PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 11, 2026Clinical and Experimental Emergency Medicine1 citationsOpen Access

From non-agentic large language models to multi-agent systems in emergency medicine: a scoping review

View Full Paper
HKHyunwoo KimSJSeunghoon JoMLMin Hyuk Lim

Key Points

  • The review aims to assess the role of large language models (LLMs) and how they can evolve into multi-agent systems in emergency medicine.
  • Scoping review of existing literature on LLMs in emergency medicine
  • Analysis of task-level decision support and documentation capabilities
  • Identification of gaps in research regarding dynamic workflows
  • Current focus is primarily on non-agentic LLMs for task support
  • Limited literature on workflows specific to emergency departments
  • Need for future studies on multimodal data integration and operational evaluation

Abstract

LLMs in emergency medicine have shown potential for task-level decision support and documentation. However, current literature remains focused on non-agentic LLM-based task support, while studies reflecting the dynamic workflow of real EDs remain limited. Future research should expand toward workflow-aware design, operational evaluation, multimodal data integration, multi-agent-based role coordination, and safety and trustworthiness validation.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/69d9e64e78050d08c1b76a19https://doi.org/10.15441/ceem.26.136
Ask AI
Helpful
Bookmark
Share
View Full Paper