Personalized Statin Therapy Recommendation Platform Based on Federated Learning

초록

Dyslipidemia, a significant risk factor for cardiovascular disease, is commonly treated with statins. However, individual response variability and potential side effects necessitate personalized statin therapy. This study aimed to develop a federated learning model to recommend personalized statin types and dosages. The model was then integrated into a web-based platform. The results showed promising performance of the federated learning models in predicting the achievement of target LDL-C levels. The study highlights the potential of federated learning in personalizing statin therapy and improving LDL-C management.