CET and skills guides

Study and gain CET points through OT’s online CET exams, and access archived CET, CPD articles and skills guides in our education library

Find out more

Science and vision

News and features about the latest scientific developments and advances in optometry, ophthalmology and eye medicine

Find out more

Professional support

News and features about the latest developments relating to professional support from across optics. This includes updates from optical organisations such as the AOP and the GOC

Find out more

In practice

News and in-depth features about business management and career development in optics

Find out more


Explore the latest UK and global jobs in the optical sector for optometrists, dispensing opticians and more

Find out more

Predicting conversion to wet age-related macular degeneration using deep learning

Dr Pearse Keane, consultant ophthalmologist at Moorfields Eye Hospital, tells OT  about how AI can predict the emergence of wet AMD

Pearse Keane

The team at Moorfields Eye Hospital in London is using deep learning to predict the development of wet age-related macular degeneration (AMD) in a patient’s ‘good eye’, potentially six months before symptoms begin to appear.

It’s hoped that, for patients who are receiving treatment in the other eye already, this could act as an early warning system for wet AMD - the most common cause of blindness in the UK.

Dr Pearse Keane, consultant ophthalmologist at Moorfields Eye Hospital, believes that this could help ophthalmologists predict six months ahead whether the disease is going to develop in the patient’s currently healthy eye.

He said: “The fact that we have two eyes, and one of them can get affected first, means that we're in that unique position for these patients.

“In about 30 - 40% of patients who are receiving injections in one eye, we can predict with very high specificity whether they will develop wet AMD in their good eye within the next six months. It's by no means everybody, but in that 30 - 40% of patients we can really begin to target this.”

In the US there have been trials with patients injected with anti-VEGF in their ‘good eye’, but they have, so far, been small scale. Dr Keane hopes that the current research will allow for clinical trials to take place in the UK. The next step towards this would be to plan a clinical trial with an AI to identify high risk patients and then follow up with a trial of the preventative treatment, he told OT.

“In identifying those patients that are the highest risk, we could move towards doing another clinical trial where we explore preventative treatment,” Dr Keane said. “So, for example, that could be with anti-VEGF injections.

“The key point is using AI to identify those patients most likely to develop this condition and so it allows you to do more accurate and more efficient clinical trials, and hopefully be more successful.”

Dr Keane believes that until there is a COVID-19 vaccine available, community optometrists will continue to be vital and that the way they work with hospital ophthalmologists will become increasingly sophisticated. He believes that AI will be part of that progress - not as a luxury, but as standard.

Predicting conversion to wet age-related macular degeneration using deep learning

OT speaks to Dr Pearse Keane about clinical trials that could detect wet AMD in patients’ ‘good eyes’

Dr Pearse Keane will be taking part in an AOP webinar on 9th July, discussing the subject of transforming eye care with artificial intelligence. Sign up for Transforming eye care with artificial intelligence - lessons from optometry and ophthalmology.