dementia. Some suggested these organisations were best placed to deliver services (if appropriately commissioned) as they had the time, resources, and specialist knowledge to do so. Alongside charities and the voluntary sector, stakeholders described collaborations with national sporting agencies such as Sport England and other partnerships, including universities, place-based partnerships, social enterprises, the Fire and Rescue Service, community groups, commercial advisors, professional sports teams, and health and social care organisations. These partnerships were seen to facilitate service sustainability and long-term presence in the community.

Organisational partnerships also facilitated the financing of dementia friendly services. These organisations had grants which could fund services, though these were often short lived. Financing was a significant barrier to the commissioning and implementation of dementia friendly interventions. There were tensions between the responsibility for funding:

‘Personally, I think [the] NHS should give us money towards it if they want us to implement it… it will have a knock-on effect on the admissions because if we reduce falls for a longer period of time, it means they’ve got less operations to do and less throughput of hospitals,’ Participant 4 (Occupational Therapist).

The private versus public funding debate was influenced by several factors. Some reported private financing of services was a feasible method for delivering interventions like PrAISED. In contrast, public funding was regarded as difficult to obtain and was frequently linked to other constructs, such as external policy and incentives, and available resources in the inner setting. The VCS thus frequently bridged the gap, and there was a reliance on this sector, which was not without consequences:

‘It is a difficult one because it it’s one of the areas where there is a lot of reliance on almost free services as in non-funded services so that they're either a charitable or community… which means it’s quite piecemeal and quite localized. So, it’s quite hard,’ Participant 7 (Commercial Director).

In terms of what drove the commissioning and implementation of dementia friendly services in the outer setting, there was little reference to peer pressure, though participant 9 highlighted the importance of being aware of what competing organisations were doing and what services were already available. A more commonly cited construct was external policy and incentives. There were conflicting views on the value of external policy and incentives in influencing the commissioning and implementation of dementia friendly services, where it was seen as sometimes a facilitator and at other times, non-influential:

‘We always say “oh policy drives action,” but it doesn’t always… At the end of the day, policy is slightly important… this is my own view, [NHS] Trusts tend not to buy things because of policy. Trusts buy things because it solves a problem for them,’ Participant 7 (Commercial Director).

However, other participants felt policy acted as a facilitator:

‘The easiest way to get it funded is where actual national policy says you must have X service in place. That’s the easiest thing. And you have ring fenced money… it’s really hard if you don’t have that… if we’ve got a national policy, we do have to respond to it,’ Participant 1 (Commissioner).

They went onto suggest external monitoring, performance management and Key Performance Indicators (KPIs) also facilitated commissioning.

Local strategy and policy were also seen to both facilitate and hinder implementation, as budgets would be allocated accordingly:

‘I think probably the one of the main factors is it being a strategic priority locally, because then you’ve got the buy in from the whole system and at the top. So, if it ain’t a strategic priority, then even if it is really good, it might not continue to be funded because of the things which are meeting those strategic priorities will likely get more resources allocated because budgets will be allocated on what are those strategic priorities,’ Participant 5 (Commissioning Manager).

Financial incentives and penalties which are used across OECD (Organisation for Economic Co-operation and Development) member countries to motivate performance in health systems [ 34 ] were also perceived facilitators:

‘I suppose targets and financial incentives or financial pen- well incentives are better than penalties, but usually in the NHS is about punishment. So, you know some sort of stimulus that’s hard for them to ignore. So simply giving them advice that they should is “well, we can ignore that then.” So, it needs to be a bit of force behind it to make people actually implement things,’ Participant 8 (Professor of Dementia Research).

Inner setting

Participants described a need to shift the culture of commissioning from short to long term. Several participants expressed concern that commissioners focussed on ‘crisis management’ due to the NHS climate, rather than on preventative interventions that would provide cost efficiency savings longer term. It was perceived as more difficult to achieve buy-in to such interventions, as often cost savings were not immediately visible. Physical activity and public health interventions were perceived as key to preventative care, and whilst there was a shift towards these types of interventions, there was still work to be done:

‘…in terms of how much we value we place on physical activity in terms of prevention and treatment for long term conditions… I don’t think we’re quite where we should be with that… the health service has been increasingly crisis weighted and I think that limits how much we think about building in preventative or wellbeing factors into primary services,’ Participant 12 (Partnership Manager).

There was a shift in culture towards collaborative working, both within the inner setting (networks and communications), and outer setting (cosmopolitanism/partnerships and connections). However, inner setting decision making processes remained complex and, at times, posed a barrier to commissioning and implementation. Indeed, for participant 11, they had observed how networks facilitated implementation, but also introduced biases, causing them to question the system:

‘I seem to find if they like something and they have a good relationship with an organisation, funnily enough, that sometimes leads to funding and renewal of funding… it would be nice to think it is a fair process… but I think with a lot of things particularly that are NHS system based is that they're very rigid in what they want them to achieve and although they may say that they’re person-centred, really, they’re system-centred and then the person is expected to fit in with that,’ Participant 11 (Researcher).

As described earlier, there was an identified need for dementia friendly activity-based interventions. For three participants, their views met the criteria for coding under the construct tension for change, as they viewed the current situation as intolerable or requiring urgent change. Nonetheless, this was subject to challenges. It was important for any innovation attempting commissioning and/or implementation to be compatible with the existing local systems. For example, whether the innovation could be embedded or absorbed into existing services (compatibility), which is linked to the adaptability construct (innovation characteristics). This was a significant facilitator for implementation success.

Furthermore, the relative priority of the innovation was both a barrier and facilitator. Priorities within the commissioning cycle could prevent similar services from being commissioned. For example, participant 5 suggested that if a falls prevention programme had recently been commissioned, other dementia friendly activity-based interventions would be a lower priority for commissioning. Moreover, the wider social, political, and economic climate also shifted commissioning priorities; the most recent example being the COVID-19 pandemic, where public health and pandemic management were inevitably given greater priority. Furthermore, organisational rewards, measurement and KPIs acted as incentives to implement innovations, but only if local priorities and strategies deemed dementia care and falls prevention a priority. More so, should the innovation align with the goals and mission statement of the organisation, this too would escalate the priority of commissioning and implementation.

One of the most significant and highly cited barriers to commissioning and implementing dementia friendly services was a lack of available resources. This included workforce, time, capacity, available providers, and most significantly, funding. Appropriate (and long-term) funding to commission, implement and deliver an innovation was difficult to secure. Often, budgets were already allocated and thus, unavailable:

‘The real challenge we have got of course is there isn’t new money, there isn’t spare money,’ Participant 1 (Commissioner).

Considering the vast array of contextual factors represented across the CFIR constructs, it is significant that participants often came back to the topic of resources. This issue was shared across the stakeholders, including those with commissioning responsibilities, who expressed frustration that they were unable to commission innovations:

‘There isn’t a lot of money… this is a really frustrating thing that you get all these people coming to you with some really good things [innovations], but we don’t really have money for spending on these things anymore,’ Participant 14.

In the context of limited resources, the NHS was suggested to be the most suitable provider of a service like PrAISED:

‘The problem for dementia is that much of it falls between health and social care. Social care is so poorly funded that it is difficult to see it doing a great deal… probably for it to become more widespread the way things currently are, it would require NHS commissioning, I think are the only people with any money,’ Participant 8 (Professor of Dementia Research).

In addition to funding, inadequate staffing levels and capacity of existing staff hampered implementation. Staff would be required to take on additional workload or redirect time from other services to implement innovations, which was undesirable. This was also the case for allocating time for training. Some suggested additional staff could be hired to facilitate implementation; however, this was associated with greater costs, temporary contracts, and thus, job insecurity. The demands of a lengthy programme like PrAISED (delivered over 12 months) was deemed unfeasible, as participant 4 described when looking to implement Otago, a home-based balance and strengthening programme effective at reducing falls in over 65 s [ 15 ]:

‘The main thing is time and follow ups. We just can’t… Otago’s 12 months. We can’t do it. We can’t do it,’ Participant 4 (Occupational Therapist).

Although leadership engagement (such as service managers) could facilitate this, resources frequently dictated the success of commissioning and implementing innovations.

Individual characteristics

The characteristics of individuals responsible for commissioning, implementing and delivering interventions like PrAISED, acted as potential facilitators to success. Participants identified areas where knowledge could be instilled to upskill caregivers (formal and informal) to engage people living with dementia in physical activity interventions. Furthermore, the knowledge of and belief in such interventions acted as a driver. Individuals’ stage of change [ 18 ] thus could initiate service development; for example, when asked what a persuading factor in the commissioning and implementation of a dementia friendly intervention could be, participant 6 stated:

‘I wouldn’t need persuading because I’m completely on board with it,’ Participant 6 (Sports Development Officer).

As mentioned earlier (innovation characteristics), many participants suggested the intervention could be delivered by other professional groups, such as exercise instructors, personal trainers, domiciliary care workers and support workers/therapy assistants. This was captured under the other personal attributes construct of the individual characteristics domain. Professional groups outside of physiotherapy and occupational therapy were suggested as potential deliverers of interventions like PrAISED due to their cheaper cost, connections to local communities (e.g., gyms, leisure centres, community groups), and their perceived undervalue as an untapped workforce with relevant skills. Furthermore, difficulty in recruiting clinicians and the pressure existing clinicians were under were acknowledged and thus, alternative groups taking responsibility for an intervention like PrAISED would ease pressure.

Most participants expressed a growing appreciation of exercise professionals in delivering physical activity interventions:

‘…there are thousands of physical activity exercise professionals who are highly qualified… Let’s use that workforce. Why not? You know, they are an untapped workforce and there’s a lot of them out there who are already got those connections in the community… they’ve got those behaviours, skills and those motivational interviewing techniques to work with those individuals and then perhaps to support the carers directly as well as those are being cared for. So huge opportunities there,’ Participant 10 (Project Manager).

Many suggested these members of the workforce were qualified and competent to deliver an intervention like PrAISED, with many having undergone specialist training in long term conditions. Thus, it was not always deemed necessary to have registered clinical qualified healthcare professionals’ oversight, though some suggested clinicians could work collaboratively to oversee the programme with exercise professionals delivering the intervention. The use of an existing, untapped workforce could impact the success of commissioning, though this had implications for the intervention:

‘…with all the pressures in the system, with workforce, the interventions that can be delivered successfully, carefully, safely, but with the lowest level of staff training required are very appealing… what is the lowest level of staff that you could utilize on this without making it unsafe or ineffective?’ Participant 7 (Commercial Director).

Some suggested having non-registered clinical staff delivering the intervention would be the most realistic option for commissioning and implementing a service such as PrAISED.

References to planning the implementation process were mostly dominated by the planning of commissioning. As this work package was not reflecting retrospectively on an implemented service, participants spoke hypothetically about this process. The greatest concern was how to plan the business case or model to facilitate successful commissioning/securement of funding. These concerns were mostly related to other constructs such as financing (outer setting) and available resources (inner setting). Other concerns were regarding the organisational model within local systems, such as commercialisation and licencing and how these would be managed in the future, as this had implications for an intervention’s sustainability. Additionally, participants suggested it was imperative to be cognisant of the commissioning cycle and plan attempted business cases accordingly, as this could affect success. Participant 5 described it as being ‘in the right place, at the right time.’

In the case of the English NHS, having a range of engaged individuals was integral to implementation success. Participants provided several examples, including opinion leaders (e.g., leaders in dementia research, dementia advocates), formally appointed implementation leaders (e.g., project leads, healthy aging leads), external change agents (e.g., opinion leaders, politicians, councillors, commissioners, advisors, television personalities Footnote 1 ), champions (self and/or formally appointed), key stakeholders (healthcare professionals, staff, organisations), and innovation participants (service users and caregivers). These champions were considered key to driving the implementation process, particularly when faced with challenges or decreasing momentum:

‘We do need to have if you want to call [them] falls, champions or dementia champions, if that’s the right word, but more ambassadors or business change agents…. Within those day services who can take a bit of ownership and accountability to ramp up that effort, ’ Participant 9 (Programme Manager [Commissioning]).

‘…it’s enthusiasm and passion for me that’s such an important driver,’ Participant 11 (Health and Activity Researcher).

Reflection and evaluation were critical parts of the implementation process for some participants and was something that needed to be built in as part of the planning process. This was important to not only evaluate implementation success and ‘continuous improvement,’ but to provide lessons for future implementation.

The aim of the current study was to explore the barriers and facilitators to commissioning and implementing health and social care interventions for people with dementia in England, using a dementia-friendly exercise and physical activity-based intervention (PrAISED) as a case study. We found facilitators and barriers mapped onto the CIFR [ 17 ] which showed:

The credibility and cost-saving nature of the intervention was important, along with the ability to adapt it to local provision and skill mix.

Interventions such as PrAISED may fill the post-diagnostic gap, but there needs to be an organisational system that will get them commissioned; this involves collaboration between commissioners, providers and other stakeholders, including dementia advocates and caregivers.

There also needs to be a policy culture that values prevention, prioritises dementia and is willing to commit resource to it to make it work.

The post-diagnostic gap

The post-diagnostic gap is defined as ‘ an umbrella term encompassing the variety of official and informal services and information aimed at promoting the health, social, and psychological wellbeing of people with dementia and their carers after a diagnosis. Integrated treatment, care, and support are the pillars of effective post-diagnosis models,’  [ 23 ], p.21). This was a common theme in this study and is a global problem [ 22 , 26 ], despite efforts designed to address this [ 10 , 35 ].

Consequently, there is a need for innovations that address the service gap. Many participants advocated for physical activity interventions, though they also identified a broader need for psychosocial, emotional, logistical, practical, and peer support. This echoes the findings of Bamford et al. [ 8 ], who identified 20 components of post-diagnostic support, extending across five themes (timely identification and management of needs,understanding and managing dementia,emotional and psychological wellbeing; practical support; and integrating support). Bamford et al. [ 8 ] suggested there is a need for local planning and coordination of such services, and there was evidence of this in this study, though wider barriers to commissioning and implementation had the potential to hamper efforts.

This study’s findings reflect other literature exploring barriers and facilitators to commissioning and implementing post-diagnostic services. Wheatley et al. [ 41 ] identified unsupportive infrastructure, limited proactive, holistic tailored support, and limited capacity and capability as barriers to implementation. They identified strategies to address this, such as creating opportunities for service improvement, facilitating collaborative working, supporting non-specialists (e.g., non-medically qualified healthcare professionals) to deliver dementia care, and the development of ongoing holistic support [ 41 ]. The current study provides evidence that these strategies are being undertaken, though there is more to be done to enhance collaboration and the utilisation of existing workforces.

Some research suggests that physical activity interventions for older people can be delivered safely and effectively by non-clinically registered professionals (e.g., exercise instructors, postural stability instructors) [ 30 ] and can be delivered in novel environments outside of traditional healthcare settings [ 32 ]. Furthermore, a physical activity intervention for older people with cognitive impairment, delivered by exercise instructors, showed promising improvements in physical and cognitive function, quality of life and caregiver burden, though the sample size was small [ 9 ]. Therefore, the delivery of physical activity interventions by these professionals may offer a solution to the commonly cited barrier of available resources, which was recommended by Wheatley et al. [ 41 ].

The culture of commissioning in England

This study identified the need for a policy culture that values prevention. In the UK, prevention of ill health is described as a role for individuals, communities, NHS, social care, public health, and local and national government [ 19 ], and is a global priority [ 42 ]. However, these findings demonstrate the complexities of prevention in practice in a universal publicly funded health system.

Interventions like PrAISED are preventative and they were considered harder to secure commissioning commitment. Participants suggested this was twofold: 1) the benefit of such interventions was not immediately visible, and 2) commissioning was focussed on short term ‘crisis management.’ Participants suggested the underappreciation of preventative services meant interventions that may provide longer term cost savings were harder to gain support for and thus implement. This was coupled with difficulty in evidencing cost savings, particularly as commissioners wanted to be able to evidence specifically where cost savings would be delivered, e.g., health or social care. Despite this, participants with commissioning responsibilities were generally acutely aware of the need for preventative services, with some creating dementia strategies and influencing local priorities to address this. Nonetheless, this has the potential to create fragmentation and inequity across sectors and geographies. Furthermore, despite actions to address this, commissioners were also subject to the barriers to commissioning and implementation identified in this study.

In the wider literature, the discourse surrounding joint commissioning emphasises prevention [ 21 ]. Miller et al. [ 33 ] suggest delaying deterioration and maintaining physical and mental health in older people (and thus, their use of health services) is a commonly cited aspiration in commissioning (e.g., [ 2 ]). However, it appears the ability to exercise this rhetoric is limited in the face of competing priorities and restricted resources (affordability). In this study, the VCS was seen as an able facilitator and provider of preventative care, something earlier suggested by Miller et al. [ 33 ]. While there have been successful examples of this, the issues with demonstrating preventative and rehabilitative services, as well as the need to rebalance the system with such care being integrated [ 2 ], continue to pose challenges in commissioning.

The current study has considered the commissioning and implementation of dementia friendly exercise and physical activity-based interventions using PrAISED as a case study. It has identified key considerations for the future of dementia care, particularly in relation to provision of post-diagnostic support and the culture of commissioning in contemporary healthcare. Furthermore, it has identified barriers (cost/financing, the culture of commissioning, and available resources) and facilitators (adaptability of the intervention, cosmopolitanism/partnerships and connections, external policy and incentives, and use of already existing workforces) to commissioning dementia friendly services. Thus, this study provides insight for stakeholders planning the commissioning, implementation and promotion of dementia services.

Recommendations for commissioning and implementing dementia services

A series of recommendations have been collated based upon the barriers and facilitators identified in this study:

Map out local needs and resources

The needs and resources of the population living with dementia and their caregivers should be identified (including the needs of underserved communities)

Involve people living with dementia and their caregivers in identifying these needs

Map existing services (and how/where the intervention would fit)

Evidence the intervention

Evidence the outcomes of the intervention, including effectiveness and cost-effectiveness (e.g., physical and mental health, psychosocial factors, and financial such as cost benefit analysis, patient and deliverer satisfaction [e.g., qualitative data]), to ensure stakeholders value the innovation and its potential impact to ensure it is commissioned/funded and integrated into routine clinical practice.

Create/utilise networks and partnerships with stakeholders with a role in implementing, commissioning, providing, and promoting dementia friendly interventions

Identify local/organisational priorities, resources, and opportunities for collaboration to facilitate commissioning and implementation

Involve these networks and partnerships in the early stages to plan for sustainability

Plan required resources for delivery (cost, staffing, equipment)

Assess capacity in the local system for non-medical professionals delivering exercise and physical activity interventions (e.g., exercise instructors), where able to do so safely and appropriately.

Strengths and limitations

This study presents the perspectives of a small number of stakeholders thus they will not necessarily represent the views of all stakeholders involved in dementia care or commissioning. As this study was carried out in England, the views may not be representative of stakeholders in other countries and care systems. As this study aimed to investigate the views of those with direct responsibility for commissioning and implementing health and social care interventions, we did not include people with dementia or their caregivers in the interviews. These persons could have important insights into the commissioning and implementation of health and social care interventions for people with dementia; hence, this is a limitation of the study and an area which could be explored in future research.

A strength of the study was the range of perspectives and expertise collected, as all participants were involved in dementia services commissioning and provision. Furthermore, the collective discussion of coding decisions within the wider implementation research team meant a range of perspectives were utilised during data analysis.

This study identified several barriers and facilitators to the commissioning and implementation of health and social care interventions for people with dementia, using a dementia-friendly exercise and physical activity-based intervention (PrAISED) as a case study. Key barriers to commissioning and implementing dementia specific services included their cost/financing, competing commissioning priorities and having available resources. Key facilitators included the adaptability of the intervention, having good partnerships and connections in place, external policy and incentives, and the use of already existing (and untapped) workforces.

Based on the results of this study, four actions are recommended to facilitate the commissioning and implementation of interventions like PrAISED: 1) map out local needs and resources, 2) evidence the intervention including effectiveness and cost-effectiveness, 3) create/utilise networks with stakeholders, and 4) plan required resources. Further research is required to explore the outcomes of proposed recommendations.

Availability of data and materials

The datasets generated and/or analysed during the current study are not publicly available to honour the privacy and confidentiality of participants but are available from the corresponding author on reasonable request.

One participant identified television actress Vicky McClure who had worked extensively with a dementia choir, increasing awareness of the condition (see https://www.ourdementiachoir.com/about-the-choir ).

Abbreviations

Clinical Commissioning Group

Consolidated Framework for Intervention Research

Integrated Care System

National Health Service

National Institute for Health and Care Excellence

Organisation for Economic Co-operation and Development

Promoting Activity, Stability and Independence in Early Dementia and Mild Cognitive Impairment

Voluntary and community sector

World Health Organisation

Adams EJ, Burgon C, Lock J, Smith H, Vickers R, Tucker R, Timmons S, Orton E, Goldberg SE, Gladman J, Masud T, Harwood RH. Implementation of the PrAISED (Promoting Activity, Independence and Stability in Early Dementia) intervention in practice: a mixed methods study. MedRxiv. 2023. https://doi.org/10.1101/2023.05.24.23289730 .

Allen K, Glasby J. The (Multi-) billion dollar question: embedding prevention and rehabilitation in English health and social care. J Integr Care. 2010;18(4):26–35. https://doi.org/10.5042/jic.2010.0376 .

Alzheimer’s Association. 2023 Alzheimer’s disease facts and figures. Alzheimers Dementia. 2023;19:1598–695. https://doi.org/10.1002/alz.13016 .

Article   Google Scholar  

Alzheimer’s Society. Dementia- the true cost: fixing the care crisis. 2018. Available at:  https://www.alzheimers.org.uk/sites/default/files/2018-05/Dementiathetruecost-AlzheimersSocietyreport.pdf . Accessed 5 Feb 2023.

Alzheimer’s Society. What is dementia? 2021. Available at: https://www.alzheimers.org.uk/sites/default/files/2018-10/400Whatisdementia.pdf . Accessed 28 Oct 2022.

Bajwa R, Goldberg S, Van der Wardt V, Burgon C, Di Lorito C, Godfrey M, Dunlop M, Logan P, Masud T, Gladman J, Smith H, Hood-Moore V, Booth V, Das Nair R, Pollock K, Vedhara K, Tudor Edwards R, Jones C, Hoare Z, Brand A, Harwood R. A randomised controlled trial of an exercise intervention promoting activity, independence and stability in older adults with mild cognitive impairment and early dementia (PrAISED) - a protocol. Trials. 2019;20:815. https://doi.org/10.1186/s13063-019-3871-9 .

Article   PubMed   PubMed Central   Google Scholar  

Balas EA, Boren SA. (2000) Managing clinical knowledge for health care improvement. Yearb Med Inform. 2000;1:65–70.  https://doi.org/10.1055/s-0038-1637943 .

Bamford C, Wheatley A, Brunskill G, Booi L, Allan L, Banerjee S, Harrison Dening K, Manthorpe J, Robinson L, PriDem study team. Key components of post-diagnostic support for people with dementia and their carers: a qualitative study. PLoS ONE. 2021;16(12):e0260506. https://doi.org/10.1371/journal.pone.0260506 .

Article   CAS   PubMed   PubMed Central   Google Scholar  

Barnes DE, Mehling W, Wu E, Beristianos M, Yaffe K, Skultety K, Chesney MA. Preventing loss of independence through exercise (PLIÉ): a pilot clinical trial in older adults with dementia. PLoS One. 2015;10(2):e0113367. https://doi.org/10.1371/journal.pone.0113367 .

Barrett E, Burns A. Dementia Revealed Toolkit: What Primary Care Needs to Know. A Primer for General Practice. Department of Health and the Royal College of General Practitioners; 2014. Available at: https://www.england.nhs.uk/wp-content/uploads/2014/09/dementia-revealed-toolkit.pdf . Accessed 29 Nov 2022.

Booth V, Harwood RH, Hood-Moore V, et al. Promoting activity, independence and stability in early dementia and mild cognitive impairment (PrAISED): development of an intervention for people with mild cognitive impairment and dementia. Clin Rehabil. 2018;32(7):855–64. https://doi.org/10.1177/0269215518758149 .

Braun V, Clarke V. Using thematic analysis in psychology. Qual Res Psychol. 2006;3(2):77–101. https://doi.org/10.1191/1478088706qp063oa .

Braun V, Clarke V, Hayfield N, Terry G. Thematic analysis. In: Liamputtong P, editor. Handbook of research methods in health social sciences. Singapore: Springer; 2019. https://doi.org/10.1007/978-981-10-5251-4_103 .

Chapter   Google Scholar  

Buck D, Ewbank L. What is social prescribing? 2020. Available at: https://www.kingsfund.org.uk/publications/social-prescribing . Accessed 20 Dec 2022.

Campbell AJ, Robertson MC. Otago exercise programme to prevent falls in older adults. A home based, individually tailored strength and balance retraining programme. Wellington, New Zealand: Accident Compensation Corporation; 2007. ISBN 0–478–25194–7.

Charles A. Integrated care systems explained: making sense of systems, places and neighbourhoods. The Kings Fund; 2022. Available at: https://www.kingsfund.org.uk/publications/integrated-care-systems-explained . Accessed 21 Dec 2022.

Damschroder LJ, Aron DC, Keith RE, et al. Fostering implementation of health services research findings into practice: a consolidated framework for advancing implementation science. Implement Sci. 2009;4:50. https://doi.org/10.1186/1748-5908-4-50 .

Damschroder LJ, Reardon CM, Widerquist MAO, et al. The updated consolidated framework for implementation research based on user feedback. Implement Sci. 2022;17:75. https://doi.org/10.1186/s13012-022-01245-0 .

Department for Health and Social Care. Prevention is better than cure: our vision to help you live well for longer. 2018. https://assets.publishing.service.gov.uk/media/5be00437e5274a6e174bdac1/Prevention_is_better_than_cure_5-11.pdf . Accessed 15 Apr 2024.

Department for Health and Social Care. The NHS Constitution. 2021. Available at:  https://www.gov.uk/government/publications/the-nhs-constitution-for-england/the-nhs-constitution-for-england . Accessed 21 Dec 2022.

Dickinson H, Glasby J, Nicholds A, Sullivan H. (2013) Making sense of joint commissioning: three discourses of prevention empowerment and efficiency. BMC Health Services Research. 2013;13(S1). https://doi.org/10.1186/1472-6963-13-S1-S6 .

Gauthier S, Rosa-Neto P, Morais JA, Webster C. World Alzheimer Report. Journey through the diagnosis of dementia. London: Alzheimer’s Disease International; 2021. Available at: https://www.alzint.org/u/World-Alzheimer-Report-2021.pdf . Accessed 29 Nov 2022.

Gauthier S, Webster C, Servaes S, Morais JA, Rosa-Neto P. World Alzheimer Report. Life after diagnosis: navigating treatment, care and support. London: Alzheimer’s Disease International; 2022. Available at: https://www.alzint.org/u/World-Alzheimer-Report-2022.pdf . Accessed 29 Nov 2022.

Gitlin LN, Baier RR, Jutkowitz E, Baker ZG, Gustavson AM, Sefcik JS, Hodgson NA, Koeuth S, Gaugler JE. Dissemination and implementation of evidence-based dementia care using embedded pragmatic trials. J Am Geriatr Soc. 2020;68 Suppl 2(Suppl 2):S28–36. https://doi.org/10.1111/jgs.16622 .

Article   PubMed   Google Scholar  

Goldberg S, van der Wardt V, Brand A, Burgon C, Bajwa R, Hoare Z, Logan P, Harwood R. Promoting activity, Independence and stability in early dementia (PrAISED): a, multisite, randomised controlled, feasibility trial. BMC Geriatr. 2019;19:353. https://doi.org/10.1186/s12877-019-1379-5 .

Gresham M. Forward with Dementia: Improving post-diagnostic support. 2022. https://www.alzint.org/newsevents/news/forward-with-dementia-improving-post-diagnostic-support/ . Accessed 15 Apr 2024.

Groot Kormelinck CM, Janus SIM, Smalbrugge M, Gerritsen DL, Zuidema SU. Systematic review on barriers and facilitators of complex interventions for residents with dementia in long-term care. Int Psychogeriatr. 2021;33(9):873–89. https://doi.org/10.1017/S1041610220000034 .

Harwood RH, Goldberg SE, Brand A, van Der Wardt V, Booth V, Di Lorito C, et al. Promoting Activity, Independence, and Stability in Early Dementia and mild cognitive impairment (PrAISED): randomised controlled trial. BMJ. 2023;382:e074787. https://doi.org/10.1136/bmj-2023-074787 .

Illife, S. Commissioning services for people with dementia: how to get it right. The Psychiatrist. 2018;37(4):121–123. https://doi.org/10.1192/pb.bp.112.040329 .

Iliffe S, Kendrick D, Morris R, Masud T, Gage H, Skelton D, et al. Multicentre cluster randomised trial comparing a community group exercise programme and home-based exercise with usual care for people aged 65 years and over in primary care. Health Technol Assess. 2014;18(49):1–105. https://doi.org/10.3310/hta18490 .

Kirk MA, Kelley C, Yankey N, Birken SA, Abadie B, Damschroder L. A systematic review of the use of the consolidated framework for implementation research. Implement Sci. 2016;11:72. https://doi.org/10.1186/s13012-016-0437-z .

Long A, Di Lorito C, Logan P, Booth V, Howe L, Hood-Moore V, van der Wardt V. The impact of a dementia-friendly exercise class on people living with dementia: a mixed-methods Study. Int J Environ Res Public Health. 2020;17:4562. https://doi.org/10.3390/ijerph17124562 .

Miller R, Allen K, Mangan C, Glasby J. Singing from the same hymn sheet? Commissioning of preventative services from the third sector. J Integr Care. 2013;21(5):288–99. https://doi.org/10.1108/JICA-07-2013-0026 .

Milstein R, Schreyoegg J. Pay for performance in the inpatient sector: a review of 34 P4P programs in 14 OECD countries. Health Policy. 2016;120:1125–40.  https://doi.org/10.1016/j.healthpol.2016.08.009 .

National Institute for Health and Care Excellence (NICE). Dementia- discussing and planning support after diagnosis: a quick guide for people with dementia and their family and carers. 2018. Available at: https://www.nice.org.uk/Media/Default/About/NICE-Communities/Social-care/quick-guides/Dementia-quick-guide.pdf . Accessed 29 Nov 2022.

NHS England. Who commissions NHS services? NHS England; 2022. Available at: https://www.england.nhs.uk/commissioning/who-commissions-nhs-services/ . Accessed 15 Apr 2024

Nichols E, Steinmetz J, Vollset SE, Abd-Allah F, Abdoli A, Abu-Gharbieh E, Alipour V, Almustanyir S, Amu H, Arabloo J, Ayano G, Ayuso-Mateos JL, Baune BT, Béjot Y, Bezabhe WMM, Bijani A, Burkart K, et al. Estimation of the global prevalence of dementia in 2019 and forecasted prevalence in 2050: an analysis for the global burden of disease study 2019. Lancet Public Health. 2022;7(2):e105–25. https://doi.org/10.1016/S2468-2667(21)00249-8 .

Lumivero. NVivo Version 13 (2020 R1). 2020. https://lumivero.com/products/nvivo/ . Accessed 5 Apr 2024.

The Kings Fund. Social care in a nutshell. 2022. Available at: https://www.kingsfund.org.uk/projects/nhs-in-a-nutshell/social-care-nutshell . Accessed 5 Feb 2023.

Wenzel L, Robertson R. What is commissioning and how is it changing? 2019. Available at: https://www.kingsfund.org.uk/publications/what-commissioning-and-how-it-changing . Accessed 5 Feb 2023.

Wheatley A, Bamford C, Brunskill G, Booi L, Harrison Dening K, Robinson L, on behalf of the PriDem study team. Implementing post-diagnostic support for people living with dementia in England: a qualitative study of barriers and strategies used to address these in practice. Age Ageing. 2021;50(6):2230–7. https://doi.org/10.1093/ageing/afab114 .

World Health Organisation. Follow-up to the political declaration of the third high-level meeting of the General Assembly on the prevention and control of non-communicable diseases. Seventy-second World Health Assembly Agenda item 11.8. 2019. https://apps.who.int/gb/ebwha/pdf_files/WHA72/A72(11)-en.pdf . Accessed 15 Apr 2024.

World Health Organisation. Dementia. 2022. Available at: https://www.who.int/news-room/fact-sheets/detail/dementia . Accessed 20 Dec 2022.

Download references

Acknowledgements

The authors would like to thank all participants who took part in this research.

This project was funded by the NIHR Programme Grants for Applied Research funding scheme [RP-PG-0614-20007]. The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care.

Author information

Authors and affiliations.

School of Health Sciences, University of Nottingham, Queen’s Medical Centre, Nottingham, UK

Rachael Tucker, Emma J. Adams, Sarah E. Goldberg & Rowan H. Harwood

School of Medicine, University of Nottingham, Queen’s Medical Centre, Nottingham, UK

Robert Vickers, Clare Burgon, Juliette Lock, John Gladman & Elizabeth Orton

Nottingham University Hospitals NHS Trust, Nottingham, UK

John Gladman, Tahir Masud & Rowan H. Harwood

National Institute for Health and Social Care Research (NIHR) Nottingham Biomedical Research Centre (BRC), Nottingham, UK

John Gladman

National Institute for Health and Social Care Research (NIHR) Applied Research Collaboration (ARC) East Midlands, Nottingham, UK

Robert Vickers & John Gladman

Nottingham University Business School, Nottingham, UK

Stephen Timmons

You can also search for this author in PubMed   Google Scholar

Contributions

Conceptualisation: EA, RV, SG, JG, TM, RH Methodology: RV, EA, JG, EO, ST, SG, RH Data collection: RT, RV Data analysis: RT, RV, EA, CB, JL Writing- original draft: RT Writing- review and editing: RT, RV, EA, CB, JL, SG, JG, TM, EO, ST, RH Implementation research expertise: EO, ST, JG All authors reviewed the manuscript and agreed to its submission and publication.

Corresponding author

Correspondence to Emma J. Adams .

Ethics declarations

Ethics approval and consent to participate.

The study received research governance approvals and ethical approval from the Bradford Leeds Research Ethics Committee (18/YH/0059; 236099). All participants provided consent before taking part.

Consent for publication

All participants agreed to the publication of findings of this study.

Competing interests

Rachael Tucker is a Scientific Editor at Elsevier Cell Press. The work presented in this paper was carried out whilst RT worked as a Research Assistant at the University of Nottingham. All other authors have no competing interests to declare. The study was funded by the NIHR Programme Grants for Applied Research funding scheme [RP-PG-0614-20007]. The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Tucker, R., Vickers, R., Adams, E.J. et al. Factors influencing the commissioning and implementation of health and social care interventions for people with dementia: commissioner and stakeholder perspectives. Arch Public Health 82 , 54 (2024). https://doi.org/10.1186/s13690-024-01283-8

Download citation

Received : 12 December 2023

Accepted : 06 April 2024

Published : 23 April 2024

DOI : https://doi.org/10.1186/s13690-024-01283-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Cognitive impairment
• Facilitators
• Physical activity
• Commissioning
• Implementation

Archives of Public Health

ISSN: 2049-3258

• General enquiries: [email protected]

Articles from Emerging Infectious Diseases

Volume 30, Number 5—May 2024

[PDF - 14.66 MB - 228 pages]

Research Letters

About the cover.

Crimean-Congo hemorrhagic fever (CCHF), caused by CCHF virus, is a tickborne disease that can cause a range of illness outcomes, from asymptomatic infection to fatal viral hemorrhagic fever; the disease has been described in >30 countries. We conducted a literature review to provide an overview of the virology, pathogenesis, and pathology of CCHF for clinicians. The virus life cycle and molecular interactions are complex and not fully described. Although pathogenesis and immunobiology are not yet fully understood, it is clear that multiple processes contribute to viral entry, replication, and pathological damage. Limited autopsy reports describe multiorgan involvement with extravasation and hemorrhages. Advanced understanding of CCHF virus pathogenesis and immunology will improve patient care and accelerate the development of medical countermeasures for CCHF.

Crimean-Congo hemorrhagic fever (CCHF) is a tickborne infection that can range from asymptomatic to fatal and has been described in >30 countries. Early identification and isolation of patients with suspected or confirmed CCHF and the use of appropriate prevention and control measures are essential for preventing human-to-human transmission. Here, we provide an overview of the epidemiology, clinical features, and prevention and control of CCHF. CCHF poses a continued public health threat given its wide geographic distribution, potential to spread to new regions, propensity for genetic variability, and potential for severe and fatal illness, in addition to the limited medical countermeasures for prophylaxis and treatment. A high index of suspicion, comprehensive travel and epidemiologic history, and clinical evaluation are essential for prompt diagnosis. Infection control measures can be effective in reducing the risk for transmission but require correct and consistent application.

Crimean-Congo hemorrhagic fever virus (CCHFV) is the most geographically widespread tickborne viral infection worldwide and has a fatality rate of up to 62%. Despite its widespread range and high fatality rate, no vaccines or treatments are currently approved by regulatory agencies in the United States or Europe. Supportive treatment remains the standard of care, but the use of antiviral medications developed for other viral infections have been considered. We reviewed published literature to summarize the main aspects of CCHFV infection in humans. We provide an overview of diagnostic testing and management and medical countermeasures, including investigational vaccines and limited therapeutics. CCHFV continues to pose a public health threat because of its wide geographic distribution, potential to spread to new regions, propensity for genetic variability, potential for severe and fatal illness, and limited medical countermeasures for prophylaxis and treatment. Clinicians should become familiar with available diagnostic and management tools for CCHFV infections in humans.

Jamestown Canyon virus (JCV) is a mosquitoborne orthobunyavirus in the California serogroup that circulates throughout Canada and the United States. Most JCV exposures result in asymptomatic infection or a mild febrile illness, but JCV can also cause neurologic diseases, such as meningitis and encephalitis. We describe a case series of confirmed JCV-mediated neuroinvasive disease among persons from the provinces of British Columbia, Alberta, Quebec, and Nova Scotia, Canada, during 2011–2016. We highlight the case definitions, epidemiology, unique features and clinical manifestations, disease seasonality, and outcomes for those cases. Two of the patients (from Quebec and Nova Scotia) might have acquired JCV infections during travel to the northeastern region of the United States. This case series collectively demonstrates JCV’s wide distribution and indicates the need for increased awareness of JCV as the underlying cause of meningitis/meningoencephalitis during mosquito season.

We analyzed hospital discharge records of patients with coccidioidomycosis-related codes from the International Classification of Diseases, 10th revision, Clinical Modification, to estimate the prevalence of hospital visits associated with the disease in Texas, USA. Using Texas Health Care Information Collection data for 2016–2021, we investigated the demographic characteristics and geographic distribution of the affected population, assessed prevalence of hospital visits for coccidioidomycosis, and examined how prevalence varied by demographic and geographic factors. In Texas, 709 coccidioidomycosis-related inpatient and outpatient hospital visits occurred in 2021; prevalence was 3.17 cases per 100,000 total hospital visits in 2020. Geographic location, patient sex, and race/ethnicity were associated with increases in coccidioidomycosis-related hospital visits; male, non-Hispanic Black, and Hispanic patients had the highest prevalence of coccidioidomycosis compared with other groups. Increased surveillance and healthcare provider education and outreach are needed to ensure timely and accurate diagnosis and treatment of coccidioidomycosis in Texas and elsewhere.

High incidences of congenital syphilis have been reported in areas along the Pacific coast of Colombia. In this retrospective study, conducted during 2018–2022 at a public hospital in Buenaventura, Colombia, we analyzed data from 3,378 pregnant women. The opportunity to prevent congenital syphilis was missed in 53.1% of mothers because of the lack of syphilis screening. Characteristics of higher maternal social vulnerability and late access to prenatal care decreased the probability of having > 1 syphilis screening test, thereby increasing the probability of having newborns with congenital syphilis. In addition, the opportunity to prevent congenital syphilis was missed in 41.5% of patients with syphilis because of the lack of treatment, which also increased the probability of having newborns with congenital syphilis. We demonstrate the urgent need to improve screening and treatment capabilities for maternal syphilis, particularly among pregnant women who are more socially vulnerable.

Understanding SARS-CoV-2 infection in populations at increased risk for poor health is critical to reducing disease. We describe the epidemiology of SARS-CoV-2 infection in Kakuma Refugee Camp Complex, Kenya. We performed descriptive analyses of SARS-CoV-2 infection in the camp and surrounding community during March 16, 2020‒December 31, 2021. We identified cases in accordance with national guidelines.We estimated fatality ratios and attack rates over time using locally weighted scatterplot smoothing for refugees, host community members, and national population. Of the 18,864 SARS-CoV-2 tests performed, 1,024 were positive, collected from 664 refugees and 360 host community members. Attack rates were 325.0/100,000 population (CFR 2.9%) for refugees,150.2/100,000 population (CFR 1.11%) for community, and 628.8/100,000 population (CFR 1.83%) nationwide. During 2020–2021, refugees experienced a lower attack rate but higher CFR than the national population, underscoring the need to prioritize SARS-CoV-2 mitigation measures, including vaccination.

Considering patient room shortages and prevalence of other communicable diseases, reassessing the isolation of patients with Clostridioides difficile infection (CDI) is imperative. We conducted a retrospective study to investigate the secondary CDI transmission rate in a hospital in South Korea, where patients with CDI were not isolated. Using data from a real-time locating system and electronic medical records, we investigated patients who had both direct and indirect contact with CDI index patients. The primary outcome was secondary CDI transmission, identified by whole-genome sequencing. Among 909 direct and 2,711 indirect contact cases, 2 instances of secondary transmission were observed (2 [0.05%] of 3,620 cases), 1 transmission via direct contact and 1 via environmental sources. A low level of direct contact (113 minutes) was required for secondary CDI transmission. Our findings support the adoption of exhaustive standard preventive measures, including environmental decontamination, rather than contact isolation of CDI patients in nonoutbreak settings.

During the 2022 multicountry mpox outbreak, the United Kingdom identified cases beginning in May. UK cases increased in June, peaked in July, then rapidly declined after September 2022. Public health responses included community-supported messaging and targeted mpox vaccination among eligible gay, bisexual, and other men who have sex with men (GBMSM). Using data from an online survey of GBMSM during November–December 2022, we examined self-reported mpox diagnoses, behavioral risk modification, and mpox vaccination offer and uptake. Among 1,333 participants, only 35 (2.6%) ever tested mpox-positive, but 707 (53%) reported behavior modification to avoid mpox. Among vaccine-eligible GBMSM, uptake was 69% (95% CI 65%–72%; 601/875) and was 92% (95% CI 89%–94%; 601/655) among those offered vaccine. GBMSM self-identifying as bisexual, reporting lower educational qualifications, or identifying as unemployed were less likely to be vaccinated. Equitable offer and provision of mpox vaccine are needed to minimize the risk for future outbreaks and mpox-related health inequalities.

We investigated clinically suspected measles cases that had discrepant real-time reverse transcription PCR (rRT-PCR) and measles-specific IgM test results to determine diagnoses. We performed rRT-PCR and measles-specific IgM testing on samples from 541 suspected measles cases. Of the 24 IgM-positive and rRT-PCR­–negative cases, 20 were among children who received a measles-containing vaccine within the previous 6 months; most had low IgG relative avidity indexes (RAIs). The other 4 cases were among adults who had an unknown previous measles history, unknown vaccination status, and high RAIs. We detected viral nucleic acid for viruses other than measles in 15 (62.5%) of the 24 cases with discrepant rRT-PCR and IgM test results. Measles vaccination, measles history, and contact history should be considered in suspected measles cases with discrepant rRT-PCR and IgM test results. If in doubt, measles IgG avidity and PCR testing for other febrile exanthematous viruses can help confirm or refute the diagnosis.

To determine the kinetics of hepatitis E virus (HEV) in asymptomatic persons and to evaluate viral load doubling time and half-life, we retrospectively tested samples retained from 32 HEV RNA-positive asymptomatic blood donors in Germany. Close-meshed monitoring of viral load and seroconversion in intervals of ≈4 days provided more information about the kinetics of asymptomatic HEV infections. We determined that a typical median infection began with PCR-detectable viremia at 36 days and a maximum viral load of 2.0 × 10 4 IU/mL. Viremia doubled in 2.4 days and had a half-life of 1.6 days. HEV IgM started to rise on about day 33 and peaked on day 36; IgG started to rise on about day 32 and peaked on day 53 . Although HEV IgG titers remained stable, IgM titers became undetectable in 40% of donors. Knowledge of the dynamics of HEV viremia is useful for assessing the risk for transfusion-transmitted hepatitis E.

We evaluated Q fever prevalence in blood donors and assessed the epidemiologic features of the disease in Israel in 2021. We tested serum samples for Coxeilla burnetii phase I and II IgG using immunofluorescent assay, defining a result of > 200 as seropositive. We compared geographic and demographic data. We included 1,473 participants; 188 (12.7%) were seropositive. The calculated sex- and age-adjusted national seroprevalence was 13.9% (95% CI 12.2%–15.7%). Male sex and age were independently associated with seropositivity (odds ratio [OR] 1.6, 95% CI 1.1–2.2; p = 0.005 for male sex; OR 1.2, 95% CI 1.01–1.03; p<0.001 for age). Residence in the coastal plain was independently associated with seropositivity for Q fever (OR 1.6, 95% CI 1.2–2.3; p<0.001); residence in rural and farming regions was not. Q fever is highly prevalent in Israel. The unexpected spatial distribution in the nonrural coastal plain suggests an unrecognized mode of transmission.

During December 11, 2020–March 29, 2022, the US government delivered ≈700 million doses of COVID-19 vaccine to vaccination sites, resulting in vaccination of ≈75% of US adults during that period. We evaluated accessibility of vaccination sites. Sites were accessible by walking within 15 minutes by 46.6% of persons, 30 minutes by 74.8%, 45 minutes by 82.8%, and 60 minutes by 86.7%. When limited to populations in counties with high social vulnerability, accessibility by walking was 55.3%, 81.1%, 86.7%, and 89.4%, respectively. By driving, lowest accessibility was 96.5% at 15 minutes. For urban/rural categories, the 15-minute walking accessibility between noncore and large central metropolitan areas ranged from 27.2% to 65.1%; driving accessibility was 79.9% to 99.5%. By 30 minutes driving accessibility for all urban/rural categories was >95.9%. Walking time variations across jurisdictions and between urban/rural areas indicate that potential gains could have been made by improving walkability or making transportation more readily available.

We estimated COVID-19 transmission potential and case burden by variant type in Alberta, British Columbia, and Ontario, Canada, during January 23, 2020–January 27, 2022; we also estimated the effectiveness of public health interventions to reduce transmission. We estimated time-varying reproduction number (R t ) over 7-day sliding windows and nonoverlapping time-windows determined by timing of policy changes. We calculated incidence rate ratios (IRRs) for each variant and compared rates to determine differences in burden among provinces. R t corresponding with emergence of the Delta variant increased in all 3 provinces; British Columbia had the largest increase, 43.85% (95% credible interval [CrI] 40.71%–46.84%). Across the study period, IRR was highest for Omicron (8.74 [95% CrI 8.71–8.77]) and burden highest in Alberta (IRR 1.80 [95% CrI 1.79–1.81]). Initiating public health interventions was associated with lower R t and relaxing restrictions and emergence of new variants associated with increases in R t .

We conducted a large surveillance study among members of an integrated healthcare delivery system in Pacific Northwest of the United States to estimate medical costs attributable to medically attended acute gastroenteritis (MAAGE) on the day care was sought and during 30-day follow-up. We used multivariable regression to compare costs of MAAGE and non-MAAGE cases matched on age, gender, and index time. Differences accounted for confounders, including race, ethnicity, and history of chronic underlying conditions. Analyses included 73,140 MAAGE episodes from adults and 18,617 from children who were Kaiser Permanente Northwest members during 2014–2016. Total costs were higher for MAAGE cases relative to non-MAAGE comparators as were costs on the day care was sought and costs during follow-up. Costs of MAAGE are substantial relative to the cost of usual-care medical services, and much of the burden accrues during short-term follow-up.

We investigated links between antimicrobial resistance in community-onset bacteremia and 1-year bacteremia recurrence by using the clinical data warehouse of Europe’s largest university hospital group in France. We included adult patients hospitalized with an incident community-onset Staphylococcus aureus , Escherichia coli , or Klebsiella spp. bacteremia during 2017–2019. We assessed risk factors of 1-year recurrence using Fine–Gray regression models. Of the 3,617 patients included, 291 (8.0%) had > 1 recurrence episode. Third-generation cephalosporin (3GC)-resistance was significantly associated with increased recurrence risk after incident Klebsiella spp. (hazard ratio 3.91 [95% CI 2.32–6.59]) or E. coli (hazard ratio 2.35 [95% CI 1.50–3.68]) bacteremia. Methicillin resistance in S. aureus bacteremia had no effect on recurrence risk. Although several underlying conditions and infection sources increased recurrence risk, 3GC-resistant Klebsiella spp. was associated with the greatest increase. These results demonstrate a new facet to illness induced by 3GC-resistant Klebsiella spp. and E. coli in the community setting.

We conducted a cross-sectional study in wild boar and extensively managed Iberian pig populations in a hotspot area of Crimean-Congo hemorrhagic fever virus (CCHFV) in Spain. We tested for antibodies against CCHFV by using 2 ELISAs in parallel. We assessed the presence of CCHFV RNA by means of reverse transcription quantitative PCR protocol, which detects all genotypes. A total of 113 (21.8%) of 518 suids sampled showed antibodies against CCHFV by ELISA. By species, 106 (39.7%) of 267 wild boars and 7 (2.8%) of 251 Iberian pigs analyzed were seropositive. Of the 231 Iberian pigs and 231 wild boars analyzed, none tested positive for CCHFV RNA. These findings indicate high CCHFV exposure in wild boar populations in endemic areas and confirm the susceptibility of extensively reared pigs to CCHFV, even though they may only play a limited role in the enzootic cycle.

African swine fever virus (ASFV) genotype II is endemic to Vietnam. We detected recombinant ASFV genotypes I and II (rASFV I/II) strains in domestic pigs from 6 northern provinces in Vietnam. The introduction of rASFV I/II strains could complicate ongoing ASFV control measures in the region.

In a representative sample of female children and adolescents in Germany, Toxoplasma gondii seroprevalence was 6.3% (95% CI 4.7%–8.0%). With each year of life, the chance of being seropositive increased by 1.2, indicating a strong force of infection. Social status and municipality size were found to be associated with seropositivity.

We describe the detection of Paranannizziopsis sp. fungus in a wild population of vipers in Europe. Fungal infections were severe, and 1 animal likely died from infection. Surveillance efforts are needed to better understand the threat of this pathogen to snake conservation.

We evaluated the in vitro effects of lyophilization for 2 vesicular stomatitis virus–based vaccines by using 3 stabilizing formulations and demonstrated protective immunity of lyophilized/reconstituted vaccine in guinea pigs. Lyophilization increased stability of the vaccines, but specific vesicular stomatitis virus–based vaccines will each require extensive analysis to optimize stabilizing formulations.

We report a cluster of serogroup B invasive meningococcal disease identified via genomic surveillance in older adults in England and describe the public health responses. Genomic surveillance is critical for supporting public health investigations and detecting the growing threat of serogroup B Neisseria meningitidis infections in older adults.

We detected Mayaro virus (MAYV) in 3.4% (28/822) of febrile patients tested during 2018–2021 from Roraima State, Brazil. We also isolated MAYV strains and confirmed that these cases were caused by genotype D. Improved surveillance is needed to better determine the burden of MAYV in the Amazon Region.

Across 133 confirmed mpox zoonotic index cases reported during 1970–2021 in Africa, cases occurred year-round near the equator, where climate is consistent. However, in tropical regions of the northern hemisphere under a dry/wet season cycle, cases occurred seasonally. Our findings further support the seasonality of mpox zoonotic transmission risk.

We investigated molecular evolution and spatiotemporal dynamics of atypical Legionella pneumophila serogroup 1 sequence type 1905 and determined its long-term persistence and linkage to human disease in dispersed locations, far beyond the large 2014 outbreak epicenter in Portugal. Our finding highlights the need for public health interventions to prevent further disease spread.

Norovirus is a major cause of acute gastroenteritis; GII.4 is the predominant strain in humans. Recently, 2 new GII.4 variants, Hong Kong 2019 and San Francisco 2017, were reported. Characterization using GII.4 monoclonal antibodies and serum demonstrated different antigenic profiles for the new variants compared with historical variants.

Cruise ships carrying COVID-19–vaccinated populations applied near-identical nonpharmaceutical measures during July–November 2021; passenger masking was not applied on 2 ships. Infection risk for masked passengers was 14.58 times lower than for unmasked passengers and 19.61 times lower than in the community. Unmasked passengers’ risk was slightly lower than community risk.

During a 2023 outbreak of Mycoplasma pneumoniae –associated community-acquired pneumonia among children in northern Vietnam, we analyzed M. pneumoniae isolated from nasopharyngeal samples. In almost half (6 of 13) of samples tested, we found known A2063G mutations (macrolide resistance) and a novel C2353T variant on the 23S rRNA gene.

We report the detection of Crimean-Congo hemorrhagic fever virus (CCHFV) in Corsica, France. We identified CCHFV African genotype I in ticks collected from cattle at 2 different sites in southeastern and central-western Corsica, indicating an established CCHFV circulation. Healthcare professionals and at-risk groups should be alerted to CCHFV circulation in Corsica.

In Latin America, rabies virus has persisted in a cycle between Desmodus rotundus vampire bats and cattle, potentially enhanced by deforestation. We modeled bovine rabies virus outbreaks in Costa Rica relative to land-use indicators and found spatial-temporal relationships among rabies virus outbreaks with deforestation as a predictor.

With the use of metagenomic next-generation sequencing, patients diagnosed with Whipple pneumonia are being increasingly correctly diagnosed. We report a series of 3 cases in China that showed a novel pattern of movable infiltrates and upper lung micronodules. After treatment, the 3 patients recovered, and lung infiltrates resolved.

Dogs are known to be susceptible to influenza A viruses, although information on influenza D virus (IDV) is limited. We investigated the seroprevalence of IDV in 426 dogs in the Apulia region of Italy during 2016 and 2023. A total of 14 samples were positive for IDV antibodies, suggesting exposure to IDV in dogs.

We report the detection of OXA-181 carbapenemase in an azithromycin-resistant Shigella spp. bacteria in an immunocompromised patient. The emergence of OXA-181 in Shigella spp. bacteria raises concerns about the global dissemination of carbapenem resistance in Enterobacterales and its implications for the treatment of infections caused by Shigella bacteria.

Although a vaccine against SARS-CoV-2 Omicron-XBB.1.5 variant is available worldwide and recent infection is protective, the lack of recorded infection data highlights the need to assess variant-specific antibody neutralization levels. We analyzed IgG levels against receptor-binding domain–specific SARS-CoV-2 ancestral strain as a correlate for high neutralizing titers against XBB variants.

We describe a feline sporotrichosis cluster and zoonotic transmission between one of the affected cats and a technician at a veterinary clinic in Kansas, USA. Increased awareness of sporotrichosis and the potential for zoonotic transmission could help veterinary professionals manage feline cases and take precautions to prevent human acquisition.

We report a clinical isolate of Burkholderia thailandensis 2022DZh obtained from a patient with an infected wound in southwest China. Genomic analysis indicates that this isolate clusters with B. thailandensis BPM, a human isolate from Chongqing, China. We recommend enhancing monitoring and surveillance for B. thailandensis infection in both humans and livestock.

To determine changes in Bordetella pertussis and B. parapertussis detection rates, we analyzed 1.43 million respiratory multiplex PCR test results from US facilities from 2019 through mid-2023. From mid-2022 through mid-2023, Bordetella spp. detection increased 8.5-fold; 95% of detections were B. parapertussis. While B. parapertussis rates increased, B. pertussis rates decreased.

We report a case of Sphingobium yanoikuyae bacteremia in an 89-year-old patient in Japan. No standard antimicrobial regimen has been established for S. yanoikuyae infections. However, ceftriaxone and ceftazidime treatments were effective in this case. Increased antimicrobial susceptibility data are needed to establish appropriate treatments for S. yanoikuyae .

Disclaimer: Early release articles are not considered as final versions. Any changes will be reflected in the online version in the month the article is officially released.

Volume 30, Number 6—June 2024

Perspective.

• Decolonization and Pathogen Reduction to Prevent Antimicrobial Resistance and Healthcare-Associated Infections M. R. Mangalea et al.
• Deciphering Unexpected Vascular Locations of Scedosporium spp. and Lomentospora prolificans Fungal Infections, France C. Vignals et al.
• An Electronic Health Record–Based Algorithm for Respiratory Virus–like Illness N. M. Cocoros et al.
• Severe Human Parainfluenza Virus Community- and Healthcare-Acquired Pneumonia in Adults at Tertiary Hospital in Seoul, South Korea, 2010–2019 J. H. Park et al.
• SARS-CoV-2 Disease Severity in Children during Pre-Delta, Delta, and Omicron Periods, Colorado L. Bankers et al.
• Effectiveness of 23-Valent Pneumococcal Polysaccharide Vaccine Against Invasive Pneumococcal Disease in Follow-Up Study, Denmark K. Nielsen et al.
• Chest Radiograph Screening for Detection of Subclinical Tuberculosis in Asymptomatic Household Contacts, Peru Q. Tan et al.
• Outbreak of Highly Pathogenic Avian Influenza Virus H5N1 in Seals in the St. Lawrence Estuary, Quebec, Canada S. Lair et al.
• Carbapenem-Resistant and Extended-Spectrum β-Lactamase–Producing Enterobacterales Cases among Children, United States, 2016–2020 H. N. Grome et al.
• Antibodies to H5N1 Influenza A Virus in Retrieving Hunting Dogs, Washington State, USA J. D. Brown et al.

We characterized the evolution and molecular characteristics of avian influenza A(H7N9) viruses isolated in China during 2021–2023. We systematically analyzed the 10-year evolution of the hemagglutinin gene to determine the evolutionary branch. Our results showed recent antigenic drift, providing crucial clues for updating the H7N9 vaccine and disease prevention and control.

• Burkholderia semiarida as Cause of Recurrent Pulmonary Infection in Immunocompetent Patient, China D. Kuang et al.
• SARS-CoV-2 in Captive Nonhuman Primates, Spain, 2020–2023 D. Cano-Terriza et al.
• Infection- and Vaccine-Induced SARS-CoV-2 Seroprevalence in Persons 0–101 Years of Age, Japan, 2023 R. Kinoshita et al.
• Zoonotic Ancylostoma ceylanicum Infection in Coyotes from the Guanacaste Conservation Area, Costa Rica, 2021 P. A. Zendejas-Heredia et al.
• Detection of Encephalitozoon cuniculi in Cerebrospinal Fluid from Immunocompetent Patients, Czech Republic B. Sak et al.
• Emergence of Group B Streptococcus Disease in Pigs and Porcupines, Italy C. Garbarino et al.
• Molecular Identification of Fonsecaea monophora , Novel Agent of Fungal Brain Abscess S. Gourav et al.

During May–July 2023, a cluster of 7 patients at local hospitals in Florida, USA, received a diagnosis of Plasmodium vivax malaria. Whole-genome sequencing of the organism from 4 patients and phylogenetic analysis with worldwide representative P. vivax genomes indicated probable single parasite introduction from Central/South America.

Because novel SARS-CoV-2 variants continue to emerge, immunogenicity of XBB.1.5 monovalent vaccines against live clinical isolates needs to be evaluated. We report boosting of IgG (2.1×), IgA (1.5×), and total IgG/A/M (1.7×) targeting the spike receptor-binding domain and neutralizing titers against WA1 (2.2×), XBB.1.5 (7.4×), EG.5.1 (10.5×), and JN.1 (4.7×) variants.

Using the GISAID EpiCoV database, we identified 256 COVID-19 patients in Japan during March 31–December 31, 2023, who had mutations in the SARS-CoV-2 nonstructural protein 5 conferring ensitrelvir resistance. Ongoing genomic surveillance is required to monitor emergence of SARS-CoV-2 mutations that are resistant to anticoronaviral drugs.

• Novel Avian Influenza A(H5N6) in Wild Birds, South Korea, 2023 A. Cho et al.

Volume 30, Number 7—July 2024

We report highly pathogenic avian influenza A(H5N1) virus in dairy cattle and cats in Kansas and Texas, United States, which reflects the continued spread of clade 2.3.4.4b viruses that entered the country in late 2021. Infected cattle experienced nonspecific illness, reduced feed intake and rumination, and an abrupt drop in milk production, but fatal systemic influenza infection developed in domestic cats fed raw (unpasteurized) colostrum and milk from affected cows. Cow-to-cow transmission appears to have occurred because infections were observed in cattle on Michigan, Idaho, and Ohio farms where avian influenza virus–infected cows were transported. Although the US Food and Drug Administration has indicated the commercial milk supply remains safe, the detection of influenza virus in unpasteurized bovine milk is a concern because of potential cross-species transmission. Continued surveillance of highly pathogenic avian influenza viruses in domestic production animals is needed to prevent cross-species and mammal-to-mammal transmission.

• Borrelia miyamotoi -associated Acute Meningoencephalitis, Minnesota, United States J. M. Kubiak et al.

Research Letter

• Pasteurella bettyae Infections in Men Who Have Sex With Men, France A. Li et al.

Medscape, LLC is pleased to provide online continuing medical education (CME) for selected journal articles, allowing clinicians the opportunity to earn CME credit. In support of improving patient care, these activities have been planned and implemented by Medscape, LLC and Emerging Infectious Diseases. Medscape, LLC is jointly accredited by the Accreditation Council for Continuing Medical Education (ACCME), the Accreditation Council for Pharmacy Education (ACPE), and the American Nurses Credentialing Center (ANCC), to provide continuing education for the healthcare team. CME credit is available for one year after publication.

Active CME Articles

During October 2021–June 2023, a total of 392 cases of acute hepatitis of unknown etiology in children in the United States were reported to Centers for Disease Control and Prevention as part of national surveillance. We describe demographic and clinical characteristics, including potential involvement of adenovirus in development of acute hepatitis, of 8 fatally ill children who met reporting criteria. The children had diverse courses of illness. Two children were immunocompromised when initially brought for care. Four children tested positive for adenovirus in multiple specimen types, including 2 for whom typing was completed. One adenovirus-positive child had no known underlying conditions, supporting a potential relationship between adenovirus and acute hepatitis in previously healthy children. Our findings emphasize the importance of continued investigation to determine the mechanism of liver injury and appropriate treatment. Testing for adenovirus in similar cases could elucidate the role of the virus.

In 2022, concurrent outbreaks of hepatitis A, invasive meningococcal disease (IMD), and mpox were identified in Florida, USA, primarily among men who have sex with men. The hepatitis A outbreak (153 cases) was associated with hepatitis A virus genotype IA. The IMD outbreak (44 cases) was associated with Neisseria meningitidis serogroup C, sequence type 11, clonal complex 11. The mpox outbreak in Florida (2,845 cases) was part of a global epidemic. The hepatitis A and IMD outbreaks were concentrated in Central Florida and peaked during March–­June, whereas mpox cases were more heavily concentrated in South Florida and had peak incidence in August. HIV infection was more common (52%) among mpox cases than among hepatitis A (21%) or IMD (34%) cases. Where feasible, vaccination against hepatitis A, meningococcal disease, and mpox should be encouraged among at-risk groups and offered along with program services that target those groups.

Disseminated leishmaniasis (DL) is an emergent severe disease manifesting with multiple lesions. To determine the relationship between immune response and clinical and therapeutic outcomes, we studied 101 DL and 101 cutaneous leishmaniasis (CL) cases and determined cytokines and chemokines in supernatants of mononuclear cells stimulated with leishmania antigen. Patients were treated with meglumine antimoniate (20 mg/kg) for 20 days (CL) or 30 days (DL); 19 DL patients were instead treated with amphotericin B, miltefosine, or miltefosine and meglumine antimoniate. High levels of chemokine ligand 9 were associated with more severe DL. The cure rate for meglumine antimoniate was low for both DL (44%) and CL (60%), but healing time was longer in DL (p = 0.003). The lowest cure rate (22%) was found in DL patients with >100 lesions. However, meglumine antimoniate/miltefosine treatment cured all DL patients who received it; therefore, that combination should be considered as first choice therapy.

Streptococcus suis , a zoonotic bacterial pathogen circulated through swine, can cause severe infections in humans. Because human S. suis infections are not notifiable in most countries, incidence is underestimated. We aimed to increase insight into the molecular epidemiology of human S. suis infections in Europe. To procure data, we surveyed 7 reference laboratories and performed a systematic review of the scientific literature. We identified 236 cases of human S. suis infection from those sources and an additional 87 by scanning gray literature. We performed whole-genome sequencing to type 46 zoonotic S. suis isolates and combined them with 28 publicly available genomes in a core-genome phylogeny. Clonal complex (CC) 1 isolates accounted for 87% of typed human infections; CC20, CC25, CC87, and CC94 also caused infections. Emergence of diverse zoonotic clades and notable severity of illness in humans support classifying S. suis infection as a notifiable condition.

During January–August 2021, the Community Prevalence of SARS-CoV-2 Study used time/location sampling to recruit a cross-sectional, population-based cohort to estimate SARS-CoV-2 seroprevalence and nasal swab sample PCR positivity across 15 US communities. Survey-weighted estimates of SARS-CoV-2 infection and vaccine willingness among participants at each site were compared within demographic groups by using linear regression models with inverse variance weighting. Among 22,284 persons > 2 months of age and older, median prevalence of infection (prior, active, or both) was 12.9% across sites and similar across age groups. Within each site, average prevalence of infection was 3 percentage points higher for Black than White persons and average vaccine willingness was 10 percentage points lower for Black than White persons and 7 percentage points lower for Black persons than for persons in other racial groups. The higher prevalence of SARS-CoV-2 infection among groups with lower vaccine willingness highlights the disparate effect of COVID-19 and its complications.

Invasive fusariosis can be life-threatening, especially in immunocompromised patients who require intensive care unit (ICU) admission. We conducted a multicenter retrospective study to describe clinical and biologic characteristics, patient outcomes, and factors associated with death and response to antifungal therapy. We identified 55 patients with invasive fusariosis from 16 ICUs in France during 2002­–­­2020. The mortality rate was high (56%). Fusariosis-related pneumonia occurred in 76% of patients, often leading to acute respiratory failure. Factors associated with death included elevated sequential organ failure assessment score at ICU admission or history of allogeneic hematopoietic stem cell transplantation or hematologic malignancies. Neither voriconazole treatment nor disseminated fusariosis were strongly associated with response to therapy. Invasive fusariosis can lead to multiorgan failure and is associated with high mortality rates in ICUs. Clinicians should closely monitor ICU patients with a history of hematologic malignancies or stem cell transplantation because of higher risk for death.

Using whole-genome sequencing, we characterized Escherichia coli strains causing early-onset sepsis (EOS) in 32 neonatal cases from a 2019–2021 prospective multicenter study in France and compared them to E. coli strains collected from vaginal swab specimens from women in third-trimester gestation. We observed no major differences in phylogenetic groups or virulence profiles between the 2 collections. However, sequence type (ST) analysis showed the presence of 6/32 (19%) ST1193 strains causing EOS, the same frequency as in the highly virulent clonal group ST95. Three ST1193 strains caused meningitis, and 3 harbored extended-spectrum β-lactamase. No ST1193 strains were isolated from vaginal swab specimens. Emerging ST1193 appears to be highly prevalent, virulent, and antimicrobial resistant in neonates. However, the physiopathology of EOS caused by ST1193 has not yet been elucidated. Clinicians should be aware of the possible presence of E. coli ST1193 in prenatal and neonatal contexts and provide appropriate monitoring and treatment.

We describe detection of the previously rarely reported gram-positive bacterium Auritidibacter ignavus in 3 cases of chronic ear infections in Germany. In all 3 cases, the patients had refractory otorrhea. Although their additional symptoms varied, all patients had an ear canal stenosis and A. ignavus detected in microbiologic swab specimens. A correct identification of A. ignavus in the clinical microbiology laboratory is hampered by the inability to identify it by using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. Also, the bacterium might easily be overlooked because of its morphologic similarity to bacterial species of the resident skin flora. We conclude that a high index of suspicion is warranted to identify A. ignavus and that it should be particularly considered in patients with chronic external otitis who do not respond clinically to quinolone ear drop therapy.

We reviewed invasive Nocardia infections in 3 noncontiguous geographic areas in the United States during 2011–2018. Among 268 patients with invasive nocardiosis, 48.2% were from Minnesota, 32.4% from Arizona, and 19.4% from Florida. Predominant species were N. nova complex in Minnesota (33.4%), N. cyriacigeorgica in Arizona (41.4%), and N. brasiliensis in Florida (17.3%). Transplant recipients accounted for 82/268 (30.6%) patients overall: 14 (10.9%) in Minnesota, 35 (40.2%) in Arizona, and 33 (63.5%) in Florida. Manifestations included isolated pulmonary nocardiosis among 73.2% of transplant and 84.4% of non–transplant patients and central nervous system involvement among 12.2% of transplant and 3.2% of non–transplant patients. N. farcinica (20.7%) and N. cyriacigeorgica (19.5%) were the most common isolates among transplant recipients and N. cyriacigeorgica (38.0%), N. nova complex (23.7%), and N. farcinica (16.1%) among non–transplant patients. Overall antimicrobial susceptibilities were similar across the 3 study sites.

We collected stool from school-age children from 352 households living in the Black Belt region of Alabama, USA, where sanitation infrastructure is lacking. We used quantitative reverse transcription PCR to measure key pathogens in stool that may be associated with water and sanitation, as an indicator of exposure. We detected genes associated with > 1 targets in 26% of specimens, most frequently Clostridioides difficile (6.6%), atypical enteropathogenic Escherichia coli (6.1%), and enteroaggregative E. coli (3.9%). We used generalized estimating equations to assess reported risk factors for detecting > 1 pathogen in stool. We found no association between lack of sanitation and pathogen detection (adjusted risk ratio 0.95 [95% CI 0.55–1.7]) compared with specimens from children served by sewerage. However, we did observe an increased risk for pathogen detection among children living in homes with well water (adjusted risk ratio 1.7 [95% CI 1.1–2.5]) over those reporting water utility service.

Campylobacter fetus accounts for 1% of Campylobacter spp. infections, but prevalence of bacteremia and risk for death are high. To determine clinical features of C. fetus infections and risks for death, we conducted a retrospective observational study of all adult inpatients with a confirmed C. fetus infection in Nord Franche-Comté Hospital, Trevenans, France, during January 2000–December 2021. Among 991 patients with isolated Campylobacter spp. strains, we identified 39 (4%) with culture-positive C. fetus infections, of which 33 had complete records and underwent further analysis; 21 had documented bacteremia and 12 did not. Secondary localizations were reported for 7 (33%) patients with C. fetus bacteremia, of which 5 exhibited a predilection for vascular infections (including 3 with mycotic aneurysm). Another 7 (33%) patients with C. fetus bacteremia died within 30 days. Significant risk factors associated with death within 30 days were dyspnea, quick sequential organ failure assessment score > 2 at admission, and septic shock.

Group A Streptococcus (GAS) primary peritonitis is a rare cause of pediatric acute abdomen (sudden onset of severe abdominal pain); only 26 pediatric cases have been reported in the English language literature since 1980. We discuss 20 additional cases of pediatric primary peritonitis caused by GAS among patients at Starship Children’s Hospital, Auckland, New Zealand, during 2010–2022. We compare identified cases of GAS primary peritonitis to cases described in the existing pediatric literature. As rates of rates of invasive GAS increase globally, clinicians should be aware of this cause of unexplained pediatric acute abdomen.

In Mississippi, USA, infant hospitalization with congenital syphilis (CS) spiked by 1,000%, from 10 in 2016 to 110 in 2022. To determine the causes of this alarming development, we analyzed Mississippi hospital discharge data to evaluate trends, demographics, outcomes, and risk factors for infants diagnosed with CS hospitalized during 2016–2022. Of the 367 infants hospitalized with a CS diagnosis, 97.6% were newborn, 92.6% were covered by Medicaid, 71.1% were African American, and 58.0% were nonurban residents. Newborns with CS had higher odds of being affected by maternal illicit drug use, being born prematurely (<37 weeks), and having very low birthweight (<1,500 g) than those without CS. Mean length of hospital stay (14.5 days vs. 3.8 days) and mean charges ($56,802 vs. $13,945) were also higher for infants with CS than for those without. To address escalation of CS, Mississippi should invest in comprehensive prenatal care and early treatment of vulnerable populations.

Ongoing surveillance after pneumococcal conjugate vaccination (PCV) deployment is essential to inform policy decisions and monitor serotype replacement. We report serotype and disease severity trends in 3,719 adults hospitalized for pneumococcal disease in Bristol and Bath, United Kingdom, during 2006–2022. Of those cases, 1,686 were invasive pneumococcal disease (IPD); 1,501 (89.0%) had a known serotype. IPD decreased during the early COVID-19 pandemic but during 2022 gradually returned to prepandemic levels. Disease severity changed throughout this period: CURB65 severity scores and inpatient deaths decreased and ICU admissions increased. PCV7 and PCV13 serotype IPD decreased from 2006–2009 to 2021–2022. However, residual PCV13 serotype IPD remained, representing 21.7% of 2021–2022 cases, indicating that major adult PCV serotype disease still occurs despite 17 years of pediatric PCV use. Percentages of serotype 3 and 8 IPD increased, and 19F and 19A reemerged. In 2020–2022, a total of 68.2% IPD cases were potentially covered by PCV20.

Borrelia miyamotoi , transmitted by Ixodes spp. ticks, was recognized as an agent of hard tick relapsing fever in the United States in 2013. Nine state health departments in the Northeast and Midwest have conducted public health surveillance for this emerging condition by using a shared, working surveillance case definition. During 2013–2019, a total of 300 cases were identified through surveillance; 166 (55%) were classified as confirmed and 134 (45%) as possible. Median age of case-patients was 52 years (range 1–86 years); 52% were male. Most cases (70%) occurred during June–September, with a peak in August. Fever and headache were common symptoms; 28% of case-patients reported recurring fevers, 55% had arthralgia, and 16% had a rash. Thirteen percent of patients were hospitalized, and no deaths were reported. Ongoing surveillance will improve understanding of the incidence and clinical severity of this emerging disease.

During 2006–2021, Canada had 55 laboratory-confirmed outbreaks of foodborne botulism, involving 67 cases. The mean annual incidence was 0.01 case/100,000 population. Foodborne botulism in Indigenous communities accounted for 46% of all cases, which is down from 85% of all cases during 1990–2005. Among all cases, 52% were caused by botulinum neurotoxin type E, but types A (24%), B (16%), F (3%), and AB (1%) also occurred; 3% were caused by undetermined serotypes. Four outbreaks resulted from commercial products, including a 2006 international outbreak caused by carrot juice. Hospital data indicated that 78% of patients were transferred to special care units and 70% required mechanical ventilation; 7 deaths were reported. Botulinum neurotoxin type A was associated with much longer hospital stays and more time spent in special care than types B or E. Foodborne botulism often is misdiagnosed. Increased clinician awareness can improve diagnosis, which can aid epidemiologic investigations and patient treatment.

Corynebacterium ulcerans is a closely related bacterium to the diphtheria bacterium C. diphtheriae , and some C. ulcerans strains produce toxins that are similar to diphtheria toxin. C. ulcerans is widely distributed in the environment and is considered one of the most harmful pathogens to livestock and wildlife. Infection with C. ulcerans can cause respiratory or nonrespiratory symptoms in patients. Recently, the microorganism has been increasingly recognized as an emerging zoonotic agent of diphtheria-like illness in Japan. To clarify the overall clinical characteristics, treatment-related factors, and outcomes of C. ulcerans infection, we analyzed 34 cases of C. ulcerans that occurred in Japan during 2001–2020. During 2010–2020, the incidence rate of C. ulcerans infection increased markedly, and the overall mortality rate was 5.9%. It is recommended that adults be vaccinated with diphtheria toxoid vaccine to prevent the spread of this infection.

Mycolicibacterium neoaurum is a rapidly growing mycobacterium and an emerging cause of human infections. M. neoaurum infections are uncommon but likely underreported, and our understanding of the disease spectrum and optimum management is incomplete. We summarize demographic and clinical characteristics of a case of catheter-related M. neoaurum bacteremia in a child with leukemia and those of 36 previously reported episodes of M. neoaurum infection. Most infections occurred in young to middle-aged adults with serious underlying medical conditions and commonly involved medical devices. Overall, infections were not associated with severe illness or death. In contrast to other mycobacteria species, M. neoaurum was generally susceptible to multiple antimicrobial drugs and responded promptly to treatment, and infections were associated with good outcomes after relatively short therapy duration and device removal. Delays in identification and susceptibility testing were common. We recommend using combination antimicrobial drug therapy and removal of infected devices to eradicate infection.

We retrospectively reviewed consecutive cases of mucormycosis reported from a tertiary-care center in India to determine the clinical and mycologic characteristics of emerging Rhizopus homothallicus fungus. The objectives were ascertaining the proportion of R. homothallicus infection and the 30-day mortality rate in rhino-orbital mucormycosis attributable to R. homothallicus compared with R. arrhizus. R. homothallicus accounted for 43 (6.8%) of the 631 cases of mucormycosis. R. homothallicus infection was independently associated with better survival (odds ratio [OR] 0.08 [95% CI 0.02–0.36]; p = 0.001) than for R. arrhizus infection (4/41 [9.8%] vs. 104/266 [39.1%]) after adjusting for age, intracranial involvement, and surgery. We also performed antifungal-susceptibility testing, which indicated a low range of MICs for R. homothallicus against the commonly used antifungals (amphotericin B [0.03–16], itraconazole [0.03–16], posaconazole [0.03–8], and isavuconazole [0.03–16]). 18S gene sequencing and amplified length polymorphism analysis revealed distinct clustering of R. homothallicus .

Zoonotic outbreaks of sporotrichosis are increasing in Brazil. We examined and described the emergence of cat-transmitted sporotrichosis (CTS) caused by the fungal pathogen Sporothrix brasiliensis . We calculated incidence and mapped geographic distribution of cases in Curitiba, Brazil, by reviewing medical records from 216 sporotrichosis cases diagnosed during 2011–May 2022. Proven sporotrichosis was established in 84 (39%) patients and probable sporotrichosis in 132 (61%). Incidence increased from 0.3 cases/100,000 outpatient visit-years in 2011 to 21.4 cases/100,000 outpatient visit-years in 2021; of the 216 cases, 58% (n = 126) were diagnosed during 2019–2021. The main clinical form of sporotrichosis was lymphocutaneous (63%), followed by localized cutaneous (24%), ocular (10%), multisite infections (3%), and cutaneous disseminated (<0.5%). Since the first report of CTS in Curitiba in 2011, sporotrichosis has increased substantially, indicating continuous disease transmission. Clinician and public awareness of CTS and efforts to prevent transmission are needed.

Babesiosis is a globally distributed parasitic infection caused by intraerythrocytic protozoa. The full spectrum of neurologic symptoms, the underlying neuropathophysiology, and neurologic risk factors are poorly understood. Our study sought to describe the type and frequency of neurologic complications of babesiosis in a group of hospitalized patients and assess risk factors that might predispose patients to neurologic complications. We reviewed medical records of adult patients who were admitted to Yale-New Haven Hospital, New Haven, Connecticut, USA, during January 2011–October 2021 with laboratory-confirmed babesiosis. More than half of the 163 patients experienced > 1 neurologic symptoms during their hospital admissions. The most frequent symptoms were headache, confusion/delirium, and impaired consciousness. Neurologic symptoms were associated with high-grade parasitemia, renal failure, and history of diabetes mellitus. Clinicians working in endemic areas should recognize the range of symptoms associated with babesiosis, including neurologic.

Tularemia is a zoonotic infection caused by Francisella tularensis . Its most typical manifestations in humans are ulceroglandular and glandular; infections in prosthetic joints are rare. We report 3 cases of F. tularensis subspecies holarctica –related prosthetic joint infection that occurred in France during 2016–2019. We also reviewed relevant literature and found only 5 other cases of Francisella -related prosthetic joint infections worldwide, which we summarized. Among those 8 patients, clinical symptoms appeared 7 days to 19 years after the joint placement and were nonspecific to tularemia. Although positive cultures are typically obtained in only 10% of tularemia cases, strains grew in all 8 of the patients. F. tularensis was initially identified in 2 patients by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry; molecular methods were used for 6 patients. Surgical treatment in conjunction with long-term antimicrobial treatment resulted in favorable outcomes; no relapses were seen after 6 months of follow-up.

Search for articles with a simple interface. Powered by PubMed.

Search for articles by multiple keywords or authors. Results are searchable and sortable. Powered by PubMed.

Find articles by topic country with the article map. Results are searchable and sortable.

Find articles on specific topics such as Ebola, Zika, and Influenza.

Browse articles by type, such as research, letters, or dispatches.

You can find all of EID’s contents on PubMed Central.

What's New

Highly Pathogenic Avian Influenza A(H5N1) Virus Clade 2.3.4.4b Infections in Wild Terrestrial Mammals, United States, 2022 — (Length: 30:05)

Length: 30:05

To receive email updates about this page, enter your email address:

• audio icon   EID Podcasts
• twitter icon   EID on Twitter
• linkedin icon   EID on LinkedIn
• insta icon   EID on Instagram
• fb icon   EID on Facebook

• rss icon   Subscribe to RSS Feeds
• book icon   PubMed Central external icon
• Morbidity and Mortality Weekly Report (MMWR)
• Preventing Chronic Disease Journal
• Public Health Image Library (PHIL)
• Science Briefs
• Vital Signs

Exit Notification / Disclaimer Policy

• The Centers for Disease Control and Prevention (CDC) cannot attest to the accuracy of a non-federal website.
• Linking to a non-federal website does not constitute an endorsement by CDC or any of its employees of the sponsors or the information and products presented on the website.
• You will be subject to the destination website's privacy policy when you follow the link.
• CDC is not responsible for Section 508 compliance (accessibility) on other federal or private website.

Article Quick Search

• Open access
• Published: 23 April 2024

Obstructive sleep apnea and mental disorders: a bidirectional mendelian randomization study

• Heming Liu 1 ,
• Xuemei Wang 1 ,
• Hu Feng 1 ,
• Shengze Zhou 1 ,
• Jinhua Pan 1 ,
• Changping Ouyang 1 &
• Xiaobin Hu 1  

BMC Psychiatry volume  24 , Article number:  304 ( 2024 ) Cite this article

192 Accesses

2 Altmetric

Metrics details

Previous studies have reported associations between obstructive sleep apnea (OSA) and several mental disorders. However, further research is required to determine whether these associations are causal. Therefore, we evaluated the bidirectional causality between the genetic liability for OSA and nine mental disorders by using Mendelian randomization (MR).

We performed two-sample bidirectional MR of genetic variants for OSA and nine mental disorders. Summary statistics on OSA and the nine mental disorders were extracted from the FinnGen study and the Psychiatric Genomics Consortium. The primary analytical approach for estimating causal effects was the inverse-variance weighted (IVW), with the weighted median and MR Egger as complementary methods. The MR Egger intercept test, Cochran’s Q test, Rucker’s Q test, and the MR pleiotropy residual sum and outlier (MR-PRESSO) test were used for sensitivity analyses.

MR analyses showed that genetic liability for major depressive disorder (MDD) was associated with an increased risk of OSA (odds ratio [OR] per unit increase in the risk of MDD, 1.29; 95% CI, 1.11–1.49; P  < 0.001). In addition, genetic liability for OSA may be associated with an increased risk of attention-deficit/hyperactivity disorder (ADHD) (OR = 1.26; 95% CI, 1.02–1.56; p  = 0.032). There was no evidence that OSA is associated with other mental disorders.

Our study indicated that genetic liability for MDD is associated with an increased risk of OSA without a bidirectional relationship. Additionally, there was suggestive evidence that genetic liability for OSA may have a causal effect on ADHD. These findings have implications for prevention and intervention strategies targeting OSA and ADHD. Further research is needed to investigate the biological mechanisms underlying our findings and the relationship between OSA and other mental disorders.

Peer Review reports

Mental disorders are a significant global health concern and rank among the top 10 causes of burden worldwide. According to estimates, the number of mental disorder cases increased by 48.1% in 2019 compared to 1990, and the proportion of global disability-adjusted life years (DALYs) attributable to mental disorders increased from 2.3–9.4% [ 1 ]. However, the etiology of mental disorders remains unclear, and there is evidence to suggest that Obstructive sleep apnea (OSA) may be associated with a variety of mental disorders [ 2 ]. OSA is a condition caused by repeated episodes of upper airway collapse and obstruction during sleep associated with arousal from sleep with or without oxygen desaturation [ 3 ]. In the general population, the prevalence of OSA is approximately 3–7% in males and 2–5% in females [ 4 ]. Both mental disorders and OSA can significantly impact patients’ quality of life. It is crucial to establish a clear causal relationship between these conditions to inform effective prevention and treatment strategies.

In recent years, an increasing number of researches have been devoted to exploring the relationship between OSA and various mental disorders. Two cohort studies suggested that bipolar disorder (BD) and schizophrenia (SCZ) were associated with increased risks of OSA [ 5 , 6 ]. A Japanese study has also found that preschoolers with autism spectrum disorder (ASD) are more likely to have obstructive sleep apnea than the general population [ 7 ]. Moreover, there is evidence of a potential bidirectional relationship between OSA and attention deficit hyperactivity disorder (ADHD), anxiety disorder (ANX), major depressive disorder (MDD), and Post-Traumatic Stress Disorder (PTSD) [ 8 , 9 , 10 , 11 ]. However, the ability of these studies to establish causality is insufficient, and even prospective observational studies may be subject to inherent confounding or selection bias. Currently, there are limited studies on this topic, and it remains unclear whether OSA is the cause or a downstream effect of mental disorders. Therefore, any potential causal relationship still requires further research.

In this case, the genetic epidemiological method of Mendelian randomization (MR) is a powerful tool to evaluate the causal relationship between OSA and mental disorders. MR uses single nucleotide polymorphisms (SNPs) as instrumental variables to estimate their effect on the outcome of interest, minimizing bias affecting observational epidemiological studies [ 12 , 13 , 14 ] and thus enhancing causal inference of exposure and outcome. Due to the random allocation of genetic variation during meiosis and the natural causal effect of genetic variation on phenotype, SNPs are independent of potential confounders, and therefore confounders and reverse causality bias can be minimized [ 15 ]. Two-sample MR refers to MR analysis using two independent samples from different studies or databases, which are typically collected from publicly available large-scale genome-wide association studies (GWAS), and has the advantage of increased statistical power [ 16 ]. Therefore, we conducted a two-sample bidirectional MR analysis using the latest GWAS to investigate the potential association between OSA and mental disorders.

Study design

A two-sample bidirectional MR was used to evaluate the potential causal association between obstructive sleep apnoea and nine mental disorders (Fig.  1 ). The MR design is based on three fundamental assumptions three basic assumptions: (1) genetic variants must be highly correlated with exposure; (2) genetic variants cannot be associated with any potential confounders; (3) genetic variants influence outcome solely through the exposure [ 15 ]. This study used summary-level data from publicly available GWAS. Ethical approval was obtained for all original studies.

Workflow of a two-sample bidirectional MR study on obstructive sleep apnea and mental disorders.

Data source

Obstructive sleep apnea

Summary statistics for OSA were obtained from the FinnGen database with 375,657 individuals of European ancestry. FinnGen is a large public-private partnership aimed at collecting and analyzing genomic and health data from 500,000 Finnish biobank participants [ 17 ]. The GWAS included 38,998 OSA cases and 336,659 controls. Diagnostic criteria for OSA cases were based on ICD codes (ICD-10: G47.3; ICD-9: 3472), derived from the Finnish National Hospital Discharge Registry and the Causes of Death Registry. More details on the OSA GWAS can be found at https://r9.risteys.finngen.fi/endpoints/G6_SLEEPAPNO/ and https://finngen.gitbook.io/documentation/methods/phewas/ .

• Mental disorders

We used summary statistics for 9 mental disorders from different studies [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 ], which were obtained from the Psychiatric Genomics Consortium (PGC). The mental disorders included in this study are ADHD, AN, ANX, autism spectrum disorder (ASD), BD, MDD, obsessive-compulsive disorder (OCD), PTSD, and SCZ. For consistency with the OSA data, genetic data of European ancestry were used for all nine mental disorders to avoid heterogeneity. Sample sizes for each GWAS study are listed below: ADHD(38,691 cases and 186,843 controls), AN(16,992 cases and 55,525 controls), ANX(7,016 cases and 14,745 controls), ASD(18,381 cases and 27,969 controls), BD(41,917 cases and 371,549 controls), MDD(246,363 cases and 561,190 controls), OCD(2,688 cases and 7,037 controls), PTSD(23,212 cases and 151,447 controls), SCZ(53,386 cases and 77,258 controls). A detailed description of the data sources can be found in Additional file 1 .

Selection of instrument variables

The number of instrumental variables (IVs) determines statistical power and the presence of confounding factors, so the appropriate number of IVs is needed. We used four different p -value thresholds, p  < 5 × 10 − 6 (ANX, ASD, OCD, PTSD), p  < 5 × 10 − 7 (AN), p  < 5 × 10 − 8 (ADHD, BD, MDD, OSA), and p  < 5 × 10 − 12 (SCZ), and without linkage disequilibrium (10,000 kilobase pairs apart and r 2  < 0.001) to select SNPs as instrumental variables. The linkage disequilibrium (LD) reference was obtained from http://fileserve.mrcieu.ac.uk/ld/1kg.v3.tgz . After clumped SNPs for independence, PhenoScanner [ 27 , 28 ] was used to assess previous associations with potential confounding traits. PhenoScanner is a curated database holding publicly available results from large-scale genome-wide association studies. To meet the assumptions of the MR design, we excluded SNPs that were strongly associated with other traits or diseases ( p  < 5 × 10 − 8 ) to rule out possible pleiotropic effects. To evaluate the weak instrument bias, we calculated the instrument strength (F-statistic) for each IV according to the following formula: \( F= \frac{{beta}^{2}}{{se}^{2}}\) (beta: the effect size of SNP on exposure; se: its corresponding standard error) [ 29 ]. We removed SNPs associated with exposure if they could not be matched to SNPs in the outcome. Details of the SNPs that were selected as IVs are shown in Additional files 2 and 3 .

Statistical analysis

In MR analysis, the inverse-variance weighted (IVW) model is the main method for assessing the bidirectional relationship between exposure and outcome. However, if there is horizontal pleiotropy and invalid instrument bias, IVW cannot provide unbiased estimates of causal effects [ 30 , 31 ]. Therefore, we use two different MR methods that are relatively robust to horizontal pleiotropy, although at the cost of reduced statistical power [ 32 ]. First, causal effects are estimated using the weighted median method, in which only 50% of the SNPs need to be valid instruments [ 33 ]. Second, MR Egger estimates causal effects by setting an intercept that allows horizontal pleiotropy to be unbalanced or directed [ 31 , 34 ]. In addition, we used several sensitivity analyses including the MR Egger intercept test, Cochran’s Q test, Rucker’s Q test and the MR pleiotropy residual sum and outlier (MR-PRESSO) test to determine the validity and robustness of the results. The MR Egger regression provides a test for directional pleiotropy through its intercept [ 35 ]. The Cochran’s Q test and Rucker’s Q test were performed to assess the heterogeneity, and if heterogeneity was present, outlier SNPs were excluded by observing the funnel plot or sorting RSSobs in MR-PRESSO and the MR analysis was repeated [ 36 ]. MR-PRESSO was used to detect pleiotropic bias, identify outliers, and obtain the corrected results by removing outliers [ 37 ].

Associations between genetic liability for OSA and risk of mental disorders were expressed as odds ratios (ORs) and their 95% confidence intervals (CIs). We indexed the strength of evidence against the no association by the exact p -value. A p -value less than 0.0056 (0.05/9) was considered to be statistically significant evidence for a causal association. A p -value below 0.05, but above the Bonferroni-corrected threshold, was considered suggestive evidence for a potential causal association. We used an online tool called mRnd ( https://shiny.cnsgenomics.com/mRnd/ ) to calculate the statistical power of the MR analysis [ 38 ]. All statistical analyses were performed using R (version 4.3.1) with the packages “TwoSampleMr”, “MR-PRESSO” and “ieugwasr”.

Genetically predicted obstructive sleep apnea on mental disorders

The associations of OSA with 9 mental disorders are demonstrated in Fig.  2 . We observed only a weak association between genetic liability for OSA and increased risk of ADHD (IVW, OR = 1.26; 95% CI, 1.02–1.56; p  = 0.032), and there was no evidence that other mental disorders were associated with OSA. The results of the estimation using the weighted median and MR Egger methods, as well as information on statistical power, Q P -value and P intercept -value, are presented in Additional file 4 . The F-statistic of each IV we selected for OSA was greater than 10, indicating a low probability of weak instrument bias [ 39 ]. The MR-Egger intercept analysis did not indicate horizontal pleiotropy. The Rucker’s Q test revealed possible heterogeneity of individual SNPs between the effect estimates of OSA and SCZ (Rucker’s Q = 13.964, Q p -value = 0.030). Therefore, we excluded one outlier SNP (rs59333125) and performed a second MR analysis, which showed no heterogeneity (Rucker’s Q = 6.670, Q p -value = 0.246). For the SNPs we used, MR-PRESSO did not detect any potential outliers.

Associations between genetic liability for obstructive sleep apnea and risk of psychiatric disorders. For outcome phenotype SCZ, the result is shown after removing outliers due to heterogeneity.

Genetically predicted mental disorders on obstructive sleep apnea

The associations of 9 mental disorders with OSA are demonstrated in Fig.  3 . The genetic liability for MDD had an effect estimate consistent with an increased risk of OSA. However, Cochran’s Q test indicated the presence of heterogeneity (Cochran’s Q = 43.195, Q p -value = 0.009), we excluded two outlier SNPs (rs4141983, rs9529218) and performed a second MR analysis (IVW, OR = 1.37; 95%CI, 1.20–1.57; p  < 0.001), which did not show heterogeneity (Cochran’s Q = 29.474, Q p -value = 0.132). The results of the estimation using the weighted median and MR Egger methods, as well as information on statistical power, Q P -value and P intercept -value, are presented in Additional file 5 . The scatterplot, leave-one-out-sensitivity forest plot, and funnel plot of MR estimation results for MDD associated with OSA are provided in Additional file 6 . F-statistic greater than 10 for each IV for the 9 mental disorders, indicating a small magnitude of weak instrument bias. MR-Egger intercept analysis did not identify any pleiotropic SNPs. And Cochran’s Q test suggested potential heterogeneity in ADHD (Cochran’s Q = 28.816, Q p -value = 0.001, BD (Cochran’s Q = 38.784, Q p -value = 0.039), PTSD (Cochran’s Q = 22.605, Q p -value = 0.047) and SCZ (Cochran’s Q = 38.169, Q p -value = 0.012), so we excluded outlier SNPs for ADHD (rs7844069, rs2025286), BD (rs10994415), PTSD (rs1268149), and SCZ (rs145071536, rs16851048) and performed a second MR analysis, which showed no heterogeneity (Additional file 5 ). One outlier SNP in ASD (rs28729902) was excluded using the MR-PRESSO test. After correction for possible outliers, the causal effect estimates for ADHD, ASD, BD, PTSD and SCZ were still not statistically significant.

Associations between genetic liability for mental disorders and risk of obstructive sleep apnea. For exposure phenotype ASD, the result is shown after removing outliers with the MR-PRESSO test. For exposure phenotype ADHD, BD, MDD, PTSD and SCZ, the figure shows the results of the second MR analysis with outlier SNPs removed due to heterogeneity.

In our study, we performed a bidirectional MR analysis based on several large genetic populations to assess the association between genetic liability for OSA and the risk of mental disorders. Our results found possible genetic evidence that OSA was associated with an increased risk of ADHD. In the opposite direction, genetic liability for MDD was associated with an increased risk of OSA.

Our study provides suggestive evidence of a possible association between OSA and ADHD based on larger populations. Although few observational studies have conclusively confirmed the potential causal relationship between OSA and ADHD, there are still evidences that support our findings. A meta-analysis showed that children with Sleep-disordered breathing (SDB) are at increased risk of presenting with ADHD symptoms such as inattention and hyperactivity [ 40 ]. OSA is usually accompanied by decreased oxygen saturation and sleep disruption. These symptoms may affect brain development, which in turn affects cognitive function and leads to poor concentration [ 41 , 42 ]. From a pathophysiological perspective, inflammatory cytokines (C-reactive protein and interleukin-6) are elevated in children with SDB, which may lead to cognitive dysfunction [ 43 , 44 , 45 ]. In addition, several studies have shown that adenotonsillectomy (a treatment for OSA) can improve ADHD symptoms and cognitive problems [ 8 , 40 , 46 , 47 , 48 ]. However, the relationship between OSA and ADHD may be reciprocal rather than in the traditional one-way relationship, although a reverse relationship was not observed in our study. Symptoms of ADHD overlap with a diagnosis of OSA, and attentional deficits have been reported in up to 95% of OSA patients [ 49 ]. A case-control study found that 28 out of 30 ADHD patients had comorbid sleep disorders, 15 of whom had OSA [ 50 ]. In summary, the relationship between OSA and ADHD is complex and needs to be further explored in future studies.

Our study found that MDD was associated with an increased risk of OSA incidence, which is consistent with a recent MR study [ 51 ]. However, observational studies similar to ours are limited. Only one population-based longitudinal study suggested that a bidirectional link between MDD and OSA exists. This study, which included 27,073 depressed patients and 135,365 controls, demonstrated that having depression was associated with an increased risk of future OSA (HR = 2.30; 95%CI, 2.11–2.50) [ 10 ]. More observational studies consider OSA as a risk factor for MDD [ 52 , 53 , 54 , 55 ], so the relationship between MDD and OSA seems to be reciprocal as well. Two systematic reviews showed that both the prevalence of MDD among patients with OSA and the prevalence of OSA among patients with MDD were higher than in the general population [ 56 , 57 ]. This may be due to a partial overlap of symptoms and diagnostic criteria or common underlying mechanisms between MDD and OSA [ 58 , 59 , 60 ]. However, the following pathophysiological mechanisms support our derived unidirectional association between MDD and OSA. First, increased inflammatory cytokines in depressed patients may lead to neurological damage and altered circadian rhythms, which may increase the risk of OSA and exacerbate the symptoms of OSA [ 61 , 62 ]. Second, patients with depressive disorders are usually associated with central nervous system 5-HT dysfunction, with decreased plasma tryptophan (a 5-HT precursor), decreased 5-HT metabolites in cerebrospinal fluid, and decreased 5-HT 1 receptor binding [ 63 ]. The 5-HT reduction affects dilator muscles of the upper airway, narrowing the size of the upper airway, which may contribute to the incidence of OSA [ 64 ]. Third, some sleep medications and benzodiazepines are used to treat depression, and their tranquillizing effects may decrease the muscle tone of upper airway dilator muscles, thereby increasing the risk of OSA [ 65 , 66 , 67 ]. In conclusion, the relationship between MDD and OSA has not been clarified, and further research into pathogenesis is needed to provide effective and feasible treatments.

The main strength of this study is the use of two-sample bidirectional MR to assess the relationship between OSA and mental disorders, minimizing confounders and reverse causality present in observational studies. Moreover, we limited the population of the GWAS study to Europeans to minimize heterogeneity arising from ethnic differences. In addition, the IVs we used were extracted from the most recent GWAS with a large sample size, and the likelihood of weak instrument bias was minimal and only related to the exposures we were focused on.

However, there are several limitations to this study. First, both OSA and the nine mental disorders are binary exposures, and we could not know whether there would be selective bias due to underdiagnosis [ 29 ], as well as exclusive restriction bias due to the possibility that genetic variants would influence outcomes via continuous risk factors [ 68 ]. In addition, due to the lack of individual-level data from the GWAS study, we were unable to know whether the severity of the disease and medication would cause potential bias. Second, we used different thresholds for screening IVs, but this may have led to inconsistencies in the reliability of the results. Fewer IVs, while greatly reducing the potential for pleiotropy, reduced statistical power. Third, the biological roles and mechanisms of SNPs are not currently fully understood [ 69 ], and the presence of horizontal pleiotropy cannot be completely ruled out, although we performed sensitivity analyses using various methods to rule out horizontal pleiotropy. Fourth, MR estimates reflect the cumulative effects of exposure over individuals’ lifetimes, which are likely to be stronger than in observational studies and clinical trials. However, it is difficult to determine the relationship between OSA and mental disorders using randomized clinical trials due to the limitations of ethical rules and the uncertainty of etiology, and more observational studies are needed in the future to validate our findings. Finally, limiting the ancestry of the population to Europeans reduced the bias due to population stratification, but also limited the extrapolation of the results to other races.

Our study provided genetic evidence that MDD is associated with an increased risk of OSA without a bidirectional relationship. In addition, we also found genetic evidence that OSA is a potential causal risk factor for ADHD. We did not find a causal relationship between OSA and AN, ANX, ASD, BD, OCD, PTSD, and SCZ. Clinically, these findings contribute to the identification, treatment, and prevention of OSA and ADHD in patients. Further investigation is required to better understand the biological mechanisms underlying the relationship between OSA and other mental disorders. This will aid clinicians in providing more effective treatment for these conditions.

Data availability

All data used in this study are obtained from open access databases or published manuscripts. FinnGen: https://r9.risteys.finngen.fi/endpoints/G6_SLEEPAPNO . https://storage.googleapis.com/finngen-public-data-r9/summary_stats/finngen_R9_G6_SLEEPAPNO.gz . PGC: https://pgc.unc.edu/for-researchers/download-results .

Abbreviations

Attention-deficit/hyperactivity disorder

Anorexia nervosa

Anxiety disorder

Autism spectrum disorder

Bipolar disorder

Confidence interval

Genome-wide association studies

Instrumental variables

Inverse variance weighted

Linkage disequilibrium

Major depressive disorder

Mendelian randomization

Mendelian randomization pleiotropy residual sum and outlier test

Obsessive-compulsive disorder

Psychiatric Genomics Consortium

Post-traumatic stress disorder

Schizophrenia

Sleep-disordered breathing

Single nucleotide polymorphism

Ferrari AJ, Santomauro DF, Herrera AMM, Shadid J, Ashbaugh C, Erskine HE, et al. Global, regional, and national burden of 12 mental disorders in 204 countries and territories, 1990–2019: a systematic analysis for the global burden of Disease Study 2019. Lancet Psychiatry. 2022;9:137–50. https://doi.org/10.1016/S2215-0366(21)00395-3 .

Article   Google Scholar  

Lin W-C, Winkelman JW. Obstructive sleep apnea and severe mental illness: evolution and consequences. Curr Psychiat Rep. 2012;14:503–10. https://doi.org/10.1007/s11920-012-0307-6 .

Rundo JV. Obstructive sleep apnea basics. Cleve Clin J Med. 2019;86:2–9. https://doi.org/10.3949/ccjm.86.s1.02 .

Article   PubMed   Google Scholar  

Punjabi NM. The epidemiology of adult obstructive sleep apnea. Proc Am Thorac Soc. 2008;5:136–43. https://doi.org/10.1513/pats.200709-155MG .

Article   PubMed   PubMed Central   Google Scholar  

Chang E-T, Chen S-F, Chiang J-H, Wang L-Y, Hsu C-Y, Shen Y-C. Risk of obstructive sleep apnea in patients with bipolar disorder: a nationwide population-based cohort study in Taiwan. Psychiatry Clin Neurosci. 2019;73:163–8. https://doi.org/10.1111/pcn.12802 .

Wu Y-Y, Chang E-T, Yang Y-C, Chen S-F, Hsu C-Y, Shen Y-C. Risk of obstructive sleep apnea in patients with schizophrenia: a nationwide population-based cohort study. Soc Psych Psych Epid. 2020;55:1671–7. https://doi.org/10.1007/s00127-020-01870-4 .

Hirata I, Mohri I, Kato-Nishimura K, Tachibana M, Kuwada A, Kagitani-Shimono K, et al. Sleep problems are more frequent and associated with problematic behaviors in preschoolers with autism spectrum disorder. Res Dev Disabil. 2016;49–50:86–99. https://doi.org/10.1016/j.ridd.2015.11.002 .

Luis Urbano G, Janine Tablizo B, Moufarrej Y, Tablizo MA, Chen ML, Witmans M. The link between Pediatric Obstructive Sleep Apnea (OSA) and attention deficit hyperactivity disorder (ADHD). Children-Basel. 2021;8:824. https://doi.org/10.3390/children8090824 .

Diaz SV, Brown LK. Relationships between obstructive sleep apnea and anxiety. Curr Opin Pulm Med. 2016;22:563–9. https://doi.org/10.1097/MCP.0000000000000326 .

Pan M-L, Tsao H-M, Hsu C-C, Wu K-M, Hsu T-S, Wu Y-T, et al. Bidirectional association between obstructive sleep apnea and depression: a population-based longitudinal study. Med (Baltim). 2016;95:e4833. https://doi.org/10.1097/MD.0000000000004833 .

McCall CA, Watson NF. A narrative review of the association between post-traumatic stress disorder and obstructive sleep apnea. J Clin Med. 2022;11:415. https://doi.org/10.3390/jcm11020415 .

Smith GD, Ebrahim S. Mendelian randomization: can genetic epidemiology contribute to understanding environmental determinants of disease? Int J Epidemiol. 2003;32:1–22. https://doi.org/10.1093/ije/dyg070 .

Lawlor DA, Harbord RM, Sterne JAC, Timpson N, Davey Smith G. Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Stat Med. 2008;27:1133–63. https://doi.org/10.1002/sim.3034 .

Davey Smith G, Holmes MV, Davies NM, Ebrahim S. Mendel’s laws, mendelian randomization and causal inference in observational data: substantive and nomenclatural issues. Eur J Epidemiol. 2020;35:99–111. https://doi.org/10.1007/s10654-020-00622-7 .

Emdin CA, Khera AV, Kathiresan S, Mendelian Randomization. JAMA. 2017;318:1925–6. https://doi.org/10.1001/jama.2017.17219 .

Burgess S, Scott RA, Timpson NJ, Davey Smith G, Thompson SG, EPIC- InterAct Consortium. Using published data in mendelian randomization: a blueprint for efficient identification of causal risk factors. Eur J Epidemiol. 2015;30:543–52. https://doi.org/10.1007/s10654-015-0011-z .

Kurki MI, Karjalainen J, Palta P, Sipilä TP, Kristiansson K, Donner KM, et al. FinnGen provides genetic insights from a well-phenotyped isolated population. Nature. 2023;613:508–18. https://doi.org/10.1038/s41586-022-05473-8 .

Article   CAS   PubMed   PubMed Central   Google Scholar  

Demontis D, Walters GB, Athanasiadis G, Walters R, Therrien K, Nielsen TT, et al. Genome-wide analyses of ADHD identify 27 risk loci, refine the genetic architecture and implicate several cognitive domains. Nat Genet. 2023;55:198–208. https://doi.org/10.1038/s41588-022-01285-8 .

Otowa T, Hek K, Lee M, Byrne EM, Mirza SS, Nivard MG, et al. Meta-analysis of genome-wide association studies of anxiety disorders. Mol Psychiatr. 2016;21:1391–9. https://doi.org/10.1038/mp.2015.197 .

Article   CAS   Google Scholar  

Watson HJ, Yilmaz Z, Thornton LM, Hübel C, Coleman JRI, Gaspar HA, et al. Genome-wide association study identifies eight risk loci and implicates metabo-psychiatric origins for anorexia nervosa. Nat Genet. 2019;51:1207–14. https://doi.org/10.1038/s41588-019-0439-2 .

Grove J, Ripke S, Als TD, Mattheisen M, Walters RK, Won H, et al. Identification of common genetic risk variants for autism spectrum disorder. Nat Genet. 2019;51:431–44. https://doi.org/10.1038/s41588-019-0344-8 .

Mullins N, Forstner AJ, O’Connell KS, Coombes B, Coleman JRI, Qiao Z, et al. Genome-wide association study of more than 40,000 bipolar disorder cases provides new insights into the underlying biology. Nat Genet. 2021;53:817–29. https://doi.org/10.1038/s41588-021-00857-4 .

Howard DM, Adams MJ, Clarke T-K, Hafferty JD, Gibson J, Shirali M, et al. Genome-wide meta-analysis of depression identifies 102 independent variants and highlights the importance of the prefrontal brain regions. Nat Neurosci. 2019;22:343–52. https://doi.org/10.1038/s41593-018-0326-7 .

International Obsessive Compulsive Disorder Foundation Genetics Collaborative (IOCDF-GC) and OCD Collaborative Genetics Association Studies (OCGAS). Revealing the complex genetic architecture of obsessive-compulsive disorder using meta-analysis. Mol Psychiatr. 2018;23:1181–8. https://doi.org/10.1038/mp.2017.154 .

Nievergelt CM, Maihofer AX, Klengel T, Atkinson EG, Chen C-Y, Choi KW, et al. International meta-analysis of PTSD genome-wide association studies identifies sex- and ancestry-specific genetic risk loci. Nat Commun. 2019;10:4558. https://doi.org/10.1038/s41467-019-12576-w .

Trubetskoy V, Pardiñas AF, Qi T, Panagiotaropoulou G, Awasthi S, Bigdeli TB, et al. Mapping genomic loci implicates genes and synaptic biology in schizophrenia. Nature. 2022;604:502–8. https://doi.org/10.1038/s41586-022-04434-5 .

Kamat MA, Blackshaw JA, Young R, Surendran P, Burgess S, Danesh J, et al. PhenoScanner V2: an expanded tool for searching human genotype-phenotype associations. Bioinformatics. 2019;35:4851–3. https://doi.org/10.1093/bioinformatics/btz469 .

Staley JR, Blackshaw J, Kamat MA, Ellis S, Surendran P, Sun BB, et al. PhenoScanner: a database of human genotype-phenotype associations. Bioinformatics. 2016;32:3207–9. https://doi.org/10.1093/bioinformatics/btw373 .

Li J, Zhao L, Ding X, Cui X, Qi L, Chen Y. Obstructive sleep apnea and the risk of Alzheimer’s disease and Parkinson disease: a mendelian randomization study OSA, Alzheimer’s disease and Parkinson disease. Sleep Med. 2022;97:55–63. https://doi.org/10.1016/j.sleep.2022.06.004 .

Hemani G, Zheng J, Elsworth B, Wade KH, Haberland V, Baird D, et al. The MR-Base platform supports systematic causal inference across the human phenome. Elife. 2018;7:e34408. https://doi.org/10.7554/eLife.34408 .

Bowden J, Davey Smith G, Burgess S. Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression. Int J Epidemiol. 2015;44:512–25. https://doi.org/10.1093/ije/dyv080 .

Hemani G, Bowden J, Davey Smith G. Evaluating the potential role of pleiotropy in mendelian randomization studies. Hum Mol Genet. 2018;27:R195–208. https://doi.org/10.1093/hmg/ddy163 .

Bowden J, Davey Smith G, Haycock PC, Burgess S. Consistent estimation in mendelian randomization with some Invalid instruments using a weighted median estimator. Genet Epidemiol. 2016;40:304–14. https://doi.org/10.1002/gepi.21965 .

Bowden J, Del Greco MF, Minelli C, Davey Smith G, Sheehan NA, Thompson JR. Assessing the suitability of summary data for two-sample mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic. Int J Epidemiol. 2016;45:1961–74. https://doi.org/10.1093/ije/dyw220 .

Bowden J, Del Greco MF, Minelli C, Davey Smith G, Sheehan N, Thompson J. A framework for the investigation of pleiotropy in two-sample summary data mendelian randomization. Stat Med. 2017;36:1783–802. https://doi.org/10.1002/sim.7221 .

Bowden J, Del Greco MF, Minelli C, Zhao Q, Lawlor DA, Sheehan NA, et al. Improving the accuracy of two-sample summary-data mendelian randomization: moving beyond the NOME assumption. Int J Epidemiol. 2019;48:728–42. https://doi.org/10.1093/ije/dyy258 .

Verbanck M, Chen C-Y, Neale B, Do R. Detection of widespread horizontal pleiotropy in causal relationships inferred from mendelian randomization between complex traits and diseases. Nat Genet. 2018;50:693–8. https://doi.org/10.1038/s41588-018-0099-7 .

Brion M J A, Shakhbazov K, Visscher PM. Calculating statistical power in mendelian randomization studies. Int J Epidemiol. 2013;42(5):1497–501. https://doi.org/10.1093/ije/dyt179 .

Palmer TM, Lawlor DA, Harbord RM, Sheehan NA, Tobias JH, Timpson NJ, et al. Using multiple genetic variants as instrumental variables for modifiable risk factors. Stat Methods Med Res. 2012;21:223–42. https://doi.org/10.1177/0962280210394459 .

Sedky K, Bennett DS, Carvalho KS. Attention deficit hyperactivity disorder and sleep disordered breathing in pediatric populations: a meta-analysis. Sleep Med Rev. 2014;18:349–56. https://doi.org/10.1016/j.smrv.2013.12.003 .

Bass JL, Corwin M, Gozal D, Moore C, Nishida H, Parker S, et al. The effect of chronic or intermittent hypoxia on cognition in childhood: a review of the evidence. Pediatrics. 2004;114:805–16. https://doi.org/10.1542/peds.2004-0227 .

Paavonen EJ, Porkka-Heiskanen T, Lahikainen AR. Sleep quality, duration and behavioral symptoms among 5-6-year-old children. Eur Child Adoles Psy. 2009;18:747–54. https://doi.org/10.1007/s00787-009-0033-8 .

Gozal D, Crabtree VM, Sans Capdevila O, Witcher LA, Kheirandish-Gozal L. C-reactive protein, obstructive sleep apnea, and cognitive dysfunction in school-aged children. Am J Respir Crit Care Med. 2007;176:188–93. https://doi.org/10.1164/rccm.200610-1519OC .

Gozal D, Serpero LD, Sans Capdevila O, Kheirandish-Gozal L. Systemic inflammation in non-obese children with obstructive sleep apnea. Sleep Med. 2008;9:254–9. https://doi.org/10.1016/j.sleep.2007.04.013 .

Owens JA. Neurocognitive and behavioral impact of sleep disordered breathing in children. Pediatr Pulm. 2009;44:417–22. https://doi.org/10.1002/ppul.20981 .

Türkoğlu S, Tahsin Somuk B, Sapmaz E, Bilgiç A. Effect of adenotonsillectomy on sleep problems, attention deficit hyperactivity disorder symptoms, and quality of life of children with adenotonsillar hypertrophy and sleep-disordered breathing. Int J Psychiat Med. 2019;54:231–41. https://doi.org/10.1177/0091217419829988 .

Ahmadi MS, Poorolajal J, Masoomi FS, Haghighi M. Effect of adenotonsillectomy on attention deficit-hyperactivity disorder in children with adenotonsillar hypertrophy: a prospective cohort study. Int J Pediatr Otorhi. 2016;86:193–5. https://doi.org/10.1016/j.ijporl.2016.05.012 .

Amiri S, AbdollahiFakhim S, Lotfi A, Bayazian G, Sohrabpour M, Hemmatjoo T. Effect of adenotonsillectomy on ADHD symptoms of children with adenotonsillar hypertrophy and sleep disordered breathing. Int J Pediatr Otorhinolaryngol. 2015;79:1213–7. https://doi.org/10.1016/j.ijporl.2015.05.015 .

Youssef NA, Ege M, Angly SS, Strauss JL, Marx CE. Is obstructive sleep apnea associated with ADHD? Ann Clin Psychiatry. 2011;23:213–24.

PubMed   Google Scholar  

Miano S, Amato N, Foderaro G, Pezzoli V, Ramelli GP, Toffolet L, et al. Sleep phenotypes in attention deficit hyperactivity disorder. Sleep Med. 2019;60:123–31. https://doi.org/10.1016/j.sleep.2018.08.026 .

Mi C, Hou A, Liu Y, Qi X, Teng J. Assessing the causal relationship between psychiatric disorders and obstructive sleep apnea: a bidirectional Mendelian randomization. Frontiers in Psychiatry, 2024, 15[2024-03-19]. https://doi.org/10.3389/fpsyt.2024.1351216 .

Lu M-K, Tan H-P, Tsai I-N, Huang L-C, Liao X-M, Lin S-H. Sleep apnea is associated with an increased risk of mood disorders: a population-based cohort study. Sleep Breath. 2017;21:243–53. https://doi.org/10.1007/s11325-016-1389-x .

Lang CJ, Appleton SL, Vakulin A, McEvoy RD, Vincent AD, Wittert GA, et al. Associations of Undiagnosed Obstructive Sleep Apnea and Excessive Daytime Sleepiness with Depression: an Australian Population Study. J Clin Sleep Med. 2017;13:575–82. https://doi.org/10.5664/jcsm.6546 .

Chen Y-H, Keller JK, Kang J-H, Hsieh H-J, Lin H-C. Obstructive sleep apnea and the subsequent risk of depressive disorder: a population-based follow-up study. J Clin Sleep Med. 2013;9:417–23. https://doi.org/10.5664/jcsm.2652 .

Peppard PE, Szklo-Coxe M, Hla KM, Young T. Longitudinal association of sleep-related breathing disorder and depression. Arch Intern Med. 2006;166:1709–15. https://doi.org/10.1001/archinte.166.16.1709 .

Garbarino S, Bardwell WA, Guglielmi O, Chiorri C, Bonanni E, Magnavita N. Association of anxiety and depression in Obstructive Sleep Apnea patients: a systematic review and Meta-analysis. Behav Sleep Med. 2020;18:35–57. https://doi.org/10.1080/15402002.2018.1545649 .

Stubbs B, Vancampfort D, Veronese N, Solmi M, Gaughran F, Manu P, et al. The prevalence and predictors of obstructive sleep apnea in major depressive disorder, bipolar disorder and schizophrenia: a systematic review and meta-analysis. J Affect Disord. 2016;197:259–67. https://doi.org/10.1016/j.jad.2016.02.060 .

Luik AI, Noteboom J, Zuurbier LA, Whitmore H, Hofman A, Tiemeier H. Sleep apnea severity and depressive symptoms in a population-based study. Sleep Health. 2015;1:128–32. https://doi.org/10.1016/j.sleh.2015.03.002 .

Kendzerska T, Gershon AS, Hawker GA, Tomlinson GA, Leung RS. Obstructive sleep apnoea is not a risk factor for incident hospitalised depression: a historical cohort study. Eur Respir J. 2017;49:1601361. https://doi.org/10.1183/13993003.01361-2016 .

Vanek J, Prasko J, Genzor S, Ociskova M, Kantor K, Holubova M, et al. Obstructive sleep apnea, depression and cognitive impairment. Sleep Med. 2020;72:50–8. https://doi.org/10.1016/j.sleep.2020.03.017 .

Irwin MR, Miller AH. Depressive disorders and immunity: 20 years of progress and discovery. Brain Behav Immun. 2007;21:374–83. https://doi.org/10.1016/j.bbi.2007.01.010 .

Article   CAS   PubMed   Google Scholar  

Vgontzas AN, Zoumakis E, Lin H-M, Bixler EO, Trakada G, Chrousos GP. Marked decrease in sleepiness in patients with sleep apnea by etanercept, a tumor necrosis factor-alpha antagonist. J Clin Endocrinol Metab. 2004;89:4409–13. https://doi.org/10.1210/jc.2003-031929 .

Jans La, Riedel W, Markus WJ, Blokland CR. Serotonergic vulnerability and depression: assumptions, experimental evidence and implications. Mol Psychiatr. 2007;12:522–43. https://doi.org/10.1038/sj.mp.4001920 .

Fenik P, Veasey SC. Pharmacological characterization of serotonergic receptor activity in the hypoglossal nucleus. Am J Resp Crit Care. 2003;167:563–9. https://doi.org/10.1164/rccm.200202-107OC .

Cirignotta F, Mondini S, Zucconi M, Gerardi R, Farolfi A, Lugaresi E. Zolpidem-polysomnographic study of the effect of a new hypnotic drug in sleep apnea syndrome. Pharmacol Biochem Behav. 1988;29:807–9. https://doi.org/10.1016/0091-3057(88)90212-2 .

Guilleminault C. Benzodiazepines, breathing, and sleep. Am J Med. 1990;88:S25–8. https://doi.org/10.1016/0002-9343(90)90282-i .

Gupta MA, Simpson FC. Obstructive sleep apnea and psychiatric disorders: a systematic review. J Clin Sleep Med. 2015;11:165–75. https://doi.org/10.5664/jcsm.4466 .

Burgess S, Labrecque JA. Mendelian randomization with a binary exposure variable: interpretation and presentation of causal estimates. Eur J Epidemiol. 2018;33:947–52. https://doi.org/10.1007/s10654-018-0424-6 .

Choi KW, Chen C-Y, Stein MB, Klimentidis YC, Wang M-J, Koenen KC, et al. Assessment of Bidirectional relationships between physical activity and depression among adults a 2-Sample mendelian randomization study. JAMA Psychiatry. 2019;76:399–408. https://doi.org/10.1001/jamapsychiatry.2018.4175 .

Download references

Acknowledgements

We sincerely appreciate FinnGen and the PGC for providing publicly available GWAS data. We would also like to thank other faculty members in the Department of Epidemiology and Health Statistics for their help.

Not applicable.

Author information

Authors and affiliations.

Department of Epidemiology and Health Statistics, School of Public Health, Lanzhou University, No.199, Donggang West Road, Chengguan District, 730000, Lanzhou, Gansu Province, China

Heming Liu, Xuemei Wang, Hu Feng, Shengze Zhou, Jinhua Pan, Changping Ouyang & Xiaobin Hu

You can also search for this author in PubMed   Google Scholar

Contributions

HM L wrote the main manuscript as well as analysed the data. XM W and H F used PhenoScanner to exclude instrumental variables associated with other traits or diseases. CP OY and JH P made data curation. SZ Z and XB H reviewed the manuscript.

Corresponding author

Correspondence to Xiaobin Hu .

Ethics declarations

Ethics approval and consent to participate.

All data used in this work are publicly available from studies with relevant participant consent and ethical approval.

Consent for publication

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Supplementary material 2, supplementary material 3, supplementary material 4, supplementary material 5, supplementary material 6, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Liu, H., Wang, X., Feng, H. et al. Obstructive sleep apnea and mental disorders: a bidirectional mendelian randomization study. BMC Psychiatry 24 , 304 (2024). https://doi.org/10.1186/s12888-024-05754-8

Download citation

Received : 10 November 2023

Accepted : 09 April 2024

Published : 23 April 2024

DOI : https://doi.org/10.1186/s12888-024-05754-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Obstructive sleep apnea (OSA)
• Two-sample bidirectional mendelian randomization

BMC Psychiatry

ISSN: 1471-244X

• Submission enquiries: [email protected]
• General enquiries: [email protected]