A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments

Jennifer A. Pacheco, Luke V. Rasmussen, Richard C. Kiefer, Thomas R. Campion, Peter Speltz, Robert J. Carroll, Sarah C. Stallings, Huan Mo, Monika Ahuja, Guoqian Jiang, Eric R. LaRose, Peggy L. Peissig, Ning Shang, Barbara Benoit, Vivian S. Gainer, Kenneth Borthwick, Kathryn L. Jackson, Ambrish Sharma, Andy Yizhou Wu, Abel N Kho & 4 others Dan M. Roden, Jyotishman Pathak, Joshua C. Denny, William K. Thompson

Research output: Contribution to journalArticle

Abstract

Electronic health record (EHR) algorithms for defining patient cohorts are commonly shared as free-text descriptions that require human intervention both to interpret and implement. We developed the Phenotype Execution and Modeling Architecture (PhEMA, http://projectphema.org) to author and execute standardized computable phenotype algorithms. With PhEMA, we converted an algorithm for benign prostatic hyperplasia, developed for the electronic Medical Records and Genomics network (eMERGE), into a standards-based computable format. Eight sites (7 within eMERGE) received the computable algorithm, and 6 successfully executed it against local data warehouses and/or i2b2 instances. Blinded random chart review of cases selected by the computable algorithm shows PPV 90%, and 3 out of 5 sites had >90% overlap of selected cases when comparing the computable algorithm to their original eMERGE implementation. This case study demonstrates potential use of PhEMA computable representations to automate phenotyping across different EHR systems, but also highlights some ongoing challenges.

Original languageEnglish (US)
Pages (from-to)1540-1546
Number of pages7
JournalJournal of the American Medical Informatics Association
Volume25
Issue number11
DOIs
StatePublished - Nov 1 2018

Fingerprint

Electronic Health Records
Phenotype
Genomics
Prostatic Hyperplasia

Keywords

  • Algorithms
  • Architecture
  • Electronic health records
  • Genomics
  • Phenotype
  • Prostatic hyperplasia

ASJC Scopus subject areas

  • Health Informatics

Cite this

Pacheco, Jennifer A. ; Rasmussen, Luke V. ; Kiefer, Richard C. ; Campion, Thomas R. ; Speltz, Peter ; Carroll, Robert J. ; Stallings, Sarah C. ; Mo, Huan ; Ahuja, Monika ; Jiang, Guoqian ; LaRose, Eric R. ; Peissig, Peggy L. ; Shang, Ning ; Benoit, Barbara ; Gainer, Vivian S. ; Borthwick, Kenneth ; Jackson, Kathryn L. ; Sharma, Ambrish ; Wu, Andy Yizhou ; Kho, Abel N ; Roden, Dan M. ; Pathak, Jyotishman ; Denny, Joshua C. ; Thompson, William K. / A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments. In: Journal of the American Medical Informatics Association. 2018 ; Vol. 25, No. 11. pp. 1540-1546.
@article{5217cc8d3a804931a2e9bb3b57b4a99e,
title = "A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments",
abstract = "Electronic health record (EHR) algorithms for defining patient cohorts are commonly shared as free-text descriptions that require human intervention both to interpret and implement. We developed the Phenotype Execution and Modeling Architecture (PhEMA, http://projectphema.org) to author and execute standardized computable phenotype algorithms. With PhEMA, we converted an algorithm for benign prostatic hyperplasia, developed for the electronic Medical Records and Genomics network (eMERGE), into a standards-based computable format. Eight sites (7 within eMERGE) received the computable algorithm, and 6 successfully executed it against local data warehouses and/or i2b2 instances. Blinded random chart review of cases selected by the computable algorithm shows PPV 90{\%}, and 3 out of 5 sites had >90{\%} overlap of selected cases when comparing the computable algorithm to their original eMERGE implementation. This case study demonstrates potential use of PhEMA computable representations to automate phenotyping across different EHR systems, but also highlights some ongoing challenges.",
keywords = "Algorithms, Architecture, Electronic health records, Genomics, Phenotype, Prostatic hyperplasia",
author = "Pacheco, {Jennifer A.} and Rasmussen, {Luke V.} and Kiefer, {Richard C.} and Campion, {Thomas R.} and Peter Speltz and Carroll, {Robert J.} and Stallings, {Sarah C.} and Huan Mo and Monika Ahuja and Guoqian Jiang and LaRose, {Eric R.} and Peissig, {Peggy L.} and Ning Shang and Barbara Benoit and Gainer, {Vivian S.} and Kenneth Borthwick and Jackson, {Kathryn L.} and Ambrish Sharma and Wu, {Andy Yizhou} and Kho, {Abel N} and Roden, {Dan M.} and Jyotishman Pathak and Denny, {Joshua C.} and Thompson, {William K.}",
year = "2018",
month = "11",
day = "1",
doi = "10.1093/jamia/ocy101",
language = "English (US)",
volume = "25",
pages = "1540--1546",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "11",

}

Pacheco, JA, Rasmussen, LV, Kiefer, RC, Campion, TR, Speltz, P, Carroll, RJ, Stallings, SC, Mo, H, Ahuja, M, Jiang, G, LaRose, ER, Peissig, PL, Shang, N, Benoit, B, Gainer, VS, Borthwick, K, Jackson, KL, Sharma, A, Wu, AY, Kho, AN, Roden, DM, Pathak, J, Denny, JC & Thompson, WK 2018, 'A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments' Journal of the American Medical Informatics Association, vol. 25, no. 11, pp. 1540-1546. https://doi.org/10.1093/jamia/ocy101

A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments. / Pacheco, Jennifer A.; Rasmussen, Luke V.; Kiefer, Richard C.; Campion, Thomas R.; Speltz, Peter; Carroll, Robert J.; Stallings, Sarah C.; Mo, Huan; Ahuja, Monika; Jiang, Guoqian; LaRose, Eric R.; Peissig, Peggy L.; Shang, Ning; Benoit, Barbara; Gainer, Vivian S.; Borthwick, Kenneth; Jackson, Kathryn L.; Sharma, Ambrish; Wu, Andy Yizhou; Kho, Abel N; Roden, Dan M.; Pathak, Jyotishman; Denny, Joshua C.; Thompson, William K.

In: Journal of the American Medical Informatics Association, Vol. 25, No. 11, 01.11.2018, p. 1540-1546.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A case study evaluating the portability of an executable computable phenotype algorithm across multiple institutions and electronic health record environments

AU - Pacheco, Jennifer A.

AU - Rasmussen, Luke V.

AU - Kiefer, Richard C.

AU - Campion, Thomas R.

AU - Speltz, Peter

AU - Carroll, Robert J.

AU - Stallings, Sarah C.

AU - Mo, Huan

AU - Ahuja, Monika

AU - Jiang, Guoqian

AU - LaRose, Eric R.

AU - Peissig, Peggy L.

AU - Shang, Ning

AU - Benoit, Barbara

AU - Gainer, Vivian S.

AU - Borthwick, Kenneth

AU - Jackson, Kathryn L.

AU - Sharma, Ambrish

AU - Wu, Andy Yizhou

AU - Kho, Abel N

AU - Roden, Dan M.

AU - Pathak, Jyotishman

AU - Denny, Joshua C.

AU - Thompson, William K.

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Electronic health record (EHR) algorithms for defining patient cohorts are commonly shared as free-text descriptions that require human intervention both to interpret and implement. We developed the Phenotype Execution and Modeling Architecture (PhEMA, http://projectphema.org) to author and execute standardized computable phenotype algorithms. With PhEMA, we converted an algorithm for benign prostatic hyperplasia, developed for the electronic Medical Records and Genomics network (eMERGE), into a standards-based computable format. Eight sites (7 within eMERGE) received the computable algorithm, and 6 successfully executed it against local data warehouses and/or i2b2 instances. Blinded random chart review of cases selected by the computable algorithm shows PPV 90%, and 3 out of 5 sites had >90% overlap of selected cases when comparing the computable algorithm to their original eMERGE implementation. This case study demonstrates potential use of PhEMA computable representations to automate phenotyping across different EHR systems, but also highlights some ongoing challenges.

AB - Electronic health record (EHR) algorithms for defining patient cohorts are commonly shared as free-text descriptions that require human intervention both to interpret and implement. We developed the Phenotype Execution and Modeling Architecture (PhEMA, http://projectphema.org) to author and execute standardized computable phenotype algorithms. With PhEMA, we converted an algorithm for benign prostatic hyperplasia, developed for the electronic Medical Records and Genomics network (eMERGE), into a standards-based computable format. Eight sites (7 within eMERGE) received the computable algorithm, and 6 successfully executed it against local data warehouses and/or i2b2 instances. Blinded random chart review of cases selected by the computable algorithm shows PPV 90%, and 3 out of 5 sites had >90% overlap of selected cases when comparing the computable algorithm to their original eMERGE implementation. This case study demonstrates potential use of PhEMA computable representations to automate phenotyping across different EHR systems, but also highlights some ongoing challenges.

KW - Algorithms

KW - Architecture

KW - Electronic health records

KW - Genomics

KW - Phenotype

KW - Prostatic hyperplasia

UR - http://www.scopus.com/inward/record.url?scp=85055802994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055802994&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocy101

DO - 10.1093/jamia/ocy101

M3 - Article

VL - 25

SP - 1540

EP - 1546

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 11

ER -