Explainable machine learning‐driven predictive modelling of incident cognitive impairment in individuals with early‐stage cardiovascular–kidney–metabolic syndrome: Insights from a longitudinal CHARLS cohort study
Diabetes, Obesity and Metabolism · 2026-03 · 28 (3) · 1693-1709
DOI: 10.1111/dom.70346 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Diabetes, Obesity and Metabolism, online erschienen am 10.12.2025. Verfasst von Shoupeng Duan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, China. Hauptthemen laut MEDLINE: Machine Learning, Cognitive Dysfunction, Metabolic Syndrome, Cardio-Renal Syndrome. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Open Research Project of Hubei Clinical Medical Research Center for Atherosclerotic Cardiovascular Diseases, Anhui Provincial Health and Health Commission Scientific Research Project, First Affiliated Hospital of Bengbu Medical University for Excellent Young Scholars.
Abstract (Originalsprache)
Aims
While cardiovascular–kidney–metabolic (CKM) syndrome has been recognised as a continuum of interconnected metabolic, renal, and cardiovascular dysfunction, practical risk stratification tools for cognitive outcomes in the early, modifiable stages of this syndrome remain lacking. This study aimed to develop an interpretable machine learning model to estimate long‐term risk of incident cognitive impairment among early‐stage CKM syndrome. Materials and Methods This prospective cohort study leveraged data from the China Health and Retirement Longitudinal Study, a nationally representative cohort of adults. A total of 4462 participants with CKM stages 0–2 at baseline (2011) and complete follow‐up through 2020 were included. Incident cognitive impairment was defined as cognitive performance >1 SD below the age‐adjusted mean. Candidate predictors were screened using the Boruta algorithm and LASSO regression, followed by multicollinearity assessment. Nine machine learning models were trained and validated, and their discrimination, calibration, and clinical utility were evaluated. Model interpretability was assessed using Shapley Additive Explanations (SHAP).
Results
During 10 years of follow‐up, 525 participants (11.8%) developed cognitive impairment. Ten predictors were retained, including education, total cholesterol, age, fasting blood glucose, uric acid, estimated glucose disposal rate, diastolic blood pressure, relative fat mass, CKM stage, and metabolic syndrome. The XGBoost model demonstrated the best performance (validation AUC = 0.726), strong calibration, and favourable decision curve benefit. SHAP analysis identified education, total cholesterol, and age as the top predictors.
Conclusions
Our interpretable machine learning framework, built upon readily accessible clinical and metabolic parameters, provides a robust and clinically applicable tool for predicting 10‐year risk of cognitive impairment among individuals with early‐stage CKM syndrome.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, China.
- Department of Cardiology, Renmin Hospital of Wuhan University, Wuhan, Hubei, China.
- West China School of Clinical Medicine, Sichuan University, Chengdu, Sichuan, China.
- Shenzhen Hospital, Southern Medical University, Shenzhen, Guangdong, China.
- Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, China.
- Hubei Clinical Medical Research Center for Atherosclerotic Cardiovascular Diseases, Bengbu, Anhui, China.
ORCID-Profile: Jun Wang
Förderung
- Open Research Project of Hubei Clinical Medical Research Center for Atherosclerotic Cardiovascular Diseases
- Anhui Provincial Health and Health Commission Scientific Research Project
- First Affiliated Hospital of Bengbu Medical University for Excellent Young Scholars
- Science Research Project of Bengbu Medical University
- Clinical and Translational Research Project of Anhui Province
- Research Funds of Joint Research Center for Regional Diseases of IHM
- The Key Project of Natural Science Research of the Anhui Provincial Department of Education
Zitieren
APA
Duan, S., Wang, Y., Yang, X., Xu, Y., & Wang, J. (2026). Explainable machine learning‐driven predictive modelling of incident cognitive impairment in individuals with early‐stage cardiovascular–kidney–metabolic syndrome: Insights from a longitudinal CHARLS cohort study. Diabetes, Obesity and Metabolism, 28(3), 1693-1709. https://doi.org/10.1111/dom.70346
Vancouver
Duan S, Wang Y, Yang X, Xu Y, Wang J. Explainable machine learning‐driven predictive modelling of incident cognitive impairment in individuals with early‐stage cardiovascular–kidney–metabolic syndrome: Insights from a longitudinal CHARLS cohort study. Diabetes, Obesity and Metabolism. 2026;28(3):1693-1709. doi:10.1111/dom.70346
BibTeX
@article{Duan2026,
author = {Duan, Shoupeng and Wang, Yijun and Yang, Xiaomeng and Xu, Yanan and Wang, Jun},
title = {Explainable machine learning‐driven predictive modelling of incident cognitive impairment in individuals with early‐stage cardiovascular–kidney–metabolic syndrome: Insights from a longitudinal CHARLS cohort study},
journal = {Diabetes, Obesity and Metabolism},
year = {2026},
volume = {28},
number = {3},
pages = {1693--1709},
doi = {10.1111/dom.70346}
}
EUVIMED