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

Health Equity. 2023 Nov 30;7(1):809-816. doi: 10.1089/heq.2023.0037. eCollection 2023.

Authors

Justin M List^{1

2}, Paul Palevsky^{3

4}, Suzanne Tamang^{5

6}, Susan Crowley^{7

8}, David Au⁹, William C Yarbrough^{10

11}, Amol S Navathe^{12

13}, Craig Kreisler¹⁴, Ravi B Parikh^{12

15}, Jessica Wang-Rodriguez^{16

17}, J Stacey Klutts^{18

19

20}, Paul Conlin^{21

22}, Leonard Pogach²³, Esther Meerwijk⁵, Ernest Moy¹

Affiliations

¹ VA Office of Health Equity, Washington, District of Columbia, USA.
² Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA.
³ Kidney Medicine Section, Medical Service, VA Pittsburgh Healthcare System, Pittsburgh, Pennsylvania, USA.
⁴ Renal-Electrolyte Division, Department of Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.
⁵ Department of Veterans Affairs, Palo Alto, California, USA.
⁶ Department of Medicine, Stanford University School of Medicine, Stanford, California, USA.
⁷ Nephrology Section, Department of Medicine, Yale School of Medicine, New Haven, Connecticut, USA.
⁸ VA Connecticut Healthcare System, West Haven, Connecticut, USA.
⁹ Health Services Research and Development, VA Puget Sound Health Care System, Seattle, Washington, USA.
¹⁰ Department of Internal Medicine, The University of Texas Southwestern Medical Center, Dallas, Texas, USA.
¹¹ VA North Texas Health Care System, Dallas, Texas, USA.
¹² Corporal Michael J. Crescenz VA Medical Center, Philadelphia, Pennsylvania, USA.
¹³ Department of Medical Ethics and Health Policy, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
¹⁴ Analytics and Performance Integration (API), Office of Quality and Patient Safety, Veterans Health Administration, Washington, District of Columbia, USA.
¹⁵ Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
¹⁶ VA National Pathology and Laboratory Medicine Service, Washington, District of Columbia, USA.
¹⁷ Department of Pathology, University of California San Diego School of Medicine, La Jolla, California, USA.
¹⁸ National VHA Diagnostics Office, Washington, District of Columbia, USA.
¹⁹ Iowa City VA Healthcare System, Iowa City, Iowa, USA.
²⁰ Department of Pathology, University of Iowa Carver College of Medicine, Iowa City, Iowa, USA.
²¹ VA Boston Healthcare System, Boston, Massachusetts, USA.
²² Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA.
²³ Department of Veterans Affairs, New Jersey Health Care System, East Orange, New Jersey, USA.

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.