Privacy-Aware Federated Learning Architectures for Cross-Institutional Healthcare Collaboration

View Sample PDF

Author(s): S. Aarthi (Marwadi University, Rajkot, India)and Jaypalsinh A. Gohil (Marwadi University, Rajkot, India)
Copyright: 2027
Pages: 30
Source title: Managing Sensitive Health Data Through Federated Learning and Generative AI: Privacy Preserving Techniques
Source Author(s)/Editor(s): Manisha Guduri (Lawrence Technological University, USA), George Pappas (Lawrence Technological University, USA)and Sandeep Thota (Oracle Inc., USA)
DOI: 10.4018/979-8-3373-7426-0.ch006

Keywords: Health Information Systems / Information Security & Privacy / Medical Information Science Reference / Security & Forensics

Purchase

View Privacy-Aware Federated Learning Architectures for Cross-Institutional Healthcare Collaboration on the publisher's website for pricing and purchasing information.

Abstract

The chapter explores Privacy-Aware Federated Learning (FL) architectures that enable secure, collaborative healthcare model training without sharing raw patient data. It highlights how Differential Privacy, Secure Multi-Party Computation, and Homomorphic Encryption protect sensitive information during federated aggregation while maintaining model accuracy. The integration of Generative AI enhances data diversity and fairness across institutions. Case studies demonstrate real-world applications in diagnostic imaging and chronic disease prediction. The discussion emphasizes scalability, compliance with HIPAA and GDPR, and the role of blockchain and explainable AI in shaping future digital health ecosystems. The chapter concludes with insights into ethical governance and cross-domain interoperability for transparent and trustworthy healthcare collaboration.

The IRMA Community

Research IRM

Privacy-Aware Federated Learning Architectures for Cross-Institutional Healthcare Collaboration

Purchase

Abstract

Related Content

IRMA Sponsors