PMID- 27539197
OWN - NLM
STAT- MEDLINE
DCOM- 20180115
LR  - 20230821
IS  - 1527-974X (Electronic)
IS  - 1067-5027 (Print)
IS  - 1067-5027 (Linking)
VI  - 24
IP  - e1
DP  - 2017 Apr 1
TI  - A long journey to short abbreviations: developing an open-source framework for 
      clinical abbreviation recognition and disambiguation (CARD).
PG  - e79-e86
LID - 10.1093/jamia/ocw109 [doi]
AB  - 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.
CI  - (c) The Author 2016. Published by Oxford University Press on behalf of the American 
      Medical Informatics Association. All rights reserved. For Permissions, please 
      email: journals.permissions@oup.com
FAU - Wu, Yonghui
AU  - Wu Y
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston.
FAU - Denny, Joshua C
AU  - Denny JC
AD  - Department of Biomedical Informatics, Vanderbilt University School of Medicine, 
      Nashville, Tennessee.
AD  - Department of Medicine, Vanderbilt University School of Medicine.
FAU - Trent Rosenbloom, S
AU  - Trent Rosenbloom S
AD  - Department of Biomedical Informatics, Vanderbilt University School of Medicine, 
      Nashville, Tennessee.
AD  - Department of Medicine, Vanderbilt University School of Medicine.
FAU - Miller, Randolph A
AU  - Miller RA
AD  - Department of Biomedical Informatics, Vanderbilt University School of Medicine, 
      Nashville, Tennessee.
AD  - Department of Medicine, Vanderbilt University School of Medicine.
FAU - Giuse, Dario A
AU  - Giuse DA
AD  - Department of Biomedical Informatics, Vanderbilt University School of Medicine, 
      Nashville, Tennessee.
FAU - Wang, Lulu
AU  - Wang L
AD  - Department of Medicine, Vanderbilt University School of Medicine.
FAU - Blanquicett, Carmelo
AU  - Blanquicett C
AD  - Department of Medicine, University of Alabama at Birmingham, Birmingham.
FAU - Soysal, Ergin
AU  - Soysal E
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston.
FAU - Xu, Jun
AU  - Xu J
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston.
FAU - Xu, Hua
AU  - Xu H
AD  - School of Biomedical Informatics, The University of Texas Health Science Center 
      at Houston.
LA  - eng
GR  - R01 GM103859/GM/NIGMS NIH HHS/United States
GR  - R01 LM010681/LM/NLM NIH HHS/United States
PT  - Journal Article
PL  - England
TA  - J Am Med Inform Assoc
JT  - Journal of the American Medical Informatics Association : JAMIA
JID - 9430800
SB  - IM
MH  - *Abbreviations as Topic
MH  - *Electronic Health Records
MH  - Humans
MH  - *Machine Learning
MH  - *Natural Language Processing
MH  - Patient Discharge
PMC - PMC7651947
OTO - NOTNLM
OT  - clinical abbreviation
OT  - clinical natural language processing
OT  - machine learning
OT  - sense clustering
EDAT- 2016/08/20 06:00
MHDA- 2018/01/16 06:00
PMCR- 2017/08/18
CRDT- 2016/08/20 06:00
PHST- 2016/02/05 00:00 [received]
PHST- 2016/06/10 00:00 [accepted]
PHST- 2016/08/20 06:00 [pubmed]
PHST- 2018/01/16 06:00 [medline]
PHST- 2016/08/20 06:00 [entrez]
PHST- 2017/08/18 00:00 [pmc-release]
AID - ocw109 [pii]
AID - 10.1093/jamia/ocw109 [doi]
PST - ppublish
SO  - J Am Med Inform Assoc. 2017 Apr 1;24(e1):e79-e86. doi: 10.1093/jamia/ocw109.