Federated Learning for Cardiovascular Disease Prediction

Federated Learning (FL) is a machine learning technique where multiple decentralized devices (or servers) collaboratively train a shared model while keeping the training data locally on their machines. Instead of sending the raw data to a central server, each device trains the model locally and only shares the model updates such as model parameters with the central server. This study focuses on the application of FL in the healthcare sector, particularly for predicting cardiovascular disease. Our research explores the performance of various classification algorithms and federated averaging techniques in this setup. The results highlight the potential of FL to provide accurate predictive models while safeguarding patient data in sensitive environments such as hospitals.