Paper Info
Title
Recognizing Questions and Answers in EMR Templates Using Natural Language Processing.
Abstract
Templated boilerplate structures pose challenges to natural language processing (NLP) tools used for information extraction (IE). Routine error analyses while performing an IE task using Veterans Affairs (VA) medical records identified templates as an important cause of false positives. The baseline NLP pipeline (V3NLP) was adapted to recognize negation, questions and answers (QA) in various template types by adding a negation and slot: value identification annotator. The system was trained using a corpus of 975 documents developed as a reference standard for extracting psychosocial concepts. Iterative processing using the baseline tool and baseline negation+QA revealed loss of numbers of concepts with a modest increase in true positives in several concept categories. Similar improvement was noted when the adapted V3NLP was used to process a random sample of 318,000 notes. We demonstrate the feasibility of adapting an NLP pipeline to recognize templates.
Year
DOI
Venue
2014
10.3233/978-1-61499-423-7-149
Studies in Health Technology and Informatics
Keywords
Field
DocType
Natural language processing,information extraction,templates
Question answering,Information retrieval,Information extraction,Natural language processing,Artificial intelligence,Template,Medicine
Conference
Volume
ISSN
Citations 
202
0926-9630
0
PageRank 
References 
Authors
0.34
0
8
Name
Order
Citations
PageRank
Guy Divita165.48
Shuying Shen246323.81
Marjorie Carter385.52
Andrew Redd4116.59
Tyler Forbush500.34
Miland N. Palmer651.70
Matthew H. Samore714326.07
Adi Gundlapalli84714.74