NeurEYE research team leads AI-supported dementia detection program with optometrists in Scotland

Patient undergoes retinal imaging, which may leverage AI to detect Alzheimer disease in the future. (Image credit: ©Dusko—stock.adobe.com)

Edinburgh Innovations, the University of Edinburgh’s commercialization service, announced a research program which will use artificial intelligence (AI)-based software and anonymized eye scans from patients throughout Scotland. The NeurEYE research team, led by the University of Edinburgh and in conjunction with Glasgow Caledonian University, will use millions of eye scans from Scottish optometrists to create the data set. Permission to use the data comes from the Public Benefit and Privacy Panel for Health and Social Care, a part of NHS Scotland. Once data is collected and anonymized, researchers will apply AI and machine learning tools to analyze the images for dementia risk and other bioindicators of brain health.

In a press release, the University of Edinburgh shared details of the national collaboration. Along with registering new biomarkers for Alzheimer and other degenerative neurological disease, the project may accelerate the development of new treatments by identifying those who would be suitable candidates for clinical trials and enable more accurate monitoring of treatment responses.

The joint effort will also develop an AI software which optometrists will be able to use as a predictive or diagnostic tool for conditions such as Alzheimer disease. Project leads hope that the software can act as a triage tool to refer patients to secondary health services or to monitor signs of cognitive decline in patients following a diagnosis.

NeurEYE is the second project funded and supported by NEURii, a global collaboration between the University of Edinburgh, health data science institute Health Data Research UK, pharmaceutical company Eisai, Gates Ventures and medical research charity LifeArc. The first NEURii project, Scottish AI in Neuroimaging to predict Dementia and Neurodegenerative Disease (SCAN-DAN), uses brain scans and AI software to predict dementia risk. NEURii launched in 2023, and SCAN-DAN was announced in 2024.

NeurEYE co-lead Baljean Dhillon, who is a professor of clinical ophthalmology at the University of Edinburgh, said the vascular systems of the retina and the neural pathways of the brain are “intimately related.”

“Unlike the brain, we can see the retina with the simple, inexpensive equipment found in every high street in the UK and beyond,” he stated in the news release.

His fellow NeurEYE co-lead Miguel Bernabeu, a professor of computational medicine at the Usher Institute, said the dataset will be fundamental for improving dementia detection. “Recent advances in artificial Intelligence promise to revolutionize medical image interpretation and disease prediction,” he said. “However, 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.”

Optometrist Ian Cameron of Cameron Optometry in Edinburgh commented on the benefits of using data from the broader NHS optometry network. “Optometrists as primary carers is not a new thing, and in Scotland we’re becoming an increasingly allied part of the NHS,” he said. “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.

The news release also included a testimonial from retired mechanical engineer, David Steele, 65, on the importance of ocular imaging in dementia detection. Steele said his mother, who has Alzheimer disease, could have benefitted from an earlier diagnosis using predictive software.

“It took 10 years for my mum to be diagnosed with Alzheimer. 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,” he said. “The missing diagnosis meant that my late father, who was also elderly, cared for mum throughout a difficult 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.”

According to the press release, using AI and other digital tools for detecting dementia could save the NHS more than £37 million per year. All data from patient scans will be stored in the Scottish National Safe Haven, a secure platform for the research use of NHS electronic data, commissioned by Public Health Scotland and hosted by the Edinburgh International Data Facility through the Edinburgh Parallel Computing Centre at the University of Edinburgh.

Reference

1. AI software tool aims to use high street eye tests to spot dementia risk. Edinburgh Innovations, The University of Edinburgh. News release. Published January 21, 2025. Accessed January 22, 2025. https://edininnovations-newsroom.prgloo.com/news/ai-software-tool-aims-to-use-high-street-eye-tests-to-spot-dementia-risk-2