A long journey to short abbreviations: developing an open-source framework for clinical abbreviation recognition and disambiguation (CARD)
A long journey to short abbreviations: developing an open-source framework for clinical abbreviation recognition and disambiguation (CARD)
复制标题
DOI：
10.1093/jamia/ocw109
复制
发表时间：
2017-04-01
影响因子：
6.4
通讯作者：
Xu, Hua
中科院分区：
文献类型：
--
作者：
Wu, Yonghui;Denny, Joshua C.;Xu, Hua
目的：本研究的目标是开发一个实用的框架，用于识别和消除临床缩略语的歧义，从而提高当前临床自然语言处理（NLP）系统处理临床narratives.Methods中的缩写的能力：我们开发了一个开源框架，用于临床缩略语识别和消歧（CARD），利用我们以前开发的方法，包括：（1）基于机器学习的方法，以从临床语料库中识别缩写，（2）基于聚类的半自动化方法，以生成缩写的可能含义，以及（3）基于简档的词义消歧方法，用于临床缩写。我们将CARD应用于范德比尔特大学医学中心（VUMC）的临床语料库，并为出院总结和诊所访视记录中的缩写生成2个综合意义清单。此外，我们开发了一个包装器，集成CARD与MetaMap，一个广泛使用的一般临床NLP system.Results和结论：CARD检测27 317和107 303不同的缩写出院摘要和诊所访问笔记，分别。对这两个语料库中出现频率最高的1000个缩略语构建了两个词义量表。使用从出院摘要创建的意义清单，CARD在识别和消除来自VUMC出院摘要的语料库中的所有缩写词的歧义方面达到了0.755的F1评分，这比MetaMap和Apache的临床文本分析知识提取系统（cTAKES）优越上级。使用额外的外部语料库，我们还证明了MetaMap-CARD包装器提高了MetaMap在识别临床笔记中的疾病实体方面的性能。CARD框架、2个感官清单和MetaMap的包装器可在https://sbmi.uth.edu/ccb/resources/abbreviation公开获得。htm.我们相信CARD框架可以成为改善临床NLP系统中缩写识别的宝贵资源。
Objective: The goal of this study was to develop a practical framework for recognizing and disambiguating clinical abbreviations, thereby improving current clinical natural language processing (NLP) systems' capability to handle abbreviations in clinical narratives.Methods: We developed an open-source framework for clinical abbreviation recognition and disambiguation (CARD) that leverages our previously developed methods, including: (1) machine learning based approaches to recognize abbreviations from a clinical corpus, (2) clustering-based semiautomated methods to generate possible senses of abbreviations, and (3) profile-based word sense disambiguation methods for clinical abbreviations. We applied CARD to clinical corpora from Vanderbilt University Medical Center (VUMC) and generated 2 comprehensive sense inventories for abbreviations in discharge summaries and clinic visit notes. Furthermore, we developed a wrapper that integrates CARD with MetaMap, a widely used general clinical NLP system.Results and Conclusion: CARD detected 27 317 and 107 303 distinct abbreviations from discharge summaries and clinic visit notes, respectively. Two sense inventories were constructed for the 1000 most frequent abbreviations in these 2 corpora. Using the sense inventories created from discharge summaries, CARD achieved an F1 score of 0.755 for identifying and disambiguating all abbreviations in a corpus from the VUMC discharge summaries, which is superior to MetaMap and Apache's clinical Text Analysis Knowledge Extraction System (cTAKES). Using additional external corpora, we also demonstrated that the MetaMap-CARD wrapper improved MetaMap's performance in recognizing disorder entities in clinical notes. The CARD framework, 2 sense inventories, and the wrapper for MetaMap are publicly available at https://sbmi.uth.edu/ccb/resources/abbreviation. htm. We believe the CARD framework can be a valuable resource for improving abbreviation identification in clinical NLP systems.