Document Detail


Evaluation of preprocessing techniques for chief complaint classification.
MedLine Citation:
PMID:  18166502     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
OBJECTIVE: To determine whether preprocessing chief complaints before automatically classifying them into syndromic categories improves classification performance. METHODS: We preprocessed chief complaints using two preprocessors (CCP and EMT-P) and evaluated whether classification performance increased for a probabilistic classifier (CoCo) or for a keyword-based classifier (modification of the NYC Department of Health and Mental Hygiene chief complaint coder (KC)). RESULTS: CCP exhibited high accuracy (85%) in preprocessing chief complaints but only slightly improved CoCo's classification performance for a few syndromes. EMT-P, which splits chief complaints into multiple problems, substantially increased CoCo's sensitivity for all syndromes. Preprocessing with CCP or EMT-P only improved KC's sensitivity for the Constitutional syndrome. CONCLUSION: Evaluation of preprocessing systems should not be limited to accuracy of the preprocessor but should include the effect of preprocessing on syndromic classification. Splitting chief complaints into multiple problems before classification is important for CoCo, but other preprocessing steps only slightly improved classification performance for CoCo and a keyword-based classifier.
Authors:
Jagan Dara; John N Dowling; Debbie Travers; Gregory F Cooper; Wendy W Chapman
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.     Date:  2007-11-29
Journal Detail:
Title:  Journal of biomedical informatics     Volume:  41     ISSN:  1532-0480     ISO Abbreviation:  J Biomed Inform     Publication Date:  2008 Aug 
Date Detail:
Created Date:  2008-07-14     Completed Date:  2008-09-23     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  100970413     Medline TA:  J Biomed Inform     Country:  United States    
Other Details:
Languages:  eng     Pagination:  613-23     Citation Subset:  IM    
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh, 200 Meyran Avenue, VALE M-183, Pittsburgh, PA 15260, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Artificial Intelligence*
Diagnosis, Computer-Assisted / methods*
Natural Language Processing*
Pattern Recognition, Automated / methods*
Population Surveillance / methods*
Syndrome
Terminology as Topic*
Grant Support
ID/Acronym/Agency:
K22LM008301/LM/NLM NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Behavioral measures in animal studies: relevance to patients with epilepsy.
Next Document:  Cardiovascular autonomic regulation in Non-Obese Diabetic (NOD) mice.