Desiderata for computable representations of electronic health records-driven phenotype algorithms

Other collaborators

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Background Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, phenotype algorithms are most commonly represented as noncomputable descriptive documents and knowledge artifacts that detail the protocols for querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, and are primarily meant for human comprehension. We present desiderata for developing a computable phenotype representation model (PheRM). Methods A team of clinicians and informaticians reviewed common features for multisite phenotype algorithms published in PheKB.org and existing phenotype representation platforms. We also evaluated well-known diagnostic criteria and clinical decision-making guidelines to encompass a broader category of algorithms. Results We propose 10 desired characteristics for a flexible, computable PheRM: (1) structure clinical data into queryable forms; (2) recommend use of a common data model, but also support customization for the variability and availability of EHR data among sites; (3) support both humanreadable and computable representations of phenotype algorithms; (4) implement set operations and relational algebra for modeling phenotype algorithms; (5) represent phenotype criteria with structured rules; (6) support defining temporal relations between events; (7) use standardized terminologies and ontologies, and facilitate reuse of value sets; (8) define representations for text searching and natural language processing; (9) provide interfaces for external software algorithms; and (10) maintain backward compatibility. Conclusion A computable PheRM is needed for true phenotype portability and reliability across different EHR products and healthcare systems. These desiderata are a guide to inform the establishment and evolution of EHR phenotype algorithm authoring platforms and languages.

Original languageEnglish (US)
Pages (from-to)1220-1230
Number of pages11
JournalJournal of the American Medical Informatics Association
Volume22
Issue number6
DOIs
StatePublished - Jan 1 2015

Fingerprint

Electronic Health Records
Phenotype
Natural Language Processing
Translational Medical Research
Terminology
Artifacts
Language
Software
Guidelines

Keywords

  • Computable representation
  • Data models
  • Electronic health records
  • Phenotype algorithms
  • Phenotype standardization

ASJC Scopus subject areas

  • Health Informatics

Cite this

@article{f3eda3a110a14855b841a1e852973261,
title = "Desiderata for computable representations of electronic health records-driven phenotype algorithms",
abstract = "Background Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, phenotype algorithms are most commonly represented as noncomputable descriptive documents and knowledge artifacts that detail the protocols for querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, and are primarily meant for human comprehension. We present desiderata for developing a computable phenotype representation model (PheRM). Methods A team of clinicians and informaticians reviewed common features for multisite phenotype algorithms published in PheKB.org and existing phenotype representation platforms. We also evaluated well-known diagnostic criteria and clinical decision-making guidelines to encompass a broader category of algorithms. Results We propose 10 desired characteristics for a flexible, computable PheRM: (1) structure clinical data into queryable forms; (2) recommend use of a common data model, but also support customization for the variability and availability of EHR data among sites; (3) support both humanreadable and computable representations of phenotype algorithms; (4) implement set operations and relational algebra for modeling phenotype algorithms; (5) represent phenotype criteria with structured rules; (6) support defining temporal relations between events; (7) use standardized terminologies and ontologies, and facilitate reuse of value sets; (8) define representations for text searching and natural language processing; (9) provide interfaces for external software algorithms; and (10) maintain backward compatibility. Conclusion A computable PheRM is needed for true phenotype portability and reliability across different EHR products and healthcare systems. These desiderata are a guide to inform the establishment and evolution of EHR phenotype algorithm authoring platforms and languages.",
keywords = "Computable representation, Data models, Electronic health records, Phenotype algorithms, Phenotype standardization",
author = "{Other collaborators} and Huan Mo and Thompson, {William K.} and Rasmussen, {Luke V.} and Pacheco, {Jennifer A.} and Guoqian Jiang and Richard Kiefer and Qian Zhu and Jie Xu and Enid Montague and Carrell, {David S.} and Todd Lingren and Mentch, {Frank D.} and Yizhao Ni and Wehbe, {Firas H.} and Peissig, {Peggy L.} and Gerard Tromp and Larson, {Eric B.} and Chute, {Christopher G.} and Jyotishman Pathak and Denny, {Joshua C.} and Peter Speltz and Kho, {Abel N.} and Jarvik, {Gail P.} and Bejan, {Cosmin A.} and Williams, {Marc S.} and Kenneth Borthwick and Kitchner, {Terrie E.} and Roden, {Dan M.} and Harris, {Paul A.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1093/jamia/ocv112",
language = "English (US)",
volume = "22",
pages = "1220--1230",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "6",

}

Desiderata for computable representations of electronic health records-driven phenotype algorithms. / Other collaborators.

In: Journal of the American Medical Informatics Association, Vol. 22, No. 6, 01.01.2015, p. 1220-1230.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Desiderata for computable representations of electronic health records-driven phenotype algorithms

AU - Other collaborators

AU - Mo, Huan

AU - Thompson, William K.

AU - Rasmussen, Luke V.

AU - Pacheco, Jennifer A.

AU - Jiang, Guoqian

AU - Kiefer, Richard

AU - Zhu, Qian

AU - Xu, Jie

AU - Montague, Enid

AU - Carrell, David S.

AU - Lingren, Todd

AU - Mentch, Frank D.

AU - Ni, Yizhao

AU - Wehbe, Firas H.

AU - Peissig, Peggy L.

AU - Tromp, Gerard

AU - Larson, Eric B.

AU - Chute, Christopher G.

AU - Pathak, Jyotishman

AU - Denny, Joshua C.

AU - Speltz, Peter

AU - Kho, Abel N.

AU - Jarvik, Gail P.

AU - Bejan, Cosmin A.

AU - Williams, Marc S.

AU - Borthwick, Kenneth

AU - Kitchner, Terrie E.

AU - Roden, Dan M.

AU - Harris, Paul A.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Background Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, phenotype algorithms are most commonly represented as noncomputable descriptive documents and knowledge artifacts that detail the protocols for querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, and are primarily meant for human comprehension. We present desiderata for developing a computable phenotype representation model (PheRM). Methods A team of clinicians and informaticians reviewed common features for multisite phenotype algorithms published in PheKB.org and existing phenotype representation platforms. We also evaluated well-known diagnostic criteria and clinical decision-making guidelines to encompass a broader category of algorithms. Results We propose 10 desired characteristics for a flexible, computable PheRM: (1) structure clinical data into queryable forms; (2) recommend use of a common data model, but also support customization for the variability and availability of EHR data among sites; (3) support both humanreadable and computable representations of phenotype algorithms; (4) implement set operations and relational algebra for modeling phenotype algorithms; (5) represent phenotype criteria with structured rules; (6) support defining temporal relations between events; (7) use standardized terminologies and ontologies, and facilitate reuse of value sets; (8) define representations for text searching and natural language processing; (9) provide interfaces for external software algorithms; and (10) maintain backward compatibility. Conclusion A computable PheRM is needed for true phenotype portability and reliability across different EHR products and healthcare systems. These desiderata are a guide to inform the establishment and evolution of EHR phenotype algorithm authoring platforms and languages.

AB - Background Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, phenotype algorithms are most commonly represented as noncomputable descriptive documents and knowledge artifacts that detail the protocols for querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, and are primarily meant for human comprehension. We present desiderata for developing a computable phenotype representation model (PheRM). Methods A team of clinicians and informaticians reviewed common features for multisite phenotype algorithms published in PheKB.org and existing phenotype representation platforms. We also evaluated well-known diagnostic criteria and clinical decision-making guidelines to encompass a broader category of algorithms. Results We propose 10 desired characteristics for a flexible, computable PheRM: (1) structure clinical data into queryable forms; (2) recommend use of a common data model, but also support customization for the variability and availability of EHR data among sites; (3) support both humanreadable and computable representations of phenotype algorithms; (4) implement set operations and relational algebra for modeling phenotype algorithms; (5) represent phenotype criteria with structured rules; (6) support defining temporal relations between events; (7) use standardized terminologies and ontologies, and facilitate reuse of value sets; (8) define representations for text searching and natural language processing; (9) provide interfaces for external software algorithms; and (10) maintain backward compatibility. Conclusion A computable PheRM is needed for true phenotype portability and reliability across different EHR products and healthcare systems. These desiderata are a guide to inform the establishment and evolution of EHR phenotype algorithm authoring platforms and languages.

KW - Computable representation

KW - Data models

KW - Electronic health records

KW - Phenotype algorithms

KW - Phenotype standardization

UR - http://www.scopus.com/inward/record.url?scp=84954203288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954203288&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocv112

DO - 10.1093/jamia/ocv112

M3 - Article

VL - 22

SP - 1220

EP - 1230

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 6

ER -