News Release

Association of biomarker-based AI with risk of racial bias in retinal images

JAMA Ophthalmology

Peer-Reviewed Publication

JAMA Network

About The Study: Results of this diagnostic study including 4,095 retinal fundus images collected from 245 neonates suggest that it can be very challenging to remove information relevant to self-reported race 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.

Authors: J. Peter Campbell, M.D., M.P.H., of the Oregon Health & Science University in Portland, is the corresponding author.

To access the embargoed study: Visit our For The Media website at this link


Editor’s Note: Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

#  #  #

Embed this link to provide your readers free access to the full-text article This link will be live at the embargo time

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.