Gestational diabetes & diabetes in pregnancy
The use of machine learning to predict pharmacological therapy in gestational diabetes: A scoping review
Authors' conclusion
Logistic regression with common clinical variables was often used to predict pharmacological therapy for GDM. Few models were externally validated or clinically applicable.
Study context
- Population
- Studies predicting pharmacological therapy for gestational diabetes mellitus (GDM) using machine learning; Embase, Medline, IEEE Xplore and Web of Science, 1 July 2007–31 August 202417 studies · 44 models
- Outcome
- Machine learning models predicting pharmacological therapy in GDM
Methodological detailsPRISMA-ScR, Joanna Briggs Institute methodology, PROBAST quality assessment
- PRISMA-ScR
- Joanna Briggs Institute methodology
- PROBAST quality assessment
Main finding
As reported in the abstract
Models predicting any pharmacological therapy use
61.4%
27/44
Models predicting insulin use alone
38.6%
17/44
Overall AUC, median
0.75
Models validated; lack of external validation
65.9%
Original publication
The use of machine learning to predict pharmacological therapy in gestational diabetes: A scoping review. Diabet Med. Published 18 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →