Curie Brief
Turn on cookies to sign in
Signing in saves your progress to your Curie account. We can only do that with cookies on — turn them on to continue.
News
AI screening for diabetic retinopathy is proving its worth — clinically and financially. A new literature review found that AI-based screening matched or outperformed human graders in accuracy, boosted follow-up rates, and saved patients money. The catch? Reimbursement policies haven't caught up, leaving a proven tool underutilized.
AI-based screening for diabetic retinopathy (DR) is delivering real results — but an outdated payment system is holding it back. A literature review presented at the Women in Ophthalmology Summer Symposium found that AI screening achieved sensitivity and specificity above 90%, matching or surpassing human graders across diverse clinical settings. Same-visit diagnoses and real-time analysis also improved patient follow-up and screening completion rates in primary care and community settings.
The economic case is compelling too. Savings were driven by reduced transportation costs, fewer missed workdays, and lower out-of-pocket expenses — though researchers note these figures likely underestimate the true value of earlier detection and treatment.
By the Numbers:
Why it matters: With over 40 million Americans living with diabetes and DR as the leading cause of vision loss in working-age adults, scalable screening solutions are urgently needed. Yet despite FDA-approved AI tools being available for nearly a decade, inconsistent reimbursement frameworks remain a major barrier — and payer policies need to catch up with the evidence.
