AI Eye Tests Show Promise in Early Dementia Detection During Routine Optician Visits

Image Credit: Ion Fet | Splash

Artificial intelligence tools could soon enable opticians to identify early signs of dementia during standard eye exams, according to recent research from the UK and Europe.

Quartz: AI Tool Developed in the UK

Researchers at City, University of London, and St George’s, University of London, have developed an AI system named Quartz that analyses retinal blood vessel patterns to assess brain health. The system uses optical coherence tomography angiography (OCTA) images to measure the width and curvature of blood vessels in the retina, which share similarities with the brain’s own vascular network.

Research Findings and Clinical Potential

A peer-reviewed study, published in Alzheimer’s & Dementia and funded by Alzheimer’s Research UK, found changes in retinal blood vessels were associated with cognitive decline. The research team analysed tens of thousands of eye scans, reporting that the Quartz system could be integrated into routine eye examinations pending regulatory approval. “This approach could be seamlessly integrated into routine eye checks, offering a cost-effective way to identify those at risk”, said Professor Chris Owen, lead author of the study.

Dementia Prevalence and Early Diagnosis Challenges

Dementia affects approximately 944,000 people in the UK and 421,000 in Australia, according to Alzheimer’s Research UK and Dementia Australia, with numbers projected to rise substantially by 2050. Early detection can support access to interventions and planning, but current diagnostic options, such as PET brain scans, are expensive and not widely available outside hospitals.

Global AI Developments in Eye Screening

The use of AI in eye screening is also being developed elsewhere. The University of Edinburgh’s NeurEYE project, working with nearly one million Scottish eye scans, aims to create an AI prototype by 2025, with a broader rollout planned for 2026, according to Edinburgh Innovations. Another study, published in npj Digital Medicine in 2024, introduced the Eye-AD model, which detected early-stage Alzheimer’s disease and mild cognitive impairment from OCTA scans with high accuracy.

Advantages and Practical Use Cases

AI-assisted retinal imaging offers a non-invasive and potentially low-cost option for identifying dementia risk in community settings. This could be especially valuable in countries like Australia, which has a universal healthcare system, and Hong Kong, where access varies between public and private providers. Experts say such technology may broaden access to screening and ease pressure on hospital systems, although further validation is required before routine adoption.

Validation, Diversity, and Ethical Considerations

Challenges remain. Researchers note that Quartz and similar AI tools must be tested for accuracy in diverse populations, including Australia’s Indigenous communities, to avoid algorithmic bias. Ethical issues, such as managing incidental findings and obtaining patient consent, are also under review. Regulatory approval may take several years.

Dementia: A Growing Health Issue

Dementia is the second leading cause of death in Australia and a growing health issue in Hong Kong, according to regional health agencies. A 2021 study by the University of California, San Francisco, published in JAMA Ophthalmology, also found associations between retinal changes and Alzheimer’s risk in certain genetic groups.

License This Article

Source: Spotify Newsroom, NME, arVix, ACL Anthology, EventBrite, BPI

$5.00

$10.00

$20.00

$30.00

Custom Amount

Please enter an amount

$

One-Time Donation Monthly Donation Quarterly Donation Annual Donation

3% Cover the Fee

Support us to keep delivering insightful content on AI development. Your contribution fuels our mission to inspire and inform! Support us to keep delivering insightful content on AI development. Your contribution fuels our mission to inspire and inform!