Artificial Intelligence Increases Diabetic Eye Exams in Youth With Diabetes

TUESDAY, Jan. 16, 2024 (HealthDay News) -- For youth with diabetes, an autonomous artificial intelligence diabetic eye exam at the point of care is associated with increased diabetic eye exam completion rates within six months, according to a study published online Jan. 11 in Nature Communications.

Risa M. Wolf, M.D., from the Johns Hopkins School of Medicine in Baltimore, and colleagues conducted a parallel randomized controlled trial involving youth aged 8 to 21 years with type 1 and type 2 diabetes. Participants were randomly assigned to an autonomous artificial intelligence diabetic eye exam at the point of care (intervention) or scripted eye care provider referral and education (control) in an academic pediatric diabetes center (81 and 83 participants, respectively).

The researchers found that the rate of diabetic eye exam completion within six months was significantly higher in the intervention group versus control group (100 versus 22 percent). An abnormal result occurred in 25/81 participants in the intervention arm, 64 percent of whom completed follow-through with eye care providers compared with 22 percent in the control arm.

"With AI technology, more people can get screened, which could then help identify more people who need follow-up evaluation," Wolf said in a statement. "If we can offer this more conveniently at the point of care with their diabetes doctor, then we can also potentially improve health equity, and prevent the progression of diabetic eye disease."

Two authors disclosed ties to the pharmaceutical industry; relevant patents and patent applications were assigned to the University of Iowa and Digital Diagnostics.

Abstract/Full Text