04 November 2025
A new study published in Eye has outlined how artificial intelligence (AI) could be used to monitor disease activity in age-related macular degeneration (AMD).
Researchers from Moorfields Eye Hospital, University College London Institute of Ophthalmology and University of Birmingham compared clinician assessments of AMD disease activity to AI-enabled assessments of disease activity.
The study involved 521 pairs of retinal images of patients with AMD captured with optical coherence tomography (OCT) at Moorfields Eye Hospital and Newcastle Eye Centre.
The researchers found that at both study sites “there was a consistent tendency to create more treatment appointments than a reference standard deemed necessary.”
They also determined that AI-enabled assessments of disease activity offered “superior diagnostic accuracy” to that observed in real-world care.
While the research team found no evidence of bias in the AI analysis according to age, sex or ethnicity, they observed that limitations in image quality affected AI performance.
AI devices are currently approved for decision support in the UK rather than autonomous use.
Lead author, Dr Jeffry Hogg, shared that macular disease is one of the single largest demands on ophthalmology services.
“Patients lose vision if services cannot keep up with demands. With 75% of departments reporting insufficient consultant staffing, we need innovative solutions that can help deliver better care more efficiently. Our research demonstrates how AI could help to reduce clinical demand, without compromising visual outcomes for NHS patients,” he said.
Senior study author, Professor Pearse Keane, highlighted: “ This is the first published comparison of autonomous AI enabled treatment monitoring with standard NHS care across multiple centres. It provides an evidence base for how we might safely harness AI to meet the growing demands on NHS eye services.”
Comments (0)
You must be logged in to join the discussion. Log in