MedPromptExtract(医疗数据提取工具):使用 NLP 和提示工程进行匿名化与高保真自动化数据提取
MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering
AI总结:
提出 MedPromptExtract,结合 EIGEN 匿名化、NLP 与基于 Gemini Pro 的 LLM 提示工程,从 AKI 出院小结中高保真提取十二个临床特征。
摘要:
引言:从出院小结(DS)等来源提取数据的劳动密集型性质,给医疗记录数字化带来了重大障碍,尤其对中低收入国家(LMICs)而言。本文提出一种完全自动化的方法 MedPromptExtract,可在保密的同时高效地从 DS 中提取数据。方法:数据来源为 Kokilaben Dhirubhai Ambani Hospital(KDAH)中急性肾损伤(AKI)患者的出院小结(DS)。研究使用既有工具 EIGEN 对 DS 进行匿名化,该工具利用半监督学习技术实现高保真信息提取;使用自然语言处理(NLP)从常规字段中提取数据。我们使用提示工程和大语言模型(LLM),从描述患者住院情况的自由流动文本中提取定制临床信息。共提取了与 AKI 发生相关的十二个特征。LLM 的回答依据临床医生标注进行验证。结果:MedPromptExtract 工具首先使 DS 通过匿名化流程,每份小结耗时三秒。临床医生验证了匿名化成功;随后 NLP 流程以每份小结 0.2 秒的速度从匿名化 PDF 中提取结构化文本,准确率为 100%。最后,DS 由使用 Gemini Pro 的 LLM 流程针对十二个特征进行分析。通过将模型回答与临床医生标注进行比较来计算准确率指标,其中七个特征的 AUC 高于 0.9,表明提取过程具有高保真度。结论:MedPromptExtract 是一种自动化、适应性强的工具,可通过动态用户界面从医疗记录中高效提取数据。关键词:医疗记录数字化、自动化匿名化、信息检索、大语言模型、提示工程。
英文摘要:
Introduction: The labour-intensive nature of data extraction from sources like discharge summaries (DS) poses significant obstacles to the digitisation of medical records particularly for low- and middle-income countries (LMICs). In this paper we present a completely automated method MedPromptExtract to efficiently extract data from DS while maintaining confidentiality. Methods: The source of data was Discharge Summaries (DS) from Kokilaben Dhirubhai Ambani Hospital (KDAH) of patients having Acute Kidney Injury (AKI). A pre-existing tool EIGEN which leverages semi-supervised learning techniques for high-fidelity information extraction was used to anonymize the DS, Natural Language Processing (NLP) was used to extract data from regular fields. We used Prompt Engineering and Large Language Model(LLM) to extract custom clinical information from free flowing text describing the patients stay in the hospital. Twelve features associated with occurrence of AKI were extracted. The LLM responses were validated against clinicians annotations. Results: The MedPromptExtracttool first subjected DS to the anonymization pipeline which took three seconds per summary. Successful anonymization was verified by clinicians, thereafter NLP pipeline extracted structured text from the anonymized pdfs at the rate of 0.2 seconds per summary with 100% accuracy.Finally DS were analysed by the LLM pipeline using Gemini Pro for the twelve features. Accuracy metrics were calculated by comparing model responses to clinicians annotations with seven features achieving AUCs above 0.9, indicating high fidelity of the extraction process. Conclusion: MedPromptExtract serves as an automated adaptable tool for efficient data extraction from medical records with a dynamic user interface. Keywords: Digitizing Medical Records, Automated Anonymisation, Information Retrieval, Large Language Models, Prompt Engineering
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。