‘Superhuman’ AI that predicts the risk of premature death is being trialled in Britain

LONDON: A ‘superhuman’ artificial intelligence model designed to predict a patient’s risk of disease and early death will be trialled in British hospitals next year.

It is hoped that the technology – which uses the values ​​of a common and cheap heart test to alert doctors to patients who could benefit from further testing or treatment – will be used across the healthcare system within five years.

The AI ​​program, known as AI-ECG Risk Estimation, or Aire, is designed to read the results of electrocardiogram (ECG) tests, which record the electrical activity of the heart and are given to patients suspected of having heart problems.

It then uses these recordings to detect problems in the heart’s structure that doctors might not see.

The technology will be trialled for the UK National Health Service (NHS) at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust from mid-2025, with other hospital sites to be confirmed.

Dr. Fu Siong Ng, a reader in cardiac electrophysiology at Imperial College London and consultant cardiologist at Imperial College Healthcare NHS Trust, told the PA news agency: “There are three or four different trials that will be running through hospitals from the middle of next week . year.

“They need to broadly test whether these models are accurate in picking up diagnoses. So people who would already have an ECG in the hospital, we would test whether these models are accurate in picking up certain diagnoses.

“Then we can intervene in the next layer, as soon as it is visible, to show that we can change the patients’ trajectory.”

It is understood that several hundred patients will be recruited for the first trial, with numbers scaled up for subsequent studies.

Dr. Ng added: “The vision is that every ECG done in the hospital will be run through the model.

“So anyone who has an ECG anywhere in the NHS in ten or five years’ time will be put through the models and the doctors will be informed, not just about what the diagnosis is, but also about a prediction of a whole. range of health risks, which means we can intervene early and prevent diseases.

“For example, if it says that you are at high risk for a specific heart rhythm problem, you can be more aggressive in preventive treatment to prevent this.

“There are a few that are weight-related, so you can subject them to weight-loss programs.

“You could even think about previous medical treatments to prevent things from developing further, but that will be the subject of the clinical trials we plan to do.”

Dr. Arunashis Sau, a British Heart Foundation (BHF) clinical research fellow at Imperial College London’s National Heart and Lung Institute and cardiology registrar at Imperial College Healthcare NHS Trust, told PA that the aim of the Aire is not to develop anything to replace doctors, but to create something “superhuman”.

“The goal here is to try to use the ECG as a way to identify people who are at higher risk, who might then benefit from other tests that can tell us more about what’s going on,” he said .

“ECG is a common and very cheap test, but it could then be used to guide more detailed tests which could then change the way we deal with patients and potentially reduce the risk of something bad happening.

“An important distinction is that the goal here was to do something that was superhuman – so not to replace or speed up something that a doctor could do, but to do something that a doctor cannot do when looking at heart research.”

It comes after research published in Lancet Digital Health found that Aire could correctly identify a patient’s risk of death in the ten years following the ECG in 78% of cases, from high to low.

For the study, the team trained Aire using a dataset of 1.16 million ECG test results from 189,539 patients.

The platform can also predict future heart failure in 79% of cases, future serious heart rhythm problems in 76% of cases, and future atherosclerotic cardiovascular disease – where the arteries narrow, making blood flow difficult – in 70% of cases .

Dr. Sau said: “We know that not only doctors but also patients need to trust AI. And that’s a big part of the work we’ve done here.

“What we found is that AI can pick up things related to the patient’s heart structure and function, and even things as deep as genetic information were picked up that the AI ​​could use in combination to figure out that these people might be in trouble. higher risk, and these are things that are not obvious to human doctors.” – dpa/Tribune News Service