Two NHS hospital trusts in London are using AI technology to see if they can detect type 2 diabetes in patients a decade before it develops.

Imperial College and Chelsea and Westminster Hospital NHS Foundation Trust have started training an AI system – called Array-DM – which examines patients’ ECG heart traces for subtle early warning signs that doctors might otherwise miss. It is difficult to apply.

Clinical trials are planned until 2025 to see if it works as hoped.

preliminary work It is suggested that the system can detect risks about 70% of the time.

Lead researcher Dr Foo Siong Ng says the AI’s predictive power comes from giving it additional details about other background risk factors, such as a patient’s age, gender and whether they already have high blood pressure or are overweight. There may be improvement.

“It’s already good enough with ECG data, but when you add it in it’s even better,” he told BBC News.

An ECG (electrocardiogram) records and can reveal problems with the heart’s electrical activity, including speed and rhythm.

Dr. Fu says the ECG changes detected by the system are so diverse and subtle that they are not possible to interpret with the naked eye, even for highly skilled doctors.

“It’s not so easy to say it’s this or that part of the ECG. It’s looking at a combination of subtle things.”

As part of the trial, ECG scans of up to 1,000 patients across both hospitals will be read by the AI ​​system to see if it helps detect and predict the disease.

This is not something that will be offered routinely right now, although experts hope it could be introduced more widely on the NHS. This could take five years or more, says Dr. Fu.

The British Heart Foundation, which is funding the work, says finding people at risk of diabetes could ultimately save lives.

For example, having uncontrolled type 2 diabetes can lead to heart attack and stroke.

Maintaining a healthy weight and eating a healthy diet and exercising can help prevent complications.

Professor Brian Williams, Chief Scientist and Medical Officer at the British Heart Foundation, said: “This exciting research uses powerful artificial intelligence to analyze ECGs, showing how AI can recognize things that would normally be detected on a regular basis. Such insights can be a gamechanger in predicting future risk of developing type 2 diabetes, years before the condition begins.

“Type 2 diabetes is a rapidly growing health challenge that increases the risk of developing heart disease, however with the right support it is possible for people to reduce their risk of developing the condition. We look forward to seeing how “How can this technology be incorporated into the doctor’s practice through the clinic?”