Federated Split Learning for Privacy Preserving Healthcare Data Analysis

The fast shift to digital health records has made it more urgent to analyze data safely without risking personal info. Instead of gathering everything in one place - which can expose private details old style machine learning creates serious leaks for patient trust. Our work introduces Federated Split Learning (FSL), a method that keeps medical data under lock at each clinic while still allowing teams to train smart algorithms together. At every hospital involved, part of an AI network learns from local cases; then just the processed signals - not raw files - are sent to a main hub. By mixing FL’s off-site safety with SL’s split-task speed, this setup boosts both security and smarts across hospitals. A test run with fake medical data shows the FSL setup keeps accuracy high while cutting down on how much info gets exposed. These findings suggest Federated Split Learning gives a solid, safe way to analyze health records without risking privacy.