In a world first, the UK is testing an artificial intelligence (AI) tool that can predict the risk of type 2 diabetes up to 13 years before a patient develops the disease.
New AI tool reads electrocardiogram readings to predict risk of type 2 diabetes - Photo: REUTERS
To do so, the technology analyzes electrocardiogram (ECG) readings taken during routine heart checks. The tool can detect subtle changes that are not visible to the naked eye and are linked to a patient’s risk of developing type 2 diabetes later in life.
This allows doctors to intervene early and potentially help people avoid developing the disease in a variety of ways, such as changing their diet and lifestyle, according to the Guardian on December 24.
According to the British press, the UK National Health Service (NHS) will begin testing this tool in 2025 at the Royal College of Physicians NHS Trust and the Chelsea and Westminster Hospitals NHS Trust. These will be the first two health systems in the world to test this tool.
The team developing the AI-ECG risk estimation technology for diabetes (Aire-DM) hopes the technology can be rolled out across the UK health service and beyond within the next few years.
More than 500 million people worldwide are now diagnosed with type 2 diabetes - Photo: REUTERS
The team trained the AI using 1.2 million ECG records from hospital databases. They then used data from the UK Biobank, which stores genetic and medical data on more than 500,000 people in the UK, to validate the tool’s capabilities.
Tests showed the tool could accurately predict the risk of disease in people of different ages, genders, ethnicities and social backgrounds 70% of the time.
When combined with genetic and clinical information, such as age and blood pressure, the tool's predictive accuracy is improved.
“By using AI to unlock hidden information in ECG data, Aire-DM could be revolutionary in identifying early risk of type 2 diabetes in the future,” said Dr Libor Pastika, from Imperial College London.
According to the team, Aire-DM offers an inexpensive, accessible, and non-invasive method for predicting disease risk early, opening up new opportunities for more targeted preventive care to help people avoid the disease and its associated complications.
More than 500 million people worldwide are currently diagnosed with type 2 diabetes. It is estimated that 1 billion people worldwide will have the disease by 2050. Therefore, finding new ways to detect people at risk before they develop the disease is a top global health priority.
Source: https://tuoitre.vn/ai-giup-du-bao-tieu-duong-type-2-truoc-13-nam-2024122518131112.htm
Comment (0)