Skip to main content
Journal cover image

Evaluation of preprocessing techniques for chief complaint classification.

Publication ,  Journal Article
Dara, J; Dowling, JN; Travers, D; Cooper, GF; Chapman, WW
Published in: Journal of biomedical informatics
August 2008

To determine whether preprocessing chief complaints before automatically classifying them into syndromic categories improves classification performance.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)).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.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.

Duke Scholars

Published In

Journal of biomedical informatics

DOI

EISSN

1532-0480

ISSN

1532-0464

Publication Date

August 2008

Volume

41

Issue

4

Start / End Page

613 / 623

Related Subject Headings

  • Terminology as Topic
  • Syndrome
  • Population Surveillance
  • Pattern Recognition, Automated
  • Natural Language Processing
  • Medical Informatics
  • Diagnosis, Computer-Assisted
  • Biomedical Engineering
  • Artificial Intelligence
  • 4601 Applied computing
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Dara, J., Dowling, J. N., Travers, D., Cooper, G. F., & Chapman, W. W. (2008). Evaluation of preprocessing techniques for chief complaint classification. Journal of Biomedical Informatics, 41(4), 613–623. https://doi.org/10.1016/j.jbi.2007.11.004
Dara, Jagan, John N. Dowling, Debbie Travers, Gregory F. Cooper, and Wendy W. Chapman. “Evaluation of preprocessing techniques for chief complaint classification.Journal of Biomedical Informatics 41, no. 4 (August 2008): 613–23. https://doi.org/10.1016/j.jbi.2007.11.004.
Dara J, Dowling JN, Travers D, Cooper GF, Chapman WW. Evaluation of preprocessing techniques for chief complaint classification. Journal of biomedical informatics. 2008 Aug;41(4):613–23.
Dara, Jagan, et al. “Evaluation of preprocessing techniques for chief complaint classification.Journal of Biomedical Informatics, vol. 41, no. 4, Aug. 2008, pp. 613–23. Epmc, doi:10.1016/j.jbi.2007.11.004.
Dara J, Dowling JN, Travers D, Cooper GF, Chapman WW. Evaluation of preprocessing techniques for chief complaint classification. Journal of biomedical informatics. 2008 Aug;41(4):613–623.
Journal cover image

Published In

Journal of biomedical informatics

DOI

EISSN

1532-0480

ISSN

1532-0464

Publication Date

August 2008

Volume

41

Issue

4

Start / End Page

613 / 623

Related Subject Headings

  • Terminology as Topic
  • Syndrome
  • Population Surveillance
  • Pattern Recognition, Automated
  • Natural Language Processing
  • Medical Informatics
  • Diagnosis, Computer-Assisted
  • Biomedical Engineering
  • Artificial Intelligence
  • 4601 Applied computing