Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration

Justin M. List; Paul Palevsky; Suzanne Tamang; Susan Crowley; David Au; William C. Yarbrough; Amol S. Navathe; Craig Kreisler; Ravi B. Parikh; Jessica Wang-Rodriguez; J. Stacey Klutts; Paul Conlin; Leonard Pogach; Esther Meerwijk; Ernest Moy

doi:10.1089/heq.2023.0037

Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration

Justin M. List, Paul Palevsky, Suzanne Tamang, Susan Crowley, David Au, William C. Yarbrough, Amol S. Navathe, Craig Kreisler, Ravi B. Parikh, Jessica Wang-Rodriguez, J. Stacey Klutts, Paul Conlin, Leonard Pogach, Esther Meerwijk, Ernest Moy

Research output: Contribution to journal › Article › peer-review

Abstract

The Veterans Health Administration uses equity- and evidence-based principles to examine, correct, and eliminate use of potentially biased clinical equations and predictive models. We discuss the processes, successes, challenges, and next steps in four examples. We detail elimination of the race modifier for estimated kidney function and discuss steps to achieve more equitable pulmonary function testing measurement. We detail the use of equity lenses in two predictive clinical modeling tools: Stratification Tool for Opioid Risk Mitigation (STORM) and Care Assessment Need (CAN) predictive models. We conclude with consideration of ways to advance racial health equity in clinical decision support algorithms.

Original language	English (US)
Pages (from-to)	809-816
Number of pages	8
Journal	Health Equity
Volume	7
Issue number	1
DOIs	https://doi.org/10.1089/heq.2023.0037
State	Published - Nov 1 2023

Keywords

Veterans Health Administration
clinical equations
health equity
predictive models
racial bias

ASJC Scopus subject areas

Health(social science)
Health Policy
Public Health, Environmental and Occupational Health
Health Information Management

Access to Document

10.1089/heq.2023.0037

Cite this

List, J. M., Palevsky, P., Tamang, S., Crowley, S., Au, D., Yarbrough, W. C., Navathe, A. S., Kreisler, C., Parikh, R. B., Wang-Rodriguez, J., Klutts, J. S., Conlin, P., Pogach, L., Meerwijk, E., & Moy, E. (2023). Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration. Health Equity, 7(1), 809-816. https://doi.org/10.1089/heq.2023.0037

List, JM, Palevsky, P, Tamang, S, Crowley, S, Au, D, Yarbrough, WC, Navathe, AS, Kreisler, C, Parikh, RB, Wang-Rodriguez, J, Klutts, JS, Conlin, P, Pogach, L, Meerwijk, E & Moy, E 2023, 'Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration', Health Equity, vol. 7, no. 1, pp. 809-816. https://doi.org/10.1089/heq.2023.0037

@article{84df272fd87143cd879b94b8a081e05f,

title = "Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration",

abstract = "The Veterans Health Administration uses equity- and evidence-based principles to examine, correct, and eliminate use of potentially biased clinical equations and predictive models. We discuss the processes, successes, challenges, and next steps in four examples. We detail elimination of the race modifier for estimated kidney function and discuss steps to achieve more equitable pulmonary function testing measurement. We detail the use of equity lenses in two predictive clinical modeling tools: Stratification Tool for Opioid Risk Mitigation (STORM) and Care Assessment Need (CAN) predictive models. We conclude with consideration of ways to advance racial health equity in clinical decision support algorithms.",

keywords = "Veterans Health Administration, clinical equations, health equity, predictive models, racial bias",

author = "List, {Justin M.} and Paul Palevsky and Suzanne Tamang and Susan Crowley and David Au and Yarbrough, {William C.} and Navathe, {Amol S.} and Craig Kreisler and Parikh, {Ravi B.} and Jessica Wang-Rodriguez and Klutts, {J. Stacey} and Paul Conlin and Leonard Pogach and Esther Meerwijk and Ernest Moy",

note = "Publisher Copyright: {\textcopyright} Justin M. List et al., 2023.",

year = "2023",

month = nov,

day = "1",

doi = "10.1089/heq.2023.0037",

language = "English (US)",

volume = "7",

pages = "809--816",

journal = "Health Equity",

issn = "2473-1242",

publisher = "Mary Ann Liebert Inc.",

number = "1",

}

TY - JOUR

T1 - Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms

T2 - Use Cases from the Veterans Health Administration

AU - List, Justin M.

AU - Palevsky, Paul

AU - Tamang, Suzanne

AU - Crowley, Susan

AU - Au, David

AU - Yarbrough, William C.

AU - Navathe, Amol S.

AU - Kreisler, Craig

AU - Parikh, Ravi B.

AU - Wang-Rodriguez, Jessica

AU - Klutts, J. Stacey

AU - Conlin, Paul

AU - Pogach, Leonard

AU - Meerwijk, Esther

AU - Moy, Ernest

PY - 2023/11/1

Y1 - 2023/11/1

N2 - The Veterans Health Administration uses equity- and evidence-based principles to examine, correct, and eliminate use of potentially biased clinical equations and predictive models. We discuss the processes, successes, challenges, and next steps in four examples. We detail elimination of the race modifier for estimated kidney function and discuss steps to achieve more equitable pulmonary function testing measurement. We detail the use of equity lenses in two predictive clinical modeling tools: Stratification Tool for Opioid Risk Mitigation (STORM) and Care Assessment Need (CAN) predictive models. We conclude with consideration of ways to advance racial health equity in clinical decision support algorithms.

AB - The Veterans Health Administration uses equity- and evidence-based principles to examine, correct, and eliminate use of potentially biased clinical equations and predictive models. We discuss the processes, successes, challenges, and next steps in four examples. We detail elimination of the race modifier for estimated kidney function and discuss steps to achieve more equitable pulmonary function testing measurement. We detail the use of equity lenses in two predictive clinical modeling tools: Stratification Tool for Opioid Risk Mitigation (STORM) and Care Assessment Need (CAN) predictive models. We conclude with consideration of ways to advance racial health equity in clinical decision support algorithms.

KW - Veterans Health Administration

KW - clinical equations

KW - health equity

KW - predictive models

KW - racial bias

UR - http://www.scopus.com/inward/record.url?scp=85180356620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85180356620&partnerID=8YFLogxK

U2 - 10.1089/heq.2023.0037

DO - 10.1089/heq.2023.0037

M3 - Article

C2 - 38076213

AN - SCOPUS:85180356620

SN - 2473-1242

VL - 7

SP - 809

EP - 816

JO - Health Equity

JF - Health Equity

IS - 1

ER -

Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this