用大模型生成精神科病历，检验其语言与临床真实性
Almost Clinical: Linguistic properties of synthetic electronic health records
- 用LLM构建合成病历数据集，覆盖评估、会诊等四类临床文本
- 生成文本语法正确但存在术语不精准、用药描述错误等问题
- 适合做大规模语言学研究，尤其隐私受限场景下的医疗文本分析
本研究评估了大语言模型生成的精神科电子健康记录在语言和临床适用性方面的表现。首先，介绍了合成语料库的构建动机与方法；其次，通过分析评估、通信、转诊和护理计划四类临床文本中的代理性、情态和信息流特征，探讨了LLM如何通过语言选择建构医学权威与患者主体性。尽管生成文本在语法上连贯且术语使用恰当，接近临床实践，但仍存在系统性偏差，包括语域错位、临床特异性不足，以及药物使用和诊断程序上的不准确。结果表明，合成语料库在实现大规模语言学研究方面具有潜力，同时揭示了其局限性。
原文摘要 · Abstract (English)
This study evaluates the linguistic and clinical suitability of synthetic electronic health records in mental health. First, we describe the rationale and the methodology for creating the synthetic corpus. Second, we examine expressions of agency, modality, and information flow across four clinical genres (Assessments, Correspondence, Referrals and Care plans) with the aim to understand how LLMs grammatically construct medical authority and patient agency through linguistic choices. While LLMs produce coherent, terminology-appropriate texts that approximate clinical practice, systematic divergences remain, including registerial shifts, insufficient clinical specificity, and inaccuracies in medication use and diagnostic procedures. The results show both the potential and limitations of synthetic corpora for enabling large-scale linguistic research otherwise impossible with genuine patient records.
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。