research medical center nicu

• Second Opinion

The Neonatal Intensive Care Unit (NICU)

The birth of a baby is a wonderful and very complex process. Many physical and emotional changes occur for both mother and baby.

A baby must make many physical adjustments to life outside the mother's body. Leaving the uterus means that a baby can no longer depend on the mother's blood supply and placenta for important body functions.

Before birth, the baby depends on functions from the mother. These include breathing, eating, elimination of waste, and immune protection. When a baby leaves the womb, its body systems must change. For example:

The lungs must breathe air.

The cardiac and pulmonary circulation changes.

The digestive system must begin to process food and excrete waste.

The kidneys must begin working to balance fluids and chemicals in the body and excrete waste.

The liver and immune systems must begin working on their own.

Your baby's body systems must work together in a new way. In some cases, a baby has trouble making the transition outside the womb. Preterm birth, a difficult birth, or birth defects can make these changes more challenging. But a lot of special care is available to help newborn babies.

What is the neonatal intensive care unit (NICU)?

Newborn babies who need intensive medical care are often put in a special area of the hospital called the neonatal intensive care unit (NICU). The NICU has advanced technology and trained healthcare professionals to give special care for the tiniest patients. NICUs may also care areas for babies who are not as sick but do need specialized nursing care. Some hospitals don’t have the staff for a NICU and babies must be moved to another hospital. Babies who need intensive care do better if they are born in a hospital with a NICU than if they are moved after birth.

Some newborn babies will require care in a NICU. Giving birth to a sick or premature baby can be unexpected for any parent. The NICU can be overwhelming. This information is to help you understand why a baby may need to be in the NICU. You will also find out about some of the procedures that may be needed for the care of your baby.

Which babies need special care?

Most babies admitted to the NICU are preterm (born before 37 weeks of pregnancy), have low birth weight (less than 5.5 pounds), or have a health condition that needs special care. In the U.S., nearly half a million babies are born preterm. Many of these babies also have low birth weights. Twins, triplets, and other multiples often are admitted to the NICU. This is because they tend to be born earlier and smaller than single birth babies. Babies with health conditions such as breathing trouble, heart problems, infections, or birth defects are also cared for in the NICU.

Below are some factors that can place a baby at high risk and increase the chances of being admitted to the NICU. But each baby must be assessed to see if he or she needs the NICU. High-risk factors include the below.

Maternal factors include:

Being younger than age 16 or older than age 40

Drug or alcohol use

High blood pressure (hypertension)

Sexually transmitted diseases

Multiple pregnancy (twins, triplets, or more)

Too little or too much amniotic fluid

Premature rupture of membranes (also called the amniotic sac or bag of waters)

Delivery factors include:

Changes in a baby’s organ systems due to lack of oxygen (fetal distress or birth asphyxia)

Buttocks delivered first (breech birth) or other abnormal position

The baby's first stool (meconium) passed during pregnancy into the amniotic fluid

Umbilical cord wrapped around the baby's neck (nuchal cord)

Forceps or cesarean delivery

Baby factors include:

Baby born at gestational age of less than 37 weeks or more than 42 weeks

Birth weight less than 5 pounds, 8 ounces (2,500 grams) or over 8 pounds, 13 ounces (4,000 grams)

Small for gestational age

Medicine or resuscitation in the delivery room

Birth defects

Respiratory distress including rapid breathing, grunting, or stopping breathing (apnea)

Infection such as herpes, group B streptococcus, chlamydia

Low blood sugar (hypoglycemia)

Need for extra oxygen or monitoring, IV (intravenous) therapy, or medicines

Need for special treatment or procedures such as a blood transfusion

Who will care for your baby in the NICU?

Some of the specially-trained healthcare providers who may care for your baby include:

Neonatologist. This is a pediatrician with extra training in the care of sick and premature babies. The neonatologist (often called the attending physician) supervises pediatric fellows and residents, nurse practitioners, and nurses who care for babies in the NICU.

Neonatal fellow. This is a pediatrician getting extra training in the care of sick and premature babies. He or she may do procedures and direct your child's care.

Pediatric resident. This is a doctor who is getting extra training in the care of children. He or she may do or assist in procedures and help direct your child's care.

Neonatal nurse practitioner. This is a registered nurse with extra training in the care of newborn babies. He or she can do procedures and help direct your child's care.

Respiratory therapist. This is a person with special training in giving respiratory support. This includes managing breathing machines and oxygen.

Physical, occupational, and speech therapists. These types of therapists make sure a baby is developing well. They also help with care including positioning and soothing methods. Speech therapists help babies learn to eat by mouth.

Dietitians. Dietitians ensure the babies are growing well and getting good nutrition. They watch your baby's intake of calories, protein, vitamins, and minerals.

Lactation consultants. These are healthcare providers with extra training and certification in helping women and babies breastfeed. They can help with pumping, maintaining milk supply, and starting and continuing breastfeeding.

Pharmacists. Pharmacists help in the NICU by assisting the care providers choose the best medicines. They check medicine doses and levels. They keep the team aware of possible side effects and monitoring that may be needed.

Social workers. Social workers help families cope with many things when a child is ill. They give emotional support. They help families get information from healthcare providers. They support the family with other more basic care needs, too. These can include money problems, transportation, or arranging home healthcare.

Hospital chaplain. The hospital chaplain may be a priest, minister, lay pastor, or other religious advisor. The chaplain can give spiritual support and counseling to help families cope with the stress of the NICU.

NICU team members work together with parents to create a plan of care for high-risk newborns. Ask about the NICU's parent support groups and other programs designed to help parents.

Supporing each delivery with nurturing care and outstanding comfort

Related links.

• Neonatology Care
• Neonatal Intensive Care Unit
• Parent Support
• Road to Home
• Stanford Medicine Children’s Health Pediatrics – Monterey
• Bass Center for Childhood Cancer and Blood Diseases
• Children's Orthopedic and Sports Medicine Center

Related Topics

Developmental Care for Babies in the NICU

Equipment That Is Used in the NICU

Intravenous (IV) Line and Tubes

Connect with us:

Download our App:

• Leadership Team
• Vision, Mission & Values
• The Stanford Advantage
• Government and Community Relations
• Get Involved
• Volunteer Services
• Auxiliaries & Affiliates

© 123 Stanford Medicine Children’s Health

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

NICU Admission for Term Neonates in a Large Single-Center Population: A Comprehensive Assessment of Risk Factors Using a Tandem Analysis Approach

Shahar talisman.

1 Shaare Zedek Medical Center, Department of Obstetrics & Gynecology, School of Medicine, Hebrew University, Jerusalem 9103102, Israel; [email protected] (S.T.); li.gro.cmzs@f_akvir (R.F.); li.gro.cmzs@nkinbers (N.S.); moc.liamg@menahgainud (D.G.); li.gro.cmzs@aniros (S.G.G.)

Joshua Guedalia

2 The Mina and Everard Goodman Faculty of Life Sciences, Bar Ilan University, Ramat-Gan 5290002, Israel; moc.liamg@ailadeugauhsoj (J.G.); li.ca.uib.sl.1mocoib@nor (R.U.)

Rivka Farkash

Tehila avitan, naama srebnik, yair kasirer.

3 Shaare Zedek Medical Center, Department of Pediatrics, School of Medicine, Hebrew University, Jerusalem 9103102, Israel; li.gro.cmzs@risakriay (Y.K.); li.gro.cmzs@lemmihcs (M.S.S.)

Michael S. Schimmel

Dunia ghanem, sorina grisaru granovsky, associated data.

The data was retrieved from the EMR of Shaare Zedek Medical Center; available upon official request from Shaare Zedek Medical Center R&D Authority.

Objective: Neonatal intensive care unit (NICU) admission among term neonates is associated with significant morbidity and mortality, as well as high healthcare costs. A comprehensive NICU admission risk assessment using an integrated statistical approach for this rare admission event may be used to build a risk calculation algorithm for this group of neonates prior to delivery. Methods: A single-center case–control retrospective study was conducted between August 2005 and December 2019, including in-hospital singleton live born neonates, born at ≥37 weeks’ gestation. Analyses included univariate and multivariable models combined with the machine learning gradient-boosting model (GBM). The primary aim of the study was to identify and quantify risk factors and causes of NICU admission of term neonates. Results: During the study period, 206,509 births were registered at the Shaare Zedek Medical Center. After applying the study exclusion criteria, 192,527 term neonates were included in the study; 5292 (2.75%) were admitted to the NICU. The NICU admission risk was significantly higher (ORs [95%CIs]) for offspring of nulliparous women (1.19 [1.07, 1.33]), those with diabetes mellitus or hypertensive complications of pregnancy (2.52 [2.09, 3.03] and 1.28 [1.02, 1.60] respectively), and for those born during the 37th week of gestation (2.99 [2.63, 3.41]; p < 0.001 for all), adjusted for congenital malformations and genetic syndromes. A GBM to predict NICU admission applied to data prior to delivery showed an area under the receiver operating characteristic curve of 0.750 (95%CI 0.743–0.757) and classified 27% as high risk and 73% as low risk. This risk stratification was significantly associated with adverse maternal and neonatal outcomes. Conclusion: The present study identified NICU admission risk factors for term neonates; along with the machine learning ranking of the risk factors, the highly predictive model may serve as a basis for individual risk calculation algorithm prior to delivery. We suggest that in the future, this type of planning of the delivery will serve different health systems, in both high- and low-resource environments, along with the NICU admission or transfer policy.

1. Introduction

Neonatal intensive care unit (NICU) admission entails risks for newborns and stress to their families, at a high cost to the healthcare system. The majority of studies that have evaluated admission and risk factors for the NICU use have focused primarily on preterm infants. In light of well-established neonatal bed crises and increasing healthcare costs [ 1 , 2 ], analyses of NICU admissions for term neonates has become imperative. In a time trend analysis of 38 units in the United States between 2007 and 2012, the overall NICU admission rate increased by 23% after adjusting for maternal and neonatal characteristics, while the admitted neonates were increasingly likely to be at term [ 3 ]. This trend was further reinforced by the results of other recent studies showing that infants born at term (≥37 weeks’ gestation) account for 53–65% of NICU admissions [ 3 , 4 , 5 ]. Notably, some have suggested term NICU admission rates as a marker of obstetrical care quality [ 6 ].

To our knowledge, no previous studies have comprehensively examined the admission of term infants to NICUs, using an integrated statistical approach. Thus, the primary aim of this study was to identify and quantify risk factors and causes for the NICU admission of term neonates in order to develop a predictive model for use during labor to identify births at high risk for NICU admission, prior to delivery.

2.1. Study Population and Data Collection

We conducted a retrospective cohort study using the computerized medical record database of a single large obstetric center between 2005 and 2019, with a mean of 13,500 deliveries per year. We included all singleton term live births ≥37 weeks’ gestation. The following were excluded from the study: multifetal birth, preterm birth (<37 weeks’ gestation), and stillbirth (intra-uterine fetal death). Data on demographic and obstetric characteristics as well as data on the course of delivery and delivery complications, maternal blood sample results at admission, and neonatal data were derived from the electronic database management software, which is updated during labor and validated by the computer system’s personnel periodically. The data file was de-identified by the hospital personnel and constructed for analysis.

Coverage for all women and neonates for antenatal, intrapartum, NICU care, and any health costs throughout life is provided under the National Health Plan.

The study protocol was submitted to the institutional Ethical Committee (Helsinki Committee) and was exempted on the basis of an anonymous analysis (reference number SZMC_0199-19); identifying numbers were erased after the data were linked.

2.2. Data Collection and Variables

From the electronic medical record, we obtained the birth year, gestational age at delivery, data on NICU use, and maternal characteristics, including age, race and/or ethnicity, insurance, gravidity, parity, mode of delivery, hypertension, and diabetes in pregnancy. Gestational age was based on the best obstetric estimate by using last menstrual period and ultrasound data and was recorded in completed weeks. All births were analyzed, i.e., we included repeated births for the same women. All analyses were performed before and after exclusion of congenital malformations and chromosomal and genetic syndromes.

Demographic and clinical maternal data included maternal age, education, population group, ethnicity, pregnancy complications, and maternal comorbidities (gestational/pre-gestational diabetes, hypertensive disorders, and other background maternal diseases). Current and past obstetrical data included parity, assisted reproductive techniques (ART) used to achieve pregnancy, prior cesarean section, prior miscarriage, high-risk hospitalization during pregnancy, inter-pregnancy interval, antenatal care, past neonatal death, gestational age at birth (recorded by LMP; US exam < 12 weeks gestation or both), admission vital signs (diastolic and systolic blood pressure, temperature (oral), heart rate), CBC and blood type at admission, mode of labor initiation (spontaneous, induction, no trial of labor), mode of delivery (vaginal spontaneous, instrumental or cesarean section), epidural analgesia, oxytocin induction/augmentation, thick meconium, head presentation, normal fetal monitor, modified Bishop score at admission [ 7 ], total labor duration (min), stage II duration (min), stage III duration (min), on-call hours at birth, and severe placental, uterine, and maternal complications (dehiscence, uterine rupture, placenta accrete, massive bleeding, post-partum hemorrhage, blood products, re-laparotomy and uterine atony). Neonatal characteristics included birth weight, sex, 1′- and 5′-Apgar score, macrosomia (birth weight [BW] > 4000 g), small for gestational age (SGA), population growth curves [ 8 ], and NICU admission (any transfer with a length of stay of at least 4 h), congenital syndromes, and malformations. The diagnoses at admission (one or more) are listed as per ICD coding and diagnoses registered on the neonatal discharge records (three authors: RF, NS, SGG independently reviewed the diagnoses and ICD codes and reached agreement on disease categories; disagreements were discussed jointly and decided): respiratory distress and disorders, meconium aspiration, cardiovascular disorders and hemodynamic instability, 5′-Apgar score < 7 or arterial umbilical blood pH < 7.1, brain morbidities and hypoxic encephalopathy, hypoglycemia, electrolyte imbalance, neonatal jaundice, infection, digestive disorders, musculoskeletal disorders, structural congenital malformations, and chromosomal abnormalities.

In our institution, we routinely admit to the NICU all infants born at <36 weeks of gestation or with birth weight < 2000 g. The decision to admit to the NICU for medical reasons is taken by a senior physician; a staff neonatologist or a neonatology fellow. For the purpose of the study, due to the long duration of the study and possible policy and facility variations, that might determine the NICU admission decision-making process (versus observation at the neonatal maternity ward), we combined the direct delivery room-NICU admission and delayed maternity–NICU admission. The NICU admissions do not include any post-discharge (home) re-admissions; those are reared to the PICU or the pediatric ward. In the present study we decided to limit the inclusion criteria to the standard definition of term since this is the center threshold for a medically indicated NICU admission; otherwise, any newborn at 34–36 weeks gestation is transferred to the NICU for observation, with or without a medical indication for 4 h and without additional clinical judgment.

For the purpose of the study, due to the long duration of the study and possible policy and facility variations that determine the transfer policy, we combined data on direct delivery room–NICU transfer and delayed maternity–NICU transfers (data on separate early/delivery room and delayed NICU transfer were culled accordingly, not reported here).

2.3. Data Analysis

2.3.1. statistical analyses.

Subjects were divided into two groups: (1) Admitted to NICU after delivery; (2) Not admitted to NICU after delivery (no-NICU). Univariate analysis was initially conducted; continuous variables were analyzed using a T-test or Mann–Whitney U-test, and categorical variables were analyzed using Chi-square test or Fisher’s exact test. Multivariable logistic regression models were then carried out in order to identify independent risk factors for NICU admission among term neonates, including demographic, clinical, and obstetrical features. Models were adjusted for delivery and newborn characteristics: congenital malformations and genetic syndromes.

All tests were two-sided; p -values < 0.05 were considered statistically significant. Statistical analyses were performed using SPSS version 25.0 statistical package (Armonk, NY, USA, IBM Corp.).

2.3.2. Machine Learning and Gradient Boosting Model

Machine learning (ML) algorithms are built with a focus on automatically analyzing large data sets with large sets of features. The algorithms allow for learning high-order interactions within features without a priori selection of which features are significant. For the current study, the CatBoost gradient boosting model (GBM) was used to predict an individualized risk score for NICU admission among term neonates. This method is based on an ensemble of decision trees built sequentially, with each tree putting additional focus on the mistakes made in the previous decision trees. GBM has been previously used in obstetrical data analyses [ 9 ]. Model accuracy was measured via the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) and validated via 10-fold cross-validation. Confidence intervals were calculated using DeLong’s test [ 10 ]. All pre-delivery and during-delivery features were entered into the model. Since this model also uses features with incomplete data, a median imputation for cases of incomplete data was used.

Further ML analyses were performed by SHAP (Shapley additive explanation) in order to identify and interpret the importance of the top influencing features in the GBM and the interactions between specific features [ 11 ].

Subjects were then stratified, based on GBM risk score, into low and high risk for term NICU admission. The risk thresholds for high- and low-risk groups were determined using Youden’s Index [ 12 ] in order to achieve an optimal balance between sensitivity and specificity. The odds ratios (ORs) for maternal and neonatal adverse outcomes were then calculated according to the GBM risk stratification.

A multivariable regression statistical approach was applied to check for significance, magnitude and direction of the associations identified by the GBM. An accuracy correlation between the logistic regression and GBM was assessed by Spearman’s correlation.

Machine learning was performed using Python v3.6.3 (Beaverton, OR, USA, Python Software Foundation), scikit-learn library v0.20.0 (Beaverton, OR, USA, Python Software Foundation) and CatBoost version 0.15.1 (Moscow, Russia, Yandex LLC).

3.1. Study Population

During the study period 206,509 births were recorded at the Shaare Zedek Medical Center. After application of study exclusion criteria, we included 192,527 (93.23%) term singleton live births in the study (91,697 women): 5292 (2.75%) were admitted to the NICU and 187,235 (97.25%) were not ( Figure 1 ). The NICU admission rate during the study period ranged between 2.1% and 4.1% ( Appendix A ).

Study population flow diagram.

3.2. Neonatal Admission to NICU

A comparison between both study groups showed that the NICU admission group differed significantly based on maternal demographic characteristics, clinical and obstetric history, vital signs upon admission for delivery, and delivery and neonatal characteristics ( p < 0.001 for all) ( Table 1 ). Notably, the mean gestational age at birth was significantly lower, i.e., early term, for the NICU admission group than the no-NICU group (39.1 ± 1.4 weeks vs. 39.5 ± 1.2; p < 0.001). The diagnoses at admission (presented as rate of the total term neonates admitted to the NICU) were respiratory distress and disorders 47.1%, structural congenital malformations 44.7%, cardiovascular disorders and hemodynamic instability 20.3%, hypoglycemia 18.7%, 5′-Apgar score < 7 or arterial umbilical blood pH < 7.1 11.7%, neonatal jaundice 11.0%, musculoskeletal disorders 10.9%, infections 7.7%, meconium aspiration 7.1%, brain morbidities and hypoxic encephalopathy 5.5%, chromosomal abnormalities 3.3%, electrolyte imbalance 2.3%, and digestive disorders 0.001%. The blood transfusion rate for the term newborns admitted to the NICU was 1.2% and 0.028% for the entire study population. We further dissected the term period in order to quantify the risk variation for each week of gestation and observed a peak rate of NICU admission during the 37th week of gestation (8.4%), which decreased significantly thereafter, followed by an additional rise at 42 (3.1%) ( Figure 2 A). For neonates born between 37 + 0 and 37 + 6 weeks’ gestation we found that the highest rate of admission was for those born at 37 weeks + 0 days (12.7%), with a steady decline to the lowest admission risk of 5.2% at 37 weeks + 6 days ( p for trend < 0.001) ( Figure 2 B).

( A ): NICU admission rate by week of gestation at birth. ( B ): NICU admission rate within the 37th week.

Demographic, obstetrical, and neonatal characteristics of the study groups.

Data presented as the group means (SD) or as frequencies (percentages). Abbreviations: GDM/DM, gestational/pregestational diabetes mellitus; ART, Assisted reproductive technology; CS, cesarean section; TOLAC, trial of labor after cesarean; SGA, small for gestational age. Y, years; W, weeks; N, number; Min, minutes; Gr, grams.

An adjusted multivariable logistic regression model was used to assess the risk factors for NICU admission for term neonates. In this model, the significant risk factors were nulliparity (OR = 1.19, 95%CI [1.07, 1.33]; p = 0.002); pregnancy complications: hypertensive disease and gestational diabetes mellitus (OR, 95%CI 1.28 [1.02, 1.60]; p = 0.035 and 2.52 [2.09, 3.03]; p < 0.001 respectively); hospitalization during pregnancy (OR = 1.42, 95%CI [1.21, 1.66]; p < 0.001); induction of labor (OR = 1.28, 95%CI [1.12, 1.46]; p < 0.001); elective cesarean section (OR = 1.52, 95%CI [1.05, 2.22]; p < 0.001); and gestational age at birth of 37 weeks (OR = 2.99, 95%CI [2.63, 3.41]; p < 0.001) with an AUC of 0.723 (95%CI [0.712–0.735]; p < 0.001), Table 2 . Importantly, the pattern remained significant after adjustment for congenital malformations and genetic syndromes.

Neonatal intensive care admission predictors, adjusted for gestational age at birth and neonatal characteristics.

Significant differences are indicated by an asterisk (*). Model was adjusted to gestational age at birth and neonatal characteristics. Abbreviations: OR, odds ratio; CI, confidence interval; GDM/DM, gestational/pregestational diabetes mellitus; ART, Assisted reproductive technology; CS, cesarean section; W, weeks.

A GBM for predicting NICU admission was set in a 10-fold cross-validation study. The model included all features collected pre-delivery and during delivery, prior to birth, and achieved an AUC of 0.750 (95%CI 0.743–0.757). The ranking of the top ten significant features, in order of importance, was: spontaneous delivery, labor duration, thick meconium, gestational age by day, normal labor progress, first maternal white blood cell count (admission), gestational age by week, abnormal labor progress, cesarean section delivery, and admission week, Figure 3 .

Risk ranking using a gradient boosting model to identify the most important influencing features in order of relative importance. The top most influential features according to the GBM, by order of importance. As seen, spontaneous delivery was the most influential feature. Values are measured by relative importance based on shapely additive explanation (SHAP). WBC, white blood cells; CS, cesarean section; SHAP, shapely additive explanation.

The NICU admission prediction risk assessment was compared between the logistic regression and GBM models (Spearman correlation calculation), achieving an R = 0.667 ( p < 0.001).

Thus, we used the GBM to develop a standard for a clinical decision algorithm and future planning for term neonate NICU admission; the study population was divided into high and low risk for NICU admission using the GBM individualized prediction risk score. Youden’s Index threshold (4%) was applied, and the population was stratified with 27% (n = 50,537) allocated to the high-risk group and 73% (n = 141,990) to the low-risk group. Among those classified by our model as high risk, 64% were admitted to the NICU after delivery. The risk for NICU admission among the high-risk group was 5.26-fold higher as compared to those designated as low risk by our model. In order to further substantiate our stratification, the odds ratios for adverse outcomes (maternal and neonatal) were calculated by comparing the outcome incidence in the designed high-risk group using the low-risk group as reference, Table 3 . The neonates designated as being at high risk of NICU admission had increased risks for maternal and neonatal adverse outcomes. Severe maternal uterine and placental pathologies were found to have the heaviest weight odds ratios for the neonatal NICU admission high-risk group as designated by the GBM, including uterine dehiscence (OR = 43.52), uterine rupture (OR = 23.13), placenta accreta (OR = 14.05), and massive antenatal/ intrapartum bleeding (OR = 8.71).

Maternal and neonatal adverse outcomes: high- and low-risk groups for NICU admission.

The reference category is low-risk for NICU admission group. * Crude numeric results [low risk without feature, high risk without feature], [low risk with feature, high risk with feature]. Abbreviations: OR, odds ratio; CI, confidence interval; NICU, neonatal intensive care unit; PPH, post-partum hemorrhage; GIT, gastro-intestinal tract; SGA, small for gestational age.

4. Discussion

Previous studies have focused on specific maternal and neonatal characteristics associated with NICU admission for term neonates, including maternal diseases and therapies [ 6 ], mode of delivery [ 13 , 14 ], birth weight [ 15 , 16 ], delivery complications and neonatal diseases [ 17 , 18 , 19 , 20 ], breastfeeding, and mother–child bonding [ 21 , 22 ]. In this study, we examined risk factors for NICU admission in a large single-center cohort of term neonates. We show that the use of ML models allowed us to rank the risk factors and identify individual risk based on a pre-birth prediction model for NICU admission, which correlated well with the maternal and neonatal adverse outcome prediction.

The study population included 192,527 term neonates, with a 2.75% rate of NICU admission following delivery. Compared to other large-scale studies conducted [ 6 , 14 , 17 , 18 , 19 , 20 ], this admission rate for NICU lays within the lower range; in another study, the risk for NICU admission was 4.1 percent, and risk factors for admission included non-citizen status, low or no health insurance coverage, and premature rupture of membranes [ 23 ]. We suggest that the difference in NICU admission rate may be explained mainly by our study being performed at a single center, with a homogenous population covered by a national healthcare plan, no out of hospital transfers, and a highly trained neonatology service present in the delivery room. In addition, different exclusion criteria and different hospitalization protocols (e.g., induction of preterm premature rupture of membranes prior to term, at 35 weeks’ gestation) could partially explain the difference. We noted a recent increase in the NICU admission rate in the later period of the study that paralleled a large-scale building initiative and center development. This resulted in an increased availability of NICU beds and perhaps made the delivery room/maternity transfer decisions easier, probably leading to more infants with mild respiratory distress in the transition time (the immediate period after delivery) being transferred to the NICU. The main diagnoses by others for a term infant at admission to the NICU are: hypoglycemia, respiratory distress, cardiovascular instability, and hyperbilirubinemia [ 24 ]. Our population showed a similar pattern for diagnoses at the time of the NICU admission. Notably, the transfusion of blood products in critically ill newborns is important and has been a hot topic in recent years. The need for such a transfusion may reflect hemodynamic instability or an ominous in-utero condition, and as such, affects the immediate and long-term prognosis for the neonate. Since our manuscript focused on predicting NICU admission and risk factors at admission for term neonates, we did not include data regarding transfusion, as this would be a manifestation of the underlying disease and would not be the cause of admission per se. In our data, the overall blood transfusion rate for term neonates admitted to the NICU was extremely low, overall, as well as those admitted to the NICU. We assume that this is a rare event for term neonates for which the main indication for blood products transfusion is severe neonatal jaundice/exchange and rare causes of anemia. However, due to the large population in our study, we were able to comprehensively assess maternal background, vital signs and blood tests at admission for birth, characteristics of labor, and neonatal characteristics, which were included in the ML NICU admission risk stratification model. Nevertheless, our study identified nulliparity, pregnancy complications (hypertensive disease and gestational diabetes mellitus), hospitalization during pregnancy, mode of labor initiation, and gestational age at birth of 37 weeks as pre-delivery significant factors for predicting risk of NICU admission.

The strong association between gestational age at birth and the risk for NICU admission questions the definition of “term pregnancy” (≥37 weeks). The present study focused on medically indicated NICU admission for term neonates. Since different institutions use different thresholds for routine admission of near-term infants, we only included term neonates born after 37 + 0 weeks of gestation. Notably, in this population, the risk for NICU admission peaked at 37 + 0 weeks and declined with each additional day within the 37th week, continuously decreasing, reaching a nadir at 39 to 40 weeks’ gestation, followed by an increase reaching a second peak at 42–43 weeks’ gestation. The antenatal care, including US assessment, for the study population is covered by the National Health Insurance plan; the gestational age based on LMP and US is <12 weeks. This minimizes the error in the calculation of the gestational age at birth. Traditionally, infants born after 37 completed weeks’ gestation are classified as “term”. It has been shown that health outcomes vary widely according to week of gestation; morbidities such as respiratory distress syndrome (RDS), transient tachypnea of the newborn (TTN), and hypoglycemia are more common among early term infants, and incidence decreases with increasing gestational age [ 13 , 19 ]. Furthermore, infants born at 34–36 weeks of gestation, considered late pre-term, are more likely to require admission to NICUs [ 25 ]. The time elapsed within the 37th week of gestation remains vaguely defined. The American College of Obstetrics and Gynecology (ACOG) has suggested subdividing infants into groups of early term (37–39 weeks), term (39–41 weeks), late term (41–42 weeks), and post-term (42+ weeks) [ 26 , 27 ]. Our study strongly supports this classification and indicates that neonates born at 37 weeks’ gestation have a risk of NICU admission that is similar to those born at 36 weeks’ gestation rather than term (>38 weeks’ gestation). This is in accordance with other studies that showed that the elimination of early term delivery programs did not lead to a reduction in NICU admissions but were associated with fewer short NICU stays [ 13 ]. We consider that this association with NICU admission risk represents an additional milestone for re-definition of “term” neonates. However, intrapartum sentinel events such as uterine rupture, heavy meconium, and placental abruption should not be underscored as main determinants for NICU admission [ 28 , 29 ].

By using the GBM, our goal was to identify the best predictors for term NICU admission without initial processing, as used in regression models, and at different time points, including before labor and after labor outcome. We identified various pre-labor and during-labor features which were correlated with NICU admission; the ML prediction model that included all data reached a high positive predictive value for each of the features with a high predictive value for the high-risk group. Others have suggested predictive models relating to the NICU population using ML; however, these were not limited to the term neonatal population and mainly focused on NICU admission trends among different epochs and neonatal outcomes during NICU admission [ 30 , 31 , 32 ]. We based our tandem statistical approach based on previous studies which demonstrated that the machine learning methodology was able to determine additional significant medically relevant information for the prognosis, diagnosis, and therapy of several morbidities [ 33 , 34 ]. In our study, we demonstrated that the traditional statistical method risk assessment was highly correlated [R = 0.667 ( p < 0.001)] to the machine learning approach. However, we also demonstrated the superiority of the machine learning approach with an AUC of 0.750 vs. AUC of 0.723, the predictive value of the traditional model. Furthermore, we described another benefit of using the machine learning approach: specifically in the calculation of the relative weight and ranking of each risk factor. We believe this tandem approach of traditional statistics and machine learning provides a template that could be used by others in future research endeavors. Specifically, the application of machine learning to critical care data may provide important assistance in the understanding, prediction, and ranking of critical illness risk factors in infants.

Although the risk assessment correlation between the traditional statistical methods and ML was high, we postulate that using machine learning for the determination of risk factors alone is not only additive to the traditional statistical methods. ML may be used for the calculation of the relative weight and ranking of each risk factor, thus allowing more appropriate risk algorithm production. The issue of risk factors identification and ranking by ML alone in the medical field still requires additional studies in a large and variable population. The present study that used the tandem approach of the multivariate analyses and ML models in the analysis of risk assessment and risk group definition is an example for the future use of this tandem analyses while exploiting the advantages of each approach [ 35 , 36 ].

5. Strengths and Limitations

This study adds to a limited number of studies which examined risk factors and predictive models for term neonates’ NICU admission. The present study focuses on the largest population of neonates, term neonates. It was designed as a large and high-quality study based on validated linked databases within a single institution. This enabled us to adjust our analyses for congenital malformations and genetic syndromes. The use of a single center and neonates born in-hospital offers the advantage of uniform management care, both for obstetrics and neonatology. The antenatal, labor, and all health and hospitalization costs are covered by the National Health Insurance Plan for all mothers and neonates. All of these properties allow us to assess the reliability of the results and reach robust conclusions. Additionally, although the tandem use of multivariate analyses and ML in medicine is emerging, it is currently not widely used for the prediction of NICU admission among neonates and risk ranking and classification; therefore, we consider this study to be an initiator.

Nevertheless, some limitations need to be considered. Firstly, Shaare Zedek Medical Center is located in Jerusalem and serves a relatively homogeneous population, consisting mainly of religious and ultra-Orthodox Jews; therefore, it is not necessarily possible to project our results onto other populations, and therefore, it may have low external validity. However, the great variety of NICU cases and diagnoses is similar to other reports, thus partially mitigating this limitation. In order to better discuss the term definition for newborns, we lack the data on neonates less than 36 weeks; however, this was beyond the aims of the study. In addition, we lacked data on maternal nutrition supplements during pregnancy, BMI, and smoking status, which may have affected NICU admission. However, our population care is covered by the National Health Insurance plan, which is characterized by more than 80% attendance for early pregnancy care and free access to prenatal nutritional supplements.

6. Conclusions

This study integrates multivariate analyses with ML models in the NICU admission risk identification and ranking for term neonates, at different points in time, and especially before birth. Other medical facilities may apply our ML risk ranking and thresholds for the assessment of each individual neonate before birth, thereby tailoring the need for intensive care.

Term newborns: NICU admission rate by year.

Funding Statement

This study was not funded by any organization.

Author Contributions

Conceptualization, R.U.; Data curation, D.G.; Formal analysis, J.G. and R.F.; Investigation, N.S.; Methodology, Y.K.; Supervision, S.G.G.; Validation, M.S.S.; Writing—original draft, S.T.; Writing—review & editing, T.A. All authors have read and agreed to the published version of the manuscript.

Institutional Review Board Statement

The study protocol was approved by the institutional review board (Helsinki) on the basis of an anonymous analysis with a waiver for informed consent (Reference number SZMC_0199-19).

Data Availability Statement

Conflicts of interest.

The authors report no conflict of interest.

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Neonatal Intensive Care Unit (NICU)

Specialized care for newborns at duke university hospital and duke regional hospital.

Duke Health provides all levels of neonatal intensive care for babies born prematurely, at very low birth weight, or with serious medical conditions. We value you and your family as our partners. We strive to answer all your questions, keep you informed, and welcome your input regarding your child’s condition and treatments.

Level IV NICU The sickest and smallest babies receive the highest level of care in the Duke University Hospital Level IV neonatal intensive care unit (NICU). The Level IV designation indicates our NICU is staffed by pediatric medical, surgical, and other subspecialists. We work as a team to provide advanced care to newborns with serious heart, brain, and lung conditions, or abnormalities that are present at birth, such as underdeveloped organs or malformations.

Level II NICU Duke Regional Hospital’s Special Care Nursery is a Level II NICU for infants who need moderate, less urgent care. Often, babies start their care in Duke University Hospital’s NICU and are transferred to this step-down nursery as they continue their journey toward home.

Duke NICUs are located at Duke University Hospital and Duke Regional Hospital in Durham. Our special infant care clinics are located in the Duke Children's Health Center in Durham.

Conditions We Treat

Infants may have complex needs due to the following conditions.

Surgical and Medical Conditions

• Brachial Plexus Birth Palsy Injury
• Complex Surgical Conditions
• Congenital Diaphragmatic Hernia
• Congenital Heart Disease
• Congenital Malformations
• Genetic Disorders
• Pectus Excavatum
• Respiratory Failure
• Retinopathy of Prematurity (ROP)
• Sepsis and Septic Shock
• Vascular Malformations and Hemangiomas

Neurological Conditions

• Abnormal Head Shape in Babies
• Cerebral Palsy and Related Conditions
• Chiari Malformation
• Childhood Seizures and Epilepsy
• Hydrocephalus in Children
• Intraventricular Hemorrhage (IVH)
• Pediatric Neuromuscular Disease
• Perinatal Asphyxia
• Tuberous Sclerosis Complex

Prenatal Care

• Fetal Cardiology
• High-Risk Pregnancy Care
• Placenta Accreta
• Preterm Labor and Preterm Birth Prevention

Why Your Baby May Require Neonatal Intensive Care

Your doctors may determine that your baby requires intensive care after birth, during your pregnancy or at delivery if:

• Your baby is born before 37 weeks of gestation.
• Your baby is diagnosed with a condition during your pregnancy or at birth that requires immediate attention.
• Your baby needs additional support after delivery, such as respiratory or nutritional support, treatment for infection, or close monitoring.
• You are carrying multiples (twins, triplets, or more).
• You have a pre-existing condition during pregnancy that impacts your baby’s health and development after delivery.
• You are diagnosed with abnormal placement or attachment of the placenta. This can lead to significant complications for your baby during and after delivery. Examples include placenta accreta  and placenta previa.
• You are at high risk for carrying a low birth weight baby.

Prenatal Consultation and Planning for Your Baby’s NICU Care Our team of neonatologists, maternal-fetal medicine specialists, pediatric subspecialists, and surgeons work together to assess the health of your unborn baby and counsel you as needed. We prepare you and your family for the delivery of your baby and the potential need for intensive care after birth.

Fetal Diagnostics Center Advanced fetal imaging may be recommended to help doctors detect and monitor issues that can occur as your baby develops.

Delivering Your Baby at Duke University Hospital We work with your obstetrical team through your pregnancy, labor, and delivery at Duke University Hospital’s Birthing Center . The American College of Obstetrics and Gynecology designates our facility as Level IV, which means we are equipped to provide care for the most complex, critically ill pregnant people and fetuses.

We Are a Referral Center for Other Hospitals Ten to 20% of the infants who come to Duke’s NICU are transported to us for specialized care after being delivered elsewhere.

Please check your filter options and try again.

Level IV NICU -- Highest Level of Care

Treatments Available

• Hypothermia to treat infants with suspected brain injury
• Nitric oxide to treat pulmonary hypertension
• Continuous video EEG to diagnose seizure disorders
• Extracorporeal membrane oxygenation (ECMO) or cardiac bypass
• Access to investigational protocols and therapies
• Access to early cardiac intervention

A Team of Specialists Duke University Hospital’s NICU is staffed with neonatologists, neonatal nurse practitioners, and other providers including pharmacists, respiratory therapists, occupational therapists, social workers, and registered dietitian nutritionists with expertise in caring for newborn infants. We also work closely with pediatric specialists across the spectrum to provide the necessary medical and surgical care.

PT/OT and Speech Therapy Duke’s occupational, physical, and speech therapists work with families to monitor developmental progress and provide therapies while in the NICU.

Lactation Consultants Our lactation consultants support new mothers to provide their own milk for their babies while hospitalized; we can provide donor human milk from an HMBANA-certified milk bank when the mother’s milk is not available.

Kangaroo Care We encourage Kangaroo Care for you and your infant when they are safe to participate. This skin-to-skin contact has proven benefits, including stabilizing your baby’s heart rate and helping to regulate body temperature.

Developing New Approaches to Newborn Intensive Care The Duke Division of Neonatology participates in the National Institute of Child Health and Human Development (NICHD) Neonatal Research Network , a consortium of the leading neonatal intensive care units in the country that perform collaborative clinical research to improve neonatal care and outcomes. Our participation in this consortium allows us to develop and implement the latest scientifically proven approaches to neonatal care. It may also provide opportunities for your child to participate in clinical trials of new advances in care. 

Take a tour of Duke Children's Intensive Care Nursery, the largest critical care unit at Duke University Hospital.

Special Care Nursery

Level II NICU Our Level II NICUs provide some services beyond basic well-baby care for premature or sick newborns. This kind of neonatal intensive care unit is best for babies born early who may be underweight and who need equipment to help them breathe.

Babies Transition as Intensive Care Needs Lessen Babies transition to either the Duke University Hospital transitional care nursery or special care nursery at Duke University Hospital or Duke Regional Hospital as their needs for intensive care lessen. They continue to grow and develop skills -- such as feeding -- that are needed before they can safely transition to home.

Special Care Nursery at Duke Regional Hospital Babies in Duke Regional Hospital’s level II NICU receive the same expert care in an environment that may be more convenient and accessible for parents and families.

Learn more about how the staff at Duke Regional's Special Care Nursery care for your child.

Transitional Care After Discharge

Special Infant Care Clinic Our special infant care clinic provides nutrition, feeding, physical, and occupational therapies, as well as support for your child's development after discharge.

Transitional Medical Home Infants with complex problems, including those dependent on technologies such as a ventilator or feeding tube, receive comprehensive care and help during the first year after discharge. Our staff also facilitates the coordination required when multiple subspecialists provide care for complex infants.

Transitional Care for Infants with Complex Needs Once babies with complex needs leave the NICU, they may be followed through a program that provides 24-hour medical support. If your baby is eligible, pediatric specialists walk you through problems that may arise with feeding and mechanical breathing support. This program can prevent the need for babies to be readmitted to the hospital.

Reducing the Risk of Neurodevelopmental Concerns After NICU Follow-up care during the first few years of life can help identify delays early and provide intervention. Duke’s neurodevelopment team makes feeding recommendations, manages feeding tubes, monitors weight gain, supports neurodevelopment, coordinates with other specialists, and receives outpatient therapies.

Neonatal Quality of Life Program This family-centered program is for newborns and infants with life-threatening, and potentially life-limiting, conditions. Our quality-of-life team includes doctors, nurse practitioners, spiritual counselors, and social workers who specialize in maximizing comfort and providing pain and symptom relief. They also provide emotional, psychosocial, and spiritual support for your infant and family.

Duke Children's Hospital & Health Center is proud to be nationally ranked in 10 pediatric specialties.

• UTHealth Houston
• Neonatal-Perinatal Medicine
• Clinical Services
• Clinical Training
• Research Training
• Academic Activities
• Block Rotation Schedule
• Our Fellows
• How to Apply
• On-Going Studies

Learning Healthcare in the NICU

The Division of Neonatology at the University of Texas Health Science Center at Houston and the Children’s Memorial Hermann Hospital Neonatal Intensive Care Unit support the regular evaluation of clinical practices to improve the care and health of our patients.

We call the process of evaluating clinical practices to improve how we treat patients “learning healthcare.”

We implement learning healthcare through partnering with families and healthcare team members to determine the best ways to evaluate our practices. The evaluations we conduct are also overseen by an independent ethics review board .

Studies conducted by the Division of Neonatology at Children’s Memorial Hermann Hospital have impacted local neonatal care and care around the world.

Because of clinical trials of cooling therapy , fewer babies with birth asphyxia die or have handicaps .

Because of a clinical trial of delivery room CPAP , fewer preterm babies develop lung disease .

Because of our neonatal follow-up studies , families around the world have information about what to expect after a preterm baby is born .

• McGovern Medical School Facebook Page
• McGovern Medical School X Page
• McGovern Medical School Instagram Page
• McGovern Medical School YouTube Page
• McGovern Medical School LinkedIn Page
• Medical School IT (MSIT)
• Campus Carry
• Emergency Info
• How to report sexual misconduct
• University Website Policies

The effects of antibiotic therapy on neonatal sepsis-associated acute kidney injury

Affiliations.

• 1 V.I. Kulakov National Medical Research Center of Obstetrics, Gynecology, and Perinatology, Moscow, Russia; A.N. Belozersky Institute of Physico-Chemical Biology, Lomonosov Moscow State University, Moscow, Russia.
• 2 A.N. Belozersky Institute of Physico-Chemical Biology, Lomonosov Moscow State University, Moscow, Russia; Faculty of Bioengineering and Bioinformatics, Lomonosov Moscow State University, Moscow, Russia.
• 3 Independent Researcher, Moscow, Russia.
• 4 A.N. Belozersky Institute of Physico-Chemical Biology, Lomonosov Moscow State University, Moscow, Russia.
• 5 V.I. Kulakov National Medical Research Center of Obstetrics, Gynecology, and Perinatology, Moscow, Russia.
• 6 V.I. Kulakov National Medical Research Center of Obstetrics, Gynecology, and Perinatology, Moscow, Russia; A.N. Belozersky Institute of Physico-Chemical Biology, Lomonosov Moscow State University, Moscow, Russia. Electronic address: [email protected].
• PMID: 38135115
• DOI: 10.1016/j.lfs.2023.122359

Aim: Neonatal sepsis remains one of the most dangerous conditions in the neonatal intensive care units. One of the organs affected by sepsis is the kidney, making acute kidney injury (AKI) a common complication of sepsis. Treatment of sepsis almost always involves antibiotic therapy, which by itself may cause some adverse effects, including nephrotoxicity. We analyzed the mutual effect of antibiotic therapy and sepsis on AKI in an experimental and clinical study in infants and neonatal rats.

Materials and methods: We evaluated the influence of therapy with different antibiotics on the appearance of AKI markers (blood urea nitrogen (BUN), neutrophil gelatinase-associated lipocalin (NGAL), clusterin, interleukin-18 (IL-18), kidney injury molecule-1 (KIM-1), monocyte chemoattractant protein 1 (MCP-1), calbindin, glutation-S-transferase subtype π (GST-π)) and liver injury markers in newborns with or without clinical signs of sepsis in the intensive care unit. In parallel, we analyzed the development of AKI in experimental lipopolysaccharide (LPS)-induced systemic inflammation in newborn rats accompanied by antibiotic therapy.

Key findings: We showed that therapy with metronidazole or ampicillin in combination with sulbactam had a beneficial effect in children with suspected sepsis, resulting in a decrease in AKI markers levels. However, treatment of newborns with netilmicin, cefepime, linezolid, or imipenem in combination with cilastatin worsened kidney function in these patients.

Significance: This prospective study indicates which antibiotics are preferable in neonatal sepsis and which should be used with caution in view of the risk of AKI development.

Keywords: Inflammation; Kidney damage; Liver injury; Sepsis.

Copyright © 2023 Elsevier Inc. All rights reserved.

• Acute Kidney Injury* / drug therapy
• Acute Kidney Injury* / etiology
• Anti-Bacterial Agents / therapeutic use
• Neonatal Sepsis* / complications
• Neonatal Sepsis* / drug therapy
• Prospective Studies
• Sepsis* / complications
• Sepsis* / drug therapy
• Anti-Bacterial Agents

Research Medical Center

If you identify that information regarding hospital or NICU characteristics or neonatal therapy staffing is not accurate for a hospital that you are employed at, please submit updated or additional information

NICU Information

Developmental care oriented, staffing information, get in touch.

Contact us if you have any questions about our database. We will try to provide an answer.

Enter your email if you would be interested in participating in any future research

[email protected]

Find us on Facebook

www.facebook.com/groups/nicutherapylab/

NICU Therapy Lab USC Chan Division of Occupational Science and Occupational Therapy 1540 Alcazar Street, CHP 133, Los Angeles, CA 90089-9003

https://chan.usc.edu/nicu

NICU Combines Expert Care and A Gentle Touch for THE Tiniest Patients

When you need us most, Med Center Health is there to help. For premature or high-risk infants, The Medical Center at Bowling Green offers a Neonatal Intensive Care Unit (NICU), providing state-of-the-art care in the most comfortable setting.

We treat a variety of conditions in newborns including prematurity (usually born before 37 weeks), infants with infections, and heart or respiratory problems. Our high-tech facilities are equipped with the latest instruments and dedicated staff to give the best care close to home.

The Medical Center has highly-trained staff specializing in neonatal medicine, including neonatologists, registered nurses, respiratory therapists, breastfeeding or lactation consultants, occupational and speech therapists, laboratory and radiology technicians and others. We also have medical social workers/discharge planners who work with parents after discharge of newborns to coordinate care and equipment if needed.

We encourage parents to take an active role in helping to care for their infant while in the NICU. Such care, including breastfeeding and skin-to-skin contact or “kangaroo care,” helps in the baby’s recovery and development. Parents are encouraged to visit as often as possible, with 24-hour availability.

The Medical Center at Bowling Green NICU is also the first in Southcentral Kentucky to offer NICVIEW, a camera system and secure online portal that allows parents to view their baby 24-hours-a-day and monitor the care being given.

MHealth is our patient and consumer health portal, which offers secure and convenient access to your health information and helps you manage your and your family’s care.

• Neurology Specialists
• Pediatricians

Neonatal Intensive Care Unit (NICU)

When a baby is born prematurely or with a serious health condition that requires intensive care, our Neonatal Intensive Care Unit (NICU)  is located within the  Family Birth Center . This allows for immediate, on-site care of babies by an extensive team of specially-trained doctors and staff. 

The largest and most comprehensive program of its kind in Maine and New Hampshire, our 51-bed unit cares for more than 900 newborns a year. Expert  neonatologists (specially-trained physicians who care for newborns) provide 24-hour, in-house coverage along with dedicated pediatricians, nurse practitioners, registered nurses, surgeons and respiratory therapists.

On-site Newborn Care in Private Rooms

The NICU is part of  The Barbara Bush Children’s Hospital  at  Maine Medical Center  where we specialize in the care of all newborns. Some just need a little extra help with mastering new skills such as breastfeeding while others require 24/7 intensive care for serious medical conditions.

Each newborn is protected by a private room which allows for recovery and family bonding in a peaceful, soothing environment. Most important, an experienced team of board-certified specialists are always standing by if needed, including:

• Maine’s only pediatric cardiovascular surgeon and pediatric neurosurgeon
• Pediatric cardiologists
• Pediatric neurologists
• Genetic specialists
• Pediatric surgeons
• Pediatric pulmonologists  

This unique team of specially-trained staff is also involved in research that helps provide the newest treatments for your baby.

Dedicated Support for NICU Parents

Ours is the only NICU in the state that has the support of the March of Dimes Family Support Program . This means that a dedicated staff person focuses exclusively on parents and their needs as they go through what can be a scary and difficult time. You can connect with other NICU parents through the  March of Dimes website.

Research & Clinical Trials

Congenital medicine and surgery, related providers.

Alexandria M Betz, DO

• Maternal and Fetal Medicine |
• Obstetrics & Gynecology

Kelley E Conroy, MD

Christian G Litton, MD

Michael G Pinette, MD

Joseph R Wax, MD

Related locations.

InterMed Women's Health

• Phone: 207-874-2445
• Fax: 207-523-8598

MMP Women's Health

• Phone: 207-771-5549
• Fax: 207-761-1759

MMP Women's Health Division of Gynecologic Oncology

• Phone: 207-883-0069
• Fax: 207-883-0999

• NYC Health + Hospitals/Bellevue
• Bellevue Services

Neonatal Intensive Care Unit (NICU) Team

Pradeep N. Mally, M.D.

APPOINTMENTS:   212-562-5555

General:   212-562-3791

Elena V. Wachtel, M.D., M.P.H., F.A.A.P.

Sean Bailey, M.D.

Attending Physician at NYC Health + Hospitals/Bellevue Assistant

Assistant Professor, Department of Pediatrics, New York University School of Medicine

Board Certification:  American Board of Pediatrics (Neonatal-Perinatal Medicine), American Board of Pediatrics (Pediatrics)

Specialty/Area of Expertise:  Neonatal Infection, Hypoxic Ischemic Encephalopathy, Premature Birth, Neonatal Respiratory Distress, Infant Nutrition

Education/Training:  MD from Tufts University, Boston, MA, Fellowship and Residency in Neonatology and Perinatology at New York University, NYC, Residency in Pediatrics at Massachusetts General Hospital, Boston, MA

Languages Spoken:  English

Martha Caprio, M.D., F.A.C.P.

Attending Physician at NYC Health + Hospitals/Bellevue

Associate Professor New York University School of Medicine

Board Certification:  American Board of Pediatrics (Neonatal-Perinatal Medicine), American Board of Pediatrics (Pediatrics) Specialty/Area of Expertise:  Infant Nutrition, Neonatal Infection, Premature Birth, Neonatal Respiratory Distress, Breast Milk, Necrotizing Enterocolitis (NEC)

Education/Training:  MD from University of The Northeast Tampico, Tampico, Mexico, Fellowship in Neonatology from New York University, Residency in Pediatrics at New York University, NYC Languages Spoken:  English, Spanish

Purnahamsi Desai, M.D.

Board Certification:  American Board of Pediatrics (Pediatrics)

Specialty/Area of Expertise:  Neonatology, Pediatrics

Education/Training:  MD from University of Illinois at Chicago College of Medicine, Fellowship in Neonatology from Morgan Stanley Children’s Hospital of New York-Columbia University, and Residency in Pediatrics at St. Louis Children’s Hospital-Washington University in St. Louis, MO.

Heather Howell, M.D.

Board Certification:  American Board of Pediatrics (Neonatal-Perinatal Medicine)

Specialty/Area of Expertise:  Neonatal Respiratory Distress, Hypoxic Ischemic Encephalopathy, Infant Nutrition, Premature Birth, Neonatal Infection

Education/Training:  MD New York Medical College, Valhalla, NY, Fellowship in Pediatrics and Neonatology at Columbia Presbyterian Medical Center, NYC, Residency in Pediatrics at New York University, NYC

Yang S. Kim, M.D.

Board Certification:  American Board of Pediatrics

Specialty/Area of Expertise:  Neonatology, Pediatrics Encephalopathy, Infant Nutrition, Premature Birth, Neonatal Infection

Education/Training:  MD from Pusan University, Korea, Fellowship in Neonatology at New York Hospital Cornell Medical Center, Residency in Pediatrics at NYU Medical Center.

Languages Spoken:  English,Korean

Chief of Neonatology at NYC Health + Hospitals/Bellevue

Associate Professor Pediatrics and Director of the Perinatal and Neonatal Medicine Fellowship Program at New York University School of Medicine

Specialty/Area of Expertise:  Neonatal Respiratory Distress, Premature Birth, Infant Nutrition, Hypoxic Ischemic Encephalopathy, Neonatal Infection

Education/Training:  MD from Kasturba Medical College, India, Fellowship in Neonatology at Westchester County Medical Center, NY, Residency in Pediatrics at Maimonides Medical Center, NYC.

Tara Randis, M.D., M.S.

Specialty/Area of Expertise:  Neonatology

Education/Training:  MD from Drexel University School of Medicine, Philadelphia, PA, Residency in Pediatrics at St. Christopher’s Hospital for Children, Philadelphia, PA, Fellowship in Neonatology at Morgan Stanley Children’s Hospital of New York-Columbia University.

Medical Director of Neonatal ICU/Co-Director of  Regional Perinatal Center  at NYC Health + Hospitals/Bellevue

Board Certification:  American Board of Pediatrics and Neonatal-Perinatal Medicine

Specialty/Area of Expertise:  Hypoxic Ischemic Encephalopathy, Neuroprotection, Neonatal Respiratory Distress, Premature Birth, Infant Nutrition, Neonatal Infection, Public Health.

Education/Training:  MD from Russian State Medical University, Moscow, Russia, Fellowship in Neonatology at New York University, Residency in Pediatrics at Harlem Hospital Center & Columbia University College of Physicians and Surgeons, Master of Public Health from The College of Global Public Health at New York University, NYC.

Languages Spoken:  English,Russian