Predicting Infection Risk in Rheumatoid Arthritis Patients Treated with Biological and Targeted Synthetic Disease-Modifying Anti-Rheumatic Drugs: An Application of Machine Learning.

Patients with rheumatoid arthritis (RA) on biologic or targeted synthetic DMARDs (b/ts DMARDs) face increased serious infection risk. This study developed and validated a machine learning model to predict one-year risk using data from Hong Kong's CDARS and the U.S. All of Us database. Among 3,159 CDARS and 1,845 All of Us patients, AUROCs were 0.840 and 0.729. Key predictors included prior infections, diabetes, DMARD type, and inflammatory markers. Rituximab posed the highest risk. The model supports personalized RA treatment and infection prevention.