Predicting Neonatal Hypoglycemia Using AI Neural Networks in Infants from Mothers with Gestational Diabetes Mellitus.

Abstract

BACKGROUND This study aimed to develop a predictive model for the association between maternal and neonatal anthropometric data and neonatal hypoglycemia based on data from mothers with gestational diabetes mellitus (GDM) and their neonates. MATERIAL AND METHODS We included 106 pregnant women with GDM (based on the World Health Organization International Association of Diabetes and Pregnancy Study Groups) and their neonates. Neonatal hypoglycemia was defined as a threshold of 2.5 mmol/L. Neonatal blood glucose levels were performed at 0, 0.5, 1, 3, and 24 h after birth. An artificial neural network (ANN) and recurrent neural network (RNN) were developed to predict the neonate blood concentrations and investigate the relative contribution of maternal and neonate clinical variables to neonatal hypoglycemia. RESULTS Of 106 mothers with GDM, 85% had obesity, and 78% had vaginal deliveries, with neonates averaging a birth weight of 3335.83 g. The ANN model, based on the clinical data from mothers and neonates, predicted blood glucose levels with a high degree of accuracy, achieving a coefficient of determination of 0.869 and a root mean square error (RMSE) of 0.274. Neonatal birth weight and maternal body mass index were the 2 most significant factors in predicting neonatal hypoglycemia, contributing 18.6% and 15.9%, respectively. The RNN model similarly forecasted glucose levels effectively, addressing the dynamic changes in blood glucose with 0.63 mmol/L RMSE and 0.53 mmol/L mean absolute error. CONCLUSIONS ANN and RNN models effectively predict neonatal hypoglycemia in infants of mothers with GDM, highlighting the critical role of maternal and neonatal factors.