SECUREHEALTH: EDGE-ENHANCED FEDERATED ARCHITECTURE WITH ZERO-TRUST FRAMEWORK FOR PRIVACY-PRESERVED PATIENT MONITORING

Abstract

This article introduces a novel architectural framework that addresses the critical challenges of privacy, security, and real-time monitoring in modern healthcare systems. The proposed Edge-Enhanced Federated Cloud Architecture (EEFCA) integrates edge computing capabilities with federated learning principles, underpinned by a comprehensive zero-trust security framework. By processing sensitive health data at the edge and implementing federated learning for distributed model training, the architecture significantly reduces data exposure while maintaining analytical capabilities. The zero-trust framework ensures continuous verification of access requests, establishing a robust security posture across all architectural layers. Implementation in a real-world remote patient monitoring scenario demonstrates the architecture's effectiveness in reducing latency while enhancing privacy preservation and regulatory compliance. Comparative analysis against traditional cloud-based solutions reveals substantial improvements in both performance and security metrics. The proposed framework provides a scalable and secure foundation for next-generation healthcare systems, effectively balancing the demands of real-time monitoring with stringent privacy requirements. This article contributes to the growing body of knowledge in secure healthcare systems, offering practical insights for implementing privacy-preserved patient monitoring at scale.