A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

Casey Lynnette Overby, Jyotishman Pathak, Omri Gottesman, Krystl Haerian, Adler Perotte, Sean Murphy, Kevin Bruce, Stephanie Johnson, Jayant Talwalkar, Yufeng Shen, Steve Ellis, Iftikhar Jan Kullo, Christopher Chute, Carol Friedman, Erwin Bottinger, George Hripcsak, Chunhua Weng

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Objective To describe a collaborative approach for developing an electronic health record (EHR) phenotyping algorithm for drug-induced liver injury (DILI). Methods We analyzed types and causes of differences in DILI case definitions provided by two institutions- Columbia University and Mayo Clinic; harmonized two EHR phenotyping algorithms; and assessed the performance, measured by sensitivity, specificity, positive predictive value, and negative predictive value, of the resulting algorithm at three institutions except that sensitivity was measured only at Columbia University. Results Although these sites had the same case definition, their phenotyping methods differed by selection of liver injury diagnoses, inclusion of drugs cited in DILI cases, laboratory tests assessed, laboratory thresholds for liver injury, exclusion criteria, and approaches to validating phenotypes. We reached consensus on a DILI phenotyping algorithm and implemented it at three institutions. The algorithm was adapted locally to account for differences in populations and data access. Implementations collectively yielded 117 algorithm-selected cases and 23 confirmed true positive cases. Discussion Phenotyping for rare conditions benefits significantly from pooling data across institutions. Despite the heterogeneity of EHRs and varied algorithm implementations, we demonstrated the portability of this algorithm across three institutions. The performance of this algorithm for identifying DILI was comparable with other computerized approaches to identify adverse drug events. Conclusions Phenotyping algorithms developed for rare and complex conditions are likely to require adaptive implementation at multiple institutions. Better approaches are also needed to share algorithms. Early agreement on goals, data sources, and validation methods may improve the portability of the algorithms.

Original languageEnglish (US)
JournalJournal of the American Medical Informatics Association
Volume20
Issue numberE2
DOIs
StatePublished - 2013

Fingerprint

Chemical and Drug Induced Liver Injury
Electronic Health Records
Information Storage and Retrieval
Liver
Wounds and Injuries
Drug-Related Side Effects and Adverse Reactions
Meta-Analysis

ASJC Scopus subject areas

  • Health Informatics

Cite this

A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury. / Overby, Casey Lynnette; Pathak, Jyotishman; Gottesman, Omri; Haerian, Krystl; Perotte, Adler; Murphy, Sean; Bruce, Kevin; Johnson, Stephanie; Talwalkar, Jayant; Shen, Yufeng; Ellis, Steve; Kullo, Iftikhar Jan; Chute, Christopher; Friedman, Carol; Bottinger, Erwin; Hripcsak, George; Weng, Chunhua.

In: Journal of the American Medical Informatics Association, Vol. 20, No. E2, 2013.

Research output: Contribution to journalArticle

Overby, CL, Pathak, J, Gottesman, O, Haerian, K, Perotte, A, Murphy, S, Bruce, K, Johnson, S, Talwalkar, J, Shen, Y, Ellis, S, Kullo, IJ, Chute, C, Friedman, C, Bottinger, E, Hripcsak, G & Weng, C 2013, 'A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury', Journal of the American Medical Informatics Association, vol. 20, no. E2. https://doi.org/10.1136/amiajnl-2013-001930
Overby, Casey Lynnette ; Pathak, Jyotishman ; Gottesman, Omri ; Haerian, Krystl ; Perotte, Adler ; Murphy, Sean ; Bruce, Kevin ; Johnson, Stephanie ; Talwalkar, Jayant ; Shen, Yufeng ; Ellis, Steve ; Kullo, Iftikhar Jan ; Chute, Christopher ; Friedman, Carol ; Bottinger, Erwin ; Hripcsak, George ; Weng, Chunhua. / A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury. In: Journal of the American Medical Informatics Association. 2013 ; Vol. 20, No. E2.
@article{71ea4dbfe11f425b86b861eb5684daa9,
title = "A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury",
abstract = "Objective To describe a collaborative approach for developing an electronic health record (EHR) phenotyping algorithm for drug-induced liver injury (DILI). Methods We analyzed types and causes of differences in DILI case definitions provided by two institutions- Columbia University and Mayo Clinic; harmonized two EHR phenotyping algorithms; and assessed the performance, measured by sensitivity, specificity, positive predictive value, and negative predictive value, of the resulting algorithm at three institutions except that sensitivity was measured only at Columbia University. Results Although these sites had the same case definition, their phenotyping methods differed by selection of liver injury diagnoses, inclusion of drugs cited in DILI cases, laboratory tests assessed, laboratory thresholds for liver injury, exclusion criteria, and approaches to validating phenotypes. We reached consensus on a DILI phenotyping algorithm and implemented it at three institutions. The algorithm was adapted locally to account for differences in populations and data access. Implementations collectively yielded 117 algorithm-selected cases and 23 confirmed true positive cases. Discussion Phenotyping for rare conditions benefits significantly from pooling data across institutions. Despite the heterogeneity of EHRs and varied algorithm implementations, we demonstrated the portability of this algorithm across three institutions. The performance of this algorithm for identifying DILI was comparable with other computerized approaches to identify adverse drug events. Conclusions Phenotyping algorithms developed for rare and complex conditions are likely to require adaptive implementation at multiple institutions. Better approaches are also needed to share algorithms. Early agreement on goals, data sources, and validation methods may improve the portability of the algorithms.",
author = "Overby, {Casey Lynnette} and Jyotishman Pathak and Omri Gottesman and Krystl Haerian and Adler Perotte and Sean Murphy and Kevin Bruce and Stephanie Johnson and Jayant Talwalkar and Yufeng Shen and Steve Ellis and Kullo, {Iftikhar Jan} and Christopher Chute and Carol Friedman and Erwin Bottinger and George Hripcsak and Chunhua Weng",
year = "2013",
doi = "10.1136/amiajnl-2013-001930",
language = "English (US)",
volume = "20",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "E2",

}

TY - JOUR

T1 - A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury

AU - Overby, Casey Lynnette

AU - Pathak, Jyotishman

AU - Gottesman, Omri

AU - Haerian, Krystl

AU - Perotte, Adler

AU - Murphy, Sean

AU - Bruce, Kevin

AU - Johnson, Stephanie

AU - Talwalkar, Jayant

AU - Shen, Yufeng

AU - Ellis, Steve

AU - Kullo, Iftikhar Jan

AU - Chute, Christopher

AU - Friedman, Carol

AU - Bottinger, Erwin

AU - Hripcsak, George

AU - Weng, Chunhua

PY - 2013

Y1 - 2013

N2 - Objective To describe a collaborative approach for developing an electronic health record (EHR) phenotyping algorithm for drug-induced liver injury (DILI). Methods We analyzed types and causes of differences in DILI case definitions provided by two institutions- Columbia University and Mayo Clinic; harmonized two EHR phenotyping algorithms; and assessed the performance, measured by sensitivity, specificity, positive predictive value, and negative predictive value, of the resulting algorithm at three institutions except that sensitivity was measured only at Columbia University. Results Although these sites had the same case definition, their phenotyping methods differed by selection of liver injury diagnoses, inclusion of drugs cited in DILI cases, laboratory tests assessed, laboratory thresholds for liver injury, exclusion criteria, and approaches to validating phenotypes. We reached consensus on a DILI phenotyping algorithm and implemented it at three institutions. The algorithm was adapted locally to account for differences in populations and data access. Implementations collectively yielded 117 algorithm-selected cases and 23 confirmed true positive cases. Discussion Phenotyping for rare conditions benefits significantly from pooling data across institutions. Despite the heterogeneity of EHRs and varied algorithm implementations, we demonstrated the portability of this algorithm across three institutions. The performance of this algorithm for identifying DILI was comparable with other computerized approaches to identify adverse drug events. Conclusions Phenotyping algorithms developed for rare and complex conditions are likely to require adaptive implementation at multiple institutions. Better approaches are also needed to share algorithms. Early agreement on goals, data sources, and validation methods may improve the portability of the algorithms.

AB - Objective To describe a collaborative approach for developing an electronic health record (EHR) phenotyping algorithm for drug-induced liver injury (DILI). Methods We analyzed types and causes of differences in DILI case definitions provided by two institutions- Columbia University and Mayo Clinic; harmonized two EHR phenotyping algorithms; and assessed the performance, measured by sensitivity, specificity, positive predictive value, and negative predictive value, of the resulting algorithm at three institutions except that sensitivity was measured only at Columbia University. Results Although these sites had the same case definition, their phenotyping methods differed by selection of liver injury diagnoses, inclusion of drugs cited in DILI cases, laboratory tests assessed, laboratory thresholds for liver injury, exclusion criteria, and approaches to validating phenotypes. We reached consensus on a DILI phenotyping algorithm and implemented it at three institutions. The algorithm was adapted locally to account for differences in populations and data access. Implementations collectively yielded 117 algorithm-selected cases and 23 confirmed true positive cases. Discussion Phenotyping for rare conditions benefits significantly from pooling data across institutions. Despite the heterogeneity of EHRs and varied algorithm implementations, we demonstrated the portability of this algorithm across three institutions. The performance of this algorithm for identifying DILI was comparable with other computerized approaches to identify adverse drug events. Conclusions Phenotyping algorithms developed for rare and complex conditions are likely to require adaptive implementation at multiple institutions. Better approaches are also needed to share algorithms. Early agreement on goals, data sources, and validation methods may improve the portability of the algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84890538875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890538875&partnerID=8YFLogxK

U2 - 10.1136/amiajnl-2013-001930

DO - 10.1136/amiajnl-2013-001930

M3 - Article

C2 - 23837993

AN - SCOPUS:84890538875

VL - 20

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - E2

ER -