Evaluation of the Efficacy of Artificial Intelligence-Based Screening for Diabetic Retinopathy in a…

AI / informaticsSouthern medical journal· Jul 2026

Evaluation of the Efficacy of Artificial Intelligence-Based Screening for Diabetic Retinopathy in a Predominantly Non-White Population.

Sydney Marie Galindez, Michael Wang, Queenie Wang … David Miguel Hinkle

RetinaAI / informaticsClinical practiceQ3IF 0.7

Nearly 30% of patients with positive diabetic retinopathy screens missed follow-up.

Evaluation of the Efficacy of Artificial Intelligence-Based Screening for Diabetic Retinopathy in a Predominantly Non-White Population.

Sydney Marie Galindez … David Miguel Hinkle

Southern medical journal · Jul 2026 · Q3 in General Medicine

Purpose

To evaluate the diagnostic accuracy of Luminetics Core, a Food and Drug Administration-cleared artificial intelligence-based screening system, in the detection of diabetic retinopathy (diabetic retinopathy) in a predominately non-White population and identify potential shortcomings in clinical implementation that should be addressed to mitigate disparities in health care.

Methods

Data were acquired via retrospective chart review and included 225 patients with a diagnosis of diabetes mellitus who were screened for diabetic retinopathy using the LumineticsCore system (formerly IDx-diabetic retinopathy) at the University Medical Center New Orleans (Louisiana).

n = 225 patients

29.8%

Results

29.8%

patients with positive screenings for diabetes-related eye disease who missed follow-up eye exams

n = 225 patients

More results

The study population had a diverse demographic profile, with 69.0% of subjects identifying as African American, 13.1% Hispanic, 10.7% White, 3.6% Asian, and 3.6% of subjects who either did not identify with the above racial/ethnic groups or declined to self-identify.

More results

The system yielded favorable performance measures in the study population regarding detection accuracy.

“

Conclusion · 1 of 2

The LumineticsCore system was found to be a reliable screening test for the detection of diabetic retinopathy in the study population.

Conclusion · 2 of 2

The relatively high no-show rate for scheduled ophthalmology referrals in patients with positive screen results, however, sheds light on an implementation system issue in need of further evaluation.

Evaluation of the Efficacy of Artificial Intelligence-Based Screening for Diabetic Retinopathy in a Predominantly Non-White Population.

Evaluation of the Efficacy of Artificial Intelligence-Based Screening for Diabetic Retinopathy in a Predominantly Non-White Population.

Related papers