通过对风险的批判性评估探讨大型语言模型创新中的稳健隐私保护
Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks
AI总结:
本研究探讨将EHRs和NLP与LLMs结合以生成符合HIPAA的合成患者记录,发现基于关键词的方法在隐私保护和数据实用性间取得了良好平衡,且重新标识化数据优于去标识化数据。
摘要:
本研究探讨了将EHRs(电子健康记录)和NLP(自然语言处理)与大型语言模型(LLMs)相集成,以改善医疗数据管理和患者护理。研究重点在于使用先进模型创建用于生物医学研究的安全、符合HIPAA(健康保险流通与责任法案)的合成患者记录。该研究使用了去标识化和重新标识化的MIMIC III数据集,结合GPT-3.5、GPT-4和Mistral 7B来生成合成记录。文本生成采用了模板和关键词提取技术以获取上下文相关的记录,并使用单次生成方法进行对比。隐私评估检查了PHI(受保护健康信息)的出现情况,而文本实用性则通过ICD-9编码任务进行测试。文本质量使用ROUGE和余弦相似度指标进行评估,以衡量与源记录的语义相似度。对PHI出现情况和基于ICD-9编码任务的文本实用性的分析表明,基于关键词的方法具有低风险和良好的性能。单次生成方法显示出最高的PHI暴露率和PHI共现率,尤其是在地理位置和日期类别中。归一化单次生成方法获得了最高的分类准确率。隐私分析揭示了数据实用性与隐私保护之间的关键平衡,这影响了未来的数据使用和共享。重新标识化数据始终优于去标识化数据。本研究展示了基于关键词的方法在生成保留数据可用性的隐私保护合成临床记录方面的有效性,这可能会改变临床数据共享实践。重新标识化数据优于去标识化数据的卓越表现,表明了一种向通过使用虚假PHI来迷惑隐私攻击从而增强实用性和隐私的方法的转变。
英文摘要:
This study examines integrating EHRs and NLP with large language models (LLMs) to improve healthcare data management and patient care. It focuses on using advanced models to create secure, HIPAA-compliant synthetic patient notes for biomedical research. The study used de-identified and re-identified MIMIC III datasets with GPT-3.5, GPT-4, and Mistral 7B to generate synthetic notes. Text generation employed templates and keyword extraction for contextually relevant notes, with one-shot generation for comparison. Privacy assessment checked PHI occurrence, while text utility was tested using an ICD-9 coding task. Text quality was evaluated with ROUGE and cosine similarity metrics to measure semantic similarity with source notes. Analysis of PHI occurrence and text utility via the ICD-9 coding task showed that the keyword-based method had low risk and good performance. One-shot generation showed the highest PHI exposure and PHI co-occurrence, especially in geographic location and date categories. The Normalized One-shot method achieved the highest classification accuracy. Privacy analysis revealed a critical balance between data utility and privacy protection, influencing future data use and sharing. Re-identified data consistently outperformed de-identified data. This study demonstrates the effectiveness of keyword-based methods in generating privacy-protecting synthetic clinical notes that retain data usability, potentially transforming clinical data-sharing practices. The superior performance of re-identified over de-identified data suggests a shift towards methods that enhance utility and privacy by using dummy PHIs to perplex privacy attacks.
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。