Interpretable Machine Learning Framework for Predicting Major Adverse Cardiovascular Events in Rheumatoid Arthritis Using Electronic Health Records: Multicenter Cohort Study
JMIR Formative Research · 2026-06-05 · 10 · e91790-e91790
DOI: 10.2196/91790 ↗At a glance
Multizentrische Studie in JMIR Formative Research, published online on 2026-06-05. Written by Wei-Chen Chiang and 8 co-authors. Institution: Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 9F, Education and Research Buildi…. Major MEDLINE topics: Arthritis, Rheumatoid, Cardiovascular Diseases, Machine Learning. 53 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Patients with rheumatoid arthritis (RA) face higher risks of major adverse cardiovascular events than the general population. While machine learning offers powerful predictive capabilities, its clinical adoption is hindered by the “black-box” nature of complex algorithms.
Objective
This study aimed to develop interpretable survival models to predict the risk of major adverse cardiovascular events in patients with RA, providing transparent and actionable insights for personalized clinical prognosis management.
Methods
Using data from the Taipei Medical University Clinical Research Database (2011-2022) for 2461 patients with RA, machine learning survival models, including random survival forest (RSF), DeepSurv, and Cox-Time, were compared with the traditional Cox proportional hazards model. Performance was evaluated using the C-index and integrated Brier score. Permutation importance and Shapley additive explanations (SHAP) analyses were integrated to provide explainability for individual-level risk predictions.
Results
RSF demonstrated superior performance, achieving a C-index of 0.8771 and an integrated Brier score of 0.0775. Permutation importance identified key features, including creatinine, conventional synthetic disease-modifying antirheumatic drugs, C-reactive protein, alanine aminotransferase, and age at RA diagnosis. SHAP analysis further quantified feature-specific effects, revealing both protective and risk-increasing associations between medications and laboratory indicators.
Conclusions
RSF outperformed traditional methods, and integrating SHAP enabled transparent, personalized risk interpretation, translating complex models into actionable insights for clinicians. This approach empowers clinicians to identify high-risk individuals and advances precision medicine in rheumatology. Future work should include temporal validation using data from later years and external validation using datasets from other health care systems to further assess model generalizability.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 9F, Education and Research Building, Shuang Ho Campus No. 301, Yuantong Rd, Zhonghe Dist, New Taipei, 2…
- Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Taipei Medical University-Shuang Ho Hospital, Ministry of Health and Welfare, New Taipei City, Taiwan.
- Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Ministry of Health and Welfare, Taipei, Taiwan.
- School of Nursing, College of Medicine, National Taiwan University, Taipei, Taiwan.
- International Center for Health Information and Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
- Graduate Institute of Data Science, College of Management, Taipei Medical University, Taipei, Taiwan.
ORCID profiles: Wei-Chen Chiang, Guan-Ling Lin, Yu-Sheng Chang, Yu-Chen Liu, Chih-Wei Huang, Phung Anh Nguyen, Jason C Hsu, Der-Ming Liou, Hsuan-Chia Yang
Cite
APA
Chiang, W. C., Lin, G. L., Chang, Y. S., Liu, Y. C., Huang, C. W., Nguyen, P. A., Hsu, J. C., Liou, D. M., & Yang, H. C. (2026). Interpretable Machine Learning Framework for Predicting Major Adverse Cardiovascular Events in Rheumatoid Arthritis Using Electronic Health Records: Multicenter Cohort Study. JMIR Formative Research, 10, e91790-e91790. https://doi.org/10.2196/91790
Vancouver
Chiang WC, Lin GL, Chang YS, Liu YC, Huang CW, Nguyen PA, et al. Interpretable Machine Learning Framework for Predicting Major Adverse Cardiovascular Events in Rheumatoid Arthritis Using Electronic Health Records: Multicenter Cohort Study. JMIR Formative Research. 2026;10:e91790-e91790. doi:10.2196/91790
BibTeX
@article{Chiang2026,
author = {Chiang, Wei-Chen and Lin, Guan-Ling and Chang, Yu-Sheng and Liu, Yu-Chen and Huang, Chih-Wei and Nguyen, Phung Anh and Hsu, Jason C and Liou, Der-Ming and Yang, Hsuan-Chia},
title = {Interpretable Machine Learning Framework for Predicting Major Adverse Cardiovascular Events in Rheumatoid Arthritis Using Electronic Health Records: Multicenter Cohort Study},
journal = {JMIR Formative Research},
year = {2026},
volume = {10},
pages = {e91790--e91790},
doi = {10.2196/91790}
}
EUVIMED