使用大型语言模型(LLM)进行救护车调度与分诊
该研究将美国一座大都市的真实救护车请求每4条分为一组,让未经过任务专项训练的LLM(ChatGPT 4o Mini)判断应优先处理哪位患者,并与资深重症护理辅助医疗人员小组的投票结果比较。共98组(392条请求),LLM与小组一致76.5%(n=75);在小组意见一致的分组(n=48)中一致93.8%(n=45)。作者认为LLM可能成为急诊分诊与资源分配的有用工具,尤其在专家意见一致时,但需进一步研究。
要点
- 共98组、392条真实救护车请求,LLM与辅助医疗人员小组一致76.5%(n=75)。
- 小组意见一致的分组(n=48)中,LLM一致率为93.8%(n=45)。
- 所用LLM为ChatGPT 4o Mini,未经过任务专项训练。
- 作者认为LLM可能成为急诊分诊与资源分配的有用工具,尤其在专家意见一致时。
适用人群与场景
- 美国一座大都市的真实救护车请求,每4条请求分为一组。
研究设计与关键结果
- 研究类型:初步分析,比较LLM与资深重症护理辅助医疗人员小组对救护车请求的优先处理判断。
- 样本:98组(392条请求),每4条一组。
- 干预:LLM(ChatGPT 4o Mini,Open AI,San Francisco,CA,USA)无任务专项训练,对每组4条请求判断应优先处理哪位患者;对照为资深重症护理辅助医疗人员小组投票。
- 主要结果:LLM与小组一致76.5%(n=75)。
- 次要结果:小组意见一致的分组(n=48)中,LLM与一致意见一致93.8%(n=45)。
证据类型、等级与局限
- 证据类型:初步分析。
- 局限:原文报告需进一步研究以更好理解和明确LLM如何最好地发挥作用。
对床旁实践的改变
- 作者认为LLM可能成为急诊分诊与资源分配的有用工具,尤其在主题专家意见一致的情况下。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
INTRODUCTION: Large language models (LLMs) have grown in popularity in recent months and have demonstrated advanced clinical reasoning ability. Given the need to prioritize the sickest patients requesting emergency medical services (EMS), we attempted to identify if an LLM could accurately triage ambulance requests using real-world data from a major metropolitan area.
METHODS: An LLM (ChatGPT 4o Mini, Open AI, San Francisco, CA, USA) with no prior task-specific training was given real ambulance requests from a major metropolitan city in the United States. Requests were batched into groups of four, and the LLM was prompted to identify which of the four patients should be prioritized. The same groupings of four requests were then shown to a panel of experienced critical care paramedics who voted on which patient should be prioritized.
RESULTS: Across 98 groupings of four ambulance requests (392 total requests), the LLM agreed with the paramedic panel in most cases (76.5 %, n = 75). In groupings where the paramedic panel was unanimous in their decision (n = 48), the LLM agreed with the unanimous panel in 93.8 % of groupings (n = 45).
CONCLUSIONS: Our preliminary analysis indicates LLMs may have the potential to become a useful tool for triage and resource allocation in emergency care settings, especially in cases where there is consensus among subject matter experts. Further research is needed to better understand and clarify how they may best be of service.
参考来源
- Shekhar AC, Kimbrell J, Saharan A, et al. Use of a large language model (LLM) for ambulance dispatch and triage. Am J Emerg Med. 2024. PMID: 39675178. doi:10.1016/j.ajem.2024.12.032
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。