Antenatal Prediction Model for Neonatal Intensive Care Unit Admission in Late Preterm Infants

Area of Science:

• Obstetrics and Gynecology
• Neonatal Medicine
• Clinical Prediction Modeling

Background:

• Late preterm infants (34-36 weeks gestation) have higher risks of adverse outcomes.
• Accurate prediction of neonatal intensive care unit (NICU) admission is crucial for resource allocation and timely intervention.
• Existing prediction tools may not fully utilize routinely available antenatal data.

Purpose of the Study:

• To develop and internally validate an antenatal prediction model for NICU admission in late preterm infants.
• To identify key maternal and obstetric predictors of NICU admission.
• To create a nomogram for individualized risk assessment.

Main Methods:

• Retrospective observational cohort study of 2007 late preterm deliveries.
• Variable selection using LASSO and penalized logistic regression.
• Model validation included C-index, bootstrap analysis, calibration, and decision curve analysis.

Main Results:

• The final model included gestational age, fetal growth restriction, twin pregnancy, cesarean delivery, and antenatal corticosteroids.
• The model showed good discrimination (C-index ~0.75) and excellent calibration.
• A nomogram was developed for estimating individual NICU admission risk.

Conclusions:

• A validated antenatal prediction model using routine clinical data can estimate NICU admission risk for late preterm infants.
• The developed nomogram facilitates individualized risk assessment.
• External validation is recommended to confirm generalizability.