Machine Learning Approach for Predicting Systemic Lupus Erythematosus in Oman-Based Cohort

The study designed a machine learning framework to predict Systemic Lupus Erythematosus (SLE) in a cohort of 219 Omani patients, with 138 having SLE and 81 having other rheumatologic diseases. Using Recursive Feature Selection (RFE) and the CatBoost classification algorithm, the model achieved an AUC score of 0.95 and a Sensitivity of 92%. The SHAP algorithm identified alopecia, renal disorders, Acute Cutaneous Lupus, hemolytic anemia, and patient age as key predictive features. The framework provides explainable predictions validated by rheumatologists, enabling early intervention and improved healthcare outcomes.