Healthcare (Commonwealth Union) – A recent study from the University of Dundee has demonstrated that artificial intelligence (AI) can analyze images captured during routine diabetic eye screenings to gain insights into kidney health.
This cutting-edge method can forecast whether individuals with type 2 diabetes are at risk of developing chronic kidney disease years in advance—before symptoms appear or conventional tests identify any issues—enabling earlier diagnosis and treatment.
Type 2 diabetes occurs when the insulin produced by the pancreas is ineffective or insufficient, causing dangerously high blood sugar levels. Over time, this can result in significant damage to the body, increasing the risk of severe complications such as heart attacks, strokes, vision impairment, and kidney disease.
Kidney disease associated with diabetes can progress unnoticed for years, often remaining undiagnosed until it reaches an advanced stage. Around 20% of people with diabetes will require kidney disease treatment in their lifetime, and nearly one in three patients undergoing dialysis or a kidney transplant has diabetes.
In the UK, individuals with diabetes aged 12 and above are routinely invited for eye screenings, during which retinal images are taken to check for signs of damage. In a recent study, researchers from the Universities of Dundee and Glasgow investigated whether AI could analyze these images to identify those at risk of developing kidney disease in the future.
Led by Dr. Alexander Doney, the research team developed an AI tool using nearly one million retinal photographs from approximately 100,000 people in Scotland with type 2 diabetes. These images were cross-referenced with existing kidney health data, allowing the AI to learn how to differentiate between individuals with and without kidney disease. The tool was then tested using data from nearly 30,000 additional type 2 diabetes patients.
The AI system successfully identified current cases of kidney disease being 86 percent precise. Among those without the condition, it also predicted who would develop it within the next five years with a 78 percent success rate. Most importantly, the AI outperformed conventional kidney function tests, detecting future risks in patients who showed no warning signs through standard screenings.
The research team envisions AI as a game-changer in detecting kidney disease by uncovering subtle indicators within eye screening images. By identifying individuals at risk long before symptoms appear or traditional tests detect issues, this innovative tool could pave the way for early interventions, potentially preventing serious complications for millions in the future.
Dr. Elizabeth Robertson, Director of Research at Diabetes UK, emphasized the importance of early diagnosis, pointing out that kidney damage can advance unnoticed until it reaches a critical stage, making early detection essential. She further indicated that this groundbreaking study has provided a unique insight 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, the lead researcher, pointed out that the retina at the back of the eye is the only place where the body’s intricate network of blood vessels—essential for overall organ health—can be easily observed and photographed. AI can be trained to detect subtle features and patterns in these images that are invisible to the human eye. He further indicated that these patterns may signal early signs of deterioration in other organs, such as the kidneys, well before standard clinical tests can provide any indication adding that this technology offers doctors a crucial opportunity to intervene early, potentially preventing irreversible kidney damage.
