Related Experiment Video
Updated: Jun 22, 2025
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
Machine learning risk stratification for high-risk infant follow-up of term and late preterm infants
Katherine Carlton1, Jian Zhang2, Erwin Cabacungan3
1Department of Pediatrics, Division of Neonatology, Medical College of Wisconsin, Milwaukee, WI, USA. kcarlton@mcw.edu.
Insights
Machine learning can identify term and late preterm infants at high risk for abnormal developmental screening. This allows for targeted enrollment in follow-up programs, improving developmental outcomes for at-risk infants.
Area of Science:
- Neonatal intensive care
- Developmental pediatrics
- Machine learning in healthcare
Background:
- Term and late preterm infants discharged from neonatal intensive care units (NICUs) are not routinely enrolled in high-risk follow-up programs.
- There is a need to identify factors predicting abnormal developmental screening in these infants.
- Developing a risk-stratification model is crucial for targeted follow-up enrollment.
Purpose of the Study:
- To identify neonatal intensive care unit (NICU) factors associated with abnormal developmental screening in infants born at or after 34 weeks gestation.
- To develop and evaluate machine learning models for predicting high-risk infants needing follow-up enrollment.
Main Methods:
- Retrospective cohort study of infants born ≥34 weeks gestation admitted to a level IV NICU.
- Development of five machine learning models (CART, random forest, gradient boosting, MARS, regularized logistic regression) using NICU predictors.
- Evaluation of model performance using sensitivity, specificity, accuracy, precision, and AUC.
Main Results:
- 47% of screened infants (87% of cohort) had abnormal developmental screening results.
- Key NICU predictors included oral feeding, discharge medications, and follow-up appointments.
- All models achieved an AUC > 0.7, specificity > 70%, and sensitivity > 60%.
Conclusions:
- Machine learning effectively stratifies developmental risk in term and late preterm infants.
- The study demonstrates the feasibility of using machine learning to expand high-risk infant follow-up criteria.
- The Classification and Regression Tree (CART) algorithm can guide targeted enrollment for infants who would benefit most.
Background:
Term and late preterm infants are not routinely referred to high-risk infant follow-up programs at neonatal intensive care unit (NICU) discharge. We aimed to identify NICU factors associated with abnormal developmental screening and develop a risk-stratification model using machine learning for high-risk infant follow-up enrollment.
Methods:
We performed a retrospective cohort study identifying abnormal developmental screening prior to 6 years of age in infants born ≥34 weeks gestation admitted to a level IV NICU. Five machine learning models using NICU predictors were developed by classification and regression tree (CART), random forest, gradient boosting TreeNet, multivariate adaptive regression splines (MARS), and regularized logistic regression analysis. Performance metrics included sensitivity, specificity, accuracy, precision, and area under the receiver operating curve (AUC).
Results:
Within this cohort, 87% (1183/1355) received developmental screening, and 47% had abnormal results. Common NICU predictors across all models were oral (PO) feeding, follow-up appointments, and medications prescribed at NICU discharge. Each model resulted in an AUC > 0.7, specificity >70%, and sensitivity >60%.
Conclusion:
Stratification of developmental risk in term and late preterm infants is possible utilizing machine learning. Applying machine learning algorithms allows for targeted expansion of high-risk infant follow-up criteria.
Impact:
This study addresses the gap in knowledge of developmental outcomes of infants ≥34 weeks gestation requiring neonatal intensive care. Machine learning methodology can be used to stratify early childhood developmental risk for these term and late preterm infants. Applying the classification and regression tree (CART) algorithm described in the study allows for targeted expansion of high-risk infant follow-up enrollment to include those term and late preterm infants who may benefit most.
