| Automatically detecting medications and the reason for their prescription in clinical narrative text documents. | |
| | |
MedLine Citation:
|
PMID: 20841823 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
An important proportion of the information about the medications a patient is taking is mentioned only in narrative text in the electronic health record. Automated information extraction can make this information accessible for decision support, research, or any other automated processing. In the context of the "i2b2 medication extraction challenge," we have developed a new NLP application called Textractor to automatically extract medications and details about them (e.g., dosage, frequency, reason for their prescription). This application and its evaluation with part of the reference standard for this "challenge" are presented here, along with an analysis of the development of this reference standard. During this evaluation, Textractor reached a system-level overall F<inf>1</inf>-measure, the reference metric for this challenge, of about 77% for exact matches. The best performance was measured with medication routes (F<inf>1</inf>-measure 86.4%), and the worst with prescription reasons (F<inf>1</inf>-measure 29%). These results are consistent with the agreement observed between human annotators when developing the reference standard, and with other published research. |
| | |
Authors:
|
Stéphane M Meystre; Julien Thibault; Shuying Shen; John F Hurdle; Brett R South |
Related Documents
:
|
11229993 - Hallucinogens on the internet: a vast new source of underground drug information. 10259403 - Bargaining for concessions: what information must the employer provide? 11623773 - Vernacularization as an intellectual and social bridge. the catalan translations of teo... |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: Studies in health technology and informatics Volume: 160 ISSN: 0926-9630 ISO Abbreviation: Stud Health Technol Inform Publication Date: 2010 |
Date Detail:
|
Created Date: 2010-09-15 Completed Date: 2011-04-15 Revised Date: 2011-12-21 |
Medline Journal Info:
|
Nlm Unique ID: 9214582 Medline TA: Stud Health Technol Inform Country: Netherlands |
Other Details:
|
Languages: eng Pagination: 944-8 Citation Subset: T |
Affiliation:
|
Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, USA. stephane.meystre@hsc.utah.edu |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Drug Prescriptions* Electronic Health Records / standards Humans Information Storage and Retrieval / methods* Natural Language Processing Vocabulary, Controlled |
| Grant Support | |
ID/Acronym/Agency:
|
R21 LM009967-01/LM/NLM NIH HHS; R21 LM009967-01S1/LM/NLM NIH HHS; R21 LM009967-02/LM/NLM NIH HHS |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Data mining techniques for analyzing stroke care processes.
Next Document: Extracting medication information from French clinical texts.