Mitigation of AI adoption bias through an improved autonomous AI system for diabetic retinal disease

Authors

Michael D. Abràmoff, Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA, USA. michael-abramoff@uiowa.edu.
Philip T. Lavin, Boston Biostatistics Research Foundation, Inc., Framingham, MA, USA.
Julie R. Jakubowski, Baxter International Inc, Deerfield, IL, USA.
Barbara A. Blodi, Department of Ophthalmology and Visual Sciences, Wisconsin Reading Center, University of Wisconsin, Madison, WI, USA.
Mia Keeys, Department of Public Health, George Washington University, Washington, DC, USA.
Cara Joyce, Department of Medicine, Stritch School of Medicine, Loyola University Chicago, Chicago, IL, USA.
James C. Folk, Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA, USA.

Document Type

Journal Article

Publication Date

12-19-2024

Journal

NPJ digital medicine

Volume

7

Issue

1

DOI

10.1038/s41746-024-01389-x

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 fundus camera (RetinaVue700, Baxter Healthcare, Deerfield, IL) to identify DRD in participants with diabetes without known DRD, in primary care. In 626 participants (1252 eyes) 50.8% male, 45.7% Hispanic, 17.3% Black, DRD prevalence was 29.0%, all prespecified non-inferiority endpoints were met and no racial, ethnic or sex bias was identified, against a Wisconsin Reading Center level I prognostic standard using widefield stereoscopic photography and macular Optical Coherence Tomography. Results suggest this improved autonomous AI system can mitigate AI adoption bias, while preserving safety and efficacy, potentially contributing to rapid scaling of health access equity. ClinicalTrials.gov NCT05808699 (3/29/2023).

APA Citation

Abràmoff, Michael D.; Lavin, Philip T.; Jakubowski, Julie R.; Blodi, Barbara A.; Keeys, Mia; Joyce, Cara; and Folk, James C., "Mitigation of AI adoption bias through an improved autonomous AI system for diabetic retinal disease" (2024). GW Authored Works. Paper 6124.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/6124

Department

Public Health Student Works