A machine learning-based predictive model for gestational diabetes mellitus based on first trimester clinical indicators

A machine learning-based predictive model for gestational diabetes mellitus based on first trimester clinical indicators. A machine learning-based predictive model for gestational diabetes mellitus based on first trimester clinical indicators Article Open access Published: 28 October 2026 Cite this article You have full access to this open access article Download PDF View saved research A machine learning-based predictive model for gestational diabetes mellitus based on first trimester clinical indicators Download PDF Abstract Gestational diabetes mellitus (GDM) is a common pregnancy complication associated with adverse maternal and neonatal outcomes. Early identification remains challenging because diagnosis typically occurs in the second trimester.

We assessed whether routine first trimester laboratory indicators combined with machine learning (ML) could enable early risk prediction. A total of 260 pregnant women (130 GDM and 130 control) were included and 16 first trimester indicators were collected. The participants were randomly divided into a training (182 women) and a test cohort (78 women).

Nine predictive features were selected from the training cohort using the least absolute shrinkage and selection operator (LASSO) regression. After assessing multicollinearity using collinearity diagnostics, eight ML models were constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curves.

Medical Disclaimer: This article is for informational purposes only and does not constitute medical advice. Always consult with qualified healthcare professionals for medical decisions and treatment options.