用GPT从病历中提取信息，提升患者死亡预测准确率
Paging Dr. GPT: Extracting Information from Clinical Notes to Enhance Patient Predictions
- 让GPT读出院记录回答临床问题，把答案当特征训练模型
- 纯GPT模型比传统表格数据模型更准，组合使用AUC提升5.1%
- 适合想用大模型挖掘医疗文本价值的研究者和医生
医疗领域长期依赖电子病历中的结构化表格数据构建预测模型，但忽略了未结构化临床笔记中包含的诊断、治疗、用药和护理计划等关键信息。本研究探索了在访问患者出院摘要的前提下，GPT-4o-mini对简单临床问题的回答，能否辅助患者死亡率预测。基于MIMIC-IV Note数据集中的14,011例首次入住冠心病或心血管重症监护病房的患者数据，我们构建了一个透明框架，将GPT生成的回答作为逻辑回归模型的输入特征。结果显示，仅使用GPT生成特征的模型已优于仅使用标准表格数据的模型；而两者结合后，平均提升AUC 5.1个百分点，高风险人群的阳性预测值提高29.9%。这些发现凸显了将大语言模型融入临床预测任务的价值，并表明在任何未充分利用非结构化文本数据的领域，该方法均具广泛潜力。
原文摘要 · Abstract (English)
There is a long history of building predictive models in healthcare using tabular data from electronic medical records. However, these models fail to extract the information found in unstructured clinical notes, which document diagnosis, treatment, progress, medications, and care plans. In this study, we investigate how answers generated by GPT-4o-mini (ChatGPT) to simple clinical questions about patients, when given access to the patient's discharge summary, can support patient-level mortality prediction. Using data from 14,011 first-time admissions to the Coronary Care or Cardiovascular Intensive Care Units in the MIMIC-IV Note dataset, we implement a transparent framework that uses GPT responses as input features in logistic regression models. Our findings demonstrate that GPT-based models alone can outperform models trained on standard tabular data, and that combining both sources of information yields even greater predictive power, increasing AUC by an average of 5.1 percentage points and increasing positive predictive value by 29.9 percent for the highest-risk decile. These results highlight the value of integrating large language models (LLMs) into clinical prediction tasks and underscore the broader potential for using LLMs in any domain where unstructured text data remains an underutilized resource.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。