The NHS is starting the first-ever trial of an AI tool to find out the risk of type 2 diabetes
Exclusive: Two London hospitals to test tool that predicts who may develop type 2 diabetes up to 13 years early
The NHS in England is starting a world-first trial of an artificial intelligence tool that can find people at risk of type 2 diabetes over 10 years before they get the condition.
More than 500 million people around the world have type 2 diabetes, and finding new ways to identify those at risk early is a major health goal. Experts believe 1 billion people could have type 2 diabetes by 2050.
Type 2 diabetes is a leading cause of blindness, kidney failure, heart problems, strokes, and amputations. It is often linked to being overweight, inactive, or having a family history of diabetes, although not everyone with the condition fits these categories.
Doctors and scientists have now created a powerful AI tool that can predict who is at risk of type 2 diabetes up to 13 years before it starts developing.
This technology looks at electrocardiogram (ECG) readings during normal heart tests. It can spot small changes that are too tiny for the human eye to see, which might help identify early signs of type 2 diabetes.
By detecting these signs early, it could allow people to make changes to their diet and lifestyle to prevent getting diabetes.
The NHS will start testing this tool in 2025 at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust. It will be the first healthcare system in the world to try it, according to the Guardian.
The team behind the technology, called AI-ECG risk estimation for diabetes mellitus (Aire-DM), hopes it will be used across England’s health service and in other countries within a few years.
“AI has great potential to improve healthcare and make a big difference in people’s health,” said Dr. Libor Pastika, a clinical research fellow at Imperial. “By using AI to analyze ECG data, Aire-DM could be a game-changer in spotting the risk of type 2 diabetes early.”
“Aire-DM offers a cheap, easy, and non-invasive way to predict the risk of type 2 diabetes early. This could lead to better, more focused care, helping people avoid the disease and its related complications.”
A team led by Dr. Fu Siong Ng and Dr. Arunashis Sau at Imperial developed the tool using 1.2 million ECGs from hospital records. They also tested it using data from the UK Biobank, which has genetic and medical records of over 500,000 people, to check if the tool could detect small changes in ECGs.
The tool looks for tiny ECG patterns that are more common in people who will develop type 2 diabetes in the future and then checks for those same patterns in new ECGs.
The warning signs include small changes in how the heart’s electrical signals move, like differences in the timing, shape, or patterns of certain electrical waves.
The tool can also detect longer times for the heart’s electrical signals to activate or reset. Though these changes may seem small, they show early effects of diabetes on the heart, even before any symptoms appear.
Tests have shown that the tool predicts risk accurately about 70% of the time, for people of different ages, genders, ethnicities, and backgrounds.
When the AI predictions were combined with genetic and health information, like age and blood pressure, the accuracy improved, giving a clearer picture of risk, according to the researchers.
Professor Bryan Williams, the chief scientific and medical officer at the British Heart Foundation, which helped fund the development of the tool, said: “This exciting research uses advanced AI to analyze ECGs, showing how AI can find things that are usually missed in everyday health data.”
This insight could make a big difference in predicting the risk of getting type 2 diabetes, even years before it happens.
Type 2 diabetes is a growing health problem that raises the chance of heart disease. However, with the right support, people can lower their risk of developing it.
We are excited to see how this technology can be used in healthcare, allowing doctors to act early to reduce the risk or even prevent type 2 diabetes and its related health issues.
Published: 24th December 2024
Also Read:
Machine restores donor organs in UK’s double-lung transplant
Energy firms to invest £77B in upgrading GB’s power grid
UK inflation hits 8-month high, pushing interest rates up
