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 B. Larson, Hongfang 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 L. Pereira, Euijung Ryu, Richard A. Dart, Peggy PeissigJames G. Linneman, Gail P. Jarvik, Eric B. Larson, Jonathan A. Bock, Gerard C. Tromp, Mariza de Andrade, Véronique L. Roger

Research output: Contribution to journalArticlepeer-review

25 Scopus citations

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)
Pages (from-to)475-483
Number of pages9
JournalJournal of cardiovascular translational research
Volume8
Issue number8
DOIs
StatePublished - Nov 1 2015
Externally publishedYes

Bibliographical note

Funding Information:
The Mayo Clinic Biobank and the Mayo Genome Consortia is funded by the Mayo Clinic Center for Individualized Medicine. Additional funding for this work came from National Institutes of Health grants R01HL72435 (Heart Failure in the Community Cohort), R01AG034676 (The Rochester Epidemiology Project), R01GM102282 (Natural Language Processing for Clinical and Translational Research), the Electronic Medical Record and Genomics (eMERGE) Network U01 HG06379 (Mayo Clinic), U01HG006375 (Group Health/University of Washington); U01HG006382 (Geisinger Health System); U01HG006389 (Essentia Health & Marshfield Clinic Research Foundation); U01HG006388 (Northwestern University); HG004438 (Center for Inherited Disease Research, Johns Hopkins University); HG004424 (Broad Institute of Harvard & MIT); U01HG006378, U01HG006385 (Vanderbilt University); U01HG006380 (The Mt. Sinai Hospital); U01HG006828 (Cincinnati Children’s Hospital Medical Center/Harvard); U01HG006830 (Children’s Hospital of Philadelphia), NIA grant U01AG006781-25, Life Sciences Discovery Fund Grant #2065508, and additional support was provided by a State of Washington Life Sciences Discovery Fund award to the Northwest Institute of Genetic Medicine.

Publisher Copyright:
© 2015, Springer Science+Business Media New York.

Keywords

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

Fingerprint

Dive into the research topics of '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'. Together they form a unique fingerprint.

Cite this