A fair machine learning model to predict flares of systemic lupus erythematosus
JAMIA Open · 03.07.2025 · 8 (4)
DOI: 10.1093/jamiaopen/ooaf072 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 26.07.2025. Verfasst von Yongqiu Li und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, 32611, United States. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objective
Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that disproportionately affects women and racial/ethnic minority groups. Predicting disease flares is essential for improving patient outcomes, yet few studies integrate both clinical and social determinants of health (SDoH). We therefore developed FLAME (FLAre Machine learning prediction of SLE), a machine learning pipeline that uses electronic health records (EHRs) and contextual-level SDoH to predict 3-month flare risk, emphasizing explainability and fairness. Materials and Methods We conducted a retrospective cohort study of 28 433 patients with SLE from the University of Florida Health (2011-2022), linked to 675 contextual-level SDoH variables. We used XGBoost and logistic regression models to predict 3-month flare risk, evaluating model performance using the area under the receiver operating characteristic (AUROC). We applied SHapley Additive exPlanations (SHAP) values and causal structure learning to identify key predictors. Fairness was assessed using the equality of opportunity metric, measured by the false-negative rate across racial/ethnic groups.
Results
The FLAME model, incorporating clinical and contextual-level SDoH, achieved an AUROC of 0.66. The clinical-only model performed slightly better (AUROC of 0.67), while the SDoH-only model had lower performance (AUROC of 0.54). SHAP analysis identified headache, organic brain syndrome, and pyuria as key predictors. Causal learning revealed interactions between clinical factors and contextual-level SDoH. Fairness assessments showed no significant biases across groups.
Discussion
FLAME offers a fair and interpretable approach to predicting SLE flares, providing meaningful insights that may guide future clinical interventions.
Conclusions
FLAME shows promise as an EHR-based tool to support personalized, equitable, and holistic SLE care.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, 32611, United States.
- Polygon Health Analytics LLC, Chalfont, PA, 18914, United States.
- Pharmaceutical Outcomes & Policy, University of Florida, Gainesville, FL, 32611, United States.
- Department of Biostatistics and Health Data Science, Indiana University School of Medicine, IN, 46202, United States.
- Center for Biomedical Informatics, Regenstrief Institute, Indianapolis, IN, 46202, United States.
- Division of Rheumatology, Department of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, United States.
Zitieren
APA
Li, Y., Yao, L., Lee, Y. A., Huang, Y., Merkel, P. A., Vina, E., Yeh, Y. Y., Li, Y., Allen, J. M., Bian, J., & Guo, J. (2025). A fair machine learning model to predict flares of systemic lupus erythematosus. JAMIA Open, 8(4). https://doi.org/10.1093/jamiaopen/ooaf072
Vancouver
Li Y, Yao L, Lee YA, Huang Y, Merkel PA, Vina E, et al. A fair machine learning model to predict flares of systemic lupus erythematosus. JAMIA Open. 2025;8(4). doi:10.1093/jamiaopen/ooaf072
BibTeX
@article{Li2025,
author = {Li, Yongqiu and Yao, Lixia and Lee, Yao An and Huang, Yu and Merkel, Peter A and Vina, Ernest and Yeh, Ya-Yun and Li, Yujia and Allen, John M and Bian, Jiang and Guo, Jingchuan},
title = {A fair machine learning model to predict flares of systemic lupus erythematosus},
journal = {JAMIA Open},
year = {2025},
volume = {8},
number = {4},
doi = {10.1093/jamiaopen/ooaf072}
}
EUVIMED