ACCESS: AI for pediatriC diabetiC Eye examS Study

Autonomous AI for Diabetic Retinopathy Screening in Youth (AI-DR): A Randomized Control Trial

The purpose of this study is to determine if providing in clinic point-of-care autonomous AI diabetic retinopathy exams improves screening rates compared to standard of care referral to an eye care provider, in a randomized control trial in a racially and ethnically diverse cohort of youth.

This study will recruit 164 individuals ages 8-21 with type 1 and type 2 diabetes. Participants will be randomized to usual care (referral to an eye care provider for a dilated eye exam) or the intervention arm and undergo a point-of-care diabetic eye exam using autonomous AI software on a non-mydriatic fundus camera. Participants in the intervention group will receive the diabetic eye exam results immediately from the autonomous AI system, and if abnormal will be referred to an eye care provider for a dilated eye exam. Participants in the standard of care group will have 6 months to complete the diabetic eye exam.

Inclusion Criteria:

Meets American Diabetes Association (ADA) criteria for diabetic retinopathy screening:

• Diagnosis of Type 1 diabetes for ≥3 years, and age 11 or in puberty
• Diagnosis of Type 2 diabetes

Exclusion Criteria:

• Diabetic eye exam within the last 6 months
• Known diabetic retinopathy