用大模型从病历文本中自动提取阿尔茨海默病特征，提升早期诊断能力
LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes
- 基于大语言模型构建病历特征提取框架，融合专家定义的表型列表
- 记忆障碍是区分不同患者群体最强的特征，聚类效果优于传统方法（ARI=0.290）
- 适合临床研究者和医疗AI开发者用于挖掘未结构化病历中的疾病信号
从电子健康记录（EHR）中准确提取阿尔茨海默病及相关痴呆（ADRD）表型对早期检测和疾病分期至关重要。然而，这些信息通常嵌入在非结构化文本中而非表格数据，难以精准提取。为此，我们提出LLM-MINE，一种基于大语言模型的表型挖掘框架，用于从临床笔记中自动提取ADRD表型。利用两个专家定义的表型列表，我们通过检验表型在队列间的统计显著性及其在无监督疾病分层中的效用来评估提取结果。卡方检验证实各队列间表型差异具有统计显著性，其中记忆障碍为最强区分特征。采用组合表型列表进行少样本提示，聚类表现最佳（ARI=0.290，NMI=0.232），显著优于生物医学命名实体识别和字典基基线。结果表明，基于大模型的表型提取是发现临床有意义的ADRD信号的有力工具。
原文摘要 · Abstract (English)
Accurate extraction of Alzheimer's Disease and Related Dementias (ADRD) phenotypes from electronic health records (EHR) is critical for early-stage detection and disease staging. However, this information is usually embedded in unstructured textual data rather than tabular data, making it difficult to be extracted accurately. We therefore propose LLM-MINE, a Large Language Model-based phenotype mining framework for automatic extraction of ADRD phenotypes from clinical notes. Using two expert-defined phenotype lists, we evaluate the extracted phenotypes by examining their statistical significance across cohorts and their utility for unsupervised disease staging. Chi-square analyses confirm statistically significant phenotype differences across cohorts, with memory impairment being the strongest discriminator. Few-shot prompting with the combined phenotype lists achieves the best clustering performance (ARI=0.290, NMI=0.232), substantially outperforming biomedical NER and dictionary-based baselines. Our results demonstrate that LLM-based phenotype extraction is a promising tool for discovering clinically meaningful ADRD signals from unstructured notes.
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。