PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 31, 2026Human Factors in Healthcare0 citationsOpen Access

Multi-Agent System for Emergent Care (MAS-EC): Focused on Workload, Efficiency, and User Experience

View Full Paper
ZWZehaan WaljiRBReyansh BadhwarPDParshva Dave

Key Points

  • The research aims to assess the performance of a specialized multi-agent system in emergency first aid situations compared to a large-language model.
  • Conducted a repeated-measures experiment with 13 participants
  • Compared MAS-EC with GPT-4o in CPR and epinephrine scenarios
  • Recorded behavioral efficiency, subjective workload, and usability using established metrics
  • MAS-EC reduced clarification queries by 56%
  • Overall workload as measured by NASA-TLX was significantly lower with MAS-EC
  • Efficiency findings were confirmed through Poisson generalized linear mixed models

Abstract

Efficient, low-workload conversational support is critical when untrained bystanders must deliver urgent first aid. We compared a role-specialized multi-agent system (MAS-EC) with a state-of-the-art large-language model (GPT-4o) across cardiopulmonary resuscitation (CPR) and epinephrine-auto-injector scenarios in a fully counter-balanced, repeated-measures experiment involving 13 participants. Behavioral efficiency (clarification-query count), subjective workload (NASA-TLX), and usability (SASSI) were recorded. Repeated-measures ANOVA showed that MAS-EC cut queries by 56 % ( F = 18.84, p = .001) and reduced overall NASA-TLX scores ( F = 34.95, p < .001). An AI × Task interaction indicated GPT overhead was negligible for CPR but tripled for the more cognitively demanding epinephrine scenario ( F = 20.09, p < .001), whereas SASSI ratings did not differ. Poisson GLMM confirmed efficiency findings despite non-normal count data. The study demonstrates that decentralizing expertise across cooperative agents simultaneously improves interaction efficiency and lowers cognitive load without sacrificing perceived usability. Limitations include a modest sample, text-only simulations, and a single MAS-EC configuration; future work should test multimodal conditions and additional ensemble strategies.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Walji et al. (2026) studied this question.

synapsesocial.com/papers/69cb6541e6a8c024954b9653https://doi.org/10.1016/j.hfh.2026.100133
Ask AI
Helpful
Bookmark
Share
View Full Paper