Multiple sclerosis (MS) is a neurodegenerative disease with a complex pathogenesis. Re-lapsing-remitting multiple sclerosis (RRMS) is the most common subset of MS, accounting for approximately 85% of cases. Recent studies have shown that ferroptosis may contribute to the progression of RRMS, but the underlying mechanism remains to be elucidated. Herein, this study intended to explore the molecular network of ferroptosis associated with RRMS and establish a predictive model for efficacy diagnosis. Firstly, RRMS-related module genes were identified using weighted gene co-expression network analysis (WGCNA). Secondly, the optimal machine learning model was selected from four options: the generalized linear model (GLM), random forest model (RF), support vector machine model (SVM), and extreme gradient boosting model (XGB). Subsequently, the predictive efficacy of the diagnostic model was evaluated using receiver operator characteristic (ROC) analysis. Finally, a SVM diagnostic model based on five genes (JUN, TXNIP, NCOA4, EIF2AK4, PIK3CA) was established, and it demonstrated good predictive performance in the validation dataset. In summary, our study provides a systematic exploration of the complex relationship between ferroptosis and RRMS, which may contribute to a better understanding of the role of ferroptosis in the pathogenesis of RRMS and provide promising diagnostic strategies for RRMS patients.