Could an AI-powered eye test spot dementia early on?
Baljean Dhillon, professor of clinical ophthalmology at the University of Edinburgh and NeurEYE co-lead.
A collaboration between data scientists, clinical researchers, and community opticians in the UK is hoping to develop an artificial intelligence-powered digital tool to predict dementia risk as part of a routine eye test.
A team from the University of Edinburgh and Glasgow Caledonian University in Scotland have already collected almost a million scans from opticians across the country. They will serve as a training resource for an AI that will look for signs of dementia in the retina, including changes to blood vessels, tissue thinning, and deposits of amyloid – the aberrant protein that forms clumps in the brains of people with Alzheimer's disease.
The retinal scans will be cross-referenced with anonymised patient data on demographics, treatment history, and pre-existing conditions to develop the AI.
The NeurEYE project is the fruit of a collaboration between Edinburgh University and pharma company Eisai – which was the first company to bring a new generation of amyloid-targeting therapies for Alzheimer's to market in collaboration with Biogen – along with Gates Ventures, medical research charity LifeArc, and Health Data Research UK.
The alliance – known as NEURii – is also using CT and MRI brain scans from the Scottish population to build another AI tool that they hope will be able to predict a person's risk of dementia in the SCAN-DAN project. A third project will develop a digital speech bank and speech-based real-time digital assessment tool to detect neurodegeneration.
"The eye can tell us far more than we thought possible. The blood vessels and neural pathways of retina and brain are intimately related," said Baljean Dhillon, professor of clinical ophthalmology at the University of Edinburgh and NeurEYE co-lead.
"But, unlike the brain, we can see the retina with the simple, inexpensive equipment found in every high street in the UK and beyond," he added.
The hope is that this could allow for the development of predictive or diagnostic tools for Alzheimer's and other forms of dementia, potentially even to monitor cognitive decline, and give an overall picture of brain health.
Retired mechanical engineer, David Steele, whose mother has Alzheimer's, said predictive software like this could have saved his family 10 years of heartache and struggle.
"It took ten years for my mum to be diagnosed with Alzheimer's. She was initially diagnosed with dry macular degeneration, but this masked the underlying issue that we now know to be cerebral blindness linked to Alzheimer's," he commented.
"The connection between brain and eye was the missing link in her case," added Steele. "The missing diagnosis meant that my late father, who was also elderly, cared for mum throughout a difficult period without knowing what was wrong."
Knowing who is at risk of dementia could also accelerate the development of new treatments by identifying people who are more likely to benefit from clinical trials and enabling better monitoring of treatment responses, according to the partners.
