Mechanistic and Data-Driven Models for Predicting Glucose Levels during Gestation

Gestational diabetes mellitus (GDM) is a prevalent health issue among pregnant women, associated with elevated risks and complications for both maternal and fetal health. Effective blood glucose monitoring in pregnant women is critical for managing GDM and mitigating adverse fetal outcomes.In this study, we evaluate and compare the performance of various modeling approaches—including statistical, data-driven, and mechanistic models—in predicting future glucose levels based on continuous glucose monitoring (CGM) data in pregnant women. The primary objectives are to assess the predictive accuracy of each model type and investigate the potential of hybrid modeling methodologies to enhance glucose management during pregnancy.