Computerized Text Analysis to Enhance Automated Pneumonia Detection

Authors

  • Sylvain DeLisle VA Maryland Health Care System; Medicine, University of Maryland
  • Tariq Siddiqui VA Maryland Health Care System; Medicine, University of Maryland
  • Adi Gundlapalli VA Salt Lake City Health Care System; University of Utah
  • Matthew Samore VA Salt Lake City Health Care System; University of Utah
  • Leonard D'Avolio VA Boston Health Care System; Harvard Medical School

DOI:

https://doi.org/10.5210/ojphi.v5i1.4602

Abstract

Information about disease severity could help with both detection and situational awareness during outbreaks of acute respiratory infections. In this work, we describe the methods by which automated text analyses of chest imaging reports can combine with structured EMR data to accurately identify outpatients with pneumonia (sensitivities of 58-75%, and PPV of 64-86%).

Author Biography

Sylvain DeLisle, VA Maryland Health Care System; Medicine, University of Maryland

Dr. DeLisle trained in Pulmonary/Critical Care Med-icine at McGill University and at the University of Iowa, and holds an MBA from the Johns Hopkins University. He is currently an Associate Professor of Medicine at the University of Maryland. In research work supported by the CDC and the VA, he studies how electronic medical records can best be utilized to discover and guide the management of patients with acute respiratory infections.

Downloads

Published

2013-03-24

How to Cite

DeLisle, S., Siddiqui, T., Gundlapalli, A., Samore, M., & D’Avolio, L. (2013). Computerized Text Analysis to Enhance Automated Pneumonia Detection. Online Journal of Public Health Informatics, 5(1). https://doi.org/10.5210/ojphi.v5i1.4602

Issue

Section

Oral Presentations: Syndrome Development & Validation & Natural Language Processing