A comprehensive survey of AI agents in healthcare

Комплексный обзор ИИ-агентов в здравоохранении
Alan Yuille, Yiyu Shi, Wei Jin, Toby Jia-Jun Li, Gelei Xu, Xueyang Li, Yixiong Chen, Yuying Duan, Shuqing Wu, Haoxinran Yu, Ching-Hao Chiu, Juntong Ni, Ningzhi Tang, Yixiong Chen, Ching-Hao Chiu
2026-04-18

AI agents in healthcareautonomous systemsclinical decision-makingmulti-agent collaborationmultimodal clinical data
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.
1
Applications are structured by stakeholder roles, including clinicians, patients, researchers, and administrators.
2
Current research is concentrated in benchmark and controlled settings; clinical translation requires improved reliability, privacy, governance, and operational integration.
3
Healthcare agent capabilities are organized around tool use, reasoning, memory, and multi-agent collaboration across clinical workflows.
4
It introduces a lifecycle-oriented taxonomy covering multimodal clinical perception, agent capabilities, applications, and evaluation protocols.
5
The survey synthesizes over 200 recent studies to systematically map the rapidly expanding field of AI agents in healthcare.

AI agents in healthcare

their perception, capabilities, applications, evaluation, and deployment readiness under medical safety, reliability, privacy, governance, and clinical-integration constraints

Publication Details
Publication Date
2026-04-18
Journal
Publisher
ISSN
Cited by
41
Access Type
Author Information
Authors
Alan Yuille
Yiyu Shi
Wei Jin
Toby Jia-Jun Li
Gelei Xu
Xueyang Li
Yixiong Chen
Yuying Duan
Shuqing Wu
Haoxinran Yu
Ching-Hao Chiu
Juntong Ni
Ningzhi Tang
Yixiong Chen
Ching-Hao Chiu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%