aceCardiovascular Classification in Middle-Aged and Elderly CKD Patients: A Machine Learning Approach in China and the United States
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 p…
Interpretable ML models classified prevalent CVD among middle-aged and elderly CKD patients with test AUCs of 0.753 in the US NHANES cohort using XGBoost and 0.769 in the China CHARLS cohort using logistic regression.
The same CVD classification models lost discriminative performance when deployed across US and Chinese CKD populations, indicating limited cross-population transportability.
Models showed reduced discriminative performance when deployed across countries, indicating limited cross-population transportability and supporting need for population-calibrated models.
Evidence
- Peer-reviewedDiabetes, Obesity and Metabolism2026-09-27
How should this claim be treated?
Truvace Impact Record TRV-2026-1220, v1: “Cardiovascular Classification in Middle-Aged and Elderly CKD Patients: A Machine Learning Approach in China and the United States.” Truvace, 2026-09-30. /record/TRV-2026-1220 (accessed at citation time). sha256 c3b3351e1f37c4a1…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1220 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.