Detecting Common Sources of AI Bias: Questions to Ask When Procuring an AI Solution

Radiology

HomeRadiologyVol. 307, No. 3 PreviousNext Reviews and CommentaryEditorialDetecting Common Sources of AI Bias: Questions to Ask When Procuring an AI SolutionAli S. Tejani , Tara A. Retson, Linda Moy, Tessa S. CookAli S. Tejani , Tara A. Retson, Linda Moy, Tessa S. CookAuthor AffiliationsFrom the Departments of Radiology of University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390 (A.S.T.); University of California–San Diego, La Jolla, Calif (T.A.R.); New York University Grossman School of Medicine, New York, NY (L.M.); and Hospital of the University of Pennsylvania, Philadelphia, Pa (T.S.C.).Address correspondence to A.S.T. (email: [email protected]).Ali S. Tejani Tara A. RetsonLinda MoyTessa S. CookPublished Online:Mar 21 2023https://doi.org/10.1148/radiol.230580MoreSectionsFull textPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked In References1. Rouzrokh P, Khosravi B, Faghani S, et al. Mitigating Bias in Radiology Machine Learning: 1. Data Handling. Radiol Artif Intell 2022;4(5):e210290. Link, Google Scholar2. Zhang K, Khosravi B, Vahdati S, et al. Mitigating Bias in Radiology Machine Learning: 2. Model Development. Radiol Artif Intell 2022;4(5):e220010. Link, Google Scholar3. Parikh RB, Teeple S, Navathe AS. Addressing Bias in Artificial Intelligence in Health Care. JAMA 2019;322(24):2377–2378. Crossref, Medline, Google Scholar4. Marin JR, Rodean J, Hall M, et al. Racial and Ethnic Differences in Emergency Department Diagnostic Imaging at US Children's Hospitals, 2016-2019. JAMA Netw Open 2021;4(1):e2033710. Crossref, Medline, Google Scholar5. Yu AC, Mohajer B, Eng J. External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review. Radiol Artif Intell 2022;4(3):e210064. Link, Google Scholar6. Yi PH, Kim TK, Siegel E, Yahyavi-Firouz-Abadi N. Demographic Reporting in Publicly Available Chest Radiograph Data Sets: Opportunities for Mitigating Sex and Racial Disparities in Deep Learning Models. J Am Coll Radiol 2022;19(1 Pt B):192–200. Crossref, Medline, Google Scholar7. Abdalla M, Fine B. Hurdles to Artificial Intelligence Deployment: Noise in Schemas and "Gold" Labels . Radiol Artif Intell 2023. https://doi.org/10.1148/ryai.220056. Published online January 11, 2023. Link, Google Scholar8. Daye D, Wiggins WF, Lungren MP, et al. Implementation of Clinical Artificial Intelligence in Radiology: Who Decides and How? Radiology 2022;305(3):555–563 [Published correction appears in Radiology 2022;305(1):E62.]. Link, Google Scholar9. Maier-Hein K, Reinke A, Godau P, et al. Metrics reloaded: Pitfalls and recommendations for image analysis validation. arXiv preprint arXiv:2206.01653. https://arxiv.org/abs/2206.01653. Posted June 3, 2022. Accessed March 6, 2023. Google Scholar10. Seyyed-Kalantari L, Zhang H, McDermott MBA, Chen IY, Ghassemi M. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat Med 2021;27(12):2176–2182. Crossref, Medline, Google ScholarArticle HistoryReceived: Mar 6 2023Accepted: Mar 8 2023Published online: Mar 21 2023 FiguresReferencesRelatedDetailsRecommended Articles Short-, Mid-, and Long-term Strategies to Manage the Shortage of IohexolRadiology2022Volume: 304Issue: 2pp. 289-293Iodinated Contrast Material Shortage: Perspectives from the Cancer Imaging CommunityRadiology: Imaging Cancer2022Volume: 4Issue: 4Translating AI to Clinical Practice: Overcoming Data Shift with ExplainabilityRadioGraphics2023Volume: 43Issue: 5Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological PitfallsRadiology: Artificial Intelligence2022Volume: 5Issue: 1Customer Service in Radiology: Satisfying Your Patients and ReferrersRadioGraphics2018Volume: 38Issue: 6pp. 1872-1887See More RSNA Education Exhibits The On-Call Radiology Residents Guide to Managing the Reading Room: Distractions, Downtimes, and DiscussionsDigital Posters2019Snowball Sampling On Social Media: Advantages And Methodology Of Using Twitter As A Survey Distribution Tool In RadiologyDigital Posters2021Implementing Perfusion Protocols for Tumor Differentiation and Analysis of Post-Treatment Changes into Busy Clinical PracticeDigital Posters2022 RSNA Case Collection Caudal Regression SyndromeRSNA Case Collection2021Ingested Button Battery RSNA Case Collection2021Familial cerebral cavernous malformationsRSNA Case Collection2021 Vol. 307, No. 3 Metrics Altmetric Score PDF download

Visit paper website