文献速递医学人工智能与信息学医学教育与科研方法

GPT-4辅助提升医生在患者照护任务中的表现:一项随机对照试验

GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial.
PubMed 文献 · Nat Med · 2025-02-05

这项前瞻性随机对照试验于2023年11月至2024年4月纳入92名执业医生,在模拟环境中回答5个专家开发的临床案例,评估GPT-4辅助是否改善开放式管理推理任务的表现。结果显示,使用大语言模型的医生总分显著高于仅用常规资源的医生(平均差6.5%,95%CI 2.7至10.2,P<0.001),但每例耗时更长(平均差119.3秒,95%CI 17.4至221.2,P=0.02)。

要点

  • 与常规资源相比,GPT-4辅助使医生在管理推理任务上的总分显著提高6.5%。
  • 使用大语言模型的医生每例花费时间平均增加119.3秒。
  • 大语言模型辅助医生与单独使用大语言模型的总分无显著差异。

核心结论

  • 与常规资源相比,大语言模型辅助可改善医生在复杂临床案例中的管理推理表现,并应在真实临床实践中验证。

研究设计与样本

  • 前瞻性随机对照试验,于2023年11月至2024年4月纳入92名执业医生,随机分配使用GPT-4联合常规资源或仅常规资源,在模拟环境中回答5个基于真实脱敏患者诊疗、信息序贯揭示的专家开发临床案例。

主要发现

  • 使用大语言模型的医生总分显著高于仅使用常规资源的医生(平均差=6.5%,95%CI=2.7至10.2,P<0.001)。
  • 使用大语言模型的医生每例花费时间多于仅使用常规资源的医生(平均差=119.3秒,95%CI=17.4至221.2,P=0.02)。
  • 大语言模型辅助医生与单独使用大语言模型的总分无显著差异(-0.9%,95%CI=-9.0至7.2,P=0.8)。

关键数值与推荐

  • 主要结局为组间在专家开发评分量表上的总分差异。
  • 次要结局包括领域特异性评分和每例花费时间。

临床怎么用

  • 原文结论指出大语言模型辅助可改善医生管理推理表现,并应在真实临床实践中验证。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

While large language models (LLMs) have shown promise in diagnostic reasoning, their impact on management reasoning, which involves balancing treatment decisions and testing strategies while managing risk, is unknown. This prospective, randomized, controlled trial assessed whether LLM assistance improves physician performance on open-ended management reasoning tasks compared to conventional resources. From November 2023 to April 2024, 92 practicing physicians were randomized to use either GPT-4 plus conventional resources or conventional resources alone to answer five expert-developed clinical vignettes in a simulated setting. All cases were based on real, de-identified patient encounters, with information revealed sequentially to mirror the nature of clinical environments. The primary outcome was the difference in total score between groups on expert-developed scoring rubrics. Secondary outcomes included domain-specific scores and time spent per case. Physicians using the LLM scored significantly higher compared to those using conventional resources (mean difference = 6.5%, 95% confidence interval (CI) = 2.7 to 10.2, P < 0.001). LLM users spent more time per case (mean difference = 119.3 s, 95% CI = 17.4 to 221.2, P = 0.02). There was no significant difference between LLM-augmented physicians and LLM alone (-0.9%, 95% CI = -9.0 to 7.2, P = 0.8). LLM assistance can improve physician management reasoning in complex clinical vignettes compared to conventional resources and should be validated in real clinical practice. ClinicalTrials.gov registration: NCT06208423 .

来源:Nat Med,查看原文。版权归原作者所有。

引用

  1. Goh E, Gallo RJ, Strong E, et al. GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial. Nat Med. 2025. PMID: 39910272. doi:10.1038/s41591-024-03456-y

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。