News

New AI developed to spot eye diseases

Clinical
New AI developed to spot eye diseases

An artificial intelligence (AI) system has identified eye diseases as accurately as experts has been developed by researchers.

A study undertaken in 2016 by teams at Moorfields Eye Hospital, DeepMind Health and University College London (UCL) Institute of Ophthalmology described how machine learning technology has been trained to identify eye diseases and recommend how patients should be referred for care.

The AI technology can be applied to different types of eye scanners. It uses two types of mathematical systems to recognise features of eye diseases, having originally learnt to do so from complex OCT scans. It can then decide how to refer the patient based on the urgency of the identified conditions. The study concluded that the technology was correct 94% of the time.

It was hoped that the technology could help professionals to spot conditions earlier and prioritise patients with serious eye diseases before any irreversible damage.

Dr Pearse Keane, consultant ophthalmologist at Moorfields Eye Hospital NHS Foundation Trust and clinician scientist at the UCL Institute of Ophthalmology, said: ‘The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight.’

Clinical trials will be held for the technology and if they are successful Moorfields can use it across all 30 of its UK hospitals and community clinics for five years initially.