The NHS in England is starting a groundbreaking trial of a new AI tool that can predict if a person is at risk of developing type 2 diabetes up to 13 years before symptoms appear. This tool could help doctors take action early to prevent the condition.
Type 2 diabetes affects over 500 million people worldwide and is expected to rise to 1 billion by 2050. It can lead to severe health problems like blindness, kidney failure, heart attacks, strokes, and amputations. Risk factors include being overweight, inactive, or having a family history of diabetes.
The new AI tool, called Aire-DM, analyzes heart scans (ECGs) to detect tiny changes that might go unnoticed by the human eye. These changes could indicate an early risk of type 2 diabetes. By identifying this risk, doctors can suggest diet and lifestyle changes to help patients avoid developing the condition.
The NHS will test this tool in 2025 at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust. If successful, it could be introduced in England and other countries soon after.
This tool was developed using 1.2 million ECGs from hospital records and further tested with data from the UK Biobank, which includes health information from over 500,000 people. Aire-DM is about 70% accurate in predicting diabetes risk and becomes even more precise when combined with other data like age and blood pressure.
Health experts believe this AI tool could be revolutionary. Dr. Libor Pastika from Imperial called it a “cheap, accessible, and non-invasive” way to identify diabetes risk early, offering more targeted and preventive care.
The British Heart Foundation, which supported the tool’s development, sees this as a major step in preventing type 2 diabetes and reducing its complications. This innovative approach could transform how healthcare systems tackle the growing challenge of diabetes worldwide.
Source: theguardian
