Combining free text and structured electronic medical record entries to detect acute respiratory infections

Sylvain DeLisle, Brett South, Jill A. Anthony, Ericka Kalp, Adi Gundlapallli, Frank C. Curriero, Greg E. Glass, Matthew Samore, Trish M. Perl

Research output: Contribution to journalReview article

24 Citations (Scopus)

Abstract

Background: The electronic medical record (EMR) contains a rich source of information that could be harnessed for epidemic surveillance. We asked if structured EMR data could be coupled with computerized processing of free-text clinical entries to enhance detection of acute respiratory infections (ARI). Methodology:A manual review of EMR records related to 15,377 outpatient visits uncovered 280 reference cases of ARI. We used logistic regression with backward elimination to determine which among candidate structured EMR parameters (diagnostic codes, vital signs and orders for tests, imaging and medications) contributed to the detection of those reference cases. We also developed a computerized free-text search to identify clinical notes documenting at least two non-negated ARI symptoms. We then used heuristics to build case-detection algorithms that best combined the retained structured EMR parameters with the results of the text analysis. Principal Findings:An adjusted grouping of diagnostic codes identified reference ARI patients with a sensitivity of 79%, a specificity of 96% and a positive predictive value (PPV) of 32%. Of the 21 additional structured clinical parameters considered, two contributed significantly to ARI detection: new prescriptions for cough remedies and elevations in body temperature to at least 38°C. Together with the diagnostic codes, these parameters increased detection sensitivity to 87%, but specificity and PPV declined to 95% and 25%, respectively. Adding text analysis increased sensitivity to 99%, but PPV dropped further to 14%. Algorithms that required satisfying both a query of structured EMR parameters as well as text analysis disclosed PPVs of 52-68% and retained sensitivities of 69-73%. Conclusion:Structured EMR parameters and free-text analyses can be combined into algorithms that can detect ARI cases with new levels of sensitivity or precision. These results highlight potential paths by which repurposed EMR information could facilitate the discovery of epidemics before they cause mass casualties.

Original languageEnglish (US)
Article numbere13377
JournalPLoS One
Volume5
Issue number10
DOIs
StatePublished - Nov 17 2010

Fingerprint

Electronic medical equipment
Electronic Health Records
Respiratory Tract Infections
electronics
infection
Mass Casualty Incidents
cough
Vital Signs
information sources
Body Temperature
Cough
body temperature
signs and symptoms (animals and humans)
Sensitivity analysis
drug therapy
Prescriptions
Logistics
Outpatients
Logistic Models
image analysis

ASJC Scopus subject areas

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

Cite this

Combining free text and structured electronic medical record entries to detect acute respiratory infections. / DeLisle, Sylvain; South, Brett; Anthony, Jill A.; Kalp, Ericka; Gundlapallli, Adi; Curriero, Frank C.; Glass, Greg E.; Samore, Matthew; Perl, Trish M.

In: PLoS One, Vol. 5, No. 10, e13377, 17.11.2010.

Research output: Contribution to journalReview article

DeLisle, S, South, B, Anthony, JA, Kalp, E, Gundlapallli, A, Curriero, FC, Glass, GE, Samore, M & Perl, TM 2010, 'Combining free text and structured electronic medical record entries to detect acute respiratory infections', PLoS One, vol. 5, no. 10, e13377. https://doi.org/10.1371/journal.pone.0013377
DeLisle, Sylvain ; South, Brett ; Anthony, Jill A. ; Kalp, Ericka ; Gundlapallli, Adi ; Curriero, Frank C. ; Glass, Greg E. ; Samore, Matthew ; Perl, Trish M. / Combining free text and structured electronic medical record entries to detect acute respiratory infections. In: PLoS One. 2010 ; Vol. 5, No. 10.
@article{2f4dbae899b84d19974a9cbd9accf785,
title = "Combining free text and structured electronic medical record entries to detect acute respiratory infections",
abstract = "Background: The electronic medical record (EMR) contains a rich source of information that could be harnessed for epidemic surveillance. We asked if structured EMR data could be coupled with computerized processing of free-text clinical entries to enhance detection of acute respiratory infections (ARI). Methodology:A manual review of EMR records related to 15,377 outpatient visits uncovered 280 reference cases of ARI. We used logistic regression with backward elimination to determine which among candidate structured EMR parameters (diagnostic codes, vital signs and orders for tests, imaging and medications) contributed to the detection of those reference cases. We also developed a computerized free-text search to identify clinical notes documenting at least two non-negated ARI symptoms. We then used heuristics to build case-detection algorithms that best combined the retained structured EMR parameters with the results of the text analysis. Principal Findings:An adjusted grouping of diagnostic codes identified reference ARI patients with a sensitivity of 79{\%}, a specificity of 96{\%} and a positive predictive value (PPV) of 32{\%}. Of the 21 additional structured clinical parameters considered, two contributed significantly to ARI detection: new prescriptions for cough remedies and elevations in body temperature to at least 38°C. Together with the diagnostic codes, these parameters increased detection sensitivity to 87{\%}, but specificity and PPV declined to 95{\%} and 25{\%}, respectively. Adding text analysis increased sensitivity to 99{\%}, but PPV dropped further to 14{\%}. Algorithms that required satisfying both a query of structured EMR parameters as well as text analysis disclosed PPVs of 52-68{\%} and retained sensitivities of 69-73{\%}. Conclusion:Structured EMR parameters and free-text analyses can be combined into algorithms that can detect ARI cases with new levels of sensitivity or precision. These results highlight potential paths by which repurposed EMR information could facilitate the discovery of epidemics before they cause mass casualties.",
author = "Sylvain DeLisle and Brett South and Anthony, {Jill A.} and Ericka Kalp and Adi Gundlapallli and Curriero, {Frank C.} and Glass, {Greg E.} and Matthew Samore and Perl, {Trish M.}",
year = "2010",
month = "11",
day = "17",
doi = "10.1371/journal.pone.0013377",
language = "English (US)",
volume = "5",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

TY - JOUR

T1 - Combining free text and structured electronic medical record entries to detect acute respiratory infections

AU - DeLisle, Sylvain

AU - South, Brett

AU - Anthony, Jill A.

AU - Kalp, Ericka

AU - Gundlapallli, Adi

AU - Curriero, Frank C.

AU - Glass, Greg E.

AU - Samore, Matthew

AU - Perl, Trish M.

PY - 2010/11/17

Y1 - 2010/11/17

N2 - Background: The electronic medical record (EMR) contains a rich source of information that could be harnessed for epidemic surveillance. We asked if structured EMR data could be coupled with computerized processing of free-text clinical entries to enhance detection of acute respiratory infections (ARI). Methodology:A manual review of EMR records related to 15,377 outpatient visits uncovered 280 reference cases of ARI. We used logistic regression with backward elimination to determine which among candidate structured EMR parameters (diagnostic codes, vital signs and orders for tests, imaging and medications) contributed to the detection of those reference cases. We also developed a computerized free-text search to identify clinical notes documenting at least two non-negated ARI symptoms. We then used heuristics to build case-detection algorithms that best combined the retained structured EMR parameters with the results of the text analysis. Principal Findings:An adjusted grouping of diagnostic codes identified reference ARI patients with a sensitivity of 79%, a specificity of 96% and a positive predictive value (PPV) of 32%. Of the 21 additional structured clinical parameters considered, two contributed significantly to ARI detection: new prescriptions for cough remedies and elevations in body temperature to at least 38°C. Together with the diagnostic codes, these parameters increased detection sensitivity to 87%, but specificity and PPV declined to 95% and 25%, respectively. Adding text analysis increased sensitivity to 99%, but PPV dropped further to 14%. Algorithms that required satisfying both a query of structured EMR parameters as well as text analysis disclosed PPVs of 52-68% and retained sensitivities of 69-73%. Conclusion:Structured EMR parameters and free-text analyses can be combined into algorithms that can detect ARI cases with new levels of sensitivity or precision. These results highlight potential paths by which repurposed EMR information could facilitate the discovery of epidemics before they cause mass casualties.

AB - Background: The electronic medical record (EMR) contains a rich source of information that could be harnessed for epidemic surveillance. We asked if structured EMR data could be coupled with computerized processing of free-text clinical entries to enhance detection of acute respiratory infections (ARI). Methodology:A manual review of EMR records related to 15,377 outpatient visits uncovered 280 reference cases of ARI. We used logistic regression with backward elimination to determine which among candidate structured EMR parameters (diagnostic codes, vital signs and orders for tests, imaging and medications) contributed to the detection of those reference cases. We also developed a computerized free-text search to identify clinical notes documenting at least two non-negated ARI symptoms. We then used heuristics to build case-detection algorithms that best combined the retained structured EMR parameters with the results of the text analysis. Principal Findings:An adjusted grouping of diagnostic codes identified reference ARI patients with a sensitivity of 79%, a specificity of 96% and a positive predictive value (PPV) of 32%. Of the 21 additional structured clinical parameters considered, two contributed significantly to ARI detection: new prescriptions for cough remedies and elevations in body temperature to at least 38°C. Together with the diagnostic codes, these parameters increased detection sensitivity to 87%, but specificity and PPV declined to 95% and 25%, respectively. Adding text analysis increased sensitivity to 99%, but PPV dropped further to 14%. Algorithms that required satisfying both a query of structured EMR parameters as well as text analysis disclosed PPVs of 52-68% and retained sensitivities of 69-73%. Conclusion:Structured EMR parameters and free-text analyses can be combined into algorithms that can detect ARI cases with new levels of sensitivity or precision. These results highlight potential paths by which repurposed EMR information could facilitate the discovery of epidemics before they cause mass casualties.

UR - http://www.scopus.com/inward/record.url?scp=78149436687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149436687&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0013377

DO - 10.1371/journal.pone.0013377

M3 - Review article

VL - 5

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e13377

ER -