Embedding Neonatal Mortality Prediction into Perinatal Workflows: A Machine-Learning Approach from the IMaN Registry

Neonatal mortality remains a major challenge in resource-limited settings, where delayed recognition of high-risk cases and inconsistent clinical decisions hinder timely and targeted interventions, which are essential for reducing preventable deaths. In response, this study developed and evaluated machine-learning models to predict neonatal death using maternal and neonatal features collected both before and after delivery. To this end, guided by the CRISP-DM data-mining framework, we analyzed a dataset of ۷,۲۱۴ births (۵,۰۰۰ survivors and ۲,۲۱۴ deaths) from ۲۰۲۱–۲۰۲۲, derived from routinely collected records in the Iranian Maternal and Neonatal (IMaN) registry. As a result, among the data-mining models—Random Forest, XGBoost, and Support Vector Machine—trained with imbalance-sensitive techniques, XGBoost achieved the best performance (ROC-AUC = ۰.۹۶۷, PR-AUC = ۰.۹۴۰). Feature importance analysis identified gestational age (importance = ۰.۱۷۹) and birth weight (۰.۱۰۹) as the dominant predictors, followed by nervous system malformations (۰.۰۳۵), musculoskeletal malformations (۰.۰۳۳), high-risk delivery indicators (۰.۰۳۲), and other congenital malformations (۰.۰۳۱). The contribution of this study is in twofolds, first, these findings demonstrate that accurate, real-time prediction of neonatal mortality is achievable. Seconds, beyomd a prognostic tool, the final model can serve as an operational lever within neonatal services; when embedded into a clinical decision support system, it can enhance early risk detection, improve triage accuracy, facilitate timely NICU preparedness, and strengthen overall process reliability and system performance in resource-limited care settings.

Keywords:

Neonatal mortality , Improving neonatal services system , Machine learning , Clinical decision support system , Prediction of neonatal mortality