The future of digital health with federated learning

Abstract

Abstract Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.

Keywords

Affiliated Institutions

• German Cancer Research Center DE
• Institute on Governance CA
• University Hospital Heidelberg DE
• Philadelphia University US
• King's College London GB
• King's College School GB
• Nvidia (United Kingdom) GB
• Imperial College London GB
• Nvidia (United States) US
• Vanderbilt University US
• Intel (United States) US
• University of Pennsylvania US
• University of Oxford GB
• Technical University of Munich DE
• Heidelberg University DE
• National Institutes of Health US
• Open Group GB

Related Publications