大语言模型优化ICU临床试验招募:以呼吸机诱导膈肌功能障碍为例
本研究开发基于大语言模型的预筛流程,从ICU出院小结中评估靶向呼吸机诱导膈肌功能障碍的2期试验入组标准,并部署于2024年全部ICU住院记录。在蒙彼利埃大学医院2024年连续1,342例ICU住院中,选定模型识别出532例机械通气≥3天的患者,应用排除标准后185例可能合格,专家审核确认133例合格,阳性预测值为72%(95%CI 65-78)。大语言模型辅助流程使临床医生审核时间估计减少86%。结论认为该预筛方法有望用于重症监护试验候选者识别,未来部署应包括针对性专家验证和持续监测。
要点
- 在蒙彼利埃大学医院2024年连续1,342例ICU住院中,大语言模型预筛识别出532例机械通气≥3天患者,应用排除标准后185例可能合格。
- 专家审核确认133例合格,阳性预测值为72%(95%CI 65-78)。
- 最佳模型GPT-OSS:120B的标准级F1评分为0.82,各模型标准级F1评分范围为0.73至0.82。
- 大语言模型辅助流程使临床医生审核时间估计减少86%。
- 作者认为未来部署应包括针对性专家验证和持续监测,以确保安全性和泛化性。
适用人群与场景
- 2024年蒙彼利埃大学医院全部ICU住院记录,共1,342例连续ICU住院。
- 靶向呼吸机诱导膈肌功能障碍的未来2期临床试验的候选者预筛。
诊断标准与关键阈值
- 入选条件包括机械通气≥3天;应用排除标准后剩余患者为可能合格。
研究设计与关键结果
- 研究类型为基于大语言模型的预筛流程开发与评估,部署于2024年全部ICU住院记录,共1,342例连续ICU住院。
- 最佳模型为GPT-OSS:120B,标准级F1评分为0.82;各模型标准级F1评分范围为0.73至0.82。
- 选定模型识别出532例机械通气≥3天患者,应用排除标准后185例可能合格,专家审核确认133例合格,阳性预测值为72%(95%CI 65-78)。
- 大语言模型辅助流程使临床医生审核时间估计减少86%。
- 50例ICU住院的富集集由6名临床医生独立标注以定义参考标准,用于评估标准级模型性能。
证据类型、等级与局限
- 证据类型为基于大语言模型的预筛流程开发与评估研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为基于大语言模型的预筛有望用于重症监护试验候选者识别,优先安排候选者供临床医生审核。
- 作者认为未来部署应包括针对性专家验证和持续监测,以确保安全性和泛化性。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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
BACKGROUND: Ventilator-induced diaphragm dysfunction (VIDD) is a frequent and under-recognized consequence of prolonged mechanical ventilation in intensive-care unit (ICU) patients. Identifying eligible candidates for clinical trials targeting VIDD remains a major operational challenge. This study evaluates the use of large language models (LLMs) to automate patient prescreening from ICU discharge summaries and estimate recruitment capacity for a future phase 2 trial.
METHODS: We developed an LLM-based prescreening pipeline to assess trial eligibility criteria from ICU discharge summaries, which was deployed to screen all 2024 ICU stays. Stays that were flagged as potentially eligible underwent expert adjudication. An enriched set of 50 ICU stays was independently annotated by six clinicians to define a reference standard, which was used to evaluate criterion-level model performances using F1-scores.
RESULTS: The best-performing model was GPT-OSS:120B with a criterion-level F1-score of 0.82. When applied to consecutive 1,342 ICU stays from Montpellier University Hospital in 2024, the selected model identified 532 patients with ≥ 3 days of mechanical ventilation. After applying exclusion criteria, 185 patients remained potentially eligible. Expert review confirmed 133 patients as eligible, resulting in a positive predictive value of 72% (95% CI 65-78). The LLM-assisted workflow resulted in an estimated 86% reduction in clinician review time. The LLM-based prescreening pipelines achieved criterion-level F1 scores ranging from 0.73 to 0.82, with GPT-OSS:120B demonstrating the highest performance.
CONCLUSIONS: LLM-based prescreening offers a promising approach for identifying trial candidates in critical care, prioritizing candidates for clinician review. Future deployments should include targeted expert validation and ongoing monitoring to ensure safety and generalizability.
参考来源
- Korvin K, Loi Z, Morquin D, et al. Large language models for optimizing clinical trial recruitment in ICUs: application to ventilator-induced diaphragm dysfunction. Crit Care. 2026. PMID: 42277838. doi:10.1186/s13054-026-06127-1
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。