From the Journals

Can Diabetic Eye Testing Be Simplified?

Three-test models matched nine-test battery in classifying disease stages

Share

In a cross-sectional study published in BMJ Open Ophthalmology, researchers developed machine learning models to classify stages of diabetic eye disease using age, sex, and up to three visual function tests. The study evaluated 1,901 eyes from 1,032 participants, achieving high classification performance with area under the curve values of 0.94 or higher. The models performed comparably to traditional nine-test batteries, suggesting a streamlined approach for assessing diabetic retinopathy and related conditions while emphasizing the necessity for longitudinal studies for better prognostic insights.

Original Source(s)

Can Diabetic Eye Testing Be Simplified?

Three-test models matched nine-test battery in classifying disease stages

  • by Julie Greenbaum

  • February 18, 2026

  • 4 min

Related Content

Metformin and AMD: Signal or Noise?

Five-year population study details 37% lower incidence of intermediate AMD in type 2 diabetic patients prescribed metformin

FDA Rejects Extended Dosing Intervals for Eylea HD

The agency did not agree with Regeneron’s proposal to add dosing intervals greater than every 16 weeks, the maximum interval currently indicated for aflibercept 8 mg injections.

Integration of Vision Services Remains an Unmet Need in FQHCs

Telemedicine, funding, and provider partnerships can help, researchers say.