Data-Driven Phenotypic Clusters of Gestational Diabetes Mellitus and Associations With Risk of Perinatal Complications and Postpartum Diabetes
Abstract
Objective: Management of gestational diabetes mellitus (GDM) largely follows a uniform approach, despite growing recognition of GDM heterogeneity. We aimed to identify data-driven GDM clusters by using machine learning techniques and clinical data and to assess their associations with perinatal complications and postpartum diabetes risk.
Research design and methods: In a population-based cohort study, 37,544 individuals with GDM were followed up through 12 years postpartum. In the discovery (70%) and validation (30%) sets, we applied dimension reduction and clustering methods using routinely available sociodemographic, behavioral, and clinical variables. Covariate-adjusted modified Poisson and Cox regression models were used to assess associations of GDM clusters with risk of perinatal complications and postpartum diabetes.
Results: Four data-driven GDM phenotypic clusters were identified. Cluster 1 (C1) (65.6%), C2 (14.5%), C3 (12.0%), and C4 (7.8%) comprised the discovery set, with similar distributions in the validation set (C1-C4 66.7%, 14.0%, 12.0%, 7.4%, respectively). C2-C4 compared with C1 (late-diagnosed, lower-BMI, and postload hyperglycemia GDM) were associated with higher risks of perinatal complications and new-onset postpartum diabetes, especially C4 (early-diagnosed, comorbidity-related, and high-glucose challenge test GDM) (adjusted relative risks: severe maternal morbidity 1.43 [95% CI 1.19, 1.72] and neonatal intensive unit admission 1.53 [1.41, 1.66];…
How strong is the evidence?
Evidence Hub reads this as a cohort study, done in people. Its evidence level is 3 of 5 (Moderate · trial / cohort / secondary analysis). Trials without a large randomized design, cohorts and secondary analyses give moderate evidence. Reported size: 37,544 participants or records.
Read the paper
Related studies
- Increased expression of circulating miRNA-93 in women with polycystic ovary syndrome may represent a novel, non-invasive biomarker for diagnosis
- Identification of key genes associated with polycystic ovary syndrome (PCOS) and ovarian cancer using an integrated bioinformatics analysis
- Identification of key pathways and genes in polycystic ovary syndrome via integrated bioinformatics analysis and prediction of small therapeutic molecules
- Regulation of Androgen Receptor Expression Alters AMPK Phosphorylation in the Endometrium: In Vivo and In Vitro Studies in Women with Polycystic Ovary Syndrome
- Effect of oral administration of low-dose follicle stimulating hormone on hyperandrogenized mice as a model of polycystic ovary syndrome
- Systems pharmacology to investigate the interaction of berberine and other drugs in treating polycystic ovary syndrome
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.