[论文解读] Generating SOAP Notes from Doctor-Patient Conversations

Kundan Krishna, Sopan Khosla+2 more|arXiv (Cornell University)|May 4, 2020

Topic Modeling参考文献 7被引用 22

一句话总结

本文提出了一种两阶段流水线，用于从医生-患者对话转录本生成SOAP病历，首先通过多标签分类和聚类提取关键语句并按部分分类，然后基于这些聚类生成摘要句。与端到端生成方法相比，该方法在ROUGE-1上提升了7个百分点，通过改进提取过程还可获得进一步提升。

ABSTRACT

Following each patient visit, physicians must draft detailed clinical summaries called SOAP notes. Moreover, with electronic health records, these notes must be digitized. For all the benefits of this documentation the process remains onerous, contributing to increasing physician burnout. In a parallel development, patients increasingly record audio from their visits (with consent), often through dedicated apps. In this paper, we present the first study to evaluate complete pipelines for leveraging these transcripts to train machine learning model to generate these notes. We first describe a unique dataset of patient visit records, consisting of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence. We decompose the problem into extractive and abstractive subtasks, exploring a spectrum of approaches according to how much they demand from each component. Our best performing method first (i) extracts noteworthy utterances via multi-label classification assigns them to summary section(s); (ii) clusters noteworthy utterances on a per-section basis; and (iii) generates the summary sentences by conditioning on the corresponding cluster and the subsection of the SOAP sentence to be generated. Compared to an end-to-end approach that generates the full SOAP note from the full conversation, our approach improves by 7 ROUGE-1 points. Oracle experiments indicate that fixing our generative capabilities, improvements in extraction alone could provide (up to) a further 9 ROUGE point gain.

研究动机与目标

• 解决电子健康记录中SOAP病历文档耗时导致的医生职业倦怠问题。
• 探索利用患者录制的就诊转录本自动化生成SOAP病历的可行性。
• 开发并评估一种将病历生成分解为抽取式和生成式阶段的结构化流水线。
• 评估组件级改进（尤其是语句提取）对最终生成质量的影响。

提出的方法

• 构建一个独特的数据集，包含转录本、配对的SOAP病历，以及标记出与每个摘要句相关语句的注释。
• 将任务分解为抽取式和生成式两个部分：首先通过多标签分类识别关键语句。
• 按SOAP部分（如主观、客观）对提取的语句进行聚类，以整合语义相关的语料。
• 基于对应聚类和部分上下文条件生成每个摘要句的生成式内容。
• 训练一个条件序列模型，使用聚类后的语句作为上下文生成句子。
• 将该流水线与端到端生成方法进行比较，以评估性能提升。

实验结果

研究问题

• RQ1 是否两阶段流水线（将语句提取与句子生成分离）能够优于端到端的SOAP病历生成？
• RQ2 语句提取的质量在多大程度上影响整体生成性能？
• RQ3 仅改进提取过程能在多大程度上提升最终的ROUGE分数，而独立于生成模型的质量？
• RQ4 对提取语句进行聚类在组织内容以实现分部分摘要方面有多有效？

主要发现

• 所提出的流水线相比端到端生成方法，ROUGE-1得分提升了7个百分点。
• Oracle实验表明，若固定生成组件，通过改进提取过程，ROUGE得分最高可再提升9分。
• 对关键语句的多标签分类能有效识别与每个SOAP部分相关的语料内容。
• 按部分对语句进行聚类可提升生成摘要句的连贯性和相关性。
• 当基于聚类后的语句作为条件时，生成式阶段能产生流畅且上下文恰当的句子。
• 结果表明，提取质量是关键瓶颈，识别重要临床内容方面仍有显著提升空间。