NHS to trial 'superhuman' AI for predicting disease and early death risk

A "superhuman" artificial intelligence (AI) model to help predict a person's risk of disease and early death is to be trialled in NHS hospitals.

It analyses the results of an electrocardiogram (ECG) - a common test for people suspected of having heart problems - and tells doctors if they might benefit from further tests or treatment.

The AI does this by detecting issues in the heart's structure that medics wouldn't be able to see.

It will be tested from mid-2025 in London, at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, with other sites to be confirmed.

Several hundred patients will be recruited initially and it's hoped the technology - called AI-ECG risk estimation, or AIRE - will be used across the health service within five years.

AIRE was able to correctly identify a patient's risk of death in the next 10 years, from high to low, in 78% of cases, according to research in Lancet Digital Health.

It was trained on data from 1.16 million ECG results from nearly 190,000 people.

The AI predicted heart failure in 79% of cases, heart rhythm problems in 76% of cases, and a type of cardiovascular disease where arteries narrow in 70% of cases.

Dr Arunashis Sau, a cardiology registrar and researcher at Imperial College, said it would "guide more detailed testing that could then change how we manage patients and potentially reduce the risk of anything bad happening".

He added: "One key distinction is that the goal here was to do something that was superhuman - so not replace or speed up something that a doctor could do, but to do something that a doctor cannot do from looking at heart tracing."

Follow Sky News on WhatsApp

Keep up with all the latest news from the UK and around the world by following Sky News

Tap here

Read more from Sky News:
British volunteers wanted for norovirus vaccine trial
AI child abuse images increasing at 'chilling' rate

The goal is that eventually all ECGs will be put through the AI model, said Dr Fu Siong Ng, a consultant cardiologist at Imperial College.

He explained: "So anyone who has an ECG anywhere in the NHS in 10 years' time, or five years' time, would be put through the models and the clinicians will be informed, not just about what the diagnosis is, but a prediction of a whole range of health risks, which means that we can then intervene early and prevent disease."