chronic kidney failure research papers

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
• HHS Author Manuscripts

Chronic Kidney Disease Diagnosis and Management

Author Contributions: Dr Grams had full access to all of the data in the study and takes responsibility for the integrity of the data and the accuracy of the data analysis.

Acquisition, analysis, or interpretation of data: Chen, Grams.

Drafting of the manuscript: Chen.

Critical revision of the manuscript for important intellectual content: All authors.

Statistical analysis: Grams.

Administrative, technical, or material support: Chen, Knicely.

Supervision: Grams.

Additional Contributions: We thank Andrew S. Levey, MD, Tufts Medical Center, and Natalie Daya, MS, Johns Hopkins University, for helpful input on the manuscript (uncompensated).

Chronic kidney disease (CKD) is the 16th leading cause of years of life lost worldwide. Appropriate screening, diagnosis, and management by primary care clinicians are necessary to prevent adverse CKD-associated outcomes, including cardiovascular disease, end-stage kidney disease, and death.

OBSERVATIONS

Defined as a persistent abnormality in kidney structure or function (eg, glomerular filtration rate [GFR] <60 mL/min/1.73 m 2 or albuminuria ≥30 mg per 24 hours) for more than 3 months, CKD affects 8% to 16% of the population worldwide. In developed countries, CKD is most commonly attributed to diabetes and hypertension. However, less than 5% of patients with early CKD report awareness of their disease. Among individuals diagnosed as having CKD, staging and new risk assessment tools that incorporate GFR and albuminuria can help guide treatment, monitoring, and referral strategies. Optimal management of CKD includes cardiovascular risk reduction (eg, statins and blood pressure management), treatment of albuminuria (eg, angiotensin-converting enzyme inhibitors or angiotensin II receptor blockers), avoidance of potential nephrotoxins (eg, nonsteroidal anti-inflammatory drugs), and adjustments to drug dosing (eg, many antibiotics and oral hypoglycemic agents). Patients also require monitoring for complications of CKD, such as hyperkalemia, metabolic acidosis, hyperphosphatemia, vitamin D deficiency, secondary hyperparathyroidism, and anemia. Those at high risk of CKD progression (eg, estimated GFR <30 mL/min/1.73 m 2 , albuminuria ≥300 mg per 24 hours, or rapid decline in estimated GFR) should be promptly referred to a nephrologist.

CONCLUSIONS AND RELEVANCE

Diagnosis, staging, and appropriate referral of CKD by primary care clinicians are important in reducing the burden of CKD worldwide.

Chronic kidney disease (CKD) affects between 8% and 16% of the population worldwide and is often underrecognized by patients and clinicians. 1 – 4 Defined by a glomerular filtration rate (GFR) of less than 60 mL/min/1.73 m 2 , albuminuria of at least 30 mg per 24 hours, or markers of kidney damage (eg, hematuria or structural abnormalities such as polycystic or dysplastic kidneys) persisting for more than 3 months, 5 CKD is more prevalent in low- and middle-income than in high-income countries. 6 Globally, CKD is most commonly attributed to diabetes and/or hypertension, but other causes such as glomerulonephritis, infection, and environmental exposures (such as air pollution, herbal remedies, and pesticides) are common in Asia, sub-Saharan Africa, and many developing countries. 4 Genetic risk factors may also contribute to CKD risk. For example, sickle cell trait and the presence of 2 APOL1 risk alleles, both common in people of African ancestry but not European ancestry, may double the risk of CKD. 4 , 7 – 10

In the United States, the average rate of GFR decline is approximately 1 mL/min/1.73 m 2 per year in the general population, 11 , 12 and the lifetime risk of developing a GFR of less than 60 mL/min/1.73 m 2 is more than 50%. 13 Early detection and treatment by primary care clinicians is important because progressive CKD is associated with adverse clinical outcomes, including end-stage kidney disease (ESKD), cardiovascular disease, and increased mortality. 14 – 17 Recent professional guidelines suggest a risk-based approach to the evaluation and management of CKD. 5 , 18 – 20 This review includes discussion of new calculators for determining risk of CKD progression that may be useful in clinical practice (eg, https://kidneyfailurerisk.com/ ) and focuses on the diagnosis, evaluation, and management of CKD for primary care clinicians. Considerations for referral to a nephrologist and dialysis initiation are also covered.

A literature search to April 2019 was conducted using Medline and PubMed with search terms including CKD , chronic renal failure , chronic renal insufficiency , epidemiology , incidence , prevalence , occurrence , diagnosis , assessment , identification , screening , workup , etiology , causes , management , treatment , intervention , therapy , and prevention . Results were restricted to English-language, human studies, and academic journals and guidelines. The initial search resulted in 998 articles, including clinical trials, meta-analyses, practice guidelines, and systematic reviews, and was later expanded to include review articles and observational studies, including cross-sectional studies, and more recent publications contained in reference lists of identified articles. All clinical trials for treatment or prevention of CKD were included without regard to study size or age of patient population.

Clinical Presentation

Chronic kidney disease is typically identified through routine screening with serum chemistry profile and urine studies or as an incidental finding. Less commonly, patients may present with symptoms such as gross hematuria, “foamy urine” (a sign of albuminuria), nocturia, flank pain, or decreased urine output. If CKD is advanced, patients may report fatigue, poor appetite, nausea, vomiting, metallic taste, unintentional weight loss, pruritus, changes in mental status, dyspnea, or peripheral edema. 21

In evaluating a patient with known or suspected CKD, clinicians should inquire about additional symptoms that might suggest a systemic cause (eg, hemoptysis, rash, lymphadenopathy, hearing loss, neuropathy) or urinary obstruction (eg, urinary hesitancy, urgency, or frequency or incomplete bladder emptying). 21 Moreover, patients should be assessed for risk factors of kidney disease, including prior exposure to potential nephrotoxins (eg, nonsteroidal anti-inflammatory drugs [NSAIDs], phosphate-based bowel preparations, herbal remedies such as those containing aristolochic acid, antibiotic therapies such as gentamicin, and chemotherapies), history of nephrolithiasis or recurrent urinary tract infections, presence of comorbidities (eg, hypertension, diabetes, autoimmune disease, chronic infections), family history of kidney disease, and, if available, other known genetic risk factors such as sickle cell trait. 9 , 18 , 21 – 24

A detailed physical examination may provide additional clues regarding the underlying cause of CKD and should include careful evaluation of a patient’s volume status. Signs of volume depletion may reflect poor oral intake, vomiting, diarrhea, or overdiuresis, whereas signs of volume overload may be due to decompensated heart failure, liver failure, or nephrotic syndrome. The presence of arterial-venous nicking or retinopathy on retinal examination suggests long-standing hypertension or diabetes. Patients with carotid or abdominal bruits may have renovascular disease. Flank pain or enlarged kidneys should prompt consideration of obstructive uropathy, nephrolithiasis, pyelonephritis, or polycystic kidney disease. Neuropathy may be due to diabetes or less commonly vasculitis, or amyloidosis. Skin findings may include rash (systemic lupus erythematosus, acute interstitial nephritis), palpable purpura (Henoch-Schonlein purpura, cryoglobulinemia, vasculitis), telangiectasias (scleroderma, Fabry disease), or extensive sclerosis (scleroderma). Patients with advanced CKD may exhibit pallor, skin excoriations, muscle wasting, asterixis, myoclonic jerks, altered mental status, and pericardial rub. 21

CKD Definition and Staging

Chronic kidney disease is defined as the presence of an abnormality in kidney structure or function persisting for more than 3 months. 5 , 25 This includes 1 or more of the following: (1) GFR less than 60 mL/min/1.73 m 2 ; (2) albuminuria (ie, urine albumin ≥30 mg per 24 hours or urine albumin-to-creatinine ratio [ACR] ≥30 mg/g); (3) abnormalities in urine sediment, histology, or imaging suggestive of kidney damage; (4) renal tubular disorders; or (5) history of kidney transplantation. 5 If the duration of kidney disease is unclear, repeat assessments should be performed to distinguish CKD from acute kidney injury (change in kidney function occurring within 2–7 days) and acute kidney disease (kidney damage or decreased kidney function present for ≤3 months). 25 Evaluation for the etiology of CKD should be guided by a patient’s clinical history, physical examination, and urinary findings ( Figure 1 ). 5 , 18 , 21

a Other imaging modalities or urine studies may also be considered.

b A variety of scores are available, eg, https://kidneyfailurerisk.com/ .

Once a diagnosis of CKD has been made, the next step is to determine staging, which is based on GFR, albuminuria, and cause of CKD ( Figure 2 ). 5 Staging of GFR is classified as G1 (GFR ≥90 mL/min/1.73 m 2 ), G2 (GFR 60–89 mL/min/1.73 m 2 ), G3a (45–59 mL/min/1.73 m 2 ), G3b (30–44 mL/min/1.73 m 2 ), G4 (15–29 mL/min/1.73 m 2 ), and G5 (<15 mL/min/1.73 m 2 ). 5 Although GFR can be directly measured by clearance of agents such as iohexol or iothalamate, 26 – 28 the development of estimating equations (eg, the Chronic Kidney Disease Epidemiology Collaboration [CKD-EPI] and Modification of Diet in Renal Disease Study [MDRD] equations) has largely replaced the need for direct measurement in clinical practice. 29 – 31 Clinical laboratories now routinely report estimated GFR (eGFR) based on filtration markers. The most common filtration marker used is creatinine, a 113 dalton byproduct of creatine metabolism 25 and one for which laboratory assays have been standardized since 2003. 32 The preferred estimating equation in the United States and much of the world is the CKD-EPI 2009 creatinine equation, which is more accurate than the earlier MDRD equation, particularly for eGFR values greater than 60 mL/min/1.73 m 2 ( https://www.kidney.org/professionals/kdoqi/gfr_calculator). 29 , 30 In situations requiring additional accuracy and precision, cystatin C can be used with creatinine in the CKD-EPI 2012 creatinine-cystatin C equation. 31 Adding cystatin C may be particularly useful for individuals with altered creatinine production and/or metabolism (eg, extremely high or low body size or muscle mass, limb amputation, high-protein diet, use of creatinine supplements, or use of drugs affecting tubular secretion of creatinine). 5 , 25

GFR indicates glomerular filtration rate; KDIGO, Kidney Disease Improving Global Outcomes. Categories are grouped by risk of progression, which includes chronic kidney disease progression, defined by a decline in GFR category (accompanied by a ≥25% decrease in estimated GFR from baseline) or sustained decline in estimated GFR greater than 5 mL/min/1.73 m 2 per year. Green indicates low risk (if no other markers of kidney disease and no CKD); yellow, moderately increased risk; orange: high risk; and red, very high risk. Reproduced with permission from Kidney International Supplements . 5

Albuminuria should ideally be quantified by a urine ACR. Albuminuria staging is classified as A1 (urine ACR <30 mg/g), A2 (30–300 mg/g), and A3 (>300 mg/g). 5 Guidelines recommend the use of urine ACR to stage CKD rather than urine protein-to-creatinine ratio because assays for the former are more likely to be standardized and have better precision at lower values of albuminuria. 5 , 33 The most precise measurements come from a first morning sample or 24-hour collection, as there is high biological variability in urine albumin excretion over the course of the day. 5 , 34 , 35 Random samples, however, are also acceptable in initial screening. 5 Compared with urine protein-to-creatinine ratio, urine ACR is believed to be a more sensitive and specific marker of glomerular pathology 5 since some urine proteins such as uromodulin are present (and may even be protective) in normal physiology. 36 – 38 If tubular or overflow proteinuria is suspected, then urine protein electrophoresis or testing for the specific protein can be pursued (eg, immunoglobulin heavy and light chains, α 1 -microglobulin, and β 2 -microglobulin). 5 Imaging by kidney ultrasound to assess morphology and to rule out urinary obstruction should be considered in all patients diagnosed as having CKD. 5

Cause of CKD can be difficult to discern but is generally classified by the presence or absence of systemic disease and the location of anatomic abnormality. Examples of systemic disease include diabetes, autoimmune disorders, chronic infection, malignancy, and genetic disorders in which the kidney is not the only organ affected. Anatomic locations are divided into glomerular, tubulointerstitial, vascular, and cystic/congenital diseases. 5 Determining the cause of CKD may have important implications on prognosis and treatment. For example, polycystic kidney disease may progress to ESKD faster than other causes and often requires evaluation for extrarenal manifestations and consideration of specific therapies such as tolvaptan, a vasopressin V2 receptor antagonist that slows decline in GFR. 39 , 40 Patients with unexplained causes of CKD should be referred to a nephrologist.

Screening for CKD

Given that most patients with CKD are asymptomatic, screening may be important to early detection of disease. 18 The National Kidney Foundation has developed a kidney profile test that includes measuring both serum creatinine for estimating GFR and urine ACR. 41 A risk-based approach to screening is suggested by many clinical practice guidelines, with screening recommended in those older than 60 years or with a history of diabetes or hypertension. 18 – 20 Screening should also be considered in those with clinical risk factors, including autoimmune disease, obesity, kidney stones, recurrent urinary tract infections, reduced kidney mass, exposure to certain medications such as NSAIDs or lithium, and prior episodes of acute kidney injury, among others ( Box ). 9 , 18 , 42 – 45 However, no randomized clinical trials have demonstrated that screening asymptomatic patients for CKD improves outcomes.

Clinical, Sociodemographic, and Genetic Risk Factors for Chronic Kidney Disease

Hypertension

Autoimmune diseases

Systemic infections (eg, HIV, hepatitis B virus, hepatitis C virus)

Nephrotoxic medications (eg, nonsteroidal anti-inflammatory drugs, herbal remedies, lithium)

Recurrent urinary tract infections

Kidney stones

Urinary tract obstruction

Reduced kidney mass (eg, nephrectomy, low birth weight)

History of acute kidney injury

Intravenous drug use (eg, heroin, cocaine)

Family history of kidney disease

Sociodemographic

Age >60 years

Nonwhite race

Low education

APOL1 risk alleles

Sickle cell trait and disease

Polycystic kidney disease

Alport syndrome

Congenital anomalies of the kidney and urinary tract

Other familial causes

Other Risk Factors for CKD

There are several sociodemographic factors that contribute to increased risk of CKD, including nonwhite race, low education, low income, and food insecurity. 18 , 43 , 46 Compared with whites, African Americans and Pacific Islanders have a substantially greater risk of ESKD. 47 This is in part due to an increased prevalence of hypertension, diabetes, and obesity. 11 However, genetic factors likely also contribute. More specifically, risk alleles in the gene encoding apolipoprotein L1 ( APOL1 ) may increase risk of kidney disease in a recessive genetic manner 7 , 8 : individuals with 2 APOL1 risk alleles (present in approximately 13% of African Americans) have a 2-fold risk of CKD progression and up to a 29-fold risk of specific CKD etiologies (eg, focal-segmental glomerulosclerosis and HIV-associated nephropathy) compared with those with 0 or 1 risk allele. 11 , 44 , 45 , 48 , 49 Sickle cell trait (present in approximately 8% of African Americans) has also been associated with an increased risk of kidney disease. Compared with noncarriers, individuals with sickle cell trait have a 1.8-fold odds of incident CKD, 1.3-fold odds of eGFR decline greater than 3 mL/min/1.73 m 2 , and 1.9-fold odds of albuminuria. 9

Management of Patients With CKD

Reducing risk of cardiovascular disease.

The prevalence of cardiovascular disease is markedly higher among individuals with CKD compared with those without CKD. For example, in a Medicare 5% sample, 65% of the 175 840 adults aged 66 years or older with CKD had cardiovascular disease compared with 32% of the 1 086 232 without CKD. 47 Moreover, presence of CKD is associated with worse cardiovascular outcomes. For example, in the same population, the presence of CKD was associated with lower 2-year survival in people with coronary artery disease (77% vs 87%), acute myocardial infarction (69% vs 82%), heart failure (65% vs 76%), atrial fibrillation (70% vs 83%), and cerebrovascular accident/transient ischemic attack (73% vs 83%). 47

Therefore, a major component of CKD management is reduction of cardiovascular risk. It is recommended that patients aged 50 years or older with CKD be treated with a low- to moderate-dose statin regardless of low-density lipoprotein cholesterol level. 50 – 52 Smoking cessation should also be encouraged. 5 , 53 Both the Eighth Joint National Committee (JNC 8) and Kidney Disease: Improving Global Outcomes (KDIGO) guidelines have recommended goal systolic and diastolic blood pressures of less than 140 mm Hg and less than 90 mm Hg, respectively, among adults with CKD based on expert opinion. 5 , 54 The KDIGO guidelines further recommend that adults with urine ACR of at least 30 mg per 24 hours (or equivalent) have systolic and diastolic blood pressures maintained below 130 mm Hg and 80 mm Hg, respectively. 5 More recently, the Systolic Blood Pressure Intervention Trial (SPRINT) demonstrated that among individuals with increased risk of cardiovascular disease but without diabetes, more intensive blood pressure control (goal systolic blood pressure <120 mm Hg) was associated with a 25% lower (1.65% vs 2.19% per year) risk of a major cardiovascular event and a 27% lower risk of all-cause mortality compared with standard blood pressure control (goal systolic blood pressure <140 mm Hg). 55 The intensive treatment group had a greater risk of at least a 30% decline in eGFR to a level below 60 mL/min/1.73 m 2 ; however, this may have been due to hemodynamic changes rather than true kidney function loss. 55 , 56 Importantly, the benefits of intensive blood pressure control on cardiovascular events were similar in participants with and without baseline CKD. 57

Management of Hypertension

Many guidelines provide algorithms detailing which agents should be used to treat hypertension in people with CKD. 54 , 58 Presence and severity of albuminuria should be evaluated. Blockade of the renin-angiotensin-aldosterone system with either an angiotensin-converting enzyme inhibitor (ACE-I) or an angiotensin II receptor blocker (ARB) is recommended for adults with diabetes and a urine ACR of at least 30 mg per 24 hours or any adult with a urine ACR of at least 300 mg per 24 hours. 5 , 18 , 58 Dual therapy with an ACE-I and an ARB is generally avoided, given associated risks of hyperkalemia and acute kidney injury. 5 , 18 , 59 Aldosterone receptor antagonists may also be considered in patients with albuminuria, resistant hypertension, or heart failure with reduced ejection fraction. 58 , 60 – 64

Management of Diabetes Mellitus

Optimal management of diabetes is also important. First, glycemic control may delay progression of CKD, with most guidelines recommending a goal hemoglobin A1c of ~ 7.0%. 5 , 18 , 19 , 65 – 67 Second, dose adjustments in oral hypoglycemic agents may be necessary. In general, drugs that are largely cleared by the kidneys (eg, glyburide) should be avoided, whereas drugs metabolized by the liver and/or partially excreted by the kidneys (eg, metformin and some dipeptidyl peptidase 4 [DPP-4] and sodium-glucose cotransporter-2 [SGLT-2] inhibitors) may require dose reduction or discontinuation, particularly when eGFR falls below 30 mL/min/1.73 m 2 . 18 , 19 Third, use of specific medication classes such as SGLT-2 inhibitors in those with severely increased albuminuria should be considered. The Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation (CREDENCE) trial demonstrated that, among 4401 patients with type 2 diabetes and CKD stage G2-G3/A3 (baseline eGFR 30 to <90 mL/min/1.73 m 2 and urine ACR>300 to 5000 mg/24 hours) taking ACE-I or ARB therapy, those randomized to canagliflozin had a 30% lower risk (43.2 vs 61.2 events per 1000 patient-years) of developing the primary composite renal outcome (doubling of serum creatinine, ESKD, or death from a renal or cardiovascular cause) compared with those randomized to placebo. 68 Prior trials have also suggested cardiovascular benefit with this class of medications, which may extend to patients with CKD who have lower levels of albuminuria. 69 , 70

Nephrotoxins

All patients with CKD should be counseled to avoid nephrotoxins. Although a complete list is beyond the scope of this review, a few warrant mentioning. Routine administration of NSAIDs in CKD is not recommended, especially among individuals who are taking ACE-I or ARB therapy. 5 , 18 Herbal remedies are not regulated by the US Food and Drug Administration, and some (such as those containing aristolochic acid or anthraquinones) have been reported to cause a myriad of kidney abnormalities, including acute tubular necrosis, acute or chronic interstitial nephritis, nephrolithiasis, rhabdomyolysis, hypokalemia, and Fanconi syndrome. 22 Phosphate-based bowel preparations (both oral and enema formulations) are readily available over the counter and can lead to acute phosphate nephropathy. 23 , 24 Proton pump inhibitors are widely used and have been associated with acute interstitial nephritis in case reports and incident CKD in population-based studies. 71 – 73 In the population-based Atherosclerosis Risk in Communities cohort, the incidence of CKD was 14.2 events in those taking proton pump inhibitors and 10.7 per 1000 events in people who did not take them. 71 Uniform discontinuation of proton pump inhibitors in CKD is not necessary. However, indications for use should be addressed at each primary care visit.

Drug Dosing

Adjustments in drug dosing are frequently required in patients with CKD. Of note, the traditional Cockcroft-Gault equation often poorly reflects measured GFR, whereas estimation of GFR using the CKD-EPI equation likely correlates better with drug clearance by the kidneys. 74 , 75 Common medications that require dose reductions include most antibiotics, direct oral anticoagulants, gabapentin and pregabalin, oral hypoglycemic agents, insulin, chemotherapeutic agents, and opiates, among others. 5 , 18 In general, use of medications with low likelihood of benefit should be minimized because patients with CKD are at high risk of adverse drug events. 76 – 79 Gadolinium-based contrast agents are contraindicated in individuals with acute kidney injury, eGFR less than 30 mL/min/1.73 m 2 , or ESKD given the risk of nephrogenic systemic fibrosis, a painful and debilitating disorder characterized by marked fibrosis of the skin and occasionally other organs. 5 , 18 , 80 , 81 Newer macrocyclic chelate formulations (eg, gadoteridol, gadobutrol, or gadoterate) are much less likely to cause nephrogenic systemic fibrosis, but the best prevention may still be to avoid gadolinium altogether. If administration of gadolinium is deemed essential, the patient must be counseled on the potential risk of nephrogenic systemic fibrosis and a nephrologist may be consulted for consideration of postexposure hemodialysis. 5 , 18 , 80 – 82

Dietary Management

Dietary management to prevent CKD progression is controversial since large trials have had equivocal results. 83 – 85 For example, the MDRD study evaluated 2 levels of protein restriction in 840 patients, finding that a low-protein diet compared with usual protein intake resulted in slower GFR decline only after the initial 4 months, and that a very low-protein diet compared with a low-protein diet was not significantly associated with slower GFR decline. Both levels of protein restriction appeared to have benefit in the subgroup with proteinuria greater than 3 g per day, although this group was small. 83 Other, smaller trials have suggested a benefit of protein restriction in the prevention of CKD progression or ESKD. 86 – 88 The KDIGO guidelines recommend that protein intake be reduced to less than 0.8 g/kg per day (with proper education) in adults with CKD stages G4-G5 and to less than 1.3 g/kg per day in other adult patients with CKD at risk of progression. 5 The possible benefits of dietary protein restriction must be balanced with the concern of precipitating malnutrition and/or protein wasting syndrome. 5 , 83 , 84 , 89 Lower dietary acid loads (eg, more fruits and vegetables and less meats, eggs, and cheeses) may also help protect against kidney injury. 90 , 91 Low-sodium diets (generally <2 g per day) are recommended for patients with hypertension, proteinuria, or fluid overload. 5

Monitoring of Established CKD and Treatment of Complications

Once CKD is established, the KDIGO guidelines recommend monitoring eGFR and albuminuria at least once annually. For patients at high risk, these measures should be monitored at least twice per year; patients at very high risk should be monitored at least 3 times per year ( Figure 2 ). 5 Patients with moderate to severe CKD are at increased risk of developing electrolyte abnormalities, mineral and bone disorders, and anemia. 92 Screening and frequency of assessment for laboratory abnormalities is dictated by stage of CKD and includes measurement of complete blood count, basic metabolic panel, serum albumin, phosphate, parathyroid hormone, 25-hydroxyvitamin D, and lipid panel ( Table ). 5 , 50 , 93 , 94

Screening, Monitoring, and Management of the Complications of Chronic Kidney Disease (CKD)

Anemia and the Role of Erythropoietin in CKD

Anemia is among the most common complications of CKD. In a study that included 19 CKD cohorts from across the world, 41% of the 209 311 individuals had low levels of hemoglobin (defined as <13 g/dL in men and <12 g/dL in women). 92 The initial workup of anemia should include assessment of iron stores: those who are iron deficient may benefit from oral or intravenous iron repletion. Patients with hemoglobin levels persistently below 10 g/dL despite addressing reversible causes can be referred to a nephrologist for consideration of additional medical therapy, including erythropoietin-stimulating agents; however, erythropoietin-stimulating agents have been associated with increased risk of death, stroke, and venous thromboembolism, and these risks must be weighed against any potential benefits. 93

Electrolyte, Mineral, and Bone Abnormalities in CKD

Electrolyte abnormalities are present in 3% to 11% of patients with CKD. 92 Initial treatment strategies usually involve dietary restrictions and prescription of supplements. For example, primary care clinicians should recommend low-potassium diets for patients with hyperkalemia and low-phosphorus diets for patients with hyperphosphatemia. 5 , 18 , 94 , 95 For patients with a serum bicarbonate level persistently below 22 mmol/L, oral bicarbonate supplementation should be considered, as studies have suggested that chronic metabolic acidosis is associated with faster CKD progression. 5 , 18 , 96 – 99

Mineral and bone disorders are also common. In a study that included 42 985 patients with CKD, 58% had intact parathyroid hormone levels greater than 65 pg/mL. 92 Although the optimal intact parathyroid hormone level for CKD remains unclear, most nephrologists agree that concomitant hyperphosphatemia, hypocalcemia, and vitamin D deficiency should be addressed, such as with a low-phosphate diet, phosphate binders, adequate elemental calcium intake, and vitamin D supplementation ( Table ). 94 , 95

Prognosis of CKD

The incidence of ESKD varies by the presence of risk factors and geographical location. For example, in North America, the incidence among individuals with eGFR less than 60 mL/min/1.73 m 2 ranged from 4.9 to 168.3 ESKD events per 1000 patient-years in 16 cohorts; in 15 non–North American cohorts, the incidence ranged from 1.2 to 131.3 ESKD events per 1000 patient-years. 100 Most patients with CKD do not require kidney replacement therapy during their lifetime. 101 Simple online tools are available to help with risk stratification. For example, the Kidney Failure Risk Equation (KFRE; https://kidneyfailurerisk.com/ ) predicts the 2-year and 5-year probabilities of requiring dialysis or transplant among individuals with eGFR less than 60 mL/min/1.73 m 2 . 100 , 102 The KFRE, which has been validated in more than 700 000 individuals from more than 30 countries, uses readily available clinical and laboratory variables. The 4-variable equation includes age, sex, eGFR, and urine ACR, whereas the 8-variable equation further incorporates serum albumin, phosphate, calcium, and bicarbonate levels. 100 , 102 Some health systems have tested the implementation of KFRE in clinical practice: nephrology referrals based on a 5-year KFRE greater than 3% led to shorter wait times, 103 and a 2-year KFRE greater than 10% was used to guide referrals to multidisciplinary CKD clinics. 104 An ongoing trial is evaluating whether a KFRE risk-based approach improves CKD management. 105 For patients with eGFR less than 30mL/min/1.73m 2 , the CKD G4+ risk calculator ( https://www.kdigo.org/equation/ ) may provide additional information on the risks of cardiovascular disease and death. 106 , 107 Importantly, risk prognostication may be helpful in not only identifying individuals at high risk of disease progression but also providing reassurance to those with mild CKD such as stage G3a A1.

Referral to a Nephrologist and Timing of Kidney Replacement Therapy

The KDIGO guidelines recommend that patients with CKD be referred to a nephrologist when eGFR falls below 30 mL/min/1.73 m 2 (stage G4) and/or urine ACR increases above 300 mg per 24 hours (stage A3). 5 The presence of albuminuria greater than 2200 mg per 24 hours should prompt expedited evaluation by a nephrologist and consideration of nephrotic syndrome. Additional indications for referral include the following: presence of greater than 20 red blood cells per high-power field of unclear etiology, red blood cell casts on urine microscopy or other indication of glomerulonephritis, CKD with uncontrolled hypertension despite 4 or more antihypertensive medications, persistent hypokalemia or hyperkalemia, anemia requiring erythropoietin replacement, recurrent or extensive kidney stones, hereditary kidney disease, acute kidney injury, and rapid CKD progression (a decrease in eGFR ≥25% from baseline or a sustained decline in eGFR >5 mL/min/1.73 m 2 ). 5 In persons without CKD, even small changes in serum creatinine (eg, from 0.7 mg/dL to 1.2 mg/dL) reflect large declines in eGFR, and primary care clinicians should attempt to identify reversible causes. Indications for kidney biopsy may include but are not limited to unexplained persistent or increasing albuminuria, presence of cellular casts or dysmorphic red blood cells on urine sediment, and unexplained or rapid decline in GFR. 5 Specific thresholds vary depending on patient characteristics and by institution. Patients with polycystic kidney disease, certain types of glomerulonephritis, and nephrotic-range albuminuria are at particularly high risk of progressing to ESKD. 5 , 39 , 102

Referral to nephrology is important for planning kidney replacement therapy and transplant evaluation. The decision to begin kidney replacement therapy is based on the presence of symptoms and not solely on level of GFR. 108 Urgent indications include encephalopathy, pericarditis, and pleuritis due to severe uremia. 109 Otherwise, initiation of dialysis should be individualized and considered when patients have uremic signs or symptoms (eg, nausea, vomiting, poor appetite, metallic taste, pericardial rub or effusion, asterixis, or altered mental status), electrolyte abnormalities (eg, hyperkalemia or metabolic acidosis), or volume overload (eg, pulmonary or lower extremity edema) refractory to medical management. 5 , 18 , 109 A shared decision-making approach is best. Patients should be educated about treatment options and actively contribute to decision-making. Early education should include information on the potential complications of CKD as well as the different modalities of kidney replacement therapy. Kidney transplantation is considered the optimal therapy for ESKD, with living donor kidney transplantations performed before or shortly after dialysis initiation having the best outcomes. 110 , 111 As such, early referral (eg, eGFR <30 mL/min/1.73 m 2 and an elevated 2-year risk of ESKD) for transplant evaluation is important. 112 , 113 Alternative therapies for ESKD may include in-center hemodialysis, home hemodialysis, peritoneal dialysis, or conservative care without dialysis. 107 Patient preference should be taken into consideration when selecting dialysis modality; however, patients with multiple abdominal surgeries with resultant peritoneal scarring or unstable housing are likely poor candidates for peritoneal dialysis. 107 , 109 Patients planning for hemodialysis who exhibit rapid decline in eGFR should be referred to an experienced vascular surgeon for arteriovenous fistula placement. The KDOQI guidelines recommend that access creation should occur when eGFR is between 15 and 20 mL/min/1.73 m 2 . 114 Of note, dialysis initiation has been associated with accelerated functional decline and high short-term mortality among older patients with poor functional status. 115 , 116 Patient preferences for conservative approaches to medical management should be discussed and honored.

Conclusions

Chronic kidney disease affects 8% to 16% of the population worldwide and is a leading cause of death. Optimal management of CKD includes cardiovascular risk reduction, treatment of albuminuria, avoidance of potential nephrotoxins, and adjustments to drug dosing. Patients also require monitoring for complications of CKD, such as hyperkalemia, metabolic acidosis, anemia, and other metabolic abnormalities. Diagnosis, staging, and appropriate referral of CKD by primary care clinicians are important in reducing the burden of CKD worldwide.

Funding/Support:

Dr Chen was supported by a Clinician Scientist Career Development Award from Johns Hopkins University and is supported by a George M. O’Brien Center for Kidney Research Pilot and Feasibility Grant from Yale University and award K08DK117068 from the National Institutes of Health/NIDDK. Dr Grams is supported by NIDDK grants DK1008803, DK100446, and DK115534.

Role of the Funder/Sponsor: The supporting institutions had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; or decision to submit the manuscript for publication.

Conflict of Interest Disclosures: Dr Chen reported receipt of grants from the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) and Yale University. Dr Grams reported receipt of grants from the NIDDK and the National Kidney Foundation and travel support from Dialysis Clinics Inc for an invited speakership at a directors’ meeting in May 2019. No other disclosures were reported.

Submissions: We encourage authors to submit papers for consideration as a Review. Please contact Edward Livingston, MD, at Edward. gro.krowtenamaj@notsgnivil or Mary McGrae McDermott, MD, at ude.nretsewhtron@806mdm .

• Open access
• Published: 10 January 2022

Chronic kidney disease and its health-related factors: a case-control study

• Mousa Ghelichi-Ghojogh 1 ,
• Mohammad Fararouei 2 ,
• Mozhgan Seif 3 &
• Maryam Pakfetrat 4  

BMC Nephrology volume  23 , Article number:  24 ( 2022 ) Cite this article

18k Accesses

8 Altmetric

Metrics details

Chronic kidney disease (CKD) is a non-communicable disease that includes a range of different physiological disorders that are associated with abnormal renal function and progressive decline in glomerular filtration rate (GFR). This study aimed to investigate the associations of several behavioral and health-related factors with CKD in Iranian patients.

A hospital-based case-control study was conducted on 700 participants (350 cases and 350 controls). Logistic regression was applied to measure the association between the selected factors and CKD.

The mean age of cases and controls were 59.6 ± 12.4 and 58.9 ± 12.2 respectively ( p  = 0.827). The results of multiple logistic regression suggested that many factors including low birth weight (OR yes/no  = 4.07, 95%CI: 1.76–9.37, P  = 0.001), history of diabetes (OR yes/no  = 3.57, 95%CI: 2.36–5.40, P  = 0.001), history of kidney diseases (OR yes/no  = 3.35, 95%CI: 2.21–5.00, P  = 0.001) and history of chemotherapy (OR yes/no  = 2.18, 95%CI: 1.12–4.23, P  = 0.02) are associated with the risk of CKD.

Conclusions

The present study covered a large number of potential risk/ preventive factors altogether. The results highlighted the importance of collaborative monitoring of kidney function among patients with the above conditions.

Peer Review reports

Chronic kidney disease (CKD) is a non-communicable disease that includes a range of different physiological disorders that are associated with an abnormal renal function and progressive decline in glomerular filtration rate (GFR) [ 1 , 2 , 3 ]. Chronic kidney disease includes five stages of kidney damage, from mild kidney dysfunction to complete failure [ 4 ]. Generally, a person with stage 3 or 4 of CKD is considered as having moderate to severe kidney damage. Stage 3 is broken up into two levels of kidney damage: 3A) a level of GFR between 45 to 59 ml/min/1.73 m 2 , and 3B) a level of GFR between 30 and 44 ml/min/1.73 m 2 . In addition, GFR for stage 4 is 15–29 ml/min/1.73 m 2 [ 4 , 5 ]. It is reported that both the prevalence and burden of CKD are increasing worldwide, especially in developing countries [ 6 ]. The worldwide prevalence of CKD (all stages) is estimated to be between 8 to 16%, a figure that may indicate millions of deaths annually [ 7 ]. According to a meta-analysis, the prevalence of stage 3 to 5 CKD in South Africa, Senegal, and Congo is about 7.6%. In China, Taiwan, and Mongolia the rate of CKD is about 10.06% and in Japan, South Korea, and Oceania the rate is about 11.73%. In Europe the prevalence of CKD is about 11.86% [ 8 ], and finally, about 14.44% in the United States and Canada. The prevalence of CKD is estimated to be about 11.68% among the Iranian adult population and about 2.9% of Iranian women and 1.3% of Iranian men are expected to develop CKD annually [ 9 ]. Patients with stages 3 or 4 CKD are at much higher risk of progressing to either end-stage renal disease (ESRD) or death even prior to the development of ESRD [ 10 , 11 ].

In general, a large number of risk factors including age, sex, family history of kidney disease, primary kidney disease, urinary tract infections, cardiovascular disease, diabetes mellitus, and nephrotoxins (non-steroidal anti-inflammatory drugs, antibiotics) are known as predisposing and initiating factors of CKD [ 12 , 13 , 14 ]. However, the existing studies are suffering from a small sample size of individuals with kidney disease, particularly those with ESRD [ 15 ].

Despite the fact that the prevalence of CKD in the world, including Iran, is increasing, the factors associated with CKD are explored very little. The present case-control study aimed to investigate the association of several behavioral and health-related factors with CKD in the Iranian population.

Materials and methods

In this study, participants were selected among individuals who were registered or were visiting Faghihi and Motahari hospitals (two largest referral centers in the South of Iran located in Shiraz (the capital of Fars province). Cases and controls were frequency-matched by sex and age. The GFR values were calculated using the CKD-EPI formula [ 16 , 17 ].

Data collection

An interview-administered questionnaire and the participant’s medical records were used to obtain the required data. The questionnaire and interview procedure were designed, evaluated, and revised by three experts via conducting a pilot study including 50 cases and 50 controls. The reliability of the questionnaire was measured using the test-retest method (Cronbach’s alpha was 0.75). The interview was conducted by a trained public health‌ nurse at the time of visiting the clinics.

Avoiding concurrent conditions that their association may interpreted as reverse causation; the questionnaire was designed to define factors preceding at least a year before experiencing CKD first symptoms. Accordingly participants reported their social and demographic characteristics (age, sex, marital status, educational level, place of residency), history of chronic diseases (diabetes, cardiovascular diseases, hypertension, kidney diseases, family history of kidney diseases, autoimmune diseases and thyroid diseases [ 18 ]). Also history of other conditions namely (smoking, urinary tract infection (UTI), surgery due to illness or accident, low birth weight, burns, kidney pain (flank pain), chemotherapy, taking drugs for weight loss or obesity, taking non-steroidal anti-inflammatory drugs, and taking antibiotic) before their current condition was started. Many researchers reported recalling birth weight to be reliable for research purposes [ 19 ]. Moreover, we asked the participants to report their birth weight as a categorical variable (< 2500 g or low, 2500- < 3500 g or normal, and > 3500 g or overweight). Medical records of the participants were used to confirm/complete the reported data. In the case of contradiction between the self-reported and recorded data, we used the recorded information for our study.

Verbal informed consent was obtained from patients because the majority of the participants were illiterate. The study protocol was reviewed and approved by the ethical committee of Shiraz University of Medical Sciences (approval number: 1399.865).

Sample size

The sample size was calculated to detect an association‌ between the history of using antibiotics (one of our main study variables) and CKD as small as OR = 1.5 [ 20 ]. With an alpha value of 0.05 (2-sided) and a power of 80%, the required sample size was estimated as large as n  = 312 participants for each group.

Selection of cases

The selected clinics deliver medical care to patients from the southern part of the country. In this study, patients with CKD who were registered with the above centers from June to December 2020 were studied. A case was a patient with a GFR < 60 (ml/min/1.73 m 2 ) at least twice in 3 months. According to the latest version of the International Classification of Diseases (2010), Codes N18.3 and N18.4 are assigned to patients who have (GFR = 30–59 (ml/min/1.73 m 2 ) and GFR = 15–29 (ml/min/1.73 m 2 ) respectively [ 21 ]. In total, 350 patients who were diagnosed with CKD by a nephrologist during the study period.

Selection of the controls

We used hospital controls to avoid recall-bias. The control participants were selected from patients who were admitted to the general surgery (due to hernia, appendicitis, intestinal obstruction, hemorrhoids, and varicose veins), and orthopedic wards‌ from June to December 2020. Using the level of creatinine in the participants’ serum samples, GFR was calculated and the individuals with normal GFR (ml/min/1.73 m 2 ) GFR > 60) and those who reported no history of CKD were included ( n  = 350).

Inclusion criteria

Patients were included if they were ≥ 20 years old and had a definitive diagnosis of CKD by a nephrologist.

Exclusion criteria

Participants were excluded if they were critically ill, had acute kidney injury, those undergone renal transplantation, and those with cognitive impairment.

Statistical analysis

The Chi-square test was used to measure the unadjusted associations between categorical variables and CKD. Multiple logistic regression was applied to measure the adjusted associations for the study variables and CKD. The backward variable selection strategy was used to include variables in the regression model. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated. All p -values were two-sided and the results were considered statistically significant at p  < 0.05. All analyses were conducted using Stata version 14.0 (Stata Corporation, College Station, TX, USA).

In total, 350 cases and 350 age and sex-matched controls were included in the analysis. The mean age of cases and controls were 59.6 ± 12.4 and 58.9 ± 12.2 respectively ( p  = 0.83). Overall, 208 patients (59.4%) and 200 controls (57.1%) were male ( p  = 0.54). Also, 149 patients (42.6%) and 133 controls (38.0%) were illiterate or had elementary education ( p  = 0.001). Most cases (96.9%) and controls (95.7%) were married ( p  = 0.42). The mean GFR for CKD and control groups were 38.6 ± 11.4 and 78.3 ± 10.2 (ml/min/1.73 m2) respectively.

Result of univariate analysis

Table  1 illustrates the unadjusted associations of demographic and health-related variables with CKD. Accordingly, significant (unadjusted) associations were found between the risk of CKD and several study variables including education, history of chronic diseases (diabetes, cardiovascular, hypertension, kidney diseases, autoimmune diseases, and hypothyroidism), family history of kidney diseases, smoking, UTI, surgery due to illness or accident, low birth weight, burns, kidney pain, chemotherapy, taking non-steroidal anti-inflammatory drugs, and taking antibiotics) ( P  < 0.05 for all).

Results of multivariable analysis

Table  2 illustrates the adjusted associations between the study variables and the risk of CKD. Most noticeably, low birth weight (OR yes/no  = 4.07, 95%CI: 1.76–9.37, P  = 0.001), history of surgery (OR yes/no  = 1.74, 95%CI: 1.18–2.54, P  = 0.004), family history of kidney diseases (OR yes/no  = 1.97, 95%CI: 1.20–3.23, P  = 0.007), and history of chemotherapy (OR yes/no  = 2.18, 95%CI: 1.12–4.23, P  = 0.02) were significantly associated with a higher risk of CKD. On the other hand, education (OR college/illiterate or primary  = 0.54, 95%CI: 0.31–0.92, P  = 0.025) was found to be inversely associated with CKD.

The results of the present study suggested that several variables including, education, history of diabetes, history of hypertension, history of kidney diseases or a family history of kidney diseases, history of surgery due to illness or accident, low birth weight, history of chemotherapy, history of taking non-steroidal anti-inflammatory drugs, and history of taking antibiotics may affect the risk of CKD.

In our study, the level of education was inversely associated with the risk of CKD. This finding is in accordance with the results of a study conducted by K Lambert et.al, who suggested that illiteracy or elementary education may raise the risk of CKD [ 22 ]. The fact that education level is associated with health literacy, may partly explain our results that lower education and inadequate health literacy in individuals with CKD is associated with worse health outcomes including poorer control of biochemical parameters, higher risk of cardiovascular diseases (CVDs); a higher rate of hospitalization, and a higher rate of infections [ 23 ].

In the current study, the history of diabetes was associated with a higher risk of CKD. This finding is consistent with the results of other studies on the same subject [ 20 , 21 , 24 , 25 , 26 , 27 ]. It is not surprising that people with diabetes have an increased risk of CKD as diabetes is an important detrimental factor for kidney functioning as approximately, 40% of patients with diabetes develop CKD [ 27 ].

The other variable that was associated with an increased risk of CKD was a history of hypertension. Our result is consistent with the results of several other studies [ 20 , 24 , 25 , 28 ]. It is reported that hypertension is both a cause and effect of CKD and accelerates the progression of the CKD to ESRD [ 29 ].

After controlling for other variables, a significant association was observed between family history of kidney diseases and risk of CKD. Published studies suggested the same pattern [ 24 ]. Inherited kidney diseases (IKDs) are considered as the foremost reasons for the initiation of CKD and are accounted for about 10–15% of kidney replacement therapies (KRT) in adults [ 30 ].

The importance of the history of surgery due to illness or accident in this study is rarely investigated by other researchers who reported the effect of surgery in patients with acute kidney injury (AKI), and major abdominal and cardiac surgeries [ 31 , 32 ] on the risk of CKD. Also, AKI is associated with an increased risk of CKD with progression in various clinical settings [ 33 , 34 , 35 ]. In a study by Mizota et.al, although most AKI cases recovered completely within 7 days after major abdominal surgery, they were at higher risk of 1-year mortality and chronic kidney disease compared to those without AKI [ 31 ].

The present study also showed that low birth weight is a significant risk factor for CKD. This finding is consistent with the results of some other studies. However, the results of very few studies on the association between birth weight and risk of CKD are controversial as some suggested a significant association [ 19 , 36 , 37 ] whereas others suggested otherwise [ 36 ]. This may be explained by the relatively smaller size and volume of kidneys in LBW infants compared to infants that are normally grown [ 38 ]. This can lead to long-term complications in adolescence and adulthood including hypertension, decreased glomerular filtration, albuminuria, and cardiovascular diseases. Eventually, these long-term complications can also cause CKD [ 39 ].

Another important result of the current study is the association between chemotherapy for treating cancers and the risk of CKD. According to a study on chemotherapy for testicular cancer by Inai et al., 1 year after chemotherapy 23% of the patients showed CKD [ 40 ]. Another study suggested that the prevalence of stage 3 CKD among patients with cancer was 12, and < 1% of patients had stage 4 CKD [ 41 , 42 ]. Other studies have shown an even higher prevalence of CKD among cancer patients. For instance, only 38.6% of patients with breast cancer, 38.9% of patients with lung cancer, 38.3% of patients with prostate cancer, 27.5% of patients with gynecologic cancer, and 27.2% of patients with colorectal cancer had a GFR ≥90 (ml/min/1.73 m 2 ) at the time of therapy initiation [ 43 , 44 ]. The overall prevalence of CKD ranges from 12 to 25% across many cancer patients [ 45 , 46 , 47 ]. These results clearly demonstrate that, when patients with cancer develop acute or chronic kidney disease, outcomes are inferior, and the promise of curative therapeutic regimens is lessened.

In our study, the history of taking nephrotoxic agents (antibiotics or NSAIDs drugs) was associated with a higher risk of CKD. Our result is following the results reported by other studies [ 48 , 49 ]. Common agents that are associated with AKI include NSAIDs are different drugs including antibiotics, iodinated contrast media, and chemotherapeutic drugs [ 50 ].

Strengths and limitations of our study

Our study used a reasonably large sample size. In addition, a considerably large number of study variables was included in the study. With a very high participation rate, trained nurses conducted the interviews with the case and control participants in the same setting. However, histories of exposures are prone to recall error (bias), a common issue in the case-control studies. It is to be mentioned that the method of selecting controls (hospital controls) should have reduced the risk of recall bias when reporting the required information. In addition, we used the participants’ medical records to complete/ confirm the reported data. Although the design of the present study was not able to confirm a causal association between the associated variables and CKD, the potential importance and modifiable nature of the associated factors makes the results potentially valuable and easily applicable in the prevention of CKD.

Given that, chemotherapy is an important risk factor for CKD, we suggest the imperative for collaborative care between oncologists and nephrologists in the early diagnosis and treatment of kidney diseases in patients with cancer. Training clinicians and patients are important to reduce the risk of nephrotoxicity. Electronic medical records can simultaneously be used to monitor prescription practices, responsiveness to alerts and prompts, the incidence of CKD, and detecting barriers to the effective implementation of preventive measures [ 51 ]. Routine follow-up and management of diabetic patients is also important for the prevention of CKD. We suggest a tight collaboration between endocrinologists and nephrologists to take care of diabetic patients with kidney problems. In addition, surgeons in major operations should refer patients, especially patients with AKI, to a nephrologist for proper care related to their kidney function. Treatment of hypertension is among the most important interventions to slow down the progression of CKD [ 12 ]. Moreover, all patients with newly diagnosed hypertension should be screened for CKD. We suggest all patients with diabetes have their GFR and urine albumin-to-creatinine ratio (UACR) checked annually. Finally, the aging population and obesity cause the absolute numbers of people with diabetes and kidney diseases to raise significantly. This will require a more integrated approach between dialectologists/nephrologists and the primary care teams (55).

Availability of data and materials

The datasets generated and/or analyzed during the current study are not publicly available due to their being the intellectual property of Shiraz University of Medical Sciences but are available from the corresponding author on reasonable request.

Abbreviations

• Chronic kidney disease

End-stage renal disease

Glomerular filtration rate

Renal replacement treatment

Urinary tract infection

Odds ratios

Confidence intervals

Hypertension

Acute kidney injury

Ghelichi Ghojogh M, Salarilak S, Taghezadeh Afshari A, Khalkhali HR, Mohammadi-Fallah MR, Mkhdoomi K. The effect of body mass index on patient and graft survival rate in kidney transplanted patients in Iran. Nephrourol Monthly. 2017;9(4):e14386.

Zeba Z, Fatema K, Sumit AF, Zinnat R, Ali L. Early screening of chronic kidney disease patients among the asymptomatic adult population in Bangladesh. J Prev Epidemiol. 2020;5(1):e10–e.

Article   Google Scholar  

Mahajan C, Tiwari V, Divyaveer SS, Patil MR, Banerjee A, Bagur V, et al. Spectrum of renal biopsies; a three-year data from a tertiary care Centre of eastern India. J Nephropharmacol. 2020;9(2):e20–e.

Article   CAS   Google Scholar  

Kimura K, Hosoya T, Uchida S, Inaba M, Makino H, Maruyama S, et al. Febuxostat therapy for patients with stage 3 CKD and asymptomatic Hyperuricemia: a randomized trial. Am J Kidney Dis. 2018;72(6):798–810.

Article   CAS   PubMed   Google Scholar  

Foster MC, Hwang S-J, Larson MG, Lichtman JH, Parikh NI, Vasan RS, et al. Overweight, obesity, and the development of stage 3 CKD: the Framingham heart study. Am J Kidney Dis. 2008;52(1):39–48.

Article   PubMed   PubMed Central   Google Scholar  

Rachmi CN, Agho KE, Li M, Baur LA. Stunting, underweight and overweight in children aged 2.0–4.9 years in Indonesia: prevalence trends and associated risk factors. PLoS One. 2016;11(5):e0154756.

Asghari G, Momenan M, Yuzbashian E, Mirmiran P, Azizi F. Dietary pattern and incidence of chronic kidney disease among adults: a population-based study. Nutr Metab. 2018;15(1):1–11.

Ruggles DR, Freyman RL, Oxenham AJ. Influence of musical training on understanding voiced and whispered speech in noise. PLoS One. 2014;9(1):e86980.

Moazzeni SS, Arani RH, Hasheminia M, Tohidi M, Azizi F, Hadaegh F. High incidence of chronic kidney disease among Iranian diabetic adults: using CKD-EPI and MDRD equations for estimated glomerular filtration rate. Korean Diabetes J. 2021;45(5):684-97.

Salam SN, Eastell R, Khwaja A. Fragility fractures and osteoporosis in CKD: pathophysiology and diagnostic methods. Am J Kidney Dis. 2014;63(6):1049–59.

Zahmatkesh M, Tamadon MR. World kidney day 2018; chronic kidney disease in women. J Nephropathol. 2017;7(1):4–6.

Noble R, Taal MW. Epidemiology and causes of chronic kidney disease. Medicine. 2019;47(9):562–6.

Lopez-Garcia E, Schulze MB, Fung TT, Meigs JB, Rifai N, Manson JE, et al. Major dietary patterns are related to plasma concentrations of markers of inflammation and endothelial dysfunction. Am J Clin Nutr. 2004;80(4):1029–35.

Sepahi MA, Niknafs B. Multifaceted role of apolipoprotein L1 risk variants and nephropathy. J Nephropathol. 2020;9(1):1-3.

Cohen JB, Tewksbury CM, Landa ST, Williams NN, Dumon KR. National postoperative bariatric surgery outcomes in patients with chronic kidney disease and end-stage kidney disease. Obes Surg. 2019;29(3):975–82.

Levey AS, Andreoli SP, DuBose T, Provenzano R, Collins AJ. Chronic kidney disease: common, harmful and treatable–world kidney day 2007. Am J Nephrol. 2007;27(1):108–12.

Article   PubMed   Google Scholar  

Argulian E, Sherrid MV, Messerli FH. Misconceptions and facts about hypertrophic cardiomyopathy. Am J Med. 2016;129(2):148–52.

Rhee CM. The interaction between thyroid and kidney disease: an overview of the evidence. Curr Opin Endocrinol Diabetes Obes. 2016;23(5):407.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Al Salmi I, Hoy WE, Kondalsamy-Chennakes S, Wang Z, Healy H, Shaw JE. Birth weight and stages of CKD: a case-control study in an Australian population. Am J Kidney Dis. 2008;52(6):1070–8.

Yacoub R, Habib H, Lahdo A, Al Ali R, Varjabedian L, Atalla G, et al. Association between smoking and chronic kidney disease: a case control study. BMC Public Health. 2010;10(1):1–6.

Saucier NA, Sinha MK, Liang KV, Krambeck AE, Weaver AL, Bergstralh EJ, et al. Risk factors for CKD in persons with kidney stones: a case-control study in Olmsted County, Minnesota. Am J Kidney Dis. 2010;55(1):61–8.

Lambert K, Mullan J, Mansfield K, Lonergan M. A cross-sectional comparison of health literacy deficits among patients with chronic kidney disease. J Health Commun. 2015;20(sup2):16–23.

Fraser SD, Roderick PJ, Casey M, Taal MW, Yuen HM, Nutbeam D. Prevalence and associations of limited health literacy in chronic kidney disease: a systematic review. Nephrol Dial Transplant. 2013;28(1):129–37.

Ji MY, Park YS, Yi SE. A case-control study to identify the risk factors of school accidents. Korean J Epidemiol. 2005;27(2):80–94.

Google Scholar  

Khajehdehi P, Malekmakan L, Pakfetrat M, Roozbeh J, Sayadi M. Prevalence of chronic kidney disease and its contributing risk factors in southern Iran a cross-sectional adult population-based study; 2014.

Li H, Lu W, Wang A, Jiang H, Lyu J. Changing epidemiology of chronic kidney disease as a result of type 2 diabetes mellitus from 1990 to 2017: estimates from global burden of disease 2017. J Diabetes Investig. 2021;12(3):346.

Xu Y, Surapaneni A, Alkas J, Evans M, Shin J-I, Selvin E, et al. Glycemic control and the risk of acute kidney injury in patients with type 2 diabetes and chronic kidney disease: parallel population-based cohort studies in US and Swedish routine care. Diabetes Care. 2020;43(12):2975–82.

Sepanlou SG, Barahimi H, Najafi I, Kamangar F, Poustchi H, Shakeri R, et al. Prevalence and determinants of chronic kidney disease in northeast of Iran: results of the Golestan cohort study. PLoS One. 2017;12(5):e0176540.

Pugh D, Gallacher PJ, Dhaun N. Management of hypertension in chronic kidney disease. Drugs. 2019;79(4):365–79.

Torra R, Furlano M, Ortiz A, Ars E. Genetic kidney diseases as an underecognized cause of chronic kidney disease: the key role of international registry reports. Clin Kidney J. 2021;14(8):1879-85.

Mizota T, Dong L, Takeda C, Shiraki A, Matsukawa S, Shimizu S, et al. Transient acute kidney injury after major abdominal surgery increases chronic kidney disease risk and 1-year mortality. J Crit Care. 2019;50:17–22.

Madsen NL, Goldstein SL, Frøslev T, Christiansen CF, Olsen M. Cardiac surgery in patients with congenital heart disease is associated with acute kidney injury and the risk of chronic kidney disease. Kidney Int. 2017;92(3):751–6.

Newsome BB, Warnock DG, McClellan WM, Herzog CA, Kiefe CI, Eggers PW, et al. Long-term risk of mortality and end-stage renal disease among the elderly after small increases in serum creatinine level during hospitalization for acute myocardial infarction. Arch Intern Med. 2008;168(6):609–16.

Ishani A, Nelson D, Clothier B, Schult T, Nugent S, Greer N, et al. The magnitude of acute serum creatinine increase after cardiac surgery and the risk of chronic kidney disease, progression of kidney disease, and death. Arch Intern Med. 2011;171(3):226–33.

James MT, Ghali WA, Knudtson ML, Ravani P, Tonelli M, Faris P, et al. Associations between acute kidney injury and cardiovascular and renal outcomes after coronary angiography. Circulation. 2011;123(4):409–16.

Esmeijer K, de Vries AP, Mook-Kanamori DO, de Fijter JW, Rosendaal FR, Rabelink TJ, et al. Low birth weight and kidney function in middle-aged men and women: the Netherlands epidemiology of obesity study. Am J Kidney Dis. 2019;74(6):751–60.

White SL, Perkovic V, Cass A, Chang CL, Poulter NR, Spector T, et al. Is low birth weight an antecedent of CKD in later life? A systematic review of observational studies. Am J Kidney Dis. 2009;54(2):248–61.

Harer MW, Charlton JR, Tipple TE, Reidy KJ. Preterm birth and neonatal acute kidney injury: implications on adolescent and adult outcomes. J Perinatol. 2020;40(9):1286–95.

Al Salmi I, Hannawi S. Birth weight and susceptibility to chronic kidney disease. Saudi J Kidney Dis Transplant. 2020;31(4):717.

Inai H, Kawai K, Ikeda A, Ando S, Kimura T, Oikawa T, et al. Risk factors for chronic kidney disease after chemotherapy for testicular cancer. Int J Urol. 2013;20(7):716–22.

Launay-Vacher V, Oudard S, Janus N, Gligorov J, Pourrat X, Rixe O, et al. Prevalence of renal insufficiency in cancer patients and implications for anticancer drug management: the renal insufficiency and anticancer medications (IRMA) study. Cancer. 2007;110(6):1376–84.

Launay-Vacher V. Epidemiology of chronic kidney disease in cancer patients: lessons from the IRMA study group. Semin Nephrol. 2010;30(6):548–56.

Launay-Vacher V, Janus N, Deray G. Renal insufficiency and cancer treatments. ESMO Open. 2016;1(4):e000091.

Janus N, Launay-Vacher V, Byloos E, Machiels JP, Duck L, Kerger J, et al. Cancer and renal insufficiency results of the BIRMA study. Br J Cancer. 2010;103(12):1815–21.

Kitchlu A, McArthur E, Amir E, Booth CM, Sutradhar R, Majeed H, et al. Acute kidney injury in patients receiving systemic treatment for Cancer: a population-based cohort study. J Natl Cancer Inst. 2019;111(7):727–36.

Kidney Disease Improving Global Outcomes (KDIGO). KDIGO clinical practice guideline for acute kidney injury. kdigo.org/wpcontent/uploads/2016/10/KDIGO-2012-AKI-Guide line-Engli sh.pdf . Accessed 23 Mar 2020.

Königsbrügge O, Lötsch F, Zielinski C, Pabinger I, Ay C. Chronic kidney disease in patients with cancer and its association with occurrence of venous thromboembolism and mortality. Thromb Res. 2014;134(1):44–9.

Goldstein SL, Mottes T, Simpson K, Barclay C, Muething S, Haslam DB, et al. A sustained quality improvement program reduces nephrotoxic medication-associated acute kidney injury. Kidney Int. 2016;90(1):212–21.

Menon S, Kirkendall ES, Nguyen H, Goldstein SL. Acute kidney injury associated with high nephrotoxic medication exposure leads to chronic kidney disease after 6 months. J Pediatr. 2014;165(3):522–7.e2.

Perazella MA, Izzedine H. New drug toxicities in the onco-nephrology world. Kidney Int. 2015;87(5):909–17.

Luyckx VA, Tuttle KR, Garcia-Garcia G, Gharbi MB, Heerspink HJL, Johnson DW, et al. Reducing major risk factors for chronic kidney disease. Kidney Int Suppl. 2017;7(2):71–87.

Download references

Acknowledgments

This paper is part of a thesis conducted by Mousa Ghelichi-Ghojogh, Ph.D. student of epidemiology, and a research project conducted at the Shiraz University of Medical sciences (99-01-04-22719). We would like to thank Dr. Bahram Shahryari and all nephrologists of Shiraz‌ University of medical sciences, interviewers, and CKD patients in Shiraz for their voluntary participation in the study and for providing data for the study.

Shiraz University of Medical Sciences financially supported this study. (Grant number: 99–01–04-22719).

Author information

Authors and affiliations.

Candidate in Epidemiology, Student Research Committee, Shiraz University of Medical Sciences, Shiraz, Iran

Mousa Ghelichi-Ghojogh

HIV/AIDS research center, School of Health, Shiraz University of Medical Sciences, P.O.Box: 71645-111, Shiraz, Iran

Mohammad Fararouei

Department of Epidemiology, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran

Mozhgan Seif

Nephrologist, Shiraz Nephro-Urology Research Center, Department of Internal Medicine, Emergency Medicine Research Center, Shiraz University of Medical Sciences, Shiraz, Iran

Maryam Pakfetrat

You can also search for this author in PubMed   Google Scholar

Contributions

MGG: Conceptualization, Methodology, Statistical analysis, Investigation, and writing the draft of the manuscript. MP: were involved in methodology, writing the draft of the manuscript, and clinical consultation. MS: was involved in the methodology and statistical analysis. MF: was involved in conceptualization, methodology, supervision, writing, and reviewing the manuscript. The authors read and approved the final manuscript.

Corresponding author

Correspondence to Mohammad Fararouei .

Ethics declarations

Ethics approval and consent to participate.

The study protocol was reviewed and approved by the ethical committee of Shiraz University of Medical Sciences (approval number: 1399.865). All methods were performed in accordance with the relevant guidelines and regulations of the Declaration of Helsinki. The participants were assured that their information is used for research purposes only. Because of the illiteracy of a considerable number of the patients, verbal informed consent was obtained from the participants. Using verbal informed consent was also granted by the ethical committee of Shiraz University of Medical Sciences.

Consent for publication

Not applicable.

Competing interests

None of the authors declare disclosures of direct relevance to the submitted work.

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.

Ghelichi-Ghojogh, M., Fararouei, M., Seif, M. et al. Chronic kidney disease and its health-related factors: a case-control study. BMC Nephrol 23 , 24 (2022). https://doi.org/10.1186/s12882-021-02655-w

Download citation

Received : 14 August 2021

Accepted : 24 December 2021

Published : 10 January 2022

DOI : https://doi.org/10.1186/s12882-021-02655-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

• Related factors
• Case-control

BMC Nephrology

ISSN: 1471-2369

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

Featured Clinical Reviews

• Screening for Atrial Fibrillation: US Preventive Services Task Force Recommendation Statement JAMA Recommendation Statement January 25, 2022
• Evaluating the Patient With a Pulmonary Nodule: A Review JAMA Review January 18, 2022
• Download PDF
• Share X Facebook Email LinkedIn
• Permissions

Chronic Kidney Disease Diagnosis and Management : A Review

• 1 Division of Nephrology, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
• 2 Welch Center for Prevention, Epidemiology, and Clinical Research, Johns Hopkins Medical Institutions, Baltimore, Maryland

Importance   Chronic kidney disease (CKD) is the 16th leading cause of years of life lost worldwide. Appropriate screening, diagnosis, and management by primary care clinicians are necessary to prevent adverse CKD-associated outcomes, including cardiovascular disease, end-stage kidney disease, and death.

Observations   Defined as a persistent abnormality in kidney structure or function (eg, glomerular filtration rate [GFR] <60 mL/min/1.73 m 2 or albuminuria ≥30 mg per 24 hours) for more than 3 months, CKD affects 8% to 16% of the population worldwide. In developed countries, CKD is most commonly attributed to diabetes and hypertension. However, less than 5% of patients with early CKD report awareness of their disease. Among individuals diagnosed as having CKD, staging and new risk assessment tools that incorporate GFR and albuminuria can help guide treatment, monitoring, and referral strategies. Optimal management of CKD includes cardiovascular risk reduction (eg, statins and blood pressure management), treatment of albuminuria (eg, angiotensin-converting enzyme inhibitors or angiotensin II receptor blockers), avoidance of potential nephrotoxins (eg, nonsteroidal anti-inflammatory drugs), and adjustments to drug dosing (eg, many antibiotics and oral hypoglycemic agents). Patients also require monitoring for complications of CKD, such as hyperkalemia, metabolic acidosis, hyperphosphatemia, vitamin D deficiency, secondary hyperparathyroidism, and anemia. Those at high risk of CKD progression (eg, estimated GFR <30 mL/min/1.73 m 2 , albuminuria ≥300 mg per 24 hours, or rapid decline in estimated GFR) should be promptly referred to a nephrologist.

Conclusions and Relevance   Diagnosis, staging, and appropriate referral of CKD by primary care clinicians are important in reducing the burden of CKD worldwide.

Read More About

Chen TK , Knicely DH , Grams ME. Chronic Kidney Disease Diagnosis and Management : A Review . JAMA. 2019;322(13):1294–1304. doi:10.1001/jama.2019.14745

Manage citations:

© 2024

Artificial Intelligence Resource Center

Cardiology in JAMA : Read the Latest

Browse and subscribe to JAMA Network podcasts!

Others Also Liked

Select your interests.

Customize your JAMA Network experience by selecting one or more topics from the list below.

• Academic Medicine
• Acid Base, Electrolytes, Fluids
• Allergy and Clinical Immunology
• American Indian or Alaska Natives
• Anesthesiology
• Anticoagulation
• Art and Images in Psychiatry
• Artificial Intelligence
• Assisted Reproduction
• Bleeding and Transfusion
• Caring for the Critically Ill Patient
• Challenges in Clinical Electrocardiography
• Climate and Health
• Climate Change
• Clinical Challenge
• Clinical Decision Support
• Clinical Implications of Basic Neuroscience
• Clinical Pharmacy and Pharmacology
• Complementary and Alternative Medicine
• Consensus Statements
• Coronavirus (COVID-19)
• Critical Care Medicine
• Cultural Competency
• Dental Medicine
• Dermatology
• Diabetes and Endocrinology
• Diagnostic Test Interpretation
• Drug Development
• Electronic Health Records
• Emergency Medicine
• End of Life, Hospice, Palliative Care
• Environmental Health
• Equity, Diversity, and Inclusion
• Facial Plastic Surgery
• Gastroenterology and Hepatology
• Genetics and Genomics
• Genomics and Precision Health
• Global Health
• Guide to Statistics and Methods
• Hair Disorders
• Health Care Delivery Models
• Health Care Economics, Insurance, Payment
• Health Care Quality
• Health Care Reform
• Health Care Safety
• Health Care Workforce
• Health Disparities
• Health Inequities
• Health Policy
• Health Systems Science
• History of Medicine
• Hypertension
• Images in Neurology
• Implementation Science
• Infectious Diseases
• Innovations in Health Care Delivery
• JAMA Infographic
• Law and Medicine
• Leading Change
• Less is More
• LGBTQIA Medicine
• Lifestyle Behaviors
• Medical Coding
• Medical Devices and Equipment
• Medical Education
• Medical Education and Training
• Medical Journals and Publishing
• Mobile Health and Telemedicine
• Narrative Medicine
• Neuroscience and Psychiatry
• Notable Notes
• Nutrition, Obesity, Exercise
• Obstetrics and Gynecology
• Occupational Health
• Ophthalmology
• Orthopedics
• Otolaryngology
• Pain Medicine
• Palliative Care
• Pathology and Laboratory Medicine
• Patient Care
• Patient Information
• Performance Improvement
• Performance Measures
• Perioperative Care and Consultation
• Pharmacoeconomics
• Pharmacoepidemiology
• Pharmacogenetics
• Pharmacy and Clinical Pharmacology
• Physical Medicine and Rehabilitation
• Physical Therapy
• Physician Leadership
• Population Health
• Primary Care
• Professional Well-being
• Professionalism
• Psychiatry and Behavioral Health
• Public Health
• Pulmonary Medicine
• Regulatory Agencies
• Reproductive Health
• Research, Methods, Statistics
• Resuscitation
• Rheumatology
• Risk Management
• Scientific Discovery and the Future of Medicine
• Shared Decision Making and Communication
• Sleep Medicine
• Sports Medicine
• Stem Cell Transplantation
• Substance Use and Addiction Medicine
• Surgical Innovation
• Surgical Pearls
• Teachable Moment
• Technology and Finance
• The Art of JAMA
• The Arts and Medicine
• The Rational Clinical Examination
• Tobacco and e-Cigarettes
• Translational Medicine
• Trauma and Injury
• Treatment Adherence
• Ultrasonography
• Users' Guide to the Medical Literature
• Vaccination
• Venous Thromboembolism
• Veterans Health
• Women's Health
• Workflow and Process
• Wound Care, Infection, Healing
• Register for email alerts with links to free full-text articles
• Access PDFs of free articles
• Manage your interests
• Save searches and receive search alerts

Advertisement

Chronic Kidney Disease Prediction Using Machine Learning Techniques

• Original Paper
• Published: 31 August 2022
• Volume 1 , pages 534–540, ( 2023 )

Cite this article

• Saurabh Pal   ORCID: orcid.org/0000-0001-9545-7481 1  

6346 Accesses

10 Citations

Explore all metrics

Chronic kidney disease (CKD) is a life-threatening condition that can be difficult to diagnose early because there are no symptoms. The purpose of the proposed study is to develop and validate a predictive model for the prediction of chronic kidney disease. Machine learning algorithms are often used in medicine to predict and classify diseases. Medical records are often skewed. We have used chronic kidney disease dataset from UCI Machine learning repository with 25 features and applied three machine learning classifiers Logistic Regression (LR), Decision Tree (DT), and Support Vector Machine (SVM) for analysis and then used bagging ensemble method to improve the results of the developed model. The clusters of the chronic kidney disease dataset were used to train the machine learning classifiers. Finally, the Kidney Disease Collection is summarized by category and non-linear features. We get the best result in the case of decision tree with accuracy of 95.92%. Finally, after applying the bagging ensemble method we get the highest accuracy of 97.23%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda

Yogesh Kumar, Apeksha Koul, … Muhammad Fazal Ijaz

Heart Disease Prediction using Machine Learning Techniques

Devansh Shah, Samir Patel & Santosh Kumar Bharti

Comparing different supervised machine learning algorithms for disease prediction

Shahadat Uddin, Arif Khan, … Mohammad Ali Moni

Aljaaf, A.J. 2018 Early Prediction of Chronic Kidney Disease Using Machine Learning Supported by Predictive Analytics. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC). Wellington. New Zealand

A. Nishanth, T. Thiruvaran, Identifying important attributes for early detection of chronic kidney disease. IEEE Rev. Biomed. Eng. 11 , 208–216 (2018)

Article   Google Scholar  

A. Ogunleye, Q.-G. Wang, XGBoost model for chronic kidney disease diagnosis. IEEE/ACM Trans. Comput. Biol. Bioinform. 17 , 2131–2140 (2020)

F. Aqlan, R. Markle, A. Shamsan, "Data mining for chronic kidney disease prediction." in IIE Annual Conference. Proceedings, Institute of Industrial and Systems Engineers , (IISE 2017), pp. 1789–1794

N. Borisagar, D. Barad, P. Raval, Chronic kidney disease prediction using back propagation neural network algorithm. Proce. Int. Confe. Commun. Netw. 19–20 , 295–303 (2017)

Google Scholar  

C. Bemando, E. Miranda, M. Aryuni, "Machine-Learning-Based Prediction Models of Coronary Heart Disease Using Naïve Bayes and Random Forest Algorithms," in 2021 International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM) , (IEEE, 2021), pp. 232–237

R.P. Ram Kumar, SanjeevaPolepaka, Performance comparison of random forest classifier and convolution neural network in predicting heart diseases, in Proceedings of the Third International Conference on Computational Intelligence and Informatics . ed. by K. SrujanRaju, A. Govardhan, B. PadmajaRani, R. Sridevi, M. Ramakrishna Murty (Springer, Singapore, 2020)

H. Singh, N. V. Navaneeth, G. N. Pillai, "Multisurface proximal SVM based decision trees for heart disease classification," in TENCON 2019-2019 IEEE Region 10 Conference (TENCON) , (IEEE 2019), pp. 13–18

S.D. Desai, S. Giraddi, P. Narayankar, N.R. Pudakalakatti, S. Sulegaon, Backpropagation neural network versus logistic regression in heart disease classification in advanced computing and communication technologies (Springer, Singapore, 2019)

D.D. Patil, R.P. Singh, V.M. Thakare, A.K. Gulve, Analysis of ecg arrhythmia for heart disease detection using svm and cuckoo search optimized neural network. Int. J. Eng. Technol. 7 (217), 27–33 (2018)

N. Liu, Z. Lin, J. Cao, Z. Koh, T. Zhang, G.-B. Huang, W. Ser, M.E.H. Ong, An intelligent scoring system and its application to cardiac arrest prediction. IEEE Trans. Inf Technol. Biomed. 16 (6), 1324–1331 (2012)

U. Rajendra Acharya, Oh. Shu Lih, Y. Hagiwara, J.H. Tan, M. Adam, A. Gertych, R.S. Tan, A deep convolutional neural network model to classify heartbeats. Comput. Biol. Med. 89 , 389–396 (2017)

R.S. Walse, G.D. Kurundkar, S.D. Khamitkar, A.A. Muley, P.U. Bhalchandra, S.N. Lokhande, Effective use of naïve bayes, decision tree, and random forest techniques for analysis of chronic kidney disease, in International Conference on Information and Communication Technology for Intelligent Systems . ed. by T. Senjyu, P.N. Mahalle, T. Perumal, A. Joshi (Springer, Singpore, 2020)

A. Nithya, A. Appathurai, N. Venkatadri, D.R. Ramji, C.A. Palagan, Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement (2020). https://doi.org/10.1016/j.measurement.2019.106952

Abdullah Al Imran, Md Nur Amin, and Fatema Tuj Johora. Classification of chronic kidney disease using logistic regression, feedforward neural network and wide & deep learning. In 2018 International Conference on Innovation in Engineering and Technology (ICIET), pages 1–6. IEEE, 2018.

B. Navaneeth, M. Suchetha, A dynamic pooling based convolutional neural network approach to detect chronic kidney disease. Biomed. Signal Proce. Control 62 , 102068 (2020)

A. Brunetti, G.D. Cascarano, I. De Feudis, M. Moschetta, L. Gesualdo, V. Bevilacqua, Detection and segmentation of kidneys from magnetic resonance images in patients with autosomal dominant polycystic kidney disease, in International Conference on Intelligent Computing . ed. by D.-S. Huang, K.-H. Jo, Z.-K. Huang (Springer International Publishing, Cham, 2019)

D. Ramos et al., Using decision tree to select forecasting algorithms in distinct electricity consumption context of an office building. Energy Rep. 8 , 417–422 (2022)

H.E. Song et al., Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest. Chemosphere 290 , 133388 (2022)

H.U. Rongyao et al., Multi-task multi-modality SVM for early COVID-19 diagnosis using chest CT data. Inf. Proc. Manag. 59 (1), 102782 (2022)

X.U. Ankun et al., Artificial neural network (ANN) modeling for the prediction of odor emission rates from landfill working surface. Waste Manag. 138 , 158–171 (2022)

D.C. Yadav, S. Pal, An Ensemble Approach on the behalf of Classification and Prediction of Diabetes Mellitus Disease Emerging Trends in Data Driven Computing and Communications (Springer, Singapore, 2021)

D.C. Yadav, S. Pal, Performance based evaluation of algorithms on chronic kidney disease using hybrid ensemble model in machine learning. Biomed. Pharmacol. J. 14 (3), 1633–1646 (2021)

D.C. Yadav, S. Pal, Discovery of Thyroid Disease Using Different Ensemble Methods with Reduced Error Pruning Technique, in Computer-aided Design and Diagnosis Methods on the behalf of Biomedical Applications . ed. by G.R. Varun Bajaj, V.B. Sinha, G.R. Sinha (CRC Press, Boca Raton, 2021)

A. Zoda et al., Inferring genetic characteristics of Japanese Black cattle populations using genome-wide single nucleotide polymorphism markers. J. Animal Genet. 50 (1), 3–9 (2022)

G.M. Ifraz, M.H. Rashid, T. Tazin, S. Bourouis, M.M. Khan, Comparative analysis for prediction of kidney disease using intelligent machine learning methods. Comput. Math. Methods Med. (2021). https://doi.org/10.1155/2021/6141470

S. Krishnamurthy, K.S. Kapeleshh, E. Dovgan, M. Luštrek, B.G. Piletič, K. Srinivasan, Y.C. Li, A. Gradišek, S. Syed-Abdul, "Machine learning prediction models for chronic kidney disease using national health insurance claim data in Taiwan." medRxiv. (2020). https://doi.org/10.1101/2020.06.25.20139147

Z.U. Rehman, M.S. Zia, G.R. Bojja, M. Yaqub, F. Jinchao, K. Arshid, Texture based localization of a brain tumor from MR-images by using a machine learning approach. Med. Hypotheses 141 , 109705 (2020)

X. Han, X. Zheng, Y. Wang, X. Sun, Y. Xiao, Y. Tang, W. Qin, Random forest can accurately predict the development of end-stage renal disease in immunoglobulin a nephropathy patient. Annals Transl. Med. (2019). https://doi.org/10.21037/atm.2018.12.11

E.H.A. Rady, A.S. Anwar, Prediction of kidney disease stages using data mining algorithms. Inform. Med. Unlocked (2019). https://doi.org/10.1016/j.imu.2019.100178

Z. Dong, Q. Wang, Y. Ke, W. Zhang, Q. Hong, C. Liu, X. Chen, Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records. J. Transl. Med. 20 (1), 1–10 (2022)

D.C. Yadav, S. Pal, Prediction of thyroid disease using decision tree ensemble method. Human-Intell. Syst. Integr. 2 (1), 89–95 (2020)

V. Chaurasia, S. Pal, Applications of machine learning techniques to predict diagnostic breast cancer. SN Compu. Sci. 1 (5), 1–11 (2020)

Chaurasia, V., & Pal, S. (2014). Performance analysis of data mining algorithms for diagnosis and prediction of heart and breast cancer disease. Review of research. 3(8).

Download references

Acknowledgements

Author thanks to Veer Bahadur Singh Purvanchal University, Jaunpur for providing the support for conducting this research work as a part of minor project “Analysis of Hidden Pattern and Discover Real Fact of Medical Diseases using Integrated Machine Learning Techniques.

Author information

Authors and affiliations.

Department of Computer Applications, VBS Purvanchal University, Jaunpur, India

Saurabh Pal

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Saurabh Pal .

Ethics declarations

Conflict of interest.

Author declares no conflict of interest.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Pal, S. Chronic Kidney Disease Prediction Using Machine Learning Techniques. Biomedical Materials & Devices 1 , 534–540 (2023). https://doi.org/10.1007/s44174-022-00027-y

Download citation

Received : 20 April 2022

Accepted : 16 August 2022

Published : 31 August 2022

Issue Date : March 2023

DOI : https://doi.org/10.1007/s44174-022-00027-y

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

• Chronic kidney disease
• Decision Tree
• Support Vector Machine
• Logistic Regression and Bagging Ensemble Method
• Find a journal
• Publish with us
• Track your research

• Alzheimer's disease & dementia
• Arthritis & Rheumatism
• Attention deficit disorders
• Autism spectrum disorders
• Biomedical technology
• Diseases, Conditions, Syndromes
• Endocrinology & Metabolism
• Gastroenterology
• Gerontology & Geriatrics
• Health informatics
• Inflammatory disorders
• Medical economics
• Medical research
• Medications
• Neuroscience
• Obstetrics & gynaecology
• Oncology & Cancer
• Ophthalmology
• Overweight & Obesity
• Parkinson's & Movement disorders
• Psychology & Psychiatry
• Radiology & Imaging
• Sleep disorders
• Sports medicine & Kinesiology
• Vaccination
• Breast cancer
• Cardiovascular disease
• Chronic obstructive pulmonary disease
• Colon cancer
• Coronary artery disease
• Heart attack
• Heart disease
• High blood pressure
• Kidney disease
• Lung cancer
• Multiple sclerosis
• Myocardial infarction
• Ovarian cancer
• Post traumatic stress disorder
• Rheumatoid arthritis
• Schizophrenia
• Skin cancer
• Type 2 diabetes
• Full List »

share this!

March 29, 2024

This article has been reviewed according to Science X's editorial process and policies . Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

Optimizing chronic kidney disease management through a learning health system approach

by Health Data Science

A recent publication in Health Data Science offers an in-depth exploration of an innovative approach to chronic kidney disease (CKD) management through the adoption of a learning health system (LHS) model. The study underscores a transformative shift towards more responsive and efficient health care practices, especially in managing pervasive conditions like CKD.

In the realm of medicine, the journey from research discovery to clinical application is notoriously protracted, often spanning nearly two decades. The LHS framework seeks to dramatically shorten this trajectory by leveraging real-time data analytics, thereby expediting the translation of research insights into practical health care interventions.

Associate Research Professor Guilan Kong of the National Institute of Health Data Science (NIHDS) at Peking University highlights the critical role of LHS in accelerating the data-to-evidence-to-practice continuum, an advancement he views as crucial for improving global health outcomes in the digital age.

Targeting CKD, a condition that is both widespread and undermanaged in China, the research team piloted an LHS initiative in Yinzhou, a district distinguished by its sophisticated Regional Health Information Platform (YRHIP) operational since 2009. This platform, integral to the local health care landscape, collects comprehensive patient data across various medical institutions and has been instrumental in developing a specialized CKD surveillance system initiated in 2018.

The project's inception involved assembling a diverse learning community, including medical practitioners , IT specialists, and data scientists, who collaboratively assessed CKD care in Yinzhou, identifying and addressing critical care delivery gaps. This collective effort enabled the identification of CKD patients through an advanced computable tool, facilitating targeted intervention by primary care providers.

The researchers emphasize the potential of integrating predictive analytics and clinical decision support mechanisms into the YRHIP, aiming to enhance patient triage, streamline referrals, and encourage the adoption of clinical guidelines.

Professor Luxia Zhang of NIHDS reflects on the pilot's promising outcomes, suggesting that a robust LHS infrastructure can significantly catalyze the adoption of evidence-based health care solutions. Although LHS models are prevalent in more affluent settings, their application in less economically developed regions presents unique challenges and opportunities for innovation.

As the team looks to the future, they plan to refine CKD predictive analytics and further integrate these technologies into Yinzhou's health care framework, a step Prof Kong believes will empower physicians to make more informed decisions, thereby elevating the standard of CKD care.

Explore further

Feedback to editors

New study maps a group of rare genetic diseases for the first time

1 minute ago

Early cortical remyelination has a neuroprotective effect in multiple sclerosis, study shows

29 minutes ago

Novel compound AC102 restores hearing in preclinical models of sudden hearing loss

52 minutes ago

New study seeks hereditary causes of childhood cancer

54 minutes ago

Scientists link certain gut bacteria to lower heart disease risk

Study finds triple-negative breast cancer tumors with increased immune cells have lower risk of recurrence after surgery

Study finds AI empowers patients before and after seeing physicians for radiation oncology treatment

Infant gut microbes have their own circadian rhythm: Study finds diet has little impact on how the microbiome assembles

New insights into how tumors on adrenal glands develop

Gene analysis generates spatial map of intestinal cells and traces their trajectories during gut inflammation

Related stories.

Predicting optimal medical interventions

Feb 23, 2024

Importance of physician-led team-based care underscored in new ACP policy

Dec 27, 2023

The role of the clinician-data-scientist in health care

Oct 12, 2022

Researchers identify physician and patient concerns around COVID digital detection surveillance in China

Jan 23, 2023

Computerized decision support system helps to reduce cardiovascular risk factors in patients with diabetes

Dec 6, 2022

National ICU registries as enablers of clinical research and quality improvement

Oct 18, 2023

Recommended for you

Researchers develop more broadly protective coronavirus vaccine

20 hours ago

Chatbot outperforms physicians in clinical reasoning, but also underperforms against residents on many occasions

'Pathogen prospecting': Mosquito researchers track malaria's history by examining its epidemiology

19 hours ago

Person is diagnosed with bird flu after being in contact with cows in Texas

Smartphone app may pave way to treatments for frontotemporal dementia in under-60s

Apr 1, 2024

Let us know if there is a problem with our content

Use this form if you have come across a typo, inaccuracy or would like to send an edit request for the content on this page. For general inquiries, please use our contact form . For general feedback, use the public comments section below (please adhere to guidelines ).

Please select the most appropriate category to facilitate processing of your request

Thank you for taking time to provide your feedback to the editors.

Your feedback is important to us. However, we do not guarantee individual replies due to the high volume of messages.

E-mail the story

Your email address is used only to let the recipient know who sent the email. Neither your address nor the recipient's address will be used for any other purpose. The information you enter will appear in your e-mail message and is not retained by Medical Xpress in any form.

Newsletter sign up

Get weekly and/or daily updates delivered to your inbox. You can unsubscribe at any time and we'll never share your details to third parties.

More information Privacy policy

Donate and enjoy an ad-free experience

We keep our content available to everyone. Consider supporting Science X's mission by getting a premium account.

E-mail newsletter

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 19 May 2022

Machine learning to predict end stage kidney disease in chronic kidney disease

• Qiong Bai 1 ,
• Chunyan Su 1 ,
• Wen Tang 1 &
• Yike Li 2  

Scientific Reports volume  12 , Article number:  8377 ( 2022 ) Cite this article

11k Accesses

28 Citations

22 Altmetric

Metrics details

• Chronic kidney disease
• End-stage renal disease
• Kidney diseases

The purpose of this study was to assess the feasibility of machine learning (ML) in predicting the risk of end-stage kidney disease (ESKD) from patients with chronic kidney disease (CKD). Data were obtained from a longitudinal CKD cohort. Predictor variables included patients’ baseline characteristics and routine blood test results. The outcome of interest was the presence or absence of ESKD by the end of 5 years. Missing data were imputed using multiple imputation. Five ML algorithms, including logistic regression, naïve Bayes, random forest, decision tree, and K-nearest neighbors were trained and tested using fivefold cross-validation. The performance of each model was compared to that of the Kidney Failure Risk Equation (KFRE). The dataset contained 748 CKD patients recruited between April 2006 and March 2008, with the follow-up time of 6.3 ± 2.3 years. ESKD was observed in 70 patients (9.4%). Three ML models, including the logistic regression, naïve Bayes and random forest, showed equivalent predictability and greater sensitivity compared to the KFRE. The KFRE had the highest accuracy, specificity, and precision. This study showed the feasibility of ML in evaluating the prognosis of CKD based on easily accessible features. Three ML models with adequate performance and sensitivity scores suggest a potential use for patient screenings. Future studies include external validation and improving the models with additional predictor variables.

Similar content being viewed by others

A machine learning driven nomogram for predicting chronic kidney disease stages 3–5

Samit Kumar Ghosh & Ahsan H. Khandoker

A simplified prediction model for end-stage kidney disease in patients with diabetes

Toyoshi Inoguchi, Tasuku Okui, … Naoki Nakashima

An independent validation of the kidney failure risk equation in an Asian population

Min Woo Kang, Navdeep Tangri, … Jung Pyo Lee

Introduction

Chronic kidney disease (CKD) is a significant healthcare burden that affects billions of individuals worldwide 1 , 2 and makes a profound impact on global morbidity and mortality 3 , 4 , 5 . In the United States, approximately 11% of the population or 37 million people suffer from CKD that results in an annual Medicare cost of $84 billion 6 . The prevalence of this disease is estimated at 10.8% in China, affecting about 119.5 million people 7 .

Gradual loss of the kidney function can lead to end stage kidney disease (ESKD) in CKD patients, precipitating the need for kidney replacement therapy (KRT). Timely intervention in those CKD patients who have a high risk of ESKD may not only improve these patients’ quality of life by delaying the disease progression, but also reduce the morbidity, mortality and healthcare costs resulting from KRT 8 , 9 . Because the disease progression is typically silent 10 , a reliable prediction model for risk of ESKD at the early stage of CKD can be clinically essential. Such a model is expected to facilitate physicians in making personalized treatment decisions for high-risk patients, thereby improving the overall prognosis and reducing the economic burden of this disease.

A few statistical models were developed to predict the likelihood of ESKD based on certain variables, including age, gender, lab results, and most commonly, the estimated glomerular filtration rate (eGFR) and albuminuria 11 , 12 . Although some of these models demonstrated adequate predictability in patients of a specific race, typically Caucasians 13 , 14 , 15 , literature on their generalizability in other ethnic groups, such as Chinese, remains scarce 13 , 16 . In addition, models based on non-urine variables, such as patients’ baseline characteristics and routine blood tests, have reportedly yield sufficient performance 17 , 18 . Therefore, it may be feasible to predict ESKD without urine tests, leading to a simplified model with equivalent reliability.

With the advent of the big data era, new methods became available in developing a predictive model that used to rely on traditional statistics. Machine learning (ML) is a subset of artificial intelligence (AI) that allows the computer to perform a specific task without explicit instructions. When used in predictive modeling, ML algorithm can be trained to capture the underlying patterns of the sample data and make predictions about the new data based on the acquired information 19 . Compared to traditional statistics, ML represents more sophisticated math functions and usually results in better performance in predicting an outcome that is determined by a large set of variables with non-linear, complex interactions 20 . ML has recently been applied in numerous studies and demonstrated high level of performance that surpassed traditional statistics and even humans 20 , 21 , 22 , 23 .

This article presents a proof-of-concept study with the major goal to establish ML models for predicting the risk of ESKD on a Chinese CKD dataset. The ML models were trained and tested based on easily obtainable variables, including the baseline characteristics and routine blood tests. Results obtained from this study suggest not only the feasibility of ML models in performing this clinically critical task, but also the potential in facilitating personalized medicine.

Materials and methods

Study population.

The data used for this retrospective work were obtained from a longitudinal cohort previously enrolled in an observational study 24 , 25 . The major inclusion criteria for the cohort were adult CKD patients (≥ 18 years old) with stable kidney functions for at least three months prior to recruitment. Patients were excluded if they had one or more of the following situations: (1) history of KRT in any form, including hemodialysis, peritoneal dialysis or kidney transplantation; (2) any other existing condition deemed physically unstable, including life expectancy < 6 months, acute heart failure, and advanced liver disease; (3) any pre-existing malignancy. All patients were recruited from the CKD management clinic of Peking University Third Hospital between April 2006 and March 2008. Written informed consent was obtained from all patients. They were treated according to routine clinical practice determined by the experienced nephrologists and observed until December 31 st , 2015. Detailed information regarding patient recruitment and management protocol has been described in a previous publication 24 .

Data acquisition

Patient characteristics included age, gender, education level, marriage status, and insurance status. Medical history comprised history of smoking, history of alcohol consumption, presence of each comorbid condition—diabetes, cardiovascular disease and hypertension. Clinical parameters contained body mass index (BMI), systolic pressure and diastolic pressure. Blood tests consisted of serum creatinine, uric acid, blood urea nitrogen, white blood cell count, hemoglobin, platelets count, alanine aminotransferase (ALT), aspartate aminotransferase (AST), total protein, albumin, alkaline phosphatase (ALP), high-density lipoprotein, low-density lipoprotein, triglycerides, total cholesterol, calcium, phosphorus, potassium, sodium, chloride, and bicarbonate. The estimated glomerular filtration rate and type of primary kidney disease were also used as predictors.

All baseline variables were obtained at the time of subject enrollment. The primary study end point was kidney failure which necessitated the use of any KRT. Subjects with the outcome of kidney failure were labeled as ESKD+, and the rest ESKD−. Patients who died before reaching the study end point or lost to follow up were discarded. Patients who developed ESKD after five years were labeled as ESKD−.

Data preprocessing

All categorical variables, such as insurance status, education, and primary disease, were encoded using the one-hot approach. Any variable was removed from model development if the missing values were greater than 50%. Missing data were handled using multiple imputation with five times of repetition, leading to five slightly different imputed datasets where each of the missing values was randomly sampled from their predictive distribution based on the observed data. On each imputed set, all models were trained and tested using a fivefold cross validation method. To minimize selection bias, subject assignment to train/test folds was kept consistent across all imputed sets. Data were split in a stratified fashion to ensure the same distribution of the outcome classes (ESKD+ vs. ESKD−) in each subset as the entire set.

Model development

The model was trained to perform a binary classification task with the goal of generating the probability of ESKD+ based on the given features. Five ML algorithms were employed in this study, including logistic regression, naïve Bayes, random forest, decision tree, and K-nearest neighbors. Grid search was performed to obtain the best hyperparameter combination for each algorithm.

Assessment of model performance

The performance of a classifiers was measured using accuracy, precision, recall, specificity, F1 score and area under the curve (AUC), as recommended by guidelines for results reporting of clinical prediction models 26 . All classifiers developed in this study were further compared with the Kidney Failure Risk Equation (KFRE), which estimates the 5-year risk of ESKD based on patient’s age, gender, and eGFR 12 . The KFRE is currently the most widely used model in predicting CKD progression to ESKD. The reported outcome of a model represented the average performance of 5 test folds over all imputed sets.

Statistical analysis

Basic descriptive statistics were applied as deemed appropriate. Results are expressed as frequencies and percentages for categorical variables; the mean ± standard deviation for continuous, normally distributed variables; and the median (interquartile range) for continuous variables that were not normally distributed. Patient characteristics were compared between the original dataset and the imputed sets using one-way analysis of variance (ANOVA). The AUC of each model was measured using the predicted probability. The optimal threshold of a classifier was determined based on the receiver operating characteristic (ROC) curve at the point with minimal distance to the upper left corner. For each ML model, this threshold was obtained during the training process and applied unchangeably to the test set. For the KFRE, the threshold was set at a default value of 0.5. Model development, performance evaluation and data analyses were all performed using Python 27 . The alpha level was set at 0.05.

Ethical approval

This research was conducted ethically in accordance with the World Medical Association Declaration of Helsinki. The study protocol has been approved by the Peking University Third Hospital Medical Science Research Ethics Committee on human research (No. M2020132).

Cohort characteristics

The dataset contained a total of 748 subjects with the follow-up duration of 6.3 ± 2.3 years. The baseline characteristics are summarized in Table 1 . Most patients were in stage 2 (24.5%) or 3 (47.1%) CKD at baseline. ESKD was observed in 70 patients (9.4%), all of whom subsequently received KRT, including hemodialysis in 49 patients, peritoneal dialysis in 17 and kidney transplantation in 4.

Model performance

Details of the five imputed sets are provided in the supplemental materials . There was no significant difference between the imputed sets and the original dataset in each variable where missing data were replaced by imputed values. The hyperparameter settings for each classifier are displayed in Table 2 . The best overall performance, as measured by the AUC score, was achieved by the random forest algorithm (0.81, see Table 3 ). Nonetheless, this score and its 95% confidence interval had overlap with those of the other three models, including the logistic regression, naïve Bayes, and the KFRE (Fig.  1 ). Interestingly, the KFRE model that was based on 3 simple variables, demonstrated not only a comparable AUC score but also the highest accuracy, specificity, and precision. At the default threshold, however, the KFRE was one of the least sensitive models (47%).

ROC curves of the random forest algorithm and the KFRE model.

With extensive utilization of electronic health record and recent progress in ML research, AI is expanding its impact on healthcare and has gradually changed the way clinicians pursue for problem-solving 28 . Instead of adopting a theory-driven strategy that requires a preformed hypothesis from prior knowledge, training an ML model typically follows a data-driven approach that allows the model to learn from experience alone. Specifically, the model improves its performance iteratively on a training set by comparing the predictions to the ground truths and adjusting model parameters so as to minimize the distance between the predictions and the truths. In nephrology, ML has demonstrated promising performances in predicting acute kidney injury or time to allograft loss from clinical features 29 , 30 , recognizing specific patterns in pathology slides 31 , 32 , choosing an optimal dialysis prescription 33 , or mining text in the electronic health record to find specific cases 34 , 35 . Additionally, a few recent studies were performed to predict the progression of CKD using ML methods. These models were developed to estimate the risk of short-term mortality following dialysis 36 , calculate the future eGFR values 37 , or assess the 24-h urinary protein levels 18 . To our best knowledge, there hasn’t been any attempt to apply ML methods to predict the occurrence of ESKD in CKD patients.

In the present study, a prediction model for ESKD in CKD patients was explored using ML techniques. Most classifiers demonstrated adequate performance based on easily accessible patient information that is convenient for clinical translation. In general, three ML models, including the logistic regression, naïve Bayes and random forest, showed non-inferior performance to the KFRE in this study. These findings imply ML as a feasible approach for predicting disease progression in CKD, which could potentially guide physicians in establishing personalized treatment plans for this condition at an early stage. These ML models with higher sensitivity scores may also be practically favored in patient screening over the KFRE.

To our best understanding, this study was also the first to validate the KFRE in CKD patients of Mainland China. The KFRE was initially developed and validated using North American patients with CKD stage 3–5 12 . There were seven KFRE models that consisted of different combinations of predictor variables. The most commonly used KFRE included a 4-variable model (age, gender, eGFR and urine ACR) or an 8-variable model (age, gender, eGFR, urine ACR, serum calcium, phosphorous, bicarbonate, and albumin). Besides, there was a 3-variable model (age, gender, and eGFR) that required no urine ACR and still showed comparable performance to the other models in the original article. Despite its favorable performance in prediction for ESKD in patients of Western countries 14 , 15 , 38 , 39 , the generalizability of KFRE in Asian population remained arguable following the suboptimal results revealed by some recent papers 13 , 40 , 41 . In the current study, the KFRE was validated in a Chinese cohort with CKD stage 1–5 and showed an AUC of 0.80. This result indicated the KFRE was adequately applicable to the Chinese CKD patients and even earlier disease stages. In particular, the high specificity score (0.95) may favor the use of this equation in ruling in patients who require close monitoring of disease progression. On the other hand, a low sensitivity (0.47) at the default threshold may suggest it may be less desirable than the other models for ruling out patients.

Urine test is a critical diagnostic approach for CKD. The level of albuminuria (i.e. ACR) has also been regarded as a major predictor for disease progression and therefore used by most prognostic models. However, quantitative testing for albuminuria is not always available in China especially in rural areas, which precludes clinicians from using most urine-based models for screening patients. In this regard, several simplified models were developed to predict CKD progression without the need of albuminuria. These models were based on patient characteristics (e.g. age, gender, BMI, comorbidity) and/or blood work (e.g. creatinine/eGFR, BUN), and still able to achieve an AUC of 0.87–0.89 12 , 18 or a sensitivity of 0.88 37 . Such performance was largely consistent with the findings of this study and comparable or even superior to some models incorporating urine tests 16 , 42 . Altogether, it suggested a reliable prediction for CKD progression may be obtained from routine clinical variables without urine measures. These models are expected to provide a more convenient screening tool for CKD patients in developing regions.

Missing data are such a common problem in ML research that they can potentially lead to a biased model and undermine the validity of study outcomes. Traditional methods to handle missing data include complete case analysis, missing indicator, single value imputation, sensitivity analyses, and model-based methods (e.g. mixed models or generalized estimating equations) 43 , 44 , 45 . In most scenarios, complete case analysis and single value imputation are favored by researchers primarily due to the ease of implementation 45 , 46 , 47 . However, these methods may be associated with significant drawbacks. For example, by excluding samples with missing data from analyses, complete case analysis can result in reduction of model power, overestimation of benefit and underestimation of harm 43 , 46 ; Single value imputation replaces the missing data by a single value—typically the mean or mode of the complete cases, thereby increasing the homogeneity of data and overestimating the precision 43 , 48 . In this regard, multiple imputation solves these problems by generating several different plausible imputed datasets, which account for the uncertainty about the missing data and provide unbiased estimates of the true effect 49 , 50 . It is deemed effective regardless of the pattern of missingness 43 , 51 . Multiple imputation is now widely recognized as the standard method to deal with missing data in many areas of research 43 , 45 . In the current study, a 5-set multiple imputation method was employed to obtain reasonable variability of the imputed data. The performance of each model was analyzed on each imputed set and pooled for the final result. These procedures ensured that the model bias resulting from missing data was minimized. In the future, multiple imputation is expected to become a routine method for missing data handling in ML research, as the extra amount of computation associated with multiple imputation over those traditional methods can simply be fulfilled by the high level of computational power required by ML.

Although ML has been shown to outperform traditional statistics in a variety of tasks by virtue of the model complexity, some studies demonstrated no gain or even declination of performance compared to traditional regression methods 52 , 53 . In this study, the simple logistic regression model also yielded a comparable or even superior predictability for ESKD to other ML algorithms. The most likely explanation is that the current dataset only had a small sample size and limited numbers of predictor variables, and the ESKD+ cases were relatively rare. The lack of big data and imbalanced class distribution may have negative impact on the performance of complex ML algorithms, as they are typically data hungry 54 . On the other hand, this finding could imply simple interactions among the predictor variables. In other words, the risk of ESKD may be largely influenced by only a limited number of factors in an uncomplicated fashion, which is consistent with some previous findings 12 , 18 , 55 . The fact that the 3-variable KFRE, which is also a regression model, yielded equivalent outcomes to the best ML models in this study may further support this implication. It is therefore indicated that traditional regression models may continue to play a key role in disease risk prediction, especially when a small sample size, limited predictor variables, or an imbalanced dataset is encountered. The fact that some of the complex ML models are subject to the risk of overfitting and the lack of interpretability further favors the use of simple regression models, which can be translated to explainable equations.

Several limitations should be noted. First, this cohort consisted of less than 1000 subjects and ESKD only occurred in a small portion of them, both of which might have affected model performance as discussed earlier. Second, although this study aimed to assess the feasibility of a prediction model for ESKD without any urine variables, this was partially due to the lack of quantitative urine tests at our institute when this cohort was established. As spot urine tests become increasingly popular, urine features such as ACR will be as accessible and convenient as other lab tests. They are expected to play a critical role in more predictive models. Third, the KFRE was previously established on stages 3–5 CKD patients while the current cohort contained stages 1–5. This discrepancy may have affected the KFRE performance. Forth, the generalizability of this model has not been tested on any external data due to the lack of such resource in this early feasibility study. Therefore, additional efforts are required to improve and validate this model before any clinical translation. Finally, although a simple model without urine variables is feasible and convenient, model predictability may benefit from a greater variety of clinical features, such as urine tests, imaging, or biopsy. Future works should include training ML models with additional features using a large dataset, and validating them on external patients.

In conclusion, this study showed the feasibility of ML in evaluating the prognosis of CKD based on easily accessible features. Logistic regression, naïve Bayes and random forest demonstrated comparable predictability to the KFRE in this study. These ML models also had greater sensitivity scores that were potentially advantageous for patient screenings. Future studies include performing external validation and improving the model with additional predictor variables.

Zhang, L. et al. Trends in chronic kidney disease in China. N. Engl. J. Med. 375 , 905–906. https://doi.org/10.1056/NEJMc1602469 (2016).

Article   PubMed   Google Scholar  

Bello, A. K. et al. Effective CKD care in European countries: Challenges and opportunities for health policy. Am. J. Kidney Dis. 65 , 15–25. https://doi.org/10.1053/j.ajkd.2014.07.033 (2015).

Subbiah, A. K., Chhabra, Y. K. & Mahajan, S. Cardiovascular disease in patients with chronic kidney disease: A neglected subgroup. Heart Asia 8 , 56–61. https://doi.org/10.1136/heartasia-2016-010809 (2016).

Article   PubMed   PubMed Central   Google Scholar  

Pecoits-Filho, R. et al. Interactions between kidney disease and diabetes: Dangerous liaisons. Diabetol. Metab. Syndr. 8 , 50. https://doi.org/10.1186/s13098-016-0159-z (2016).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Weiner, D. E. et al. Chronic kidney disease as a risk factor for cardiovascular disease and all-cause mortality: A pooled analysis of community-based studies. J. Am. Soc. Nephrol. 15 , 1307–1315. https://doi.org/10.1097/01.asn.0000123691.46138.e2 (2004).

Saran, R., Robinson, B., Abbott, K. C. et al. US Renal Data System 2019 Annual Data Report: Epidemiology of kidney disease in the United States. Am. J. Kidney Dis. 75 , A6–A7. https://doi.org/10.1053/j.ajkd.2019.09.003 (2020).

Zhang, L. et al. Prevalence of chronic kidney disease in China: A cross-sectional survey. Lancet (London, England) 379 , 815–822. https://doi.org/10.1016/S0140-6736(12)60033-6 (2012).

Article   Google Scholar  

Johns, T. S., Yee, J., Smith-Jules, T., Campbell, R. C. & Bauer, C. Interdisciplinary care clinics in chronic kidney disease. BMC Nephrol. 16 , 161. https://doi.org/10.1186/s12882-015-0158-6 (2015).

Lin, E., Chertow, G. M., Yan, B., Malcolm, E. & Goldhaber-Fiebert, J. D. Cost-effectiveness of multidisciplinary care in mild to moderate chronic kidney disease in the United States: A modeling study. PLoS Med. 15 , e1002532. https://doi.org/10.1371/journal.pmed.1002532 (2018).

Zhong, J., Yang, H. C. & Fogo, A. B. A perspective on chronic kidney disease progression. Am. J. Physiol. Ren. Physiol. 312 , F375–F384. https://doi.org/10.1152/ajprenal.00266.2016 (2017).

Article   CAS   Google Scholar  

Tangri, N. et al. A dynamic predictive model for progression of CKD. Am. J. Kidney Dis. 69 , 514–520. https://doi.org/10.1053/j.ajkd.2016.07.030 (2017).

Tangri, N. et al. A predictive model for progression of chronic kidney disease to kidney failure. JAMA 305 , 1553–1559. https://doi.org/10.1001/jama.2011.451 (2011).

Article   CAS   PubMed   Google Scholar  

Tangri, N. et al. Multinational assessment of accuracy of equations for predicting risk of kidney failure: A meta-analysis. JAMA 315 , 164–174. https://doi.org/10.1001/jama.2015.18202 (2016).

Major, R. W. et al. The Kidney Failure Risk Equation for prediction of end stage renal disease in UK primary care: An external validation and clinical impact projection cohort study. PLoS Med. 16 , e1002955. https://doi.org/10.1371/journal.pmed.1002955 (2019).

Peeters, M. J. et al. Validation of the kidney failure risk equation in European CKD patients. Nephrol. Dial. Transplant. Off. Publ. Eur. Dial. Transpl. Assoc. Eur. Ren. Assoc. 28 , 1773–1779. https://doi.org/10.1093/ndt/gft063 (2013).

Echouffo-Tcheugui, J. B. & Kengne, A. P. Risk models to predict chronic kidney disease and its progression: A systematic review. PLoS Med. 9 , e1001344. https://doi.org/10.1371/journal.pmed.1001344 (2012).

Chang, H. L. et al. A predictive model for progression of CKD. Medicine (Baltimore) 98 , e16186. https://doi.org/10.1097/MD.0000000000016186 (2019).

Xiao, J. et al. Comparison and development of machine learning tools in the prediction of chronic kidney disease progression. J. Transl. Med. 17 , 119. https://doi.org/10.1186/s12967-019-1860-0 (2019).

Song, H., Triguero, I. & Özcan, E. A review on the self and dual interactions between machine learning and optimisation. Prog. Artif. Intell. 8 , 143–165. https://doi.org/10.1007/s13748-019-00185-z (2019).

Mortazavi, B. J. et al. Analysis of machine learning techniques for heart failure readmissions. Circ. Cardiovasc. Qual. Outcomes 9 , 629–640. https://doi.org/10.1161/CIRCOUTCOMES.116.003039 (2016).

Deo, R. C. Machine learning in medicine. Circulation 132 , 1920–1930. https://doi.org/10.1161/CIRCULATIONAHA.115.001593 (2015).

Weng, S. F., Reps, J., Kai, J., Garibaldi, J. M. & Qureshi, N. Can machine-learning improve cardiovascular risk prediction using routine clinical data?. PLoS ONE 12 , e0174944. https://doi.org/10.1371/journal.pone.0174944 (2017).

Meiring, C. et al. Optimal intensive care outcome prediction over time using machine learning. PLoS ONE 13 , e0206862. https://doi.org/10.1371/journal.pone.0206862 (2018).

Lai, X. et al. Outcomes of stage 1–5 chronic kidney disease in Mainland China. Ren. Fail. 36 , 520–525. https://doi.org/10.3109/0886022X.2013.875859 (2014).

Bai, Q., Su, C. Y., Zhang, A. H., Wang, T. & Tang, W. Loss of the normal gradient in arterial compliance and outcomes of chronic kidney disease patients. Cardiorenal Med. 9 , 297–307. https://doi.org/10.1159/000500479 (2019).

Steyerberg, E. W. & Vergouwe, Y. Towards better clinical prediction models: Seven steps for development and an ABCD for validation. Eur. Heart J. 35 , 1925–1931. https://doi.org/10.1093/eurheartj/ehu207 (2014).

Python: A dynamic, open source programming language. https://www.python.org/ (2019).

Yu, K., Beam, A. L. & Kohane, I. S. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2 , 719–731. https://doi.org/10.1038/s41551-018-0305-z (2018).

Mohamadlou, H. et al. Prediction of acute kidney injury with a machine learning algorithm using electronic health record data. Can. J. Kidney Health Dis. 5 , 2054358118776326. https://doi.org/10.1177/2054358118776326 (2018).

Lee, H. C. et al. Derivation and validation of machine learning approaches to predict acute kidney injury after cardiac surgery. J. Clin. Med. https://doi.org/10.3390/jcm7100322 (2018).

Hermsen, M. et al. Deep learning-based histopathologic assessment of kidney tissue. J. Am. Soc. Nephrol. 30 , 1968–1979. https://doi.org/10.1681/ASN.2019020144 (2019).

Boor, P. Artificial intelligence in nephropathology. Nat. Rev. Nephrol. 16 , 4–6. https://doi.org/10.1038/s41581-019-0220-x (2020).

Barbieri, C. et al. Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: Proof of concept and first clinical assessment. Kidney Dis. (Basel) 5 , 28–33. https://doi.org/10.1159/000493479 (2019).

Garcelon, N., Burgun, A., Salomon, R. & Neuraz, A. Electronic health records for the diagnosis of rare diseases. Kidney Int. 97 , 676–686. https://doi.org/10.1016/j.kint.2019.11.037 (2020).

Rajkomar, A. et al. Scalable and accurate deep learning with electronic health records. NPJ Digit. Med. 1 , 18. https://doi.org/10.1038/s41746-018-0029-1 (2018).

Akbilgic, O. et al. Machine learning to identify dialysis patients at high death risk. Kidney Int. Rep. 4 , 1219–1229. https://doi.org/10.1016/j.ekir.2019.06.009 (2019).

Zhao, J., Gu, S. & McDermaid, A. Predicting outcomes of chronic kidney disease from EMR data based on Random Forest Regression. Math. Biosci. 310 , 24–30. https://doi.org/10.1016/j.mbs.2019.02.001 (2019).

Article   MathSciNet   PubMed   PubMed Central   MATH   Google Scholar  

Tangri, N., Ferguson, T. & Komenda, P. Pro: Risk scores for chronic kidney disease progression are robust, powerful and ready for implementation. Nephrol. Dial. Transplant. Off. Publ. Eur. Dial. Transpl. Assoc. Eur. Ren. Assoc. 32 , 748–751. https://doi.org/10.1093/ndt/gfx067 (2017).

Marks, A. et al. Looking to the future: Predicting renal replacement outcomes in a large community cohort with chronic kidney disease. Nephrol. Dial. Transplant. Off. Publ. Eur. Dial. Transpl. Assoc. Eur. Ren. Assoc. 30 , 1507–1517. https://doi.org/10.1093/ndt/gfv089 (2015).

Wang, Y. et al. Validation of the kidney failure risk equation for end-stage kidney disease in Southeast Asia. BMC Nephrol. 20 , 451. https://doi.org/10.1186/s12882-019-1643-0 (2019).

Yamanouchi, M. et al. Value of adding the renal pathological score to the kidney failure risk equation in advanced diabetic nephropathy. PLoS ONE 13 , e0190930. https://doi.org/10.1371/journal.pone.0190930 (2018).

Lin, C. C. et al. Development and validation of a risk prediction model for end-stage renal disease in patients with type 2 diabetes. Sci. Rep. 7 , 10177. https://doi.org/10.1038/s41598-017-09243-9 (2017).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Pedersen, A. B. et al. Missing data and multiple imputation in clinical epidemiological research. Clin. Epidemiol. 9 , 157–166. https://doi.org/10.2147/CLEP.S129785 (2017).

Sterne, J. A. et al. Multiple imputation for missing data in epidemiological and clinical research: Potential and pitfalls. BMJ (Clin. Res. Ed.) 338 , b2393. https://doi.org/10.1136/bmj.b2393 (2009).

Jakobsen, J. C., Gluud, C., Wetterslev, J. & Winkel, P. When and how should multiple imputation be used for handling missing data in randomised clinical trials: A practical guide with flowcharts. BMC Med. Res. Methodol. 17 , 162. https://doi.org/10.1186/s12874-017-0442-1 (2017).

Karadaghy, O. A., Shew, M., New, J. & Bur, A. M. Development and assessment of a machine learning model to help predict survival among patients with oral squamous cell carcinoma. JAMA Otolaryngol. Head Neck Surg. 145 , 1115–1120. https://doi.org/10.1001/jamaoto.2019.0981 (2019).

Bur, A. M. et al. Machine learning to predict occult nodal metastasis in early oral squamous cell carcinoma. Oral Oncol. 92 , 20–25. https://doi.org/10.1016/j.oraloncology.2019.03.011 (2019).

Zhang, Z. Missing data imputation: Focusing on single imputation. Ann. Transl. Med. 4 , 9. https://doi.org/10.3978/j.issn.2305-5839.2015.12.38 (2016).

Graham, J. W. Missing data analysis: Making it work in the real world. Annu. Rev. Psychol. 60 , 549–576. https://doi.org/10.1146/annurev.psych.58.110405.085530 (2009).

Klebanoff, M. A. & Cole, S. R. Use of multiple imputation in the epidemiologic literature. Am. J. Epidemiol. 168 , 355–357. https://doi.org/10.1093/aje/kwn071%JAmericanJournalofEpidemiology (2008).

Azur, M. J., Stuart, E. A., Frangakis, C. & Leaf, P. J. Multiple imputation by chained equations: What is it and how does it work?. Int. J. Methods Psychiatr. Res. 20 , 40–49. https://doi.org/10.1002/mpr.329 (2011).

Desai, R. J., Wang, S. V., Vaduganathan, M., Evers, T. & Schneeweiss, S. Comparison of machine learning methods with traditional models for use of administrative claims with electronic medical records to predict heart failure outcomes. JAMA Netw. Open 3 , e1918962. https://doi.org/10.1001/jamanetworkopen.2019.18962 (2020).

Christodoulou, E. et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J. Clin. Epidemiol. 110 , 12–22. https://doi.org/10.1016/j.jclinepi.2019.02.004 (2019).

Nusinovici, S. et al. Logistic regression was as good as machine learning for predicting major chronic diseases. J. Clin. Epidemiol. 122 , 56–69. https://doi.org/10.1016/j.jclinepi.2020.03.002 (2020).

Nusinovici, S. et al. Logistic regression was as good as machine learning for predicting major chronic diseases. J. Clin. Epidemiol. https://doi.org/10.1016/j.jclinepi.2020.03.002 (2020).

Download references

This work was supported by PKU-Baidu Fund (2020BD030 to Wen Tang), and by fund from China International Medical Foundation (Z-2017-24-2037 to Wen Tang). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Author information

Authors and affiliations.

Department of Nephrology, Peking University Third Hospital, 49 North Garden Rd, Haidian District, Beijing, 100191, People’s Republic of China

Qiong Bai, Chunyan Su & Wen Tang

Department of Otolaryngology-Head and Neck Surgery, Bill Wilkerson Center, Vanderbilt University Medical Center, Nashville, TN, USA

You can also search for this author in PubMed   Google Scholar

Contributions

Q.B. was involved in the data collection, data analysis, and drafting the manuscript. C.S. was involved in data collection. W.T. conceptualized the idea, interpreted the results and wrote part of the draft. Y.L. conceptualized the idea, analyzed the data, performed all coding, evaluated all machine learning models, drafted and edited the manuscript.

Corresponding authors

Correspondence to Wen Tang or Yike Li .

Ethics declarations

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 information., 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/ .

Reprints and permissions

About this article

Cite this article.

Bai, Q., Su, C., Tang, W. et al. Machine learning to predict end stage kidney disease in chronic kidney disease. Sci Rep 12 , 8377 (2022). https://doi.org/10.1038/s41598-022-12316-z

Download citation

Received : 19 July 2021

Accepted : 09 May 2022

Published : 19 May 2022

DOI : https://doi.org/10.1038/s41598-022-12316-z

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

This article is cited by

Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease.

• Takeshi Nakata
• Hirotaka Shibata

BMC Nephrology (2024)

Predicting CKD progression using time-series clustering and light gradient boosting machines

• Hirotaka Saito
• Hiroki Yoshimura
• Junichiro J. Kazama

Scientific Reports (2024)

Machine learning to predict occult metastatic lymph nodes along the recurrent laryngeal nerves in thoracic esophageal squamous cell carcinoma

• Yiliang Zhang
• Longfu Zhang
• Haiquan Chen

BMC Cancer (2023)

Machine learning models to predict end-stage kidney disease in chronic kidney disease stage 4

• Kullaya Takkavatakarn

BMC Nephrology (2023)

The genetics and pathogenesis of CAKUT

• Caroline M. Kolvenbach
• Shirlee Shril
• Friedhelm Hildebrandt

Nature Reviews Nephrology (2023)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

ORIGINAL RESEARCH article

Uncovering specific taxonomic and functional alteration of gut microbiota in chronic kidney disease through 16s rrna data provisionally accepted.

• 1 Department of Nephrology, Seventh Affiliated Hospital, Sun Yat-sen University, China
• 2 School of Medicine, Sun Yat-sen University, Shenzhen Campus, China

The final, formatted version of the article will be published soon.

Chronic kidney disease (CKD) is worldwide healthcare burden with growing incidence and death rate. Emerging evidence demonstrated the compositional and functional differences of gut microbiota in patients with CKD. As such, gut microbial features can be developed as diagnostic biomarkers and potential therapeutic target for CKD. To eliminate the outcome bias arising from factors such as geographical distribution, sequencing platform, and data analysis techniques, we conducted a comprehensive analysis of the microbial differences between patients with CKD and healthy individuals based on multiple samples worldwide. A total of 980 samples from six references across three nations were incorporated from the PubMed, Web of Science, and GMrepo databases. The obtained 16S rRNA microbiome data were subjected to DADA2 processing, QIIME2 and PICRUSt2 analyses. The gut microbiota of patients with CKD differs significantly from that of healthy controls (HC), with a substantial decrease in the microbial diversity among the CKD group. Moreover, a significantly reduced abundance of bacteria Faecalibacterium prausnitzii (F. prausnitzii) was detected in the CKD group through linear discriminant analysis effect size (LEfSe) analysis, which may be associated with the alleviating effects against CKD. Notably, we identified CKD-depleted F. prausnitzii demonstrated a significant negative correlation with three pathways based on predictive functional analysis, suggesting its potential role in regulating systemic acid-base disturbance and pro-oxidant metabolism. Our findings demonstrated notable alterations of gut microbiota in CKD patients. Specific gut-beneficial microbiota, especially F. prausnitzii, may be developed as a preventive and therapeutic tool for CKD clinical management.

Keywords: Chronic Kidney Disease, Gut Microbiota, 16S rRNA, biomarker, Probiotics

Received: 11 Jan 2024; Accepted: 01 Apr 2024.

Copyright: © 2024 Zhang, Zhong, Wang, Lin, Lin, Fang, Mou, Jiang, Huang, Zhao and Zheng. 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: Dr. Jiayuan Huang, School of Medicine, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China Prof. Wenjing Zhao, School of Medicine, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China Prof. Zhihua Zheng, Department of Nephrology, Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China

People also looked at

Executive summary of the KDIGO 2024 Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease: known knowns and known unknowns

Affiliations.

• 1 Division of Nephrology, University of British Columbia, Vancouver, British Columbia, Canada. Electronic address: [email protected].
• 2 Department of Medicine, University of Alberta, Edmonton, Alberta, Canada.
• 3 Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
• 4 Department of Pediatrics, McGill University, Montreal, Quebec, Canada.
• 5 Department of Medicine, Queensland Children's Hospital, Brisbane, Queensland, Australia.
• 6 Division of Nephrology, Duke School of Medicine, Durham, North Carolina, USA.
• 7 Nuffield Department of Population Health, University of Oxford, Oxford, UK.
• 8 Manchester, UK.
• 9 Division of Nephrology, Tufts Medical Center, Boston, Massachusetts, USA.
• 10 Division of Nephrology, Bezmialem Vakif University, Istanbul, Turkey.
• 11 Department of Clinical Biochemistry, East Kent Hospitals University NHS Foundation Trust, Canterbury, UK.
• 12 Director of Primary Care Initiatives, Canadian Heart Research Center, Toronto, Ontario, Canada.
• 13 Division of Nephrology, Instituto Nacional de Cardiología Ignacio Chavéz, Mexico City, Mexico.
• 14 London Health Sciences Centre-Victoria Hospital, Western University, London, Ontario, Canada.
• 15 Department of Nutrition and Exercise Science, Bastyr University, Kenmore, Washington, USA; Osher Center for Integrative Medicine, University of Washington, Kenmore, Washington, USA.
• 16 UW Center for Dialysis Innovation & Kidney Research Institute, Seattle, Washington, USA.
• 17 Western Renal Service, University of Sydney, Sydney, New South Wales, Australia.
• 18 Division of Nephrology and Intensive Care Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany.
• 19 Department of Medicine, University of California, San Francisco, San Francisco, California, USA.
• 20 Department of Paediatric Nephrology, UCL Great Ormond Street Hospital Institute of Child Health, London, UK.
• 21 Division of Nephrology, University of Manitoba, Winnipeg, Manitoba, Canada.
• 22 Division of Nephrology, Bhumirajanagarindra Kidney Institute, Bangkok, Thailand.
• 23 Department of Medicine, Ituku-Ozalla Campus, University of Nigeria, Enugu, Nigeria.
• 24 Division of Nephrology, Chang Gung University, Taoyuan, Taiwan.
• 25 Renal Division, Peking University First Hospital, Beijing, China.
• 26 The Johns Hopkins University Evidence-based Practice Center, Johns Hopkins University, Baltimore, Maryland, USA.
• 27 Hennepin County Medical Center, University of Minnesota, Minneapolis, Minnesota, USA.
• 28 KDIGO, Brussels, Belgium.
• 29 Department of Nephrology, Kent Kidney Care Centre, East Kent Hospitals University NHS Foundation Trust, Canterbury, UK. Electronic address: [email protected].
• PMID: 38519239
• DOI: 10.1016/j.kint.2023.10.016

The Kidney Disease: Improving Global Outcomes (KDIGO) Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease (CKD) updates the KDIGO 2012 guideline and has been developed with patient partners, clinicians, and researchers around the world, using robust methodology. This update, based on a substantially broader base of evidence than has previously been available, reflects an exciting time in nephrology. New therapies and strategies have been tested in large and diverse populations that help to inform care; however, this guideline is not intended for people receiving dialysis nor those who have a kidney transplant. The document is sensitive to international considerations, CKD across the lifespan, and discusses special considerations in implementation. The scope includes chapters dedicated to the evaluation and risk assessment of people with CKD, management to delay CKD progression and its complications, medication management and drug stewardship in CKD, and optimal models of CKD care. Treatment approaches and actionable guideline recommendations are based on systematic reviews of relevant studies and appraisal of the quality of the evidence and the strength of recommendations which followed the "Grading of Recommendations Assessment, Development, and Evaluation" (GRADE) approach. The limitations of the evidence are discussed. The guideline also provides practice points, which serve to direct clinical care or activities for which a systematic review was not conducted, and it includes useful infographics and describes an important research agenda for the future. It targets a broad audience of people with CKD and their healthcare, while being mindful of implications for policy and payment.

Keywords: CKD; KDIGO; chronic kidney disease; evaluation; guideline; management.

Copyright © 2023 Kidney Disease: Improving Global Outcomes (KDIGO). Published by Elsevier Inc. All rights reserved.

Publication types

• Practice Guideline
• Kidney Transplantation* / adverse effects
• Nephrology*
• Renal Dialysis / adverse effects
• Renal Insufficiency, Chronic* / complications
• Renal Insufficiency, Chronic* / diagnosis
• Renal Insufficiency, Chronic* / therapy