110-OR: Autonomous Artificial Intelligence Diabetic Eye Exams to Mitigate Disparities in Screening Completion

Le résumé fourni par la source

Diabetic retinopathy (DR) is a complication of diabetes that can result in vision loss, but early detection and treatment through screening can prevent this. Few individuals with diabetes meet recommended DR screening guidelines, and racial/ethnic minority youth are less likely to undergo recommended screening. We sought to determine if implementing point of care (POC) autonomous artificial intelligence (AI) screening could mitigate disparities in diabetic eye exam completion. In a preregistered prospective study, ACCESS2, youth with type 1 and type 2 diabetes meeting American Diabetes Association criteria for needing DR screening underwent point of care autonomous AI diabetic eye exams at diabetes clinic visits. Completion rates of diabetic eye screening exams were compared prior to and after implementation of autonomous AI using chi-square tests. A total of 152 youth with T1D (69.7%) and T2D (30.3%) were enrolled, mean age 15.5y, 45.4% non-Hispanic (NH) White, with duration of diabetes of 5.7y, and median HbA1c of 8%. A greater percentage of NH White participants reported any prior diabetic eye exam compared to non-white and Hispanic participants (92.8% v 65.1%, p<0.001). Multivariable analysis demonstrated that even when controlling for age, sex, HbA1c, Medicaid insurance, diabetes type and duration of diabetes, non-white youth are less likely to have had a prior diabetic eye exam (OR 0.26, CI: 0.07-0.93, p=0.04). After undergoing POC autonomous AI diabetic eye exams, completion rates were 99% for participants in all subgroups. Implementation of autonomous AI at the point of care increases access to and completion of diabetic eye exams, and promotes health equity for minority youth with diabetes. Disclosure A.Zehra: None. M.D.Abràmoff: Board Member; Digital Diagnostics, Consultant; AbbVie Inc., NovaGo Therapeutics AG, Other Relationship; Digital Diagnostics, Stock/Shareholder; Digital Diagnostics. R.M.Wolf: Research Support; Dexcom, Inc., Boehringer Ingelheim Inc. L.A.Bromberger: None. B.Pan: None. A.Shehadeh: None. D.Patel: None. E.A.Brown: None. R.Channa: None. T.Liu: None. H.Lehmann: None. Funding National Eye Institute (R01EY033233, 5K23EY030911-03)

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.