Predicting the risk of bone erosion in rheumatoid arthritis using a SHAP-based interpretable machine learning model
Clinical Rheumatology · 2026
DOI: 10.1007/s10067-026-08289-3 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Clinical Rheumatology, 2026. Verfasst von Lei Yan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, the First Affiliated Hospital, Fujian Medical University, Fuzhou, 350005, China. Hauptthemen laut MEDLINE: Arthritis, Rheumatoid, Machine Learning. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Joint Funds for the Innovation of Science and Technology, Fujian Province, Provincial Subsidy Fund for Health and Wellness from Fujian Provincial Department of Finance, 2022 Medical University Transfer Financial Special Fund Project.
Abstract (Originalsprache)
Objective
Bone erosion (BE) is a critical prognostic indicator in rheumatoid arthritis (RA). This study aimed to develop and validate an interpretable machine learning (ML) model for predicting BE risk in RA patients using the Shapley Additive exPlanations (SHAP) framework.
Methods
This multi-center retrospective study enrolled 412 RA patients without baseline BE. Patients were stratified into BE and non-bone erosion (NBE) groups confirmed by MRI or musculoskeletal ultrasound after a 2-year follow-up. After data preprocessing, including K-nearest neighbors imputation and synthetic minority over-sampling technique-based resampling to address class imbalance, least absolute shrinkage and selection operator regression was applied for feature selection. Ten ML algorithms were trained using fivefold cross-validation with GridSearchCV hyperparameter optimization. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration (Brier score), and decision curve analysis (DCA). For the optimal model, the SHAP framework was utilized to interpret both global and individual feature contributions.
Results
A total of 318 patients from Center 1 were randomly divided into a training set ( n = 222) and an internal-test set ( n = 96) at a 7:3 ratio. The 94 patients from Center 2 constituted an external-test set. The eXtreme Gradient Boosting (XGBoost) model demonstrated superior performance, achieving an AUC of 0.896 on the internal-test set and 0.893 on the external-test set. SHAP global analysis revealed that synovial Power Doppler Imaging (PDI) (mean SHAP value = 2.761), synovial hyperplasia (2.168), disease duration (1.359), and anti-cyclic citrullinated peptide (1.260) were the four most important predictors. DCA showed the XGBoost model provided net benefit across 10%–80% threshold probabilities.
Conclusion
The SHAP-interpretable XGBoost model demonstrates strong discriminative performance in predicting BE risk in RA, highlighting synovial PDI and synovial hyperplasia as pivotal factors.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ultrasound, the First Affiliated Hospital, Fujian Medical University, Fuzhou, 350005, China.
- Department of Ultrasound, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, 350212, China.
- Department of Ultrasound, Fuzhou University Affiliated Provincial Hospital, Fuzhou, China.
- Department of Ultrasound, Fuqing City Hospital, Fujian Medical University, Fuzhou, China.
- Department of Ultrasound, the First Affiliated Hospital, Fujian Medical University, Fuzhou, 350005, China. chenshu0518@163.com.
- Department of Ultrasound, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, 350212, China. chenshu0518@163.com.
Förderung
- Joint Funds for the Innovation of Science and Technology, Fujian Province
- Provincial Subsidy Fund for Health and Wellness from Fujian Provincial Department of Finance
- 2022 Medical University Transfer Financial Special Fund Project
Zitieren
APA
Yan, L., Zheng, Y., Lin, M., Ye, X., & Chen, S. (2026). Predicting the risk of bone erosion in rheumatoid arthritis using a SHAP-based interpretable machine learning model. Clinical Rheumatology. https://doi.org/10.1007/s10067-026-08289-3
Vancouver
Yan L, Zheng Y, Lin M, Ye X, Chen S. Predicting the risk of bone erosion in rheumatoid arthritis using a SHAP-based interpretable machine learning model. Clinical Rheumatology. 2026. doi:10.1007/s10067-026-08289-3
BibTeX
@article{Yan2026,
author = {Yan, Lei and Zheng, Yongqi and Lin, Minghang and Ye, Xiaojian and Chen, Shuqiang},
title = {Predicting the risk of bone erosion in rheumatoid arthritis using a SHAP-based interpretable machine learning model},
journal = {Clinical Rheumatology},
year = {2026},
doi = {10.1007/s10067-026-08289-3}
}
EUVIMED