University of Victoria

Published purpose

In the last decade, significant advances in artificial intelligence (AI) and machine learning (ML) techniques has created a growing interest in leveraging these techniques to achieve predictive healthcare delivery. It is expected that AI and ML will bring about a paradigm shift in the next generation healthcare systems. Such systems will utilize AI and take advantage of inexpensive high-performance and cloud computing environments. However, ML and AI are data-hungry and data-driven technologies. This characteristic, in particular, could potentially limit the utilization of AI in healthcare systems. The goal of this Project is to address these challenges using federated learning (FL). The Project will develop a secure and scalable federated learning framework for healthcare systems. To demonstrate the application of the proposed framework for predictive healthcare, the project team will extend the precision care ML model developed in a previous project and also create a new predictive model for breast cancer detection. The proposed framework will focus on secure data discovery, data mapping and negotiation, privacy preservation while providing trusted and traceable data access, and a sharing environment for ML-based healthcare systems.