文献速递脑血管病

结构化临床输入引导的大语言模型工作流用于急性缺血性卒中出院教育:多中心可行性研究

Structured Clinical Input-Guided Large Language Model Workflow for Acute Ischemic Stroke Discharge Education: A Multicenter Feasibility Study.
PubMed 文献 · Stroke · 2026-07-21

本研究在中国6家三级卒中中心纳入67例急性缺血性卒中患者,使用结构化临床输入引导GPT-4o、Grok-3和DeepSeek-R1生成中文出院教育草稿,并与医生常规书写的出院指导比较。两名盲法资深神经科医生评估显示,LLM草稿在危险因素控制、康复指导、随访计划和健康教育方面评分优于医生书写材料,患者中心评价总体良好。

要点

  • 结构化临床输入引导的LLM工作流可生成急性缺血性卒中出院教育草稿,初步可行。
  • 专家评价LLM草稿在多个教育维度优于医生常规出院指导。
  • 患者中心评价总体良好,GPT-4o和Grok-3共情评分高于医生书写材料。

核心结论

  • 结构化临床输入引导的LLM工作流在生成临床医生监督下的急性缺血性卒中出院教育草稿方面显示初步可行性。

研究设计与样本

  • 多中心可行性研究,纳入2024年9月1日至2025年3月31日中国6家三级卒中中心出院的急性缺血性卒中患者67例,平均年龄63.6±11.0岁,男性45例(67.2%)。

主要发现

  • 两名神经科医生评估的组间信度良好至优秀,组内相关系数范围为0.862至0.943。
  • 事后分析显示,各LLM生成草稿组在危险因素控制、康复指导、随访计划和健康教育方面的专家评分均高于医生书写出院指导(均Bonferroni校正P<0.001)。
  • 药物管理方面,校正后无配对差异保持显著。
  • 患者中心评价总体良好,GPT-4o和Grok-3的共情评分高于医生书写出院指导(均Bonferroni校正P<0.01)。
  • 专家审查未发现明显幻觉,LLM草稿的不可接受评分较少。

临床怎么用

  • 该工作流可作为临床医生监督下生成急性缺血性卒中出院教育草稿的辅助工具。
  • 生成草稿需经临床医生审核后使用。

局限性

  • 研究为初步可行性研究,需前瞻性实施研究评估工作流整合、可用性及对患者报告和临床结局的影响。

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

BACKGROUND: Large language models (LLMs) may support patient education, but their clinical use remains challenging. We aimed to evaluate the preliminary feasibility of a structured clinical input-guided LLM workflow for generating discharge education drafts for patients with acute ischemic stroke. METHODS: Patients with acute ischemic stroke discharged from 6 tertiary stroke centers in China between September 1, 2024, and March 31, 2025, were included. The workflow comprised electronic medical record-based data extraction, mapping to a predefined deidentified case report form, manual verification, standardized prompt-based LLM draft generation, and clinician-facing draft output. For each patient, Chinese-language discharge education drafts were generated using GPT-4o, Grok-3, and DeepSeek-R1. Physician-written discharge instructions prepared during routine clinical practice served as reference materials. Two blinded senior neurologists evaluated the materials across 5 predefined domains. Patient-centered evaluation was conducted in 50 patients. Interrater agreement between the 2 neurologists was assessed using intraclass correlation coefficients. Group comparisons were performed using Friedman tests followed by Bonferroni-corrected Wilcoxon signed-rank tests. RESULTS: A total of 67 patients with acute ischemic stroke were included. The mean age was 63.6±11.0 years, and 45 patients were men (67.2%). Interrater agreement was good to excellent, with intraclass correlation coefficients ranging from 0.862 to 0.943. Post hoc analyses showed that each LLM-generated draft group received higher expert ratings than physician-written discharge instructions in risk factor control, rehabilitation guidance, follow-up planning, and health education (all Bonferroni-adjusted P<0.001), whereas no pairwise difference in medication management remained significant after correction. Patient-centered ratings were generally favorable, and GPT-4o and Grok-3 received higher empathy ratings than physician-written discharge instructions (both Bonferroni-adjusted P<0.01). No clear hallucinations were identified during expert review, and LLM drafts had fewer unacceptable ratings. CONCLUSIONS: A structured clinical input-guided LLM workflow showed preliminary feasibility for generating clinician-supervised acute ischemic stroke discharge education drafts. Prospective implementation studies are warranted to evaluate workflow integration, usability, and effects on patient-reported and clinical outcomes.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Yin J, Wang W, Wu L, et al. Structured Clinical Input-Guided Large Language Model Workflow for Acute Ischemic Stroke Discharge Education: A Multicenter Feasibility Study. Stroke. 2026. PMID: 42478758. doi:10.1161/STROKEAHA.126.055189

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。