A new Australian study has found that an automated artificial intelligence (AI) enabled camera can accurately detect diabetic eye disease with more than 93% accuracy in non-eye care settings.

More than 860 people with diabetes took part in the trial in the waiting rooms of general practitioner and endocrinology clinics in Melbourne, and an Aboriginal Health Service in Western Australia between August 2021 and June 2023.

The two-year Australian trial, published in the British Journal of Ophthalmology,1 used an automated portable retinal camera – powered by an AI algorithm trained on more than 200,000 retinal images graded by 21 ophthalmologists – to guide participants to take photos of their own eyes while they waited for their medical appointment.

Trial participants received a print-out with a QR code with results of their scan to take into their appointment. Those found to have signs of diabetic eye disease (DED) were referred for follow up with an eye care specialist.

REAL WORLD

Although many studies have compared AI to human grading for diabetic eye disease, the Melbourne study is one of the first to occur in real world clinical settings.

To determine accuracy, all results were compared to the gold standard assessments of human grading. Participants and health professionals also took part in a satisfaction survey.

The study found:

• A high accuracy rate of 93.3% compared to human grading,

• 86% of participants were satisfied with the technology, and

• 85% of clinicians rated the technology highly.

POTENTIAL FOR ROUTINE CARE

Associate Professor Lisa Zhuoting Zhu and Sanil Joseph from the Centre for Eye Research Australia and University of Melbourne, and Professor Mingguang He, of the Hong Kong Polytechnic University, said their findings demonstrate the potential of AI eye screening to become part of routine clinical care for people with diabetes.

Globally, more than 529 million people are living with diabetes and at risk of vision loss and blindness from DED.

Early treatment can prevent blindness in 90% of cases, but ensuring that everyone with diabetes has access to the eye scans needed to detect the disease is a challenge for health systems worldwide.

Reference

1. Joseph S, Wang Y, He MG, et al. Effectiveness of artificial intelligence-based diabetic retinopathy screening in primary care and endocrinology settings in Australia: a pragmatic trial. Br J Ophthalmol. 2025 Aug 22:bjo-2025-327447. doi: 10.1136/bjo-2025-327447. Epub ahead of print.