GPT模型对急诊就诊建议的医学有效性及普通人解读:一项横断面研究
本研究为横断面研究,于2023年12月10日至2024年3月7日在日本开展,将临床场景输入GPT模型并评估其急诊就诊建议。共314个场景标注为红色标签(急诊,需立即就诊急诊科),152个标注为绿色标签(不太紧急)。7名医学专家评估输出有效性,157名普通人通过网页问卷解读。专家认为GPT在95.9%(301/314)的红色标签场景中准确识别重要信息,96.5%(303/314)建议立即就诊急诊科;但仅43.0%(135/314)的普通人将这些输出解读为需紧急就医。绿色标签场景中,模型在99.3%(151/152)识别重要信息,88.8%(135/152)建议不必立即就诊,但仅32.2%(49/152)的普通人认为属常规随访。结论提示GPT建议准确但普通人常误读,存在对AI医学建议的理解鸿沟。
要点
- 红色标签场景中,专家认为GPT在96.5%(303/314)建议立即就诊急诊科,但仅43.0%(135/314)的普通人解读为需紧急就医。
- 绿色标签场景中,专家认为GPT在88.8%(135/152)建议不必立即就诊,但仅32.2%(49/152)的普通人认为属常规随访。
- 专家评估GPT在95.9%(301/314)的红色标签场景和99.3%(151/152)的绿色标签场景中准确识别重要信息。
- 普通人常误读GPT输出,提示AI生成的医学建议在公众理解上存在显著鸿沟。
适用人群与场景
- 研究场景为日本急诊救护车调度中需门诊服务的轻症病例,强调改进公众急诊就医指导。
- 纳入314个红色标签(急诊,需立即就诊急诊科)场景和152个绿色标签(不太紧急)场景,由7名医学专家和157名普通人评估。
研究设计与关键结果
- 研究类型为横断面研究,时间为2023年12月10日至2024年3月7日,将临床场景输入GPT模型评估急诊就诊需求。
- 红色标签场景314个,专家认为GPT准确识别重要信息95.9%(301/314),建议立即就诊急诊科96.5%(303/314);仅43.0%(135/314)的普通人解读为需紧急就医。
- 绿色标签场景152个,专家认为GPT准确识别重要信息99.3%(151/152),建议不必立即就诊88.8%(135/152);仅32.2%(49/152)的普通人认为属常规随访。
证据类型、等级与局限
- 证据类型:横断面研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 专家评估显示GPT模型在建议急诊就诊方面高度准确,但普通人频繁误读其推荐,提示AI生成的医学建议在公众理解上存在显著鸿沟。
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
AIM: In Japan, emergency ambulance dispatches involve minor cases requiring outpatient services, emphasizing the need for improved public guidance regarding emergency care. This study evaluated both the medical plausibility of the GPT model in aiding laypersons to determine the need for emergency medical care and the laypersons' interpretations of its outputs.
METHODS: This cross-sectional study was conducted from December 10, 2023, to March 7, 2024. We input clinical scenarios into the GPT model and evaluated the need for emergency visits based on the outputs. A total of 314 scenarios were labeled with red tags (emergency, immediate emergency department [ED] visit) and 152 with green tags (less urgent). Seven medical specialists assessed the outputs' validity, and 157 laypersons interpreted them via a web-based questionnaire.
RESULTS: Experts reported that the GPT model accurately identified important information in 95.9% (301/314) of red-tagged scenarios and recommended immediate ED visits in 96.5% (303/314). However, only 43.0% (135/314) of laypersons interpreted those outputs as indicating urgent hospital visits. The model identified important information in 99.3% (151/152) of green-tagged scenarios and advised against immediate visits in 88.8% (135/152). However, only 32.2% (49/152) of laypersons considered them routine follow-ups.
CONCLUSIONS: Expert evaluations revealed that the GPT model could be highly accurate in advising on emergency visits. However, laypersons frequently misinterpreted its recommendations, highlighting a substantial gap in understanding AI-generated medical advice.
参考来源
- Tanaka C, Kinoshita T, Okada Y, et al. Medical validity and layperson interpretation of emergency visit recommendations by the GPT model: A cross-sectional study. Acute Med Surg. 2025. PMID: 40078650. doi:10.1002/ams2.70042
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。