Agentic AI in Healthcare: Opportunities, Challenges, and Future Directions
Агентный искусственный интеллект в здравоохранении: возможности, вызовы и перспективные направления
2026-05-19
SCID: 54.1/vrmmb69e
Discuss with AI
Agentic AIclinical decision supportelectronic health recordsmedical question-answeringmulti-agent systems
Figures from the paper
Abstract (AI)
The integration of Agentic AI into healthcare marks a new era in medical automation and decision support. Leveraging autonomous reasoning, planning, and collaboration, these AI systems are transforming clinical workflows, diagnostics, and patient management. Recent advancements have led Agentic AI to evolve from single-agent decision-making to multi-agent systems, enabling more sophisticated problem-solving in complex medical environments. In this survey, we provide an in-depth discussion on the core aspects and challenges of Agentic AI in healthcare, including its applications in electronic health records (EHR) interactions, clinical triage, medical question-answering, and disease diagnosis. We categorize existing single-agent and multi-agent frameworks, explore key evaluation metrics, implementation strategies, and commonly used benchmarks, and examine the communication, reasoning, and decision-making processes of these AI agents. Additionally, we address critical challenges such as model reliability, interoperability, ethical considerations, and regulatory constraints. To support further research, we summarize relevant datasets and benchmarks and we outline future research directions that emphasize human-AI collaboration, transparency, and the safe deployment of AI-driven medical systems.
Key Findings
1
Agentic AI is advancing healthcare automation and decision support through autonomous reasoning, planning, and collaboration.
2
Healthcare applications include electronic health record interaction, clinical triage, medical question-answering, and disease diagnosis.
3
Reliable deployment remains constrained by model reliability, interoperability, ethical concerns, regulatory requirements, and the need for transparency and human-AI collaboration.
4
The field is evolving from single-agent decision-making toward multi-agent systems for complex medical problem-solving.
5
The survey categorizes agent frameworks, evaluation metrics, implementation strategies, datasets, and benchmarks for healthcare Agentic AI.
Research Object
Agentic AI systems in healthcare, including single-agent and multi-agent medical systems
Research Subject
Their applications, capabilities, evaluation, implementation, communication, reasoning, decision-making, and challenges in clinical workflows and medical decision support
Publication Details
Publication Date
2026-05-19
Journal
ACM Computing Surveys
Publisher
Association for Computing Machinery
ISSN
0360-0300
Cited by
19
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
Large language models encode clinical knowledge2023
Generative Agents: Interactive Simulacra of Human Behavior2023
Prompt Injection attack against LLM-integrated Applications2023
ChatDev: Communicative Agents for Software Development2024
AgentClinic: a multimodal benchmark for tool-using clinical AI agents2026
Visibility into AI Agents2024
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI2024
Risks of AI scientists: prioritizing safeguarding over autonomy2025