Peer-Reviewed Publication
NPJ Digit Med2024;7(1):369.December 19, 2024Journal Article
Mitigation of AI adoption bias through an improved autonomous AI system for diabetic retinal disease.
Michael D Abràmoff1,2,3, Philip T Lavin4, Julie R Jakubowski5, Barbara A Blodi6, Mia Keeys7,8, Cara Joyce9, James C Folk10,11
1Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA, USA. michael-abramoff@uiowa.edu.
2Veterans Administration Medical Center, Iowa City, IA, USA. michael-abramoff@uiowa.edu.
3Digital Diagnostics, Inc., Coralville, IA, USA. michael-abramoff@uiowa.edu.
4Boston Biostatistics Research Foundation, Inc., Framingham, MA, USA.
5Baxter International Inc, Deerfield, IL, USA.
6Department of Ophthalmology and Visual Sciences, Wisconsin Reading Center, University of Wisconsin, Madison, WI, USA.
7Department of Public Health, George Washington University, Washington, DC, USA.
8Womens' Commissioner, Washington, DC, USA.
9Department of Medicine, Stritch School of Medicine, Loyola University Chicago, Chicago, IL, USA.
10Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA, USA.
11Veterans Administration Medical Center, Iowa City, IA, USA.
Abstract
Where adopted, Autonomous artificial Intelligence (AI) for Diabetic Retinal Disease (DRD) resolves longstanding racial, ethnic, and socioeconomic disparities, but AI adoption bias persists. This preregistered trial determined sensitivity and specificity of a previously FDA authorized AI, improved to compensate for lower contrast and smaller imaged area of a widely adopted, lower cost, handheld fun…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans