A comprehensive survey of AI agents in healthcare

Clinical Snapshot

Key Findings

• Effect Size: Not applicable — no quantitative clinical effect sizes reported. Qualitative finding: exponential growth in AI agent publications in healthcare noted

• Primary Outcome: Taxonomic mapping of AI agent architectures in healthcare across three pillars: (1) Perception of multi-modal clinical data (EHR, imaging, genomics); (2) Agent Capabilities (tool use, reasoning, memory, multi-agent collaboration); (3) Application Ecosystem by stakeholder role (clinicians, patients, researchers, administrators)

• Nnt Or Sensitivity: Not applicable — no clinical outcome data synthesised; no diagnostic accuracy, therapeutic efficacy, or prognostic metrics reported

• Confidence Interval: Not applicable — no statistical synthesis performed

Clinical Application

The survey's taxonomic framework may assist health systems in categorising and evaluating AI agent products entering the market. However, the absence of clinical efficacy data, safety benchmarks, and implementation guidance limits direct operational utility. Deployment of AI agents in clinical workflows requires prospective evaluation in real-world settings, which this survey does not provide. In the Australian context, AI agents in healthcare would require TGA regulatory oversight as Software as a Medical Device (SaMD) under the TGA's Digital Health guidance framework. The Australian Digital Health Agency's National Digital Health Strategy 2023–2028 provides relevant governance context. RACGP guidelines on clinical decision support tools would apply to AI agents used in general practice settings. The My Health Record system and interoperability standards (FHIR, HL7) are relevant to EHR-integrated agent deployment. PBS implications are indirect — AI agents may influence prescribing behaviour and require evaluation under PBAC frameworks if they affect medicine utilisation. The Australian Privacy Act 1988 and Health Records legislation impose strict constraints on the data handling practices of AI agents, particularly those using patient-identifiable data for reasoning or memory functions. No Australia-specific studies or regulatory considerations are addressed in this survey. Healthcare organisations, clinical informaticists, health technology assessment bodies, and policymakers considering the adoption or governance of AI agent systems across all clinical domains. Not directly applicable to individual patient care decisions given the absence of clinical outcome evidence.

Abstract

OBJECTIVE: This survey aims to systematically map the rapidly evolving landscape of AI agents in healthcare. It addresses the critical need to adapt general-purpose agentic frameworks characterized by autonomy, planning, and tool use to the high-stakes, safety-critical constraints of medical decision-making and patient care. METHODS: We conducted a comprehensive review of over 200 recent studies, synthesizing literature from major academic databases. We developed a holistic taxonomy that traces the full lifecycle of healthcare agents, analyzing perception modalities, core technical architectures, and evaluation protocols specific to autonomous systems. RESULTS: The review presents a quantitative landscape analysis showing exponential growth in the field. We structure the domain into three pillars: (1) Perception of multi-modal clinical data (e.g., EHR, imaging, genomics); (2) Agent Capabilities, including tool use, reasoning, memory, and multi-agent collaboration; and (3) an Application Ecosystem organized by stakeholder roles (clinicians, patients, researchers, and administrators). Additionally, we categorize evaluation frameworks, and discuss the deployment readiness of current systems across technical, evidentiary, and governance dimensions. Finally, we identify challenges for advancing healthcare agents from controlled evaluation toward real-world clinical integration. A continuously updated repository of related papers is available at https://github.com/AgenticHealthAI/Awesome-AI-Agents-for-Healthcare. CONCLUSION: AI agents offer significant potential to enhance healthcare through autonomous reasoning and workflow integration. However, current research remains largely concentrated in benchmark and controlled evaluation settings, and the translation into clinical practice will require advances in reliability, privacy protection, governance, and operational integration.

References

1. 1.Xu, G., Li, X., Chen, Y., Duan, Y., Wu, S., Yu, H., Chiu, C.-H., Ni, J., Tang, N., Li, T. J.-J., Yuille, A., Jin, W., & Shi, Y. (2026). A comprehensive survey of AI agents in healthcare. Journal of Biomedical Informatics. https://doi.org/10.1016/j.jbi.2026.105045