1932
0

Annual Review of Public Health

Volume 46, 2025

Racial Bias in Clinical and Population Health Algorithms: A Critical Review of Current Debates

  • Madison Coots1, Kristin A. Linn2, Sharad Goel1, Amol S. Navathe2 and Ravi B. Parikh3
  • 1Harvard Kennedy School, Harvard University, Cambridge, Massachusetts, USA 2The Parity Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA 3School of Medicine, Emory University, Atlanta, Georgia, USA; email: [email protected]
  • Vol. 46:507-523 (Volume publication date April 2025)
  • First published as a Review in Advance on December 03, 2024
  • Copyright © 2025 by the author(s).
    This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See credit lines of images or other third-party material in this article for license information.

Abstract

Among health care researchers, there is increasing debate over how best to assess and ensure the fairness of algorithms used for clinical decision support and population health, particularly concerning potential racial bias. Here we first distill concerns over the fairness of health care algorithms into four broad categories: () the explicit inclusion (or, conversely, the exclusion) of race and ethnicity in algorithms, () unequal algorithm decision rates across groups, () unequal error rates across groups, and () potential bias in the target variable used in prediction. With this taxonomy, we critically examine seven prominent and controversial health care algorithms. We show that popular approaches that aim to improve the fairness of health care algorithms can in fact worsen outcomes for individuals across all racial and ethnic groups. We conclude by offering an alternative, consequentialist framework for algorithm design that mitigates these harms by instead foregrounding outcomes and clarifying trade-offs in the pursuit of equitable decision-making.

Keyword(s): algorithms, bias, equity, fairness, health care, race
Loading

Article metrics loading...

/content/journals/10.1146/annurev-publhealth-071823-112058
2025-04-04
2025-06-13
Loading full text...

Full text loading...

/deliver/fulltext/publhealth/46/1/annurev-publhealth-071823-112058.html?itemId=/content/journals/10.1146/annurev-publhealth-071823-112058&mimeType=html&fmt=ahah

Literature Cited

  1. 1.
    Aggarwal R, Bibbins-Domingo K, Yeh RW, Song Y, Chiu N, et al. 2022.. Diabetes screening by race and ethnicity in the United States: equivalent body mass index and age thresholds. . Ann. Intern. Med. 175:(6):765–73
     [Crossref] [Google Scholar]
  2. 2.
    Aldrich MC, Mercaldo SF, Sandler KL, Blot WJ, Grogan EL, Blume JD. 2019.. Evaluation of USPSTF lung cancer screening guidelines among African American adult smokers. . JAMA Oncol. 5:(9):1318–24
     [Crossref] [Google Scholar]
  3. 3.
    Bahrami H, Kronmal R, Bluemke DA, Olson J, Shea S, et al. 2008.. Differences in the incidence of congestive heart failure by ethnicity: the Multi-Ethnic Study of Atherosclerosis. . Arch. Intern. Med. 168:(19):2138–45
     [Crossref] [Google Scholar]
  4. 4.
    Bates DW, Saria S, Ohno-Machado L, Shah A, Escobar G. 2014.. Big data in health care: using analytics to identify and manage high-risk and high-cost patients. . Health Aff. 33:(7):1123–31
     [Crossref] [Google Scholar]
  5. 5.
    Bibbins-Domingo K, Pletcher MJ, Lin F, Vittinghoff E, Gardin JM, et al. 2009.. Racial differences in incident heart failure among young adults. . N. Engl. J. Med. 360:(12):1179–90
     [Crossref] [Google Scholar]
  6. 6.
    Buckley A, Sestito S, Ogundipe T, Roig J, Rosenberg HM, et al. 2022.. Racial and ethnic disparities among women undergoing a trial of labor after cesarean delivery: performance of the VBAC calculator with and without patients’ race/ethnicity. . Reprod. Sci. 29:(7):2030–38
     [Crossref] [Google Scholar]
  7. 7.
    Carnethon MR, Pu J, Howard G, Albert MA, Anderson CAM, et al. 2017.. Cardiovascular health in African Americans: a scientific statement from the American Heart Association. . Circulation 136:(21):e393–423
     [Crossref] [Google Scholar]
  8. 8.
    CDC (Cent. Dis. Control Prev.). 2024.. Lung cancer statistics. . CDC Lung Cancer. https://www.cdc.gov/lung-cancer/statistics/
    [Google Scholar]
  9. 9.
    CDC (Cent. Dis. Control Prev.), NCHS (Natl. Cent. Health Stat.). 2024.. National Health and Nutrition Examination Survey Data. . National Center for Health Statistics. https://wwwn.cdc.gov/nchs/nhanes/
    [Google Scholar]
  10. 10.
    Cheung LC, Berg CD, Castle PE, Katki HA, Chaturvedi AK. 2019.. Life-gained-based versus risk-based selection of smokers for lung cancer screening. . Ann. Intern. Med. 171:(9):623–32
     [Crossref] [Google Scholar]
  11. 11.
    Chohlas-Wood A, Coots M, Goel S, Nyarko J. 2023.. Designing equitable algorithms. . Nat. Comput. Sci. 3::601–10
     [Crossref] [Google Scholar]
  12. 12.
    Chohlas-Wood A, Coots M, Zhu H, Brunskill E, Goel S. 2024.. Learning to be fair: a consequentialist approach to equitable decision-making. . arXiv:2109.08792v4 [cs.LG]
  13. 13.
    Cockcroft DW, Gault H. 1976.. Prediction of creatinine clearance from serum creatinine. . Nephron 16:(1):31–41
     [Crossref] [Google Scholar]
  14. 14.
    Coots M, Saghafian S, Kent D, Goel S. 2024.. A framework for considering the role of race and ethnicity in estimating disease risk. . Ann. Intern. Med. In press
    [Google Scholar]
  15. 15.
    Curtin SC, Gregory KD, Korst LM, Uddin SF. 2015.. Maternal morbidity for vaginal and cesarean deliveries, according to previous cesarean history: new data from the birth certificate, 2013. . Natl. Vital. Stat. Rep. 64:(4):1–13
     [Google Scholar]
  16. 16.
    D'Agostino RB, Grundy S, Sullivan LM, Wilson P. 2001.. Validation of the Framingham coronary heart disease prediction scores: results of a multiple ethnic groups investigation. . JAMA 286:(2):180–87
     [Crossref] [Google Scholar]
  17. 17.
    D'Agostino RB, Vasan RS, Pencina MJ, Wolf PA, Cobain M, et al. 2008.. General cardiovascular risk profile for use in primary care: the Framingham Heart Study. . Circulation 117:(6):743–53
     [Crossref] [Google Scholar]
  18. 18.
    Diao JA, He Y, Khazanchi R, Nguemeni Tiako MJ, Witonsky JI, et al. 2024.. Implications of race adjustment in lung-function equations. . N. Engl. J. Med. 390:(22):2083–97
     [Crossref] [Google Scholar]
  19. 19.
    Diao JA, Shi I, Murthy VL, Buckley TA, Patel CJ, et al. 2024.. Projected changes in statin and antihypertensive therapy eligibility with the AHA PREVENT cardiovascular risk equations. . JAMA 332::989–1000
     [Crossref] [Google Scholar]
  20. 20.
    Diao JA, Wu GJ, Taylor HA, Tucker JK, Powe NR, et al. 2021.. Clinical implications of removing race from estimates of kidney function. . JAMA 325:(2):184–86
     [Google Scholar]
  21. 21.
    Eberly LA, Richterman A, Beckett AG, Wispelwey B, Marsh RH, et al. 2019.. Identification of racial inequities in access to specialized inpatient heart failure care at an academic medical center. . Circ. Heart Fail. 12:(11):e006214
     [Crossref] [Google Scholar]
  22. 22.
    Eberly LA, Wispelwey B, Richterman A, Beckett AG, Manchanda ECC, et al. 2020.. Response by Eberly et al to letter regarding article, “Identification of Racial Inequities in Access to Specialized Inpatient Heart Failure Care at an Academic Medical Center. .” Circ. Heart Fail. 13:(6):e007193
     [Crossref] [Google Scholar]
  23. 23.
    Eneanya ND, Yang W, Reese PP. 2019.. Reconsidering the consequences of using race to estimate kidney function. . JAMA 322:(2):113–14
     [Crossref] [Google Scholar]
  24. 24.
    Goff DC Jr., Lloyd-Jones DM. 2016.. The pooled cohort risk equations—Black risk matters. . JAMA Cardiol. 1:(1):12–14
     [Crossref] [Google Scholar]
  25. 25.
    Goff DC Jr., Lloyd-Jones DM, Bennett G, Coady S, D'Agostino RB, et al. 2014.. 2013 ACC/AHA guideline on the assessment of cardiovascular risk: a report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines. . J. Am. Coll. Cardiol. 63:(25 Pt. B):2935–59
     [Crossref] [Google Scholar]
  26. 26.
    Grobman WA, Lai Y, Landon MB, Spong CY, Leveno KJ, et al. 2007.. Development of a nomogram for prediction of vaginal birth after cesarean delivery. . Obstet. Gynecol. 109:(4):806–12
     [Crossref] [Google Scholar]
  27. 27.
    Grobman WA, Lai Y, Landon MB, Spong CY, Leveno KJ, et al. 2009.. Does information available at admission for delivery improve prediction of vaginal birth after cesarean?. Am. J. Perinatol. 26::693–701
     [Crossref] [Google Scholar]
  28. 28.
    Grobman WA, Sandoval G, Rice MM, Bailit JL, Chauhan SP, et al. 2021.. Prediction of vaginal birth after cesarean delivery in term gestations: a calculator without race and ethnicity. . Am. J. Obstet. Gynecol. 225:(6):664.e1–7
     [Crossref] [Google Scholar]
  29. 29.
    Grobman WA, Sandoval GJ, Rice MM, Chauhan SP, Clifton RG, et al. 2024.. Prediction of vaginal birth after cesarean using information at admission for delivery: a calculator without race or ethnicity. . Am. J. Obstet. Gynecol. 230:(3):S804–6
     [Crossref] [Google Scholar]
  30. 30.
    Inker LA, Eneanya ND, Coresh J, Tighiouart H, Wang D, et al. 2021.. New creatinine- and cystatin C–based equations to estimate GFR without race. . N. Engl. J. Med. 385:(19):1737–49
     [Crossref] [Google Scholar]
  31. 31.
    Katki HA, Kovalchik SA, Berg CD, Cheung LC, Chaturvedi AK. 2016.. Development and validation of risk models to select ever-smokers for CT lung cancer screening. . JAMA 315:(21):2300–11
     [Crossref] [Google Scholar]
  32. 32.
    Katki HA, Kovalchik SA, Petito LC, Cheung LC, Jacobs E, et al. 2018.. Implications of nine risk prediction models for selecting ever-smokers for computed tomography lung cancer screening. . Ann. Intern. Med. 169:(1):10–19
     [Crossref] [Google Scholar]
  33. 33.
    Khan SS, Coresh J, Pencina MJ, Ndumele CE, Rangaswami J, et al. 2023.. Novel prediction equations for absolute risk assessment of total cardiovascular disease incorporating cardiovascular-kidney-metabolic health: a scientific statement from the American Heart Association. . Circulation 148:(24):1982–2004
     [Crossref] [Google Scholar]
  34. 34.
    Khan SS, Matsushita K, Sang Y, Ballew SH, Grams ME, et al. 2024.. Development and validation of the American Heart Association's PREVENT equations. . Circulation 149:(6):430–49
     [Crossref] [Google Scholar]
  35. 35.
    Krist AH, Davidson KW, Mangione CM, Barry JM, Cabana M, et al.; US Prev. Serv. Task Force. 2021.. Screening for lung cancer: US Preventive Services Task Force recommendation statement. . JAMA 325:(10):962–70
     [Crossref] [Google Scholar]
  36. 36.
    Landon MB, Leindecker S, Spong CY, Hauth JC, Bloom S, et al. 2005.. The MFMU cesarean registry: factors affecting the success of trial of labor after previous cesarean delivery. . Am. J. Obstet. Gynecol. 193:(3):1016–23
     [Crossref] [Google Scholar]
  37. 37.
    Landy R, Gomez I, Caverly TJ, Kawamoto K, Rivera MP, et al. 2023.. Methods for using race and ethnicity in prediction models for lung cancer screening eligibility. . JAMA Netw. Open. 6:(9):e2331155
     [Crossref] [Google Scholar]
  38. 38.
    Lett E, Asabor E, Beltrán S, Cannon AM, Arah OA. 2022.. Conceptualizing, contextualizing, and operationalizing race in quantitative health sciences research. . Ann. Fam. Med. 20:(2):157–63
     [Crossref] [Google Scholar]
  39. 39.
    Levey AS, Bosch JP, Lewis JB, Greene T, Rogers N, Roth D. 1999.. A more accurate method to estimate glomerular filtration rate from serum creatinine: a new prediction equation. . Ann. Intern. Med. 130:(6):461–70
     [Crossref] [Google Scholar]
  40. 40.
    Levey AS, Coresh J, Greene T, Stevens LA, Zhang Y, et al. 2006.. Using standardized serum creatinine values in the modification of diet in renal disease study equation for estimating glomerular filtration rate. . Ann. Intern. Med. 145:(4):247–54
     [Crossref] [Google Scholar]
  41. 41.
    Levey AS, Stevens LA, Schmid CH, Zhang Y, Castro AF III, et al. 2009.. A new equation to estimate glomerular filtration rate. . Ann. Intern. Med. 150:(9):604–12
     [Crossref] [Google Scholar]
  42. 42.
    Manski CF, Mullahy J, Venkataramani AS. 2023.. Using measures of race to make clinical predictions: decision making, patient health, and fairness. . PNAS 120:(35):e2303370120
     [Crossref] [Google Scholar]
  43. 43.
    Martin JA, Hamilton BE, Osterman MJK, Driscoll AK, Drake P. 2018.. Births: final data for 2017. . Natl. Vital Stat. Rep. 67:(8):34
     [Google Scholar]
  44. 44.
    Muntner P, Colantonio LD, Cushman M, Goff DC Jr., Howard G, et al. 2014.. Validation of the atherosclerotic cardiovascular disease pooled cohort risk equations. . JAMA 311:(14):1406–15
     [Crossref] [Google Scholar]
  45. 45.
    Natl. Cancer Inst. 2024.. SEER incidence data, November 2023 submission (1975–2021), SEER 22 registries. SEER*Explorer , Surveill. Res. Prog., Bethesda, MD:, retrieved May 8. https://seer.cancer.gov/statistics-network/explorer/
    [Google Scholar]
  46. 46.
    Natl. Cancer Inst. 2024.. U.S. mortality data (1969–2022). SEER*Explorer, Surveill. Res. Prog., Bethesda, MD:, retrieved May 8. https://seer.cancer.gov/statistics-network/explorer/
    [Google Scholar]
  47. 47.
    Natl. Lung Screen. Trial Res. Team , Aberle DR, Berg CD, Black WC, Church TR, et al. 2011.. The National Lung Screening Trial: overview and study design. . Radiology 258:(1):243–53
     [Crossref] [Google Scholar]
  48. 48.
    Natl. Res. Counc. (US) Comm. Popul. 1997.. Racial and Ethnic Differences in the Health of Older Americans, ed. LG Martin, BJ Soldo . Washington, DC:: Natl. Acad. Press
     [Google Scholar]
  49. 49.
    Obermeyer Z, Powers B, Vogeli C, Mullainathan S. 2019.. Dissecting racial bias in an algorithm used to manage the health of populations. . Science 366::447–53
     [Crossref] [Google Scholar]
  50. 50.
    Pasquinelli MM, Tammemägi MC, Kovitz KL, Durham ML, Deliu Z, et al. 2021.. Brief report: risk prediction model versus United States Preventive Services Task Force 2020 draft lung cancer screening eligibility criteria—reducing race disparities. . JTO Clin. Res. Rep. 2:(3):100137
     [Google Scholar]
  51. 51.
    Pauker SG, Kassirer JP. 1980.. The threshold approach to clinical decision making. . N. Engl. J. Med. 302:(20):1109–17
     [Crossref] [Google Scholar]
  52. 52.
    Peterson PN, Rumsfeld JS, Liang L, Albert NM, Hernandez AF, et al. 2010.. A validated risk score for in-hospital mortality in patients with heart failure from the American Heart Association Get with the Guidelines program. . Circ. Cardiovasc. Qual. Outcomes 3::25–32
     [Crossref] [Google Scholar]
  53. 53.
    Rivera MP, Katki HA, Tanner NT, Triplette M, Sakoda LC, et al. 2020.. Addressing disparities in lung cancer screening eligibility and healthcare access. An official American Thoracic Society statement. . Am. J. Respir. Crit. Care Med. 202:(7):e95–112
     [Crossref] [Google Scholar]
  54. 54.
    Sandel MJ. 2009.. Justice: What's the Right Thing to Do? New York:: Farrar, Straus and Giroux
     [Google Scholar]
  55. 55.
    Schwandt H, Currie J, Bär M, Banks J, Bertoli P, et al. 2021.. Inequality in mortality between Black and White Americans by age, place, and cause and in comparison to Europe, 1990 to 2018. . PNAS 118:(40):2104684118
     [Crossref] [Google Scholar]
  56. 56.
    Shaikh N, Lee MC, Stokes LR, Miller E, Kurs-Lasky M, et al. 2022.. Reassessment of the role of race in calculating the risk for urinary tract infection: a systematic review and meta-analysis. . JAMA Pediatr. 176:(6):569–75
     [Crossref] [Google Scholar]
  57. 57.
    Smith WR, Poses RM, McClish DK, Huber EC, Clemo FLW, et al. 2002.. Prognostic judgments and triage decisions for patients with acute congestive heart failure. . Chest 121:(5):1610–17
     [Crossref] [Google Scholar]
  58. 58.
    Stevens ER, Caverly T, Butler JM, Kukhareva P, Richardson S, et al. 2023.. Considerations for using predictive models that include race as an input variable: the case study of lung cancer screening. . J. Biomed. Inform. 147::104525
     [Crossref] [Google Scholar]
  59. 59.
    Stevens LA, Coresh J, Greene T, Levey AS. 2006.. Assessing kidney function—measured and estimated glomerular filtration rate. . N. Engl. J. Med. 354:(23):2473–83
     [Crossref] [Google Scholar]
  60. 60.
    Tammemägi MC, Katki HA, Hocking WG, Church TR, Caporaso N, et al. 2013.. Selection criteria for lung-cancer screening. . N. Engl. J. Med. 368:(8):728–36. Erratum . 2013.. N. Engl. J. Med. 369:(4):394
     [Google Scholar]
  61. 61.
    Vyas DA, Eisenstein LG, Jones DS. 2020.. Hidden in plain sight—reconsidering the use of race correction in clinical algorithms. . N. Engl. J. Med. 383:(9):874–82
     [Crossref] [Google Scholar]
  62. 62.
    Vyas DA, James A, Kormos W, Essien UR. 2022.. Revising the atherosclerotic cardiovascular disease calculator without race. . Lancet Digit. Health 4:(1):e4–5
     [Crossref] [Google Scholar]
  63. 63.
    Vyas DA, Jones DS, Meadows AR, Diouf K, Nour NM, Schantz-Dunn J. 2019.. Challenging the use of race in the vaginal birth after cesarean section calculator. . Women's Health Issues 29:(3):201–4
     [Crossref] [Google Scholar]
  64. 64.
    Wang JH, Hart A. 2021.. Global perspective on kidney transplantation: United States. . Kidney360 2:(11):1836–39
     [Crossref] [Google Scholar]
  65. 65.
    Wilson PWF, D'Agostino RB, Levy D, Belanger AM, Silbershatz H, Kannel WB. 1998.. Prediction of coronary heart disease using risk factor categories. . Circulation 97:(18):1837–47
     [Crossref] [Google Scholar]
  66. 66.
    Zanger-Tishler, Nyarko J, Goal S. 2024.. Risk scores, label bias, and everything but the kitchen sink. . Sci. Adv. 10::eadi8411
     [Crossref] [Google Scholar]
  67. 67.
    Zink A, Obermeyer Z, Pierson E. 2024.. Race adjustments in clinical algorithms can help correct for racial disparities in data quality. . PNAS 121:(34):e2402267121
     [Crossref] [Google Scholar]
/content/journals/10.1146/annurev-publhealth-071823-112058
Loading
Racial Bias in Clinical and Population Health Algorithms: A Critical Review of Current Debates
Annual Review of Public Health 46, 507 (2025); https://doi.org/10.1146/annurev-publhealth-071823-112058
/content/journals/10.1146/annurev-publhealth-071823-112058
/content/journals/10.1146/annurev-publhealth-071823-112058
Loading

Data & Media loading...

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error