Abstract:
Remote stakeholders analyze patient records in the smart healthcare system, improving QoL. To train AI models for disease prediction, the Internet must exchange a lot of data. Data privacy and model training at centralized servers are at risk due to communication channels’ openness. Federated learning (FL) can solve this. It trains the global model using client node results. Local training protects patient data, which aids training. FL’s benefits in healthcare are underutilized. Existing surveys mostly focused on FL’s role in various applications, but none covered FL in healthcare informatics (HI). We compare recent and proposed surveys. We proposed a FL-based layered healthcare informatics architecture and FL-EHR case study to improve patient QoL and healthcare data privacy. We discuss emerging FL models and statistical and security issues in medical FL adoption. Thus, the review helps academia and healthcare practitioners study FL application in HI ecosystems.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
