Artificial intelligence agents in healthcare research: A scoping review
Агенты искусственного интеллекта в исследованиях в области здравоохранения: обзор с картированием
2026-02-10
SCID: 54.1/zcznrnqs
Discuss with AI
AI agentshealthcaremultimodal decision supportretrieval-augmented generationscoping review
Figures from the paper
Abstract (AI)
INTRODUCTION: Artificial Intelligence (AI) agents are rapidly transforming healthcare delivery, enabling real-time decision support and sophisticated patient interaction at scale. However, the scientific landscape of this rapidly growing, multidisciplinary field remains fragmented, with technical innovation outpacing translational research and the establishment of ethical governance frameworks. To address this gap, we conducted a comprehensive scoping review analysis of AI agent research in healthcare. METHODS: We followed scoping review methodology (PRISMA-ScR guidelines). Searches across PubMed, Web of Science, arXiv, and medRxiv were conducted from January 2015 to December 7, 2025. RESULTS: The search identified 1,070 records, of which 43 studies were ultimately included after full-text review. Of these 43 included studies, 36 were published in 2025. Systems were categorized into 8 conversational agents, 17 workflow/automation assistants, and 18 multimodal decision support agents. The core mechanism across all archetypes was external tool use (e.g., retrieval-augmented generation or code execution) for grounding and iterative self-correction (e.g., multi-agent debate or self-debugging loops) for refinement. Evaluation settings were predominantly simulated environments or laboratory studies, with few clinical pilots or real-world deployments. Primary reported outcomes focused on process measures (efficiency) and diagnostic accuracy; clinical outcomes and safety endpoints were rarely addressed. CONCLUSION: Agentic AI systems are rapidly evolving from conceptual frameworks to functional prototypes, primarily targeting complex decision-making and workflow automation. While agentic capabilities are increasingly integrated, research heavily favors simulated evaluations. Future research must prioritize clinical trials and the robust assessment of safety, usability, and clinical efficacy before widespread adoption.
Key Findings
1
Across agent types, external tool use supported grounding, while iterative self-correction mechanisms enabled refinement and error reduction.
2
Evaluations predominantly used simulated or laboratory settings, with few clinical pilots or real-world deployments.
3
Included systems comprised 8 conversational agents, 17 workflow or automation assistants, and 18 multimodal decision-support agents.
4
Reported outcomes mainly concerned efficiency and diagnostic accuracy; clinical outcomes and safety endpoints were rarely assessed.
5
The field is rapidly progressing toward functional prototypes, but clinical trials and rigorous assessments of safety, usability, and efficacy remain necessary before widespread adoption.
6
The scoping review identified 1,070 records, with 43 studies meeting inclusion criteria; 36 of these were published in 2025.
Research Object
AI agent systems in healthcare research
Research Subject
Their architectures, capabilities, evaluation settings, and reported effectiveness, safety, usability, and clinical outcomes
Publication Details
Publication Date
2026-02-10
Journal
Publisher
ISSN
Cited by
25
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest