A Dictionary-based Method for Detecting Anomalous Chief Complaint Text in Individual Records

Authors

  • Sara A. Taylor Brigham Young University, Provo, UT
  • Aaron Kite-Powell MIT Lincoln Laboratory, Lexington, MA

DOI:

https://doi.org/10.5210/ojphi.v6i1.5012

Abstract

The success of syndromic surveillance depends on the ability of the surveillance community to quickly and accurately recognize anomalous data. Current methods of anomaly detection focus on sets of syndromic categories and rely on a priori knowledge to map chief complaints to these general syndromic categories. As a result, the mapping scheme may miss key terms and phrases that have not previously been used. Furthermore, analysts do not have a good way of being alerted to these new terms in order to determine if they should be added to the syndromic mapping schema. We use a dynamic dictionary of terms to side-step the downfalls of a priori knowledge in this rapidly evolving field by alerting the analyst to rare and brand new words used in the chief complaint field.

Author Biography

Sara A. Taylor, Brigham Young University, Provo, UT

Sara Taylor is a senior studying Electrical Engineering and Mathematics at Brigham Young University.  During summer 2013, she worked as an intern for MIT Lincoln Laboratory where she grew to love text mining and syndromic surveillance.  She plans on attending graduate school to continue studing data science with an emphasis in health data.  Through data science, Sara hopes to be able to enable others make healthier decisions in their personal lives. 

Downloads

Published

2014-03-03

How to Cite

Taylor, S. A., & Kite-Powell, A. (2014). A Dictionary-based Method for Detecting Anomalous Chief Complaint Text in Individual Records. Online Journal of Public Health Informatics, 6(1). https://doi.org/10.5210/ojphi.v6i1.5012

Issue

Section

Oral Presentations