用大模型把临床自由文本转为结构化问答，提升可解释性和泛化能力。
ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts
- 利用大模型将临床文本转化为任务相关的问答对，实现结构化处理。
- 在重症死亡预测任务中，AUC仅下降2-3%，性能损失小。
- 适合需要可解释性与跨系统泛化的医疗AI研发团队使用。
临床笔记包含丰富上下文信息，但其非结构化格式带来诸多挑战，如无意偏见（如性别或种族偏见）、在不同临床环境下的泛化能力差（例如，针对一种电子病历系统训练的模型在另一系统上表现不佳），以及可解释性不足。为此，我们提出ClinStructor，一个利用大语言模型（LLMs）将临床自由文本转换为结构化、任务特定的问答对的流程，用于预测建模前的预处理。该方法显著提升了透明度和可控性，相较于直接微调，仅导致预测性能小幅下降（在重症监护室死亡预测任务中AUC下降2-3%）。ClinStructor为构建可靠、可解释且具备良好泛化能力的临床机器学习模型奠定了坚实基础。
原文摘要 · Abstract (English)
Clinical notes contain valuable, context-rich information, but their unstructured format introduces several challenges, including unintended biases (e.g., gender or racial bias), and poor generalization across clinical settings (e.g., models trained on one EHR system may perform poorly on another due to format differences) and poor interpretability. To address these issues, we present ClinStructor, a pipeline that leverages large language models (LLMs) to convert clinical free-text into structured, task-specific question-answer pairs prior to predictive modeling. Our method substantially enhances transparency and controllability and only leads to a modest reduction in predictive performance (a 2-3% drop in AUC), compared to direct fine-tuning, on the ICU mortality prediction task. ClinStructor lays a strong foundation for building reliable, interpretable, and generalizable machine learning models in clinical environments.
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。