Department of Pediatrics, Dr. von Hauner Children's Hospital, University Hospital, LMU Munich, Munich, Germany.
Medical Technology and IT (MIT), University Hospital, LMU Munich, Munich, Germany.
Stud Health Technol Inform. 2024 Aug 22;316:949-950. doi: 10.3233/SHTI240567.
In the field of medical data analysis, converting unstructured text documents into a structured format suitable for further use is a significant challenge. This study introduces an automated local deployed data privacy secure pipeline that uses open-source Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) architecture to convert medical German language documents with sensitive health-related information into a structured format. Testing on a proprietary dataset of 800 unstructured original medical reports demonstrated an accuracy of up to 90% in data extraction of the pipeline compared to data extracted manually by physicians and medical students. This highlights the pipeline's potential as a valuable tool for efficiently extracting relevant data from unstructured sources.
在医学数据分析领域，将非结构化的文本文件转换为适合进一步使用的结构化格式是一项重大挑战。本研究引入了一种自动化的本地部署数据隐私安全管道，该管道使用带有检索增强生成（RAG）架构的开源大型语言模型（LLM），将带有敏感健康相关信息的德语医学文件转换为结构化格式。在一个包含 800 份非结构化原始医学报告的专有数据集上进行的测试表明，与医生和医学生手动提取的数据相比，该管道在数据提取方面的准确率高达 90%。这突出了该管道作为一种从非结构化来源高效提取相关数据的有价值工具的潜力。
