Agentic AI in Healthcare and Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-Based Agents
IEEE Access · 2026 · 14 · 4840-4863
DOI: 10.1109/access.2026.3651218 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Shubham Vatsal und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 134 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Agentic AI, realized as Large Language Model (LLM)-based agents that plan, use tools and act has begun to shape healthcare and medicine. They have been proven to excel at numerous tasks ranging from EHR analysis and differential diagnosis to treatment planning and research workflows. Yet the literature lacks a consistent lens to compare designs and appraise evidence. We review 49 studies and introduce a seven-dimensional taxonomy: Cognitive Capabilities, Knowledge Management, Interaction Patterns, Adaptation & Learning, Safety & Ethics, Framework Typology and Core Tasks & Subtasks with 29 operational sub-dimensions. Using explicit inclusion and exclusion criteria and a labeling rubric (Fully Implemented ✓, Partially Implemented ∆, Not Implemented ✗), we map each study to the taxonomy and report quantitative summaries of capability prevalence and co-occurrence patterns. Our empirical analysis surfaces clear asymmetries. For instance, the External Knowledge Integration sub-dimension under Knowledge Management is commonly realized (∼76% ✓) whereas Event-Triggered Activation sub-dimenison under Interaction Patterns is largely absent (∼92% ✗) and Drift Detection & Mitigation sub-dimension under Adaptation & Learning is rare (∼98% ✗). Architecturally, Multi-Agent Design sub-dimension under Framework Typology is the dominant pattern (∼82% ✓) while orchestration layers remain mostly partial. Across Core Tasks & Subtasks, information centric capabilities lead e.g., Medical Question Answering & Decision Support and Benchmarking & Simulation, while action and discovery oriented areas such as Treatment Planning & Prescription still show substantial gaps (∼59% ✗). Together, these findings provide an empirical baseline indicating that current agents excel at retrieval-grounded advising but require stronger adaptation and compliance platforms to move from early-stage systems to dependable clinical systems.
Zitieren
APA
Vatsal, S., Dubey, H., & Singh, A. (2026). Agentic AI in Healthcare and Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-Based Agents. IEEE Access, 14, 4840-4863. https://doi.org/10.1109/access.2026.3651218
Vancouver
Vatsal S, Dubey H, Singh A. Agentic AI in Healthcare and Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-Based Agents. IEEE Access. 2026;14:4840-4863. doi:10.1109/access.2026.3651218
BibTeX
@article{Vatsal2026,
author = {Vatsal, Shubham and Dubey, Harsh and Singh, Aditi},
title = {Agentic AI in Healthcare and Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-Based Agents},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {4840--4863},
doi = {10.1109/access.2026.3651218}
}
EUVIMED