适配后的大语言模型在临床文本摘要任务中表现可超越医学专家
Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization
AI总结：
本研究通过对8个大语言模型进行适配，验证其在四类临床文本摘要任务中的表现，发现最优适配模型的摘要质量多数情况下与医学专家相当或更优，为LLM融入临床流程、减轻文档负担提供了依据。
摘要：
分析电子健康记录中的海量文本数据并提炼关键信息，给临床医生的时间分配带来了沉重负担。尽管大语言模型（LLMs）在自然语言处理（NLP）领域已展现出应用潜力，但它们在各类临床摘要任务中的有效性仍未得到证实。本研究中，我们对8个LLMs应用适配方法，覆盖四项不同的临床摘要任务：放射报告、患者提问、病程记录以及医患对话。采用句法、语义和概念层面的NLP指标开展的定量评估，揭示了不同模型与适配方法之间的权衡关系。一项由10名医生参与的临床读者研究对摘要的完整性、正确性和简洁性进行了评估；在大多数情况下，我们性能最优的适配LLMs生成的摘要与医学专家撰写的摘要相比，要么效果相当（45%），要么更优（36%）。后续的安全性分析指出了LLMs和医学专家共同面临的挑战，我们将错误与潜在的医疗危害相关联，并对虚构信息的类型进行了分类。我们的研究提供了LLMs在多任务临床文本摘要中表现优于医学专家的证据，这表明将LLMs整合到临床工作流程中可减轻文档负担，让临床医生能更专注于患者护理。
英文摘要：
Analyzing vast textual data and summarizing key information from electronic health records imposes a substantial burden on how clinicians allocate their time. Although large language models (LLMs) have shown promise in natural language processing (NLP), their effectiveness on a diverse range of clinical summarization tasks remains unproven. In this study, we apply adaptation methods to eight LLMs, spanning four distinct clinical summarization tasks: radiology reports, patient questions, progress notes, and doctor-patient dialogue. Quantitative assessments with syntactic, semantic, and conceptual NLP metrics reveal trade-offs between models and adaptation methods. A clinical reader study with ten physicians evaluates summary completeness, correctness, and conciseness; in a majority of cases, summaries from our best adapted LLMs are either equivalent (45%) or superior (36%) compared to summaries from medical experts. The ensuing safety analysis highlights challenges faced by both LLMs and medical experts, as we connect errors to potential medical harm and categorize types of fabricated information. Our research provides evidence of LLMs outperforming medical experts in clinical text summarization across multiple tasks. This suggests that integrating LLMs into clinical workflows could alleviate documentation burden, allowing clinicians to focus more on patient care.
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。
