A fair machine learning model to predict flares of systemic lupus erythematosus.

Journal: JAMIA open
Published Date: Jul 26, 2025

Abstract

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 (re achine learning prediction of SL), a machine learning pipeline that uses electronic health records (EHRs) and contextual-level SDoH to predict 3-month flare risk, emphasizing explainability and fairness.

Authors

  • Yongqiu Li
    University of Florida, Gainesville, Florida, USA.
  • Lixia Yao
    Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA.
  • Yao An Lee
    Pharmaceutical Outcomes & Policy, University of Florida, Gainesville, FL, 32611, United States.
  • Yu Huang
    School of Data Science and Software Engineering, Qingdao University, Qingdao 266021, China.
  • Peter A Merkel
    Division of Rheumatology, Department of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, United States.
  • Ernest Vina
    Division of Rheumatology, College of Medicine, University of Arizona, Tucson, AZ, 85721, United States.
  • Ya-Yun Yeh
    Pharmaceutical Outcomes & Policy, University of Florida, Gainesville, FL, 32611, United States.
  • Yujia Li
    College of Nuclear Technology and Automation Engineering, Chengdu University of Technology, Chengdu, China.
  • John M Allen
    Department of Pharmacy Practice, Purdue University College of Pharmacy, IN, 46202, United States.
  • Jiang Bian
    Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, United States of America.
  • Jingchuan Guo
    Department of Pharmaceutical Outcomes and Policy, University of Florida, Gainesville, FL.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals