arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07332cs.LGstat.ML
收藏

MIMIC-III临床编码数据集银标的实验评价和开发

Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset

King’s College London(伦敦国王学院);University College London(伦敦大学学院)

Thomas Searle, Zina Ibrahim, Richard JB Dobson

摘要:

临床编码目前是一个劳动密集型,容易出错,但关键的管理过程,其中医院患者事件由合格的工作人员从大型,标准化的分类层次的代码手动分配代码。自动化临床编码在NLP研究中有着悠久的历史,最近出现了新的发展,创造了新的最先进的结果。在这项任务中使用的一个流行的数据集是MIMIC-III,这是一个大型重症监护数据库,包括临床自由文本注释和相关代码。我们主张重新考虑有效性MIMIC-III的分配代码,通常被视为金标准,特别是当MIMIC-III没有经过二次验证。这项工作提出了一个开源的,可重复的实验方法,用于评估来自EHR放电摘要的代码的有效性。我们使用MIMIC-III出院总结验证了该方法,并显示MIMIC-III中最常分配的代码编码不足高达35%。

英文摘要:

Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that are often treated as gold-standard, especially when MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of codes derived from EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are under-coded up to 35%.

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。

↑