Gezixuan reported on November 4 that, according to TheGuardian, the British National Health Service (NHS) is about to try out a "superhuman" artificial intelligence tool called "Aire", which can predict the risk of illness and early death of patients.

The new technology, known as AI-ECG risk estimation, or Aire for short, is trained to read the results of an electrocardiogram (ECG) test, which is able to detect underlying structural problems in the heart that doctors can't see and flag patients who may need further monitoring, testing, or treatment. It is reported that the researchers trained Aire using a dataset of 1.16 million ECG test results from 189,539 patients.

The technology will be trialled at two NHS Trust hospitals in London in the middle of next year, and experts hope to roll it out to the entire healthcare system in the next five years, according to IT House. It is reported that hundreds of patients will be recruited initially, and then expanded for further research.

The study, published in The Lancet Digital Health, found that in 78% of cases, Aire was able to correctly identify a patient's risk of death within 10 years of an ECG. In addition, Aire was 76% accurate in predicting future serious heart rhythm problems and 70% accurate in predicting future atherosclerotic cardiovascular disease.

Arunasis Sau, a registered cardiologist at Imperial College London's NHS Trust Hospital, who is involved in the trial, said the goal of the project is not to replace doctors, but to "surpass humans" through AI.