Comparative analysis of cardiometabolic multimorbidity predictors in China and the USA: A machine learning approach
Authors' conclusion
Our bidirectional, cross-nationally validated ML model enables precision CMM screening. Region-specific strategies are advised: China should prioritize grip strength and balance screening, while the USA focuses on pulse monitoring and psychological interventions.
Study context
- Population
- Participants of CHARLS (China) and HRS (USA), for prediction of cardiometabolic multimorbidity (coexisting cardiovascular disease (CVD) and metabolic diseases)
- Comparison
- Logistic regression (LR) vs gaussian naive Bayes (GNB) vs XGBoost for CVD and MD prediction; China vs USA
- Outcome
- Discrimination (AUC) of machine learning (ML) models predicting CVD and MD
Methodological detailsmachine learning, bidirectional models, cross-national external validation, SHAP analysis
- Machine learning
- Bidirectional models
- Cross-national external validation
- SHAP analysis
Performance
As reported in the abstract
CVD prediction, best model LR, both countries: AUC
0.70
MD prediction, best model in China, LR: AUC
0.71
MD prediction, best model in USA, GNB: AUC
0.65
Further findings
Risk predictors (SHAP)
- Core predictors: disease counts and moderate physical activity
- USA priority predictors: pulse, mild physical activity, emotional problems and falling
- China priority predictors: full-tandem stance and left hand's grip strength
Original publication
Comparative analysis of cardiometabolic multimorbidity predictors in China and the USA: A machine learning approach. Diabetes Res Clin Pract. Published 12 October 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →