Association of Biomarker-Based Artificial Intelligence With Risk of Racial Bias in Retinal Images

Author:

Coyner Aaron S.1,Singh Praveer23,Brown James M.4,Ostmo Susan1,Chan R.V. Paul5,Chiang Michael F.6,Kalpathy-Cramer Jayashree23,Campbell J. Peter1,Young Benjamin K7,Kim Sang Jin,7,Sonmez Kemal7,Schelonka Robert7,Jonas Karyn7,Kolli Bhavana7,Horowitz Jason7,Coki Osode7,Eccles Cheryl-Ann7,Sarna Leora7,Orlin Anton7,Berrocal Audina7,Negron Catherin7,Denser, MD Kimberly7,Cumming Kristi7,Osentoski Tammy7,Check Tammy7,Zajechowski Mary7,Lee Thomas7,Nagiel Aaron7,Kruger Evan7,McGovern Kathryn7,Contractor Dilshad7,Havunjian Margaret7,Simmons Charles7,Murthy Raghu7,Galvis Sharon7,Rotter Jerome7,Chen, PhD Ida7,Li Xiaohui7,Taylor Kent7,Roll Kaye7,Hartnett Mary Elizabeth7,Owen Leah7,Lucci Lucia7,Moshfeghi Darius7,Nunez Mariana7,Wennber-Smith Zac7,Erdogmus Deniz7,Ioannidis Stratis7,Martinez-Castellanos Maria Ana7,Salinas-Longoria Samantha7,Romero Rafael7,Arriola Andrea7,Olguin-Manriquez Francisco7,Meraz-Gutierrez Miroslava7,Dulanto-Reinoso Carlos M.7,Montero-Mendoza Cristina7,

Affiliation:

1. Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland

2. Radiology, MGH/Harvard Medical School, Charlestown, Massachusetts

3. MGH & BWH Center for Clinical Data Science, Boston, Massachusetts

4. School of Computer Science, University of Lincoln, Lincoln, United Kingdom

5. Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago

6. National Eye Institute, National Institutes of Health, Bethesda, Maryland

7. for the Imaging and Informatics in Retinopathy of Prematurity Consortium

Abstract

ImportanceAlthough race is a social construct, it is associated with variations in skin and retinal pigmentation. Image-based medical artificial intelligence (AI) algorithms that use images of these organs have the potential to learn features associated with self-reported race (SRR), which increases the risk of racially biased performance in diagnostic tasks; understanding whether this information can be removed, without affecting the performance of AI algorithms, is critical in reducing the risk of racial bias in medical AI.ObjectiveTo evaluate whether converting color fundus photographs to retinal vessel maps (RVMs) of infants screened for retinopathy of prematurity (ROP) removes the risk for racial bias.Design, Setting, and ParticipantsThe retinal fundus images (RFIs) of neonates with parent-reported Black or White race were collected for this study. A u-net, a convolutional neural network (CNN) that provides precise segmentation for biomedical images, was used to segment the major arteries and veins in RFIs into grayscale RVMs, which were subsequently thresholded, binarized, and/or skeletonized. CNNs were trained with patients’ SRR labels on color RFIs, raw RVMs, and thresholded, binarized, or skeletonized RVMs. Study data were analyzed from July 1 to September 28, 2021.Main Outcomes and MeasuresArea under the precision-recall curve (AUC-PR) and area under the receiver operating characteristic curve (AUROC) at both the image and eye level for classification of SRR.ResultsA total of 4095 RFIs were collected from 245 neonates with parent-reported Black (94 [38.4%]; mean [SD] age, 27.2 [2.3] weeks; 55 majority sex [58.5%]) or White (151 [61.6%]; mean [SD] age, 27.6 [2.3] weeks, 80 majority sex [53.0%]) race. CNNs inferred SRR from RFIs nearly perfectly (image-level AUC-PR, 0.999; 95% CI, 0.999-1.000; infant-level AUC-PR, 1.000; 95% CI, 0.999-1.000). Raw RVMs were nearly as informative as color RFIs (image-level AUC-PR, 0.938; 95% CI, 0.926-0.950; infant-level AUC-PR, 0.995; 95% CI, 0.992-0.998). Ultimately, CNNs were able to learn whether RFIs or RVMs were from Black or White infants regardless of whether images contained color, vessel segmentation brightness differences were nullified, or vessel segmentation widths were uniform.Conclusions and RelevanceResults of this diagnostic study suggest that it can be very challenging to remove information relevant to SRR from fundus photographs. As a result, AI algorithms trained on fundus photographs have the potential for biased performance in practice, even if based on biomarkers rather than raw images. Regardless of the methodology used for training AI, evaluating performance in relevant subpopulations is critical.

Publisher

American Medical Association (AMA)

Subject

Ophthalmology

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3