Layout 1


ISDS Annual Conference Proceedings 2012. This is an Open Access article distributed under the terms of the Creative Commons Attribution-
Noncommercial 3.0 Unported License (http://creativecommons.org/licenses/by-nc/3.0/), permitting all non-commercial use, distribution, and
reproduction in any medium, provided the original work is properly cited.

ISDS 2012 Conference Abstracts

Computerized Text Analysis to Enhance Automated
Pneumonia Detection
Sylvain DeLisle*1, 2, Tariq Siddiqui1, 2, Adi Gundlapalli3, 4, Matthew Samore3, 4 and Leonard
D’Avolio5, 6

1VA Maryland Health Care System, Baltimore, MD, USA; 2Medicine, University of Maryland, Baltimore, MD, USA; 3VA Salt Lake City
Health Care System, Salt Lake City, UT, USA; 4University of Utah, Salt Lake City, UT, USA; 5VA Boston Health Care System, Boston,
MA, USA; 6Harvard Medical School, Boston, MA, USA

Objective
To improve the surveillance for pneumonia using the free-text of

electronic medical records (EMR).

Introduction
Information about disease severity could help with both detection

and situational awareness during outbreaks of acute respiratory in-
fections (ARI). In this work, we use data from the EMR to identify
patients with pneumonia, a key landmark of ARI severity. We asked
if computerized analysis of the free-text of clinical notes or imaging
reports could complement structured EMR data to uncover pneumo-
nia cases.

Methods
A previously validated ARI case-detection algorithm (CDA) (sen-

sitivity, 99%; PPV, 14%) [1] flagged VAMHCS outpatient visits with
associated chest imaging (n = 2737). Manually categorized imaging
reports (Non-Negative if they could support the diagnosis of pneu-
monia, Negative otherwise; kappa = 0.88), served as a reference for
the development of an automated report classifier through machine-
learning [2]. EMR entries related to visits with Non-Negative chest
imaging were manually reviewed to identify cases with Possible
Pneumonia (new symptom(s) of cough, sputum, fever/chills/night
sweats, dyspnea, pleuritic chest pain) or with Pneumonia-in-Plan
(pneumonia listed as one of two most likely diagnoses in a physi-
cian’s note). These cases were used as reference for the development
of the EMR-based CDAs. CDA components included ICD-9 codes
for the full spectrum of ARI [1] or for the pneumonia subset, text
analysis aimed at non-negated ARI symptoms in the clinical note [1]
and the above-mentioned imaging report text classifier.

Results
The manual review identified 370 reference cases with Possible

Pneumonia and 250 with Pneumonia-in-Plan. Statistical performance
for illustrative CDAs that combined structured EMR parameters with
or without text analyses are shown in the Table. Addition of the “Text
of Imaging Report” analyses increased PPV by 38-70% in absolute
terms. Despite attendant losses in sensitivity, this classifier increased
the F-Measure of all CDAs based on a broad ARI ICD-9 codeset.
With the possible exception is CDA 6, whose F-measure was the

highest achieved in this study, the text analysis seeking ARI symp-
toms in the clinical note did not add further value to those CDAs that
also included analyses of the chest imaging reports.

Conclusions
Automated text analysis of chest imaging reports can improve our

ability to separate outpatients with pneumonia from those with a
milder form of ARI.

Keywords
situational awareness; influenza; surveillance; electronic medical
record; pneumonia

References

[1] DeLisle S, South B, Anthony JA, Kalp E, Gundlapalli A, et al. Com-
bining Free Text and Structured Electronic Medical Record Entries
to Detect Acute Respiratory Infections. PLoS ONE (2010) 5(10):
e13377.

[2] D’Avolio L, Nguyen T, Goryachev S, Fiore L. Automated Concept-
Level Information Extraction to Reduce the Need for Custom Soft-
ware and Rules Development. Journal of the American Medical
Informatics Association 2011 18(5): 607.

*Sylvain DeLisle
E-mail: sdelisle@umaryland.edu

Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * 5(1):e74, 2013