AI can use eye scans to predict kidney risk – study

Artificial intelligence (AI) can predict whether someone with type 2 diabetes will soon develop kidney disease based on changes in their eye scans, according to a study.

People with diabetes should be offered eye checks every one to two years where images are taken to the eye to check for any damage to blood vessels or a condition called diabetic retinopathy.

Researchers have now found that these images can potentially be used to also identify kidney disease among type 2 diabetes patients.

The move could mean that many patients who go on to develop kidney disease could have their condition found sooner as many early stage cases have no symptoms.

The study, presented to Diabetes UK’s Professional Conference 2025, found AI can use the scans to predict which patients will go on to develop kidney disease years before they are diagnosed by traditional methods.

Kidney disease is a serious complication linked to type 2 diabetes and can silently develop over a number of years.

One in five people with type 2 will need treatment for kidney disease.

Researchers at the universities of Dundee and Glasgow developed an AI tool using nearly one million eye screening photographs from almost 100,000 people with type 2 diabetes in Scotland.

The AI tool was trained to be able to distinguish between images from people with or without kidney disease.

It was then validated using data from 30,000 patients.

Diabetes UK said that the tool detected existing kidney disease with 86% accuracy.

The tool was also able to predict who would go on to develop it in the next five years with 78% accuracy.

The charity said the AI tool “outperformed” usual tests by detecting future kidney disease risk when standard testing provided no warning.

Study lead Dr Alex Doney said: “The retina at the back of the eye is the only place where the fragile network of blood vessels, critical to the health of all organs throughout the body, can be conveniently visualised and photographed.

“AIs can be trained to ‘see’ very early features and patterns within these photographs that humans are unable to.

“These can indicate declining health in other organs, such as the kidney in this case, before conventional clinical tests are informative.

“This provides doctors with an additional earlier opportunity to act on this information before permanent kidney damage has occurred.”

Dr Elizabeth Robertson, director of research at Diabetes UK, said: “Kidney damage often progresses silently until it becomes severe, and early detection is critical.

“This fascinating research has offered a new window into kidney health – through the eyes.

“By revealing intricate patterns in images taken during eye screenings, this AI tool could in future alert healthcare professionals to early signs of kidney damage.

“This would offer a vital opportunity to provide tailored support to slow or halt the progression of kidney disease that could ultimately save lives.

“Through harnessing the power of AI, this approach could transform routine diabetic eye screening into a versatile tool for predicting and preventing other diabetes-related complications.”