用开源大模型提取医疗文本信息，兼顾隐私与效率
Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings
- 用开源大模型直接处理荷兰语医疗文本，避免翻译损耗
- 140亿参数模型在28项任务中表现接近商用模型
- 适合资源有限但需保护患者隐私的医疗机构使用
医疗报告包含丰富临床信息，但多为非结构化且使用领域专有语言，给信息抽取带来挑战。尽管专有大型语言模型在临床自然语言处理中表现良好，但其缺乏透明性及数据隐私问题限制了其在医疗领域的应用。本研究评估了九个开源生成式大模型在DRAGON基准上的表现，该基准包含28项荷兰语临床信息抽取任务。我们开发了开源框架llm_extractinator，用于利用开源生成式大模型进行信息抽取，并在零样本设置下评估模型性能。多个140亿参数模型（Phi-4-14B、Qwen-2.5-14B、DeepSeek-R1-14B）表现优异，而更大的Llama-3.3-70B模型虽略高但计算成本更高。推理前进行英文翻译会持续降低性能，凸显原生语言处理的重要性。结果表明，结合本框架，开源大模型可为低资源环境下的临床信息抽取提供高效、可扩展且注重隐私的解决方案。
原文摘要 · Abstract (English)
Medical reports contain rich clinical information but are often unstructured and written in domain-specific language, posing challenges for information extraction. While proprietary large language models (LLMs) have shown promise in clinical natural language processing, their lack of transparency and data privacy concerns limit their utility in healthcare. This study therefore evaluates nine open-source generative LLMs on the DRAGON benchmark, which includes 28 clinical information extraction tasks in Dutch. We developed \texttt{llm\_extractinator}, a publicly available framework for information extraction using open-source generative LLMs, and used it to assess model performance in a zero-shot setting. Several 14 billion parameter models, Phi-4-14B, Qwen-2.5-14B, and DeepSeek-R1-14B, achieved competitive results, while the bigger Llama-3.3-70B model achieved slightly higher performance at greater computational cost. Translation to English prior to inference consistently degraded performance, highlighting the need of native-language processing. These findings demonstrate that open-source LLMs, when used with our framework, offer effective, scalable, and privacy-conscious solutions for clinical information extraction in low-resource settings.
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。