A Robust e-Epidemiology Tool in Phenotyping Heart Failure with Differentiation for Preserved and Reduced Ejection Fraction

the Electronic Medical Records and Genomics (eMERGE) Network

Suzette J Bielinski, Jyotishman Pathak, David S. Carrell, Paul Y Takahashi, Janet E Olson, Nicholas Larson, Hongfang D Liu, Sunghwan Sohn, Quinn S. Wells, Joshua C. Denny, Laura J. Rasmussen-Torvik, Jennifer Allen Pacheco, Kathryn L. Jackson, Timothy G. Lesnick, Rachel E. Gullerud, Paul A. Decker, Naveen Luke Pereira, Euijung Ryu, Richard A. Dart, Peggy Peissig & 7 others James G. Linneman, Gail P. Jarvik, Eric B. Larson, Jonathan A. Bock, Gerard C. Tromp, Mariza De Andrade, Veronique Lee Roger

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Identifying populations of heart failure (HF) patients is paramount to research efforts aimed at developing strategies to effectively reduce the burden of this disease. The use of electronic medical record (EMR) data for this purpose is challenging given the syndromic nature of HF and the need to distinguish HF with preserved or reduced ejection fraction. Using a gold standard cohort of manually abstracted cases, an EMR-driven phenotype algorithm based on structured and unstructured data was developed to identify all the cases. The resulting algorithm was executed in two cohorts from the Electronic Medical Records and Genomics (eMERGE) Network with a positive predictive value of >95 %. The algorithm was expanded to include three hierarchical definitions of HF (i.e., definite, probable, possible) based on the degree of confidence of the classification to capture HF cases in a whole population whereby increasing the algorithm utility for use in e-Epidemiologic research.

Original languageEnglish (US)
JournalJournal of Cardiovascular Translational Research
DOIs
StateAccepted/In press - Jul 21 2015

Fingerprint

Electronic Health Records
Genomics
Epidemiology
Heart Failure
Research
Population
Phenotype

Keywords

  • Electronic medical records
  • Heart failure
  • Natural language processing
  • Phenotyping
  • Ventricular ejection fraction

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine
  • Genetics
  • Genetics(clinical)
  • Molecular Medicine
  • Pharmaceutical Science

Cite this

A Robust e-Epidemiology Tool in Phenotyping Heart Failure with Differentiation for Preserved and Reduced Ejection Fraction : the Electronic Medical Records and Genomics (eMERGE) Network. / Bielinski, Suzette J; Pathak, Jyotishman; Carrell, David S.; Takahashi, Paul Y; Olson, Janet E; Larson, Nicholas; Liu, Hongfang D; Sohn, Sunghwan; Wells, Quinn S.; Denny, Joshua C.; Rasmussen-Torvik, Laura J.; Pacheco, Jennifer Allen; Jackson, Kathryn L.; Lesnick, Timothy G.; Gullerud, Rachel E.; Decker, Paul A.; Pereira, Naveen Luke; Ryu, Euijung; Dart, Richard A.; Peissig, Peggy; Linneman, James G.; Jarvik, Gail P.; Larson, Eric B.; Bock, Jonathan A.; Tromp, Gerard C.; De Andrade, Mariza; Roger, Veronique Lee.

In: Journal of Cardiovascular Translational Research, 21.07.2015.

Research output: Contribution to journalArticle

Bielinski, Suzette J ; Pathak, Jyotishman ; Carrell, David S. ; Takahashi, Paul Y ; Olson, Janet E ; Larson, Nicholas ; Liu, Hongfang D ; Sohn, Sunghwan ; Wells, Quinn S. ; Denny, Joshua C. ; Rasmussen-Torvik, Laura J. ; Pacheco, Jennifer Allen ; Jackson, Kathryn L. ; Lesnick, Timothy G. ; Gullerud, Rachel E. ; Decker, Paul A. ; Pereira, Naveen Luke ; Ryu, Euijung ; Dart, Richard A. ; Peissig, Peggy ; Linneman, James G. ; Jarvik, Gail P. ; Larson, Eric B. ; Bock, Jonathan A. ; Tromp, Gerard C. ; De Andrade, Mariza ; Roger, Veronique Lee. / A Robust e-Epidemiology Tool in Phenotyping Heart Failure with Differentiation for Preserved and Reduced Ejection Fraction : the Electronic Medical Records and Genomics (eMERGE) Network. In: Journal of Cardiovascular Translational Research. 2015.
@article{f54a89739d264bcc8250dedeece7e55b,
title = "A Robust e-Epidemiology Tool in Phenotyping Heart Failure with Differentiation for Preserved and Reduced Ejection Fraction: the Electronic Medical Records and Genomics (eMERGE) Network",
abstract = "Identifying populations of heart failure (HF) patients is paramount to research efforts aimed at developing strategies to effectively reduce the burden of this disease. The use of electronic medical record (EMR) data for this purpose is challenging given the syndromic nature of HF and the need to distinguish HF with preserved or reduced ejection fraction. Using a gold standard cohort of manually abstracted cases, an EMR-driven phenotype algorithm based on structured and unstructured data was developed to identify all the cases. The resulting algorithm was executed in two cohorts from the Electronic Medical Records and Genomics (eMERGE) Network with a positive predictive value of >95 {\%}. The algorithm was expanded to include three hierarchical definitions of HF (i.e., definite, probable, possible) based on the degree of confidence of the classification to capture HF cases in a whole population whereby increasing the algorithm utility for use in e-Epidemiologic research.",
keywords = "Electronic medical records, Heart failure, Natural language processing, Phenotyping, Ventricular ejection fraction",
author = "Bielinski, {Suzette J} and Jyotishman Pathak and Carrell, {David S.} and Takahashi, {Paul Y} and Olson, {Janet E} and Nicholas Larson and Liu, {Hongfang D} and Sunghwan Sohn and Wells, {Quinn S.} and Denny, {Joshua C.} and Rasmussen-Torvik, {Laura J.} and Pacheco, {Jennifer Allen} and Jackson, {Kathryn L.} and Lesnick, {Timothy G.} and Gullerud, {Rachel E.} and Decker, {Paul A.} and Pereira, {Naveen Luke} and Euijung Ryu and Dart, {Richard A.} and Peggy Peissig and Linneman, {James G.} and Jarvik, {Gail P.} and Larson, {Eric B.} and Bock, {Jonathan A.} and Tromp, {Gerard C.} and {De Andrade}, Mariza and Roger, {Veronique Lee}",
year = "2015",
month = "7",
day = "21",
doi = "10.1007/s12265-015-9644-2",
language = "English (US)",
journal = "Journal of Cardiovascular Translational Research",
issn = "1937-5387",
publisher = "Springer New York",

}

TY - JOUR

T1 - A Robust e-Epidemiology Tool in Phenotyping Heart Failure with Differentiation for Preserved and Reduced Ejection Fraction

T2 - the Electronic Medical Records and Genomics (eMERGE) Network

AU - Bielinski, Suzette J

AU - Pathak, Jyotishman

AU - Carrell, David S.

AU - Takahashi, Paul Y

AU - Olson, Janet E

AU - Larson, Nicholas

AU - Liu, Hongfang D

AU - Sohn, Sunghwan

AU - Wells, Quinn S.

AU - Denny, Joshua C.

AU - Rasmussen-Torvik, Laura J.

AU - Pacheco, Jennifer Allen

AU - Jackson, Kathryn L.

AU - Lesnick, Timothy G.

AU - Gullerud, Rachel E.

AU - Decker, Paul A.

AU - Pereira, Naveen Luke

AU - Ryu, Euijung

AU - Dart, Richard A.

AU - Peissig, Peggy

AU - Linneman, James G.

AU - Jarvik, Gail P.

AU - Larson, Eric B.

AU - Bock, Jonathan A.

AU - Tromp, Gerard C.

AU - De Andrade, Mariza

AU - Roger, Veronique Lee

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Identifying populations of heart failure (HF) patients is paramount to research efforts aimed at developing strategies to effectively reduce the burden of this disease. The use of electronic medical record (EMR) data for this purpose is challenging given the syndromic nature of HF and the need to distinguish HF with preserved or reduced ejection fraction. Using a gold standard cohort of manually abstracted cases, an EMR-driven phenotype algorithm based on structured and unstructured data was developed to identify all the cases. The resulting algorithm was executed in two cohorts from the Electronic Medical Records and Genomics (eMERGE) Network with a positive predictive value of >95 %. The algorithm was expanded to include three hierarchical definitions of HF (i.e., definite, probable, possible) based on the degree of confidence of the classification to capture HF cases in a whole population whereby increasing the algorithm utility for use in e-Epidemiologic research.

AB - Identifying populations of heart failure (HF) patients is paramount to research efforts aimed at developing strategies to effectively reduce the burden of this disease. The use of electronic medical record (EMR) data for this purpose is challenging given the syndromic nature of HF and the need to distinguish HF with preserved or reduced ejection fraction. Using a gold standard cohort of manually abstracted cases, an EMR-driven phenotype algorithm based on structured and unstructured data was developed to identify all the cases. The resulting algorithm was executed in two cohorts from the Electronic Medical Records and Genomics (eMERGE) Network with a positive predictive value of >95 %. The algorithm was expanded to include three hierarchical definitions of HF (i.e., definite, probable, possible) based on the degree of confidence of the classification to capture HF cases in a whole population whereby increasing the algorithm utility for use in e-Epidemiologic research.

KW - Electronic medical records

KW - Heart failure

KW - Natural language processing

KW - Phenotyping

KW - Ventricular ejection fraction

UR - http://www.scopus.com/inward/record.url?scp=84937605719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937605719&partnerID=8YFLogxK

U2 - 10.1007/s12265-015-9644-2

DO - 10.1007/s12265-015-9644-2

M3 - Article

JO - Journal of Cardiovascular Translational Research

JF - Journal of Cardiovascular Translational Research

SN - 1937-5387

ER -