How a collaboration between data scientists, clinicians, and optometrists is using AI and retinal imaging to improve the early detection of neurodegenerative disease.
Dementia affects tens of millions of people worldwide, yet it is frequently diagnosed late — sometimes years after symptoms first appear. By the time a formal diagnosis is reached, opportunities for early intervention, treatment, and support planning have often been missed.
The experience of David Steele, a retired mechanical engineer whose mother has Alzheimer’s, is representative of many families. It took a decade for his mother to receive an accurate diagnosis. Her initial presentation — dry macular degeneration — obscured an underlying condition now understood to be cerebral blindness linked to Alzheimer’s. Her late husband, also elderly, cared for her throughout that period without knowing what was wrong.
If we had known, then we would have had help with the additional and demanding support that became necessary. Preventing the cliff edge, when it becomes too late for the person to understand what is wrong with them, is so important."
— David Steele, family member of a person living with Alzheimer’s
The
absence of accessible, scalable screening tools has meant that primary
care professionals — including optometrists who see the same patients
year after year — have lacked the means to flag early signs of
neurodegenerative disease. The NeurEYE project, led by the University of
Edinburgh in partnership with Glasgow Caledonian University, is working
to change that.
Using the eye as a window to the brain
NeurEYE is built on a well-established scientific principle: the retina and the brain share blood vessels and neural pathways. Changes visible in a retinal scan may therefore reflect changes occurring in the brain — and the retina can be examined using standard equipment found in any high street optometry practice.
The eye can tell us far more than we thought possible. The blood vessels and neural pathways of retina and brain are intimately related. But, unlike the brain, we can see the retina with the simple, inexpensive equipment found in every high street in the UK and beyond.”
— Professor Baljean Dhillon, Professor of Clinical Ophthalmology, University of Edinburgh, and NeurEYE co-lead
The research team has collected close to one million retinal scans from optometrists across Scotland — the world’s largest dataset of its kind. This imaging data has been linked, in anonymised form, to patient records covering demographics, treatment history, and pre-existing conditions. Permission to use the data comes from the Public Benefit and Privacy Panel for Health and Social Care, a part of NHS Scotland, and all data is held securely within the Scottish National Safe Haven, a platform commissioned by Public Health Scotland and hosted by the Edinburgh International Data Facility through EPCC at the University of Edinburgh.
Artificial intelligence and machine learning are applied to this dataset to identify patterns that could indicate an individual’s risk of developing dementia. The Lancet Commission has identified vision loss as one of its key dementia risk factors, adding weight to the connection between eye health and cognitive decline that NeurEYE is investigating.
In order to develop algorithms that are equitable and unbiased, we need to train them on datasets that are representative of the whole population at risk. This dataset, along with decades-long research at the University of Edinburgh into ethical AI, can bring a step change in early detection of dementia for all.”
— Professor Miguel Bernabeu, Professor of Computational Medicine, Usher Institute, and NeurEYE co-lead
What this could mean for patients, clinicians, and the NHS
Earlier diagnosis, better outcomes for individuals and families
Identifying dementia risk at an earlier stage gives individuals and families more time for forward planning, access to appropriate support, and informed decision-making before the condition progresses significantly. It also creates an opening for medical professionals to consider lifestyle modifications — including physical activity and diet — that evidence suggests can help modify risk.
A new role for optometrists in primary care
The diagnostic software developed through NeurEYE is designed to work within existing optometry practice. It would give optometrists the means to act as a predictive and diagnostic tool for conditions such as Alzheimer’s, to triage patients to secondary health services when signs of brain disease are identified, and potentially to support the monitoring of cognitive decline over time.
Optometrists as primary carers is not a new thing, and in Scotland we’re becoming an increasingly allied part of the NHS. We see the same people year on year, whether they’re ill or not, we have all the right equipment, so it makes sense for us to be the GP of the eyes and monitor as much health as we can see.”
— Ian Cameron, Optometrist, Cameron Optometry, Edinburgh
Accelerating research into new treatments
Beyond individual diagnosis, earlier identification of people at elevated risk of dementia is expected to accelerate clinical research, supporting the recruitment of suitable trial participants and enabling more precise monitoring of treatment responses, both of which are significant bottlenecks in the development of new therapies.
Reducing the financial burden on the NHS
Earlier diagnosis and treatment is estimated to save the NHS more than £37 million per year. The United Kingdom's single-provider healthcare structure is well placed to support the development of health data-driven diagnostic tools at scale, particularly in Scotland we have one single NHS number which enables the collection of non-identifiable data from every resident.
Harnessing the potential of digital innovations in this way could ultimately save the NHS more than £37m a year because the hope is that it will speed up the diagnosis and treatment of neurodegenerative conditions like dementia.”
— Dr Dave Powell, Chief Scientific Officer, LifeArc
A partnership built for real-world impact
The project came out of a partnership called NEURii, between global pharmaceutical, philanthropic, health data and medical research organisations and the University of Edinburgh. The collaboration, facilitated by Edinburgh Innovations, aimed to harness digital, data and AI to transform care for people living with dementia.
Note: All data used in NeurEYE research is anonymised and handled in accordance with NHS Scotland governance frameworks. No individual patient can be identified from the dataset.
