文献速递神经免疫

利用大语言模型从真实世界多发性硬化数据集中检测新发病灶

Detecting New Lesions Using a Large Language Model: Applications in Real-World Multiple Sclerosis Datasets.
PubMed 文献 · Ann Neurol · 2025-04-25

研究开发并验证了一种提示词(msLesionprompt),通过ChatGPT4对单中心电子健康记录(2000-2022)中的多发性硬化(MS)磁共振报告进行分类,以识别新发T2加权病灶(newT2w)和对比增强病灶(CEL)。结果显示检测准确率高(newT2w 97%,CEL 96.8%),并应用于监测B细胞耗竭治疗(BCDT)后的反应及探索炎症活动的预测因素。

要点

  • msLesionprompt可高效分类MS磁共振报告,检测newT2w准确率97%、CEL准确率96.8%。
  • 14,888份报告在4.13小时内完成分类,成本28美元,79%报告无新发病灶。
  • BCDT后监测MRI显示新发活动抑制>97%,邻里贫困(ADI)与新发活动相关。

核心结论

  • 利用大语言模型从叙述性影像报告中提取离散信息是可行且高效的,可增强MS疾病演变和治疗反应的真实世界分析。

研究设计与样本

  • 研究将机构生态系统与ChatGPT4安全连接,应用于单中心电子健康记录(2000-2022)的临床MS磁共振报告,开发并迭代优化msLesionprompt以分类newT2w和CEL的存在与否。

主要发现

  • msLesionprompt检测newT2w的准确率为97%,检测CEL的准确率为96.8%。
  • 全部14,888份可用报告在4.13小时内完成分类,成本28美元;79%的报告显示无newT2w或CEL。
  • 数据提取显示BCDT对newT2w/CEL的抑制>97%(在初始“重新基线”扫描后的监测磁共振图像中)。
  • 邻里贫困(Area Deprivation Index)被确定为炎症活动的预测因素:newT2w的OR为1.69(95% CI 1.10-2.59,p=0.017);CEL的OR为1.54(95% CI 1.01-2.34,p=0.046)。

临床怎么用

  • 该大语言模型方法可用于从叙述性影像报告中提取离散信息,支持MS真实世界研究和治疗反应监测。

局限性

  • 原文未述局限性

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

OBJECTIVE: Neuroimaging is routinely utilized to identify new inflammatory activity in multiple sclerosis (MS). A large language model to classify narrative magnetic resonance imaging reports in the electronic health record (EHR) as discrete data could provide significant benefits for MS research. The objectives of the current study were to develop such a prompt and to illustrate its research applications through a common clinical scenario: monitoring response to B-cell depleting therapy (BCDT). METHODS: An institutional ecosystem that securely connects healthcare data with ChatGPT4 was applied to clinical MS magnetic resonance imaging reports in a single institutional EHR (2000-2022). A prompt (msLesionprompt) was developed and iteratively refined to classify the presence or absence of new T2-weighted lesions (newT2w) and contrast-enhancing lesions (CEL). The multistep validation included evaluating efficiency (time and cost), comparison with manually annotated reports using standard confusion matrix, and application to identifying predictors of newT2w/CEL after BCDT start. RESULTS: Accuracy of msLesionprompt was high for detection of newT2w (97%) and CEL (96.8%). All 14,888 available reports were categorized in 4.13 hours ($28); 79% showed no newT2w or CEL. Data extracted showed expected suppression of new activity by BCDT (>97% monitoring magnetic resonance images after an initial "rebaseline" scan). Neighborhood poverty (Area Deprivation Index) was identified as a predictor of inflammatory activity (newT2w: OR 1.69, 95% CI 1.10-2.59, p = 0.017; CEL: OR 1.54, 95% CI 1.01-2.34, p = 0.046). INTERPRETATION: Extracting discrete information from narrative imaging reports using an large language model is feasible and efficient. This approach could augment many real-world analyses of MS disease evolution and treatment response. ANN NEUROL 2025;98:308-316.

来源:Ann Neurol,查看原文。版权归原作者所有。

引用

  1. Poole S, Sisodia N, Koshal K, et al. Detecting New Lesions Using a Large Language Model: Applications in Real-World Multiple Sclerosis Datasets. Ann Neurol. 2025. PMID: 40277428. doi:10.1002/ana.27251

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。