Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.21228 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908609697284096 |
|---|---|
| author | Li, Xiang Yu, Huizi Wang, Wenkong Wu, Yiran Zhou, Jiayan Hua, Wenyue Lin, Xinxin Tan, Wenjia Zhu, Lexuan Chen, Bingyi Chen, Guang Chen, Ming-Li Zhou, Yang Li, Zhao Assimes, Themistocles L. Zhang, Yongfeng Wu, Qingyun Ma, Xin Li, Lingyao Fan, Lizhou |
| author_facet | Li, Xiang Yu, Huizi Wang, Wenkong Wu, Yiran Zhou, Jiayan Hua, Wenyue Lin, Xinxin Tan, Wenjia Zhu, Lexuan Chen, Bingyi Chen, Guang Chen, Ming-Li Zhou, Yang Li, Zhao Assimes, Themistocles L. Zhang, Yongfeng Wu, Qingyun Ma, Xin Li, Lingyao Fan, Lizhou |
| contents | Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This study aimed to develop and evaluate a taxonomy-grounded, LLM-powered multi-agent system for simulating realistic EMD scenarios. Methods: We constructed a clinical taxonomy (32 chief complaints, 6 caller identities from MIMIC-III) and a six-phase call protocol. Using this framework, we developed an AutoGen-based MAS with Caller and Dispatcher Agents. The system grounds interactions in a fact commons to ensure clinical plausibility and mitigate misinformation. We used a hybrid evaluation framework: four physicians assessed 100 simulated cases for "Guidance Efficacy" and "Dispatch Effectiveness," supplemented by automated linguistic analysis (sentiment, readability, politeness). Results: Human evaluation, with substantial inter-rater agreement (Gwe's AC1 > 0.70), confirmed the system's high performance. It demonstrated excellent Dispatch Effectiveness (e.g., 94 % contacting the correct potential other agents) and Guidance Efficacy (advice provided in 91 % of cases), both rated highly by physicians. Algorithmic metrics corroborated these findings, indicating a predominantly neutral affective profile (73.7 % neutral sentiment; 90.4 % neutral emotion), high readability (Flesch 80.9), and a consistently polite style (60.0 % polite; 0 % impolite). Conclusion: Our taxonomy-grounded MAS simulates diverse, clinically plausible dispatch scenarios with high fidelity. Findings support its use for dispatcher training, protocol evaluation, and as a foundation for real-time decision support. This work outlines a pathway for safely integrating advanced AI agents into emergency response workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21228 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services Li, Xiang Yu, Huizi Wang, Wenkong Wu, Yiran Zhou, Jiayan Hua, Wenyue Lin, Xinxin Tan, Wenjia Zhu, Lexuan Chen, Bingyi Chen, Guang Chen, Ming-Li Zhou, Yang Li, Zhao Assimes, Themistocles L. Zhang, Yongfeng Wu, Qingyun Ma, Xin Li, Lingyao Fan, Lizhou Computation and Language Human-Computer Interaction 68T07, 92C50 I.2.7; J.3 Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This study aimed to develop and evaluate a taxonomy-grounded, LLM-powered multi-agent system for simulating realistic EMD scenarios. Methods: We constructed a clinical taxonomy (32 chief complaints, 6 caller identities from MIMIC-III) and a six-phase call protocol. Using this framework, we developed an AutoGen-based MAS with Caller and Dispatcher Agents. The system grounds interactions in a fact commons to ensure clinical plausibility and mitigate misinformation. We used a hybrid evaluation framework: four physicians assessed 100 simulated cases for "Guidance Efficacy" and "Dispatch Effectiveness," supplemented by automated linguistic analysis (sentiment, readability, politeness). Results: Human evaluation, with substantial inter-rater agreement (Gwe's AC1 > 0.70), confirmed the system's high performance. It demonstrated excellent Dispatch Effectiveness (e.g., 94 % contacting the correct potential other agents) and Guidance Efficacy (advice provided in 91 % of cases), both rated highly by physicians. Algorithmic metrics corroborated these findings, indicating a predominantly neutral affective profile (73.7 % neutral sentiment; 90.4 % neutral emotion), high readability (Flesch 80.9), and a consistently polite style (60.0 % polite; 0 % impolite). Conclusion: Our taxonomy-grounded MAS simulates diverse, clinically plausible dispatch scenarios with high fidelity. Findings support its use for dispatcher training, protocol evaluation, and as a foundation for real-time decision support. This work outlines a pathway for safely integrating advanced AI agents into emergency response workflows. |
| title | DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services |
| topic | Computation and Language Human-Computer Interaction 68T07, 92C50 I.2.7; J.3 |
| url | https://arxiv.org/abs/2510.21228 |