arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.05571cs.CL
收藏

2022年n2c2/UW关于提取健康的社会决定因素的共同任务

The 2022 n2c2/UW Shared Task on Extracting Social Determinants of Health

George Mason University(乔治梅森大学);University of Washington(华盛顿大学)

Kevin Lybarger, Meliha Yetisgen, Özlem Uzuner

摘要:

目的:n2 c2/UW SDOH挑战赛探索从临床记录中提取健康社会决定因素(SDOH)信息。目标包括更广泛地用于SDOH和临床信息的自然语言处理(NLP)信息抽取技术的进步。本文介绍了共享的任务,数据,参与团队,性能结果,以及对未来工作的考虑。材料与方法:该任务使用的社会历史注释语料库(SHAC),其中包括临床文本与详细的基于事件的注释SDOH事件,如酒精,药物,烟草,就业和生活状况。每个SDOH事件都通过与状态、程度和时间性相关的属性来表征。该任务包括与信息抽取(子任务A)、概括性(子任务B)和学习迁移(子任务C)相关的三个子任务。在完成这项任务时,参与者使用了一系列技术,包括规则、知识库、n-gram、词嵌入和预训练的语言模型(LM)。结果:共有15个团队参与,最好的团队使用了预先训练的深度学习LM。所有子任务的最佳团队使用序列到序列方法,子任务A的F1为0.901,子任务B的F1为0.774,子任务C的F1为0.889。结论:与许多NLP任务和领域类似,预先训练的LM产生了最好的性能,包括概括性和学习迁移。错误分析表明,提取性能因SDOH而异,在增加健康风险(风险因素)的条件下,如物质使用和无家可归,性能较低,而在减少健康风险(保护因素)的条件下,如物质戒断和与家人生活在一起,性能较高。

英文摘要:

Objective: The n2c2/UW SDOH Challenge explores the extraction of social determinant of health (SDOH) information from clinical notes. The objectives include the advancement of natural language processing (NLP) information extraction techniques for SDOH and clinical information more broadly. This paper presents the shared task, data, participating teams, performance results, and considerations for future work. Materials and Methods: The task used the Social History Annotated Corpus (SHAC), which consists of clinical text with detailed event-based annotations for SDOH events such as alcohol, drug, tobacco, employment, and living situation. Each SDOH event is characterized through attributes related to status, extent, and temporality. The task includes three subtasks related to information extraction (Subtask A), generalizability (Subtask B), and learning transfer (Subtask C). In addressing this task, participants utilized a range of techniques, including rules, knowledge bases, n-grams, word embeddings, and pretrained language models (LM). Results: A total of 15 teams participated, and the top teams utilized pretrained deep learning LM. The top team across all subtasks used a sequence-to-sequence approach achieving 0.901 F1 for Subtask A, 0.774 F1 Subtask B, and 0.889 F1 for Subtask C. Conclusions: Similar to many NLP tasks and domains, pretrained LM yielded the best performance, including generalizability and learning transfer. An error analysis indicates extraction performance varies by SDOH, with lower performance achieved for conditions, like substance use and homelessness, that increase health risks (risk factors) and higher performance achieved for conditions, like substance abstinence and living with family, that reduce health risks (protective factors).

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。

↑