What question did this study set out to answer?

This research aims to evaluate the effectiveness of machine learning models in predicting gestational diabetes mellitus (GDM).

February 25, 2026BMC Pregnancy and ChildbirthOpen Access

The power of machine learning models in predicting gestational diabetes mellitus

View Full Paper

Ask AI

Bookmark

This research aims to evaluate the effectiveness of machine learning models in predicting gestational diabetes mellitus (GDM).
Conducted a retrospective study using clinical and demographic data from mothers admitted for delivery.
Analyzed data from January 2020 to January 2022 in a primary referral center.
Employed seven machine learning models to assess prediction capabilities using metrics such as accuracy, AUC, precision, recall, and F1 score.
Incidence rate of GDM was found to be 20.9%.
Boosting models, particularly CatBoost and XGBoost, performed best in GDM prediction, with average AUC ranging from 0.64 to 0.66.
CatBoost model showed the highest predictive capability with acceptable accuracy and average recall between 0.43 to 0.52.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Retrospective study investigates machine learning models' ability to predict gestational diabetes mellitus, highlighting their implications for health outcomes.

Cite This Study

Mehrnoush et al. (2026) studied this question.

synapsesocial.com/papers/699e921bf5123be5ed050296 https://doi.org/10.1186/s12884-026-08856-1

View Full Paper

Ask AI

Bookmark

Implication

Retrospective study investigates machine learning models' ability to predict gestational diabetes mellitus, highlighting their implications for health outcomes.

The power of machine learning models in predicting gestational diabetes mellitus

Key Points

Discussion

Implication

Cite This Study

The power of machine learning models in predicting gestational diabetes mellitus

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider