Gestational diabetes & diabetes in pregnancy
Artificial Intelligence in Gestational Diabetes Care: A Systematic Review
Authors' conclusion
AI demonstrates strong potential to improve GDM prediction, screening, and management. Nonetheless, broader validation, enhanced model interpretability, and prospective studies in diverse populations are needed to translate these technologies into clinical practice.
Study context
- Population
- Studies of artificial intelligence (AI) models in gestational diabetes mellitus (GDM) care (screening, diagnosis, management, prediction of maternal and neonatal outcomes), published up to February 2025
- Participants
- 126 studies
- Outcome
- Characteristics of AI studies in GDM care
Methodological detailssix electronic databases, QUADAS-2 (modified) risk of bias assessment, Data extraction and quality appraisal independently by six reviewers
- Six electronic databases
- QUADAS-2 (modified) risk of bias assessment
- Data extraction and quality appraisal independently by six reviewers
Pooled result
As reported in the abstract
- Retrospective designs
- 75%
- Sample sizes
- 17 to over 100 000 participants
- AI applications focused on early GDM prediction
- 85%
- Classical machine learning (logistic regression, random forest frequently used)
- 84%
- Internal validation
- 68%
- External validation
- 6%
Further pooled results
Risk of bias
- Overall moderate-to-good methodological quality, with notable deficiencies in analysis reporting
Original publication
Artificial Intelligence in Gestational Diabetes Care: A Systematic Review. J Diabetes Sci Technol. Published 25 August 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →