Diabetes: eyes as a window to kidney health

New University of Dundee research has revealed that using artificial intelligence (AI) to analyse photos taken during routine diabetes eye screenings provides a window into kidney health

The new approach, presented at the Diabetes UK Professional Conference 2025, can predict whether people with type 2 diabetes are likely to develop chronic kidney disease years before symptoms arise or current tests are able to detect kidney problems, allowing for earlier intervention and treatment.

In type 2 diabetes, insulin made by cells in the pancreas doesn’t work properly, or the pancreas doesn’t produce enough insulin. This can lead to dangerously high blood sugar levels, which over time can cause widespread damage to the body, leading to serious complications such as heart attacks and strokes, sight loss and kidney disease.

Diabetes-related kidney disease can develop silently over many years, often going undetected until it becomes severe. One in five people with diabetes will need treatment for kidney disease during their lifetime. Diabetes is a leading cause of end-stage kidney disease, with almost one in three people who need dialysis or a kidney transplant having diabetes.

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

In the UK, everyone living with diabetes over the age of 12 is regularly invited to have their eyes screened, where photos are taken of the retina to spot signs of damage. In the new study, researchers at the Universities of Dundee and Glasgow explored whether AI analysis of eye screening photos could identify those who are likely to develop kidney disease in future. The team, led by Dr Alexander Doney developed the AI tool using nearly 1 million eye screening photographs from almost 100,000 people with type 2 diabetes in Scotland. Photographs were linked with existing data on kidney health, and the AI tool was trained to distinguish between images from people with or without kidney disease. The tool was then validated with data from almost 30,000 other people with type 2 diabetes.

The AI tool detected existing kidney disease with 86% accuracy. In people without kidney disease, it was also able to predict who would go on to develop it in the next five years with 78% accuracy. Critically, the AI outperformed traditional kidney function tests, detecting future kidney disease risk in individuals where standard testing provided no warning.

The researchers hope that using AI to unlock hidden clues within eye screening images could transform how kidney disease is detected. By spotting those at-risk years before symptoms or current tests, the new tool could allow for earlier interventions that could in future help millions avoid its devastating effects.

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 invisible 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 other diabetes-related complications.”

Dr Alex Doney, study lead, 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.”

The study was funded through various sources including Astra Zeneca and Innovate UK.

Source: University of Dundee

04.03.2025