用大模型提示词集成提升电子病历实体识别准确率
LLM-based Prompt Ensemble for Reliable Medical Entity Recognition from EHRs
- 采用提示词集成策略融合多个LLM输出，增强医学实体识别可靠性
- GPT-4o在提示词集成下达到F1=0.95、召回率0.98的高精度
- 适合临床信息提取场景，尤其对少样本医学文本效果显著
电子病历（EHR）包含大量未结构化的临床文本，命名实体识别（NER）对提取问题、检查和治疗等关键医学实体至关重要。本文探索基于大语言模型（如GPT-4o和DeepSeek-R1）的提示词医学实体识别方法，采用零样本、少样本及提示词集成策略。实验表明，使用提示词集成的GPT-4o表现最佳，F1得分为0.95，召回率为0.98，优于DeepSeek-R1。该集成方法通过嵌入相似性聚合与多数投票提升结果可靠性。
原文摘要 · Abstract (English)
Electronic Health Records (EHRs) are digital records of patient information, often containing unstructured clinical text. Named Entity Recognition (NER) is essential in EHRs for extracting key medical entities like problems, tests, and treatments to support downstream clinical applications. This paper explores prompt-based medical entity recognition using large language models (LLMs), specifically GPT-4o and DeepSeek-R1, guided by various prompt engineering techniques, including zero-shot, few-shot, and an ensemble approach. Among all strategies, GPT-4o with prompt ensemble achieved the highest classification performance with an F1-score of 0.95 and recall of 0.98, outperforming DeepSeek-R1 on the task. The ensemble method improved reliability by aggregating outputs through embedding-based similarity and majority voting.
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。