The system can also predict heart attacks, heart failure and heart rhythm problems, and researchers said it could be rolled out across the National Health Service (NHS) within the next five years.
An artificial intelligence (AI) tool to help doctors identify high-risk heart patients will soon go on trial in England after a study found it could accurately predict someone’s risk of dying in the years after a heart scan. The global research team led by Imperial College London trained their AI model, known as AI-ECG Risk Assessment or AIRE, on millions of results from electrocardiograms (ECGs), a common medical test that records electrical signals within and between chambers of the heart. It is commonly used to diagnose heart attacks and other abnormalities. The goal was to identify nuanced patterns that could mean someone is at high risk of health problems or death.
Put to the test, the model predicted the likelihood of death in the decade following an EKG – and was correct 78 per cent of the time. “We believe this could have huge benefits for the NHS and globally,” Dr Fu Siong Ng, a cardiac electrophysiology researcher at Imperial College London who worked on the project, said in a statement.
The system can also predict heart attacks, heart failure and heart rhythm problems, and researchers said it could be rolled out across the National Health Service (NHS) within the next five years. Trials with real patients are already planned for several sites in London and are expected to start in mid-2025. They will evaluate the benefits of the model using patients from outpatient clinics and hospital medical wards.
AI-powered EKGs are already used to diagnose heart disease, but they are not part of routine medical care and have not yet been used to identify a specific patient’s risk levels. “This could take the use of EKGs beyond what has been possible before, helping to assess the risk of future heart and health problems, as well as the risk of death,” said Bryan Williams, chief scientific officer. and medical at the British Heart Foundation. funded the study. The researchers, who published their results in the Lancet Digital Health journal, said that predictions where the AI ​​was wrong could be due to other unknown factors, such as whether the patient received additional treatment or died suddenly.
But they noted that the model can generally pick up subtle changes in the heart’s structure that could serve as a warning sign of disease or death but that doctors might miss. “We cardiologists use our experience and standard guidelines when looking at ECGs, sorting them into ‘normal’ and ‘abnormal’ patterns to help us diagnose disease,” said Dr Arunashis Sau, an academic clinician at Imperial College London. , who led the new study. “However, the AI ​​model detects much finer details, so it can ‘spot’ problems in the EKG that would appear normal to us, and potentially long before the disease fully develops,” said Sau.
Sau said more research from hospitals and other health care settings is needed to determine the model’s future role in diagnosis and treatment, but that patients with other health problems may also benefit because other diseases, such as diabetes, also tend to affect the heart. “This can have a positive impact on how patients are treated and ultimately improve the patient’s life expectancy and quality of life,” he said.
