Photos Of This Body Part Could Help Predict Alzheimer’s Risk

Photos of the back of the eyes could offer a way to predict some of the common risk factors linked to Alzheimer’s disease, which is the leading cause of dementia.

That’s according to a new study, which used AI to analyse retinal photographs from more than 40,000 UK patients.

Alzheimer’s disease is thought to be caused by the abnormal build-up of proteins in and around brain cells. It impacts more than 520,000 people in the UK.

Some of the risk factors for developing the condition include: old age, genetics, history of head injury, smoking, obesity, diabetes, high blood pressure, high cholesterol, hearing loss, untreated depression, loneliness, drinking too much alcohol and not exercising enough.

In the latest study, researchers were able to identify regions of the retina associated with Alzheimer’s risk factors.

Lead author Ruogu Fang, a professor of biomedical engineering at the University of Florida, said most of the existing diagnostic tools for Alzheimer’s disease focus on later in life, “when it is too late to intervene”.

But by looking at retinal health earlier on, “we offer new opportunities to identify patients at risk, offer appropriate tests and encourage them to develop healthy lifestyles to mitigate their risk”, she said.

Many patients routinely have pictures of their eyes taken – whether because they have diabetes or glaucoma, or for routine eye examinations.

That means analysing retinal photographs could be a simple and low-cost way to spot Alzheimer’s risks factors compared to more expensive technologies, like MRI scans.

Co-author Seowung Leem, a doctoral student at University of Florida, said with the assistance of AI, they were able to identify subtle retinal variations that were previously overlooked across thousands of subjects – and these variations “may function as reliable indicators of future disease risk”.

Their AI model accurately predicted biological characteristics like sex or blood pressure as well as lifestyle factors associated with developing Alzheimer’s, such as smoking, alcohol use and even insomnia.

While these factors might be captured in patients’ medical charts, researchers noted those records are often incomplete. For example, people might not reliably report alcohol consumption or smoking.

Retinal photographs may provide another, more objective way to detect these risk factors, they said. Plus, they can capture damage accumulated over the years. The findings were published in the Journal of Alzheimer’s Disease.

Prof Fang’s group has already shown how retinal photographs can detect active cases of Alzheimer’s disease.

They suggested identifying early risk factors via retinal photos could better identify patients who might respond to earlier interventions – including protective lifestyle changes, some medications or brain training – before irreversible damage takes place.