Using the Electronic Medical Record to Identify Community-Acquired Pneumonia: Toward a Replicable Automated Strategy

Sylvain DeLisle, Bernard Kim, Janaki Deepak, Tariq Siddiqui, Adi Gundlapalli, Matthew Samore, Leonard D'Avolio

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Background:Timely information about disease severity can be central to the detection and management of outbreaks of acute respiratory infections (ARI), including influenza. We asked if two resources: 1) free text, and 2) structured data from an electronic medical record (EMR) could complement each other to identify patients with pneumonia, an ARI severity landmark.Methods:A manual EMR review of 2747 outpatient ARI visits with associated chest imaging identified x-ray reports that could support the diagnosis of pneumonia (kappa score = 0.88 (95% CI 0.82:0.93)), along with attendant cases with Possible Pneumonia (adds either cough, sputum, fever/chills/night sweats, dyspnea or pleuritic chest pain) or with Pneumonia-in-Plan (adds pneumonia stated as a likely diagnosis by the provider). The x-ray reports served as a reference to develop a text classifier using machine-learning software that did not require custom coding. To identify pneumonia cases, the classifier was combined with EMR-based structured data and with text analyses aimed at ARI symptoms in clinical notes.Results:370 reference cases with Possible Pneumonia and 250 with Pneumonia-in-Plan were identified. The x-ray report text classifier increased the positive predictive value of otherwise identical EMR-based case-detection algorithms by 20-70%, while retaining sensitivities of 58-75%. These performance gains were independent of the case definitions and of whether patients were admitted to the hospital or sent home. Text analyses seeking ARI symptoms in clinical notes did not add further value.Conclusion:Specialized software development is not required for automated text analyses to help identify pneumonia patients. These results begin to map an efficient, replicable strategy through which EMR data can be used to stratify ARI severity.

Original languageEnglish (US)
Article numbere70944
JournalPLoS One
Volume8
Issue number8
DOIs
StatePublished - Aug 13 2013

Fingerprint

Electronic medical equipment
Electronic Health Records
pneumonia
electronics
Pneumonia
Respiratory Tract Infections
Classifiers
X rays
infection
X-radiation
X-Rays
chest
signs and symptoms (animals and humans)
Software
Learning systems
Software engineering
sweat
Chills
Imaging techniques
cough

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Using the Electronic Medical Record to Identify Community-Acquired Pneumonia : Toward a Replicable Automated Strategy. / DeLisle, Sylvain; Kim, Bernard; Deepak, Janaki; Siddiqui, Tariq; Gundlapalli, Adi; Samore, Matthew; D'Avolio, Leonard.

In: PLoS One, Vol. 8, No. 8, e70944, 13.08.2013.

Research output: Contribution to journalArticle

DeLisle, Sylvain ; Kim, Bernard ; Deepak, Janaki ; Siddiqui, Tariq ; Gundlapalli, Adi ; Samore, Matthew ; D'Avolio, Leonard. / Using the Electronic Medical Record to Identify Community-Acquired Pneumonia : Toward a Replicable Automated Strategy. In: PLoS One. 2013 ; Vol. 8, No. 8.
@article{9ca63915031d45b083ee74e8ca81c524,
title = "Using the Electronic Medical Record to Identify Community-Acquired Pneumonia: Toward a Replicable Automated Strategy",
abstract = "Background:Timely information about disease severity can be central to the detection and management of outbreaks of acute respiratory infections (ARI), including influenza. We asked if two resources: 1) free text, and 2) structured data from an electronic medical record (EMR) could complement each other to identify patients with pneumonia, an ARI severity landmark.Methods:A manual EMR review of 2747 outpatient ARI visits with associated chest imaging identified x-ray reports that could support the diagnosis of pneumonia (kappa score = 0.88 (95{\%} CI 0.82:0.93)), along with attendant cases with Possible Pneumonia (adds either cough, sputum, fever/chills/night sweats, dyspnea or pleuritic chest pain) or with Pneumonia-in-Plan (adds pneumonia stated as a likely diagnosis by the provider). The x-ray reports served as a reference to develop a text classifier using machine-learning software that did not require custom coding. To identify pneumonia cases, the classifier was combined with EMR-based structured data and with text analyses aimed at ARI symptoms in clinical notes.Results:370 reference cases with Possible Pneumonia and 250 with Pneumonia-in-Plan were identified. The x-ray report text classifier increased the positive predictive value of otherwise identical EMR-based case-detection algorithms by 20-70{\%}, while retaining sensitivities of 58-75{\%}. These performance gains were independent of the case definitions and of whether patients were admitted to the hospital or sent home. Text analyses seeking ARI symptoms in clinical notes did not add further value.Conclusion:Specialized software development is not required for automated text analyses to help identify pneumonia patients. These results begin to map an efficient, replicable strategy through which EMR data can be used to stratify ARI severity.",
author = "Sylvain DeLisle and Bernard Kim and Janaki Deepak and Tariq Siddiqui and Adi Gundlapalli and Matthew Samore and Leonard D'Avolio",
year = "2013",
month = "8",
day = "13",
doi = "10.1371/journal.pone.0070944",
language = "English (US)",
volume = "8",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Using the Electronic Medical Record to Identify Community-Acquired Pneumonia

T2 - Toward a Replicable Automated Strategy

AU - DeLisle, Sylvain

AU - Kim, Bernard

AU - Deepak, Janaki

AU - Siddiqui, Tariq

AU - Gundlapalli, Adi

AU - Samore, Matthew

AU - D'Avolio, Leonard

PY - 2013/8/13

Y1 - 2013/8/13

N2 - Background:Timely information about disease severity can be central to the detection and management of outbreaks of acute respiratory infections (ARI), including influenza. We asked if two resources: 1) free text, and 2) structured data from an electronic medical record (EMR) could complement each other to identify patients with pneumonia, an ARI severity landmark.Methods:A manual EMR review of 2747 outpatient ARI visits with associated chest imaging identified x-ray reports that could support the diagnosis of pneumonia (kappa score = 0.88 (95% CI 0.82:0.93)), along with attendant cases with Possible Pneumonia (adds either cough, sputum, fever/chills/night sweats, dyspnea or pleuritic chest pain) or with Pneumonia-in-Plan (adds pneumonia stated as a likely diagnosis by the provider). The x-ray reports served as a reference to develop a text classifier using machine-learning software that did not require custom coding. To identify pneumonia cases, the classifier was combined with EMR-based structured data and with text analyses aimed at ARI symptoms in clinical notes.Results:370 reference cases with Possible Pneumonia and 250 with Pneumonia-in-Plan were identified. The x-ray report text classifier increased the positive predictive value of otherwise identical EMR-based case-detection algorithms by 20-70%, while retaining sensitivities of 58-75%. These performance gains were independent of the case definitions and of whether patients were admitted to the hospital or sent home. Text analyses seeking ARI symptoms in clinical notes did not add further value.Conclusion:Specialized software development is not required for automated text analyses to help identify pneumonia patients. These results begin to map an efficient, replicable strategy through which EMR data can be used to stratify ARI severity.

AB - Background:Timely information about disease severity can be central to the detection and management of outbreaks of acute respiratory infections (ARI), including influenza. We asked if two resources: 1) free text, and 2) structured data from an electronic medical record (EMR) could complement each other to identify patients with pneumonia, an ARI severity landmark.Methods:A manual EMR review of 2747 outpatient ARI visits with associated chest imaging identified x-ray reports that could support the diagnosis of pneumonia (kappa score = 0.88 (95% CI 0.82:0.93)), along with attendant cases with Possible Pneumonia (adds either cough, sputum, fever/chills/night sweats, dyspnea or pleuritic chest pain) or with Pneumonia-in-Plan (adds pneumonia stated as a likely diagnosis by the provider). The x-ray reports served as a reference to develop a text classifier using machine-learning software that did not require custom coding. To identify pneumonia cases, the classifier was combined with EMR-based structured data and with text analyses aimed at ARI symptoms in clinical notes.Results:370 reference cases with Possible Pneumonia and 250 with Pneumonia-in-Plan were identified. The x-ray report text classifier increased the positive predictive value of otherwise identical EMR-based case-detection algorithms by 20-70%, while retaining sensitivities of 58-75%. These performance gains were independent of the case definitions and of whether patients were admitted to the hospital or sent home. Text analyses seeking ARI symptoms in clinical notes did not add further value.Conclusion:Specialized software development is not required for automated text analyses to help identify pneumonia patients. These results begin to map an efficient, replicable strategy through which EMR data can be used to stratify ARI severity.

UR - http://www.scopus.com/inward/record.url?scp=84881522519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881522519&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0070944

DO - 10.1371/journal.pone.0070944

M3 - Article

C2 - 23967138

AN - SCOPUS:84881522519

VL - 8

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e70944

ER -