A body roundness index (BRI)-based predictive model for metabolic syndrome in perimenopausal and postmenopausal women-from a cross-sectional machine learning study to a longitudinal dynamic assessment
5 hours ago
- #body roundness index
- #metabolic syndrome
- #menopausal women
- Study developed a Body Roundness Index (BRI)-based model to predict metabolic syndrome (MetS) in perimenopausal and postmenopausal women, combining cross-sectional machine learning with longitudinal assessment.
- Cross-sectional analysis used NHANES 2007-2020 and hospital data; artificial neural network (ANN) performed best (AUC up to 0.878), with BRI, WBC, ALT, MCV, and AST as top predictors per SHAP analysis.
- Longitudinal analysis in a 10-year cohort showed that integrating annual change rates and cumulative exposure of key predictors improved risk prediction (C-index 0.847, time-dependent AUCs up to 0.859).
- Findings highlight BRI's strong association with MetS in this population, offering both a screening tool (ANN) and enhanced long-term prediction via longitudinal trajectories.