{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T22:46:11Z","timestamp":1776379571629,"version":"3.51.2"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"CIFAR AI Chair"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To explore the complexities of eliminating race correction in clinical artificial intelligence (AI), the pitfalls of naive solutions, and to propose systematic strategies for equitable model development.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Background and Significance<\/jats:title>\n                    <jats:p>Race correction in clinical AI, as in traditional medicine, introduces biases with potentially harmful consequences. Simple removal of race from models is insufficient due to the lasting influence of historically biased data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Approach<\/jats:title>\n                    <jats:p>We analyze 4 standardized scenarios to demonstrate how race correction manifests in clinical AI: use of race-corrected variables, explicit inclusion of race, inference via proxy variables, and use of race-specific models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For each scenario, the intuitive solution to removing race correction fails to eliminate bias, often due to legacy effects embedded in the data. More thoughtful approaches are required.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ending race correction in clinical AI requires deliberate, context-sensitive interventions, inclusion of diverse stakeholders, and strategies to make model reasoning more transparent and auditable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag012","type":"journal-article","created":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T12:32:40Z","timestamp":1768739560000},"page":"922-925","source":"Crossref","is-referenced-by-count":0,"title":["The subtleties of abolishing \u201crace correction\u201d in clinical artificial intelligence"],"prefix":"10.1093","volume":"33","author":[{"given":"Moustafa","family":"Abdalla","sequence":"first","affiliation":[{"name":"Department of Surgery, Massachusetts General Hospital, Harvard Medical School , Boston, MA, 02115,","place":["United States"]},{"name":"Department of Global Health and Social Medicine, Harvard Medical School , Boston, MA, 02115,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"LLana","family":"James","sequence":"additional","affiliation":[{"name":"Department of Biomedical & Molecular Sciences, Queen\u2019s University , Kingston, ON, K7L 2V7,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0039-7784","authenticated-orcid":false,"given":"David S","family":"Jones","sequence":"additional","affiliation":[{"name":"Department of Global Health and Social Medicine, Harvard Medical School , Boston, MA, 02115,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2776-6036","authenticated-orcid":false,"given":"Mohamed","family":"Abdalla","sequence":"additional","affiliation":[{"name":"Department of Medicine, University of Alberta , Edmonton, AB T6G 2G3,","place":["Canada"]},{"name":"Alberta Machine Intelligence Institute , Edmonton, AB, T5J 1S5,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"key":"2026041617412965800_ocag012-B1","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/S0140-6736(20)32716-1","article-title":"Abolish race correction","volume":"397","author":"Roberts","year":"2021","journal-title":"Lancet"},{"key":"2026041617412965800_ocag012-B2","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1056\/NEJMms2004740","article-title":"Hidden in plain sight\u2014reconsidering the use of race correction in clinical algorithms","volume":"383","author":"Vyas","year":"2020","journal-title":"N Engl J Med"},{"key":"2026041617412965800_ocag012-B3","author":"National Academies of Sciences Engineering, Medicine, and others","year":"2024"},{"key":"2026041617412965800_ocag012-B4","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"2026041617412965800_ocag012-B5","doi-asserted-by":"crossref","first-page":"3038","DOI":"10.1038\/s41591-024-03310-1","article-title":"An ethics assessment tool for artificial intelligence implementation in healthcare: CARE-AI","volume":"30","author":"Ning","year":"2024","journal-title":"Nat Med"},{"key":"2026041617412965800_ocag012-B6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.7326\/M23-2960","article-title":"The impact of health care algorithms on racial and ethnic disparities: a systematic review","volume":"177","author":"Siddique","year":"2024","journal-title":"Ann Intern Med"},{"key":"2026041617412965800_ocag012-B7","doi-asserted-by":"crossref","first-page":"e406","DOI":"10.1016\/S2589-7500(22)00063-2","article-title":"AI recognition of patient race in medical imaging: a modelling study","volume":"4","author":"Gichoya","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2026041617412965800_ocag012-B8","first-page":"539","article-title":"Race influences warfarin dose changes associated with genetic factors","volume":"126","author":"Limdi","year":"2015","journal-title":"Blood J Am Soc Hematol"},{"key":"2026041617412965800_ocag012-B9","doi-asserted-by":"crossref","first-page":"e213909","DOI":"10.1001\/jamanetworkopen.2021.3909","article-title":"Comparison of methods to reduce bias from clinical prediction models of postpartum depression","volume":"4","author":"Park","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2026041617412965800_ocag012-B10","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.2217\/pgs-2018-0146","article-title":"Pharmacogenetics of warfarin dosing in patients of African and European ancestry","volume":"19","author":"Shendre","year":"2018","journal-title":"Pharmacogenomics"},{"key":"2026041617412965800_ocag012-B11","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1136\/jech.2004.029496","article-title":"Estimating causal effects from epidemiological data","volume":"60","author":"Hern\u00e1n","year":"2006","journal-title":"J Epidemiol Community Health"},{"key":"2026041617412965800_ocag012-B12","author":"Shmueli","year":"2025"},{"key":"2026041617412965800_ocag012-B13","first-page":"643","author":"Kamishima","year":"2011"},{"key":"2026041617412965800_ocag012-B14","doi-asserted-by":"crossref","first-page":"e1452","DOI":"10.1002\/widm.1452","article-title":"A survey on datasets for fairness-aware machine learning","volume":"12","author":"Quy","year":"2022","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov"},{"key":"2026041617412965800_ocag012-B15","author":"Zhao","year":"2024"},{"key":"2026041617412965800_ocag012-B16","author":"Hernandez-Boussard","year":"2024"},{"key":"2026041617412965800_ocag012-B17","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s41746-023-00805-y","article-title":"An adversarial training framework for mitigating algorithmic biases in clinical machine learning","volume":"6","author":"Yang","year":"2023","journal-title":"NPJ Digit Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag012\/66799018\/ocag012.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/922\/66799018\/ocag012.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/922\/66799018\/ocag012.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:42:52Z","timestamp":1776375772000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/4\/922\/8466364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":17,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,2,6]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag012","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,2,6]]}}}