A groundbreaking ‘superhuman’ artificial intelligence (AI) model, which aims to predict a patient’s risk of disease and early death, is scheduled to undergo trials in NHS hospitals within the next year. The innovative technology, named AI-ECG risk estimation, or Aire, has been developed to analyse the results of electrocardiogram (ECG) tests. These tests, which capture the heart’s electrical activity, are typically administered to patients suspected of cardiac issues.
Aire will utilise these ECG recordings to identify structural abnormalities in the heart that may not be visible to doctors during routine examinations. The AI program is designed to alert healthcare professionals to individuals who may require further diagnostic procedures or treatments. The ultimate goal is for this technology to be integrated across the entire NHS within a five-year timeframe.
The upcoming trials of Aire will commence at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust starting in mid-2025, with additional hospital sites to be confirmed later. Dr Fu Siong Ng, a prominent figure in cardiac electrophysiology at Imperial College London and a consultant cardiologist at Imperial College Healthcare NHS Trust, expressed his enthusiasm for the forthcoming studies. He highlighted the potential for Aire to revolutionize the healthcare system by providing early intervention opportunities based on predictive insights derived from ECG data.
Dr Ng outlined, “The vision is every ECG that will be done in the hospital will be put through the model. 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.”
The research team behind Aire, including Dr Arunashis Sau, a British Heart Foundation clinical research fellow at Imperial College London, emphasised that the AI model is not intended to replace medical professionals but rather to complement their expertise. Dr Sau explained, “The goal here is to try and use the ECG as a way to identify people that are at higher risk, who will then maybe benefit from other tests that could tell us more about what’s going on.”
Recent findings published in Lancet Digital Health demonstrated that Aire successfully predicted mortality risk over a decade following an ECG test in 78% of cases. The AI platform also exhibited predictive accuracy for heart failure, serious heart rhythm abnormalities, and cardiovascular disease in subsequent years. The potential of AI to detect subtle indicators of health risks, including genetic predispositions, underscores its value as a tool for enhancing patient care.
In conclusion, the introduction of AI-ECG risk estimation into clinical practice represents a significant advancement in healthcare technology. By leveraging the power of artificial intelligence to interpret complex medical data, medical professionals can enhance their diagnostic capabilities and tailor interventions to individual patient needs more effectively. As trials progress and implementation evolves, the transformative impact of AI in healthcare is poised to improve patient outcomes and redefine standards of care.