Agentic AI in Healthcare 5.0: Reference Architecture, Applications, and Challenges

Abstract

Healthcare systems are increasingly data-rich but remain fragmented, reactive, and difficult to coordinate across institutions, devices, and clinical workflows. Healthcare 5.0 addresses these limitations through human-centricity, resilience, and symbiotic human-artificial intelligence (AI) collaboration. This survey positions agentic AI, goal-oriented systems capable of contextual perception, persistent memory, multistep planning, tool use, and bounded action, as the orchestration layer of Healthcare 5.0. We make four contributions: 1) a reference architecture that maps perception, reasoning, planning, action, and memory across device, edge, and cloud tiers; 2) an autonomy-criticality taxonomy for four healthcare application domains; 3) a structured analysis of safety, security, privacy, ethics, and regulatory challenges; and 4) a phased roadmap for responsible clinical deployment. Our analysis shows that Healthcare 5.0 requires not only capable models, but also safety-governed, auditable, and ethically aligned agentic ecosystems.