用开源大模型从放射科报告中提取肿瘤随时间变化数据，保障隐私且准确率超94%。
Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models
- 基于Qwen2.5-72b模型，按RECIST标准提取目标、非目标和新病灶信息
- 在50对荷兰胸部/腹部CT报告上，各类病灶提取准确率均超94%
- 全开源可本地部署，适合注重数据隐私的医疗机构使用
放射科报告包含肿瘤负荷、治疗反应和疾病进展等关键纵向信息，但其非结构化叙述格式使自动化分析困难。尽管大语言模型（LLMs）已推动临床文本处理发展，但多数先进系统仍为专有，限制了其在敏感医疗环境中的应用。我们提出一个完全开源、可本地部署的放射科报告纵向信息提取流程，采用llm_extractinator框架，利用qwen2.5-72b模型，根据RECIST标准提取并关联不同时间点的目标、非目标及新病灶数据。在50对荷兰胸部/腹部CT报告对上的评估显示，目标病灶属性级准确率为93.7%，非目标病灶为94.9%，新病灶为94.0%。该方法表明，开源大语言模型可在多时间点肿瘤学任务中实现临床意义的性能，同时保障数据隐私与可复现性。结果凸显了本地部署式大语言模型在从常规临床文本中规模化提取结构化纵向数据方面的潜力。
原文摘要 · Abstract (English)
Radiology reports capture crucial longitudinal information on tumor burden, treatment response, and disease progression, yet their unstructured narrative format complicates automated analysis. While large language models (LLMs) have advanced clinical text processing, most state-of-the-art systems remain proprietary, limiting their applicability in privacy-sensitive healthcare environments. We present a fully open-source, locally deployable pipeline for longitudinal information extraction from radiology reports, implemented using the llm_extractinator framework. The system applies the qwen2.5-72b model to extract and link target, non-target, and new lesion data across time points in accordance with RECIST criteria. Evaluation on 50 Dutch CT Thorax/Abdomen report pairs yielded high extraction performance, with attribute-level accuracies of 93.7% for target lesions, 94.9% for non-target lesions, and 94.0% for new lesions. The approach demonstrates that open-source LLMs can achieve clinically meaningful performance in multi-timepoint oncology tasks while ensuring data privacy and reproducibility. These results highlight the potential of locally deployable LLMs for scalable extraction of structured longitudinal data from routine clinical text.
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。