Development of an Explainable Machine Learning Model for Cardiovascular-Kidney-Metabolic Syndrome Prediction Based on Dietary Antioxidants in a National Population
XGBoost effectively predicted advanced CKM stages using a concise set of seven features. Explainable AI approaches such as SHAP enhance model transparency and clinical translation, supporting personalized CKM risk stratification based on dietary antioxidant patterns.
Authors
- Wenquan Niu (ORCID: https://orcid.org/0000-0003-1715-3372)
- Nan Ma (ORCID: https://orcid.org/0000-0003-4006-1003)
- Bo-Chun Wang
- Xiao-Qun Dong
- Xiaoqian Zhang (ORCID: https://orcid.org/0000-0003-3703-4784)
- Mei Xue (ORCID: https://orcid.org/0000-0002-7658-7552)
- Xiaoqian Wang (ORCID: https://orcid.org/0000-0002-3144-8903)
- Hannah Chang
- Chung-Chou H. Chang
Institutions
- University of Pittsburgh (US)
- Beijing University of Chinese Medicine (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- University of Michigan (US)
- China-Japan Friendship Hospital (CN)
- Capital Institute of Pediatrics (CN)
- Northeast Forestry University (CN)
- Michigan State University (US)
Publication Details
- Journal
- Journal of Vascular Research
- Published
- 2025-11-06
- DOI
- https://doi.org/10.1159/000549326
- Primary Topic
- Nutritional Studies and Diet
- Type
- article
- Field-Weighted Citation Impact
- 0.00