What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting Pub Date : 2021-06-01 DOI:10.18653/v1/2021.naacl-main.382

Griffin Adams, Emily Alsentzer, Mert Ketenci, Jason Zucker, Noémie Elhadad

{"title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization.","authors":"Griffin Adams, Emily Alsentzer, Mert Ketenci, Jason Zucker, Noémie Elhadad","doi":"10.18653/v1/2021.naacl-main.382","DOIUrl":null,"url":null,"abstract":"<p><p>Summarization of clinical narratives is a long-standing research problem. Here, we introduce the task of hospital-course summarization. Given the documentation authored throughout a patient's hospitalization, generate a paragraph that tells the story of the patient admission. We construct an English, text-to-text dataset of 109,000 hospitalizations (2M source notes) and their corresponding summary proxy: the clinician-authored \"Brief Hospital Course\" paragraph written as part of a discharge note. Exploratory analyses reveal that the BHC paragraphs are highly abstractive with some long extracted fragments; are concise yet comprehensive; differ in style and content organization from the source notes; exhibit minimal lexical cohesion; and represent silver-standard references. Our analysis identifies multiple implications for modeling this complex, multi-document summarization task.</p>","PeriodicalId":74542,"journal":{"name":"Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting","volume":"2021 ","pages":"4794-4811"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8225248/pdf/nihms-1705151.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2021.naacl-main.382","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Summarization of clinical narratives is a long-standing research problem. Here, we introduce the task of hospital-course summarization. Given the documentation authored throughout a patient's hospitalization, generate a paragraph that tells the story of the patient admission. We construct an English, text-to-text dataset of 109,000 hospitalizations (2M source notes) and their corresponding summary proxy: the clinician-authored "Brief Hospital Course" paragraph written as part of a discharge note. Exploratory analyses reveal that the BHC paragraphs are highly abstractive with some long extracted fragments; are concise yet comprehensive; differ in style and content organization from the source notes; exhibit minimal lexical cohesion; and represent silver-standard references. Our analysis identifies multiple implications for modeling this complex, multi-document summarization task.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

摘要有哪些内容？为医院课程总结的进步奠定基础。

临床叙述的总结是一个长期存在的研究问题。在此，我们介绍医院病程总结任务。给定病人住院期间撰写的文件，生成一个段落，讲述病人入院的故事。我们构建了一个英文文本到文本数据集，其中包含 109,000 个住院病例（200 万份原始病历）及其相应的摘要代理：临床医生撰写的 "简要住院病程 "段落，作为出院病历的一部分。探索性分析表明，"简要住院过程 "段落具有高度的抽象性，其中包含一些较长的提取片段；简洁而全面；在风格和内容组织方面与原始病历不同；表现出最低限度的词汇连贯性；并且代表了银标准参考文献。我们的分析为这一复杂的多文档摘要任务建模提供了多方面的启示。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting

自引率

0.00%

发文量