Emergency Medical Text Classifier: New system improves processing and classification of triage notes

Authors

  • Stephanie W Haas University of North Carolina at Chapel Hill
  • Debbie Travers University of North Carolina at Chapel Hill
  • Anna Waller University of North Carolina at Chapel Hill
  • Deepika Mahalingam University of North Carolina at Chapel Hill
  • John Crouch University of North Carolina at Chapel Hill
  • Todd A. Schwartz University of North Carolina at Chapel Hill
  • Javed Mostafa University of North Carolina at Chapel Hill

DOI:

https://doi.org/10.5210/ojphi.v6i2.5469

Abstract

Objective: Automated syndrome classification aims to aid near real-time syndromic surveillance to serve as an early warning system for disease outbreaks, using Emergency Department (ED) data. We present a system that improves the automatic classification of an ED record with triage note into one or more syndrome categories using the vector space model coupled with a ‘learning’ module that employs a pseudo-relevance feedback mechanism.

Materials and Methods: Terms from standard syndrome definitions are used to construct an initial reference dictionary for generating the syndrome and triage note vectors. Based on cosine similarity between the vectors, each record is classified into a syndrome category. We then take terms from the top-ranked records that belong to the syndrome of interest as feedback. These terms are added to the reference dictionary and the process is repeated to determine the final classification. The system was tested on two different datasets for each of three syndromes: Gastro-Intestinal (GI), Respiratory (Resp) and Fever-Rash (FR). Performance was measured in terms of sensitivity (Se) and specificity (Sp).

Results: The use of relevance feedback produced high values of sensitivity and specificity for all three syndromes in both test sets:  GI: 90% and 71%, Resp: 97% and 73%, FR: 100% and 87%, respectively, in test set 1, and GI: 88% and 69%, Resp: 87% and 61%, FR: 97% and 71%, respectively, in test set 2.

Conclusions: The new system for pre-processing and syndromic classification of ED records with triage notes achieved improvements in Se and Sp. Our results also demonstrate that the system can be tuned to achieve different levels of performance based on user requirements.

Author Biographies

Stephanie W Haas, University of North Carolina at Chapel Hill

Professor

School of Information and Library Science

Debbie Travers, University of North Carolina at Chapel Hill

Assistant Professor

School of Nursing, and School of Medicine

Anna Waller, University of North Carolina at Chapel Hill

Research Professor

School of Medicine

Deepika Mahalingam, University of North Carolina at Chapel Hill

School of Nursing

John Crouch, University of North Carolina at Chapel Hill

School of Medicine

Todd A. Schwartz, University of North Carolina at Chapel Hill

Research Associate Professor

School of Nursing, and School of Public Health

Javed Mostafa, University of North Carolina at Chapel Hill

Professor

School of Information and Library Science, and School of Medicine

Downloads

Published

2014-10-16

How to Cite

Haas, S. W., Travers, D., Waller, A., Mahalingam, D., Crouch, J., Schwartz, T. A., & Mostafa, J. (2014). Emergency Medical Text Classifier: New system improves processing and classification of triage notes. Online Journal of Public Health Informatics, 6(2). https://doi.org/10.5210/ojphi.v6i2.5469

Issue

Section

Original Articles