10-07-202646
In England, the NHS is testing a new artificial intelligence tool that operates at a 'superhuman' level.
The technology, known as Aire (AI-ECG Risk Estimation), analyses electrocardiogram (ECG) results to forecast the risk of disease development and premature death in patients. An ECG is a widely used, low-cost diagnostic procedure that records the heart's electrical activity.
The system is capable of detecting subtle structural changes in the heart that are difficult to identify with the naked eye, and of flagging patients requiring further investigation or treatment at an early stage.
For the first time in the world, Aire is being trialled at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust. In the initial phase, several hundred patients are being enrolled, with the scope of the study to be expanded subsequently.
According to research published in The Lancet Digital Health, the system achieved the following predictive accuracy:
• 10-year mortality risk — 78%;
• future heart failure — 79%;
• serious arrhythmias — 76%;
• atherosclerotic cardiovascular disease — 70%.
The Aire model was trained on 1.16 million ECG records from 189,539 patients.
Experts emphasise that Aire was designed not to replace physicians, but to enhance clinical decision-making by predicting risks beyond the scope of human perception.