Gestational diabetes & diabetes in pregnancy
Data-Driven Phenotypic Clusters of Gestational Diabetes Mellitus and Associations With Risk of Perinatal Complications and Postpartum Diabetes
Authors' conclusion
Our study identified distinct data-driven GDM phenotypic clusters with differential risks of perinatal complications and postpartum diabetes.
Study context
- Population
- Individuals with gestational diabetes mellitus (GDM) followed up through 12 years postpartum
- Participants
- 37,544 individuals
- Exposure
- Data-driven GDM phenotypic clusters C2–C4 vs C1
- Outcome
- Perinatal complications and postpartum diabetes
- Follow-up
- Through 12 years postpartum
Methodological detailsmachine learning clustering, discovery (70%) and validation (30%) sets, covariate-adjusted modified Poisson and Cox regression
- Machine learning clustering
- Discovery (70%) and validation (30%) sets
- Covariate-adjusted modified Poisson and Cox regression
Main finding
As reported in the abstract
Each group vs C1Estimate (95% CI)
C4
adjusted RR, severe maternal morbidity 1.43(1.19–1.72)
C4
adjusted RR, neonatal intensive unit admission 1.53(1.41–1.66)
C4
aHR, diabetes 4.32(3.94–4.73)
Observational data: associations, not effects.
Further findings
Cluster distribution in validation set
Subclusters within C1
- Three subclusters within C1, with differential risks of perinatal complications but not postpartum diabetes
Original publication
Data-Driven Phenotypic Clusters of Gestational Diabetes Mellitus and Associations With Risk of Perinatal Complications and Postpartum Diabetes. Diabetes Care. Published 17 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →