Key result
Machine learning classifies CVD in CKD with ~0.77 AUC but demonstrates limited cross-population transportability.
Why the study?
Conventional cardiovascular risk tools underperform in CKD patients, and few machine learning models have undergone cross-national validation for CVD classification in this population.
Can machine learning models accurately classify cardiovascular disease in middle-aged and elderly CKD patients across different national populations?
Cross-Sectional (n=2,166)
Yes
Can machine learning models accurately classify cardiovascular disease in middle-aged and elderly CKD patients across different national populations?
Cardiovascular disease-associated feature profiles differ substantially between US and Chinese CKD patients, demonstrating the necessity of population-calibrated machine learning classification models rather than unified cross-national models.
Moderate AUCs and poor transportability caution against clinical adoption; leaves open whether population-calibrated ML improves CVD classification in CKD.
Background Cardiovascular disease (CVD) drives mortality in chronic kidney disease (CKD) patients. Conventional risk tools underperform in CKD, and few machine learning (ML) models undergo cross‐national validation. We developed interpretable ML models for classifying CVD amongst Chinese and US middle‐aged and elderly CKD patients. Methods We conducted retrospective cross‐sectional analyses using two nationally representative cohorts: NHANES (2011–2016, US) and CHARLS (Wave 1 and 3, China). A total of 1057 CKD patients from NHANES and 1109 from CHARLS were included. Seven ML algorithms were trained and optimized. Model performance was assessed on internal test sets and via bidirectional cross‐population external validation. Model interpretability was achieved using SHAP (SHapley Additive exPlanations) analysis. Results The XGBoost model performed best in NHANES (test AUC: 0.753), while the Logistic Regression model was optimal for CHARLS (test AUC: 0.769). During bidirectional external validation, both models showed a decline in discriminative performance when deployed across populations, indicating limited cross‐population transportability. SHAP analysis revealed distinct feature contribution profiles: Age ranked as the top contributing feature in the US cohort, whereas hypertension was the primary contributing features in the Chinese cohort. Conclusion CVD‐associated feature profiles differ substantially between US and Chinese middle‐aged and elderly CKD patients, supporting the necessity of population‐calibrated classification models rather than applying a unified model across countries.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) conducted a cross-sectional in Chronic kidney disease (CKD) (n=2,166). Machine learning models for CVD classification was evaluated on Cardiovascular disease classification performance (AUC). Machine learning models for classifying cardiovascular disease in CKD patients achieved AUCs of 0.753 (US) and 0.769 (China), with distinct feature profiles and limited cross-population transportability.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: