AI-Enhanced ECG Identifies Patients at Future Risk of Heart Block

This can slow the heartbeat or cause skipped beats, leading to fainting, fatigue, injuries from falls, or even sudden death. Currently, doctors rely on electrocardiogram (ECG) readings and international guidelines to spot those at risk, but early abnormal heartbeats often go undetected. Researchers have now shown that a new tool can predict this condition much more accurately by using ECG data.

The tool, called AIRE-CHB, was developed by researchers at Imperial College Healthcare NHS Trust (London, UK) and uses artificial intelligence (AI) to analyze ECG data and detect the earliest signs of complete heart block. To build the system, researchers analyzed over 1.1 million ECGs from nearly 190,000 patients at a Boston hospital. They then trained the AI to recognize predictive patterns and validated it with over 50,000 participants from the UK Biobank.

In a study published in JAMA Cardiology, AIRE-CHB significantly outperformed existing methods of predicting heart block. The tool identified the risk of developing the condition with an accuracy of 84%–94% depending on the population tested, averaging 89%. In comparison, the current clinical standard identifies risk correctly only 59% of the time. Patients flagged as high-risk by the AI were seven to twelve times more likely to develop complete heart block than low-risk individuals.

These findings show that the AI model could be particularly valuable for patients with unexplained fainting episodes, where the cause might be early-stage heart block. By enabling earlier detection, doctors could monitor patients more closely or treat them with pacemakers before serious injury or emergency hospital admission occurs. The tool builds on earlier AI-ECG models, such as AIRE, that have been used to predict conditions like heart valve disease, diabetes, and high blood pressure. Clinical trials of AIRE are planned in the NHS later in 2025.

“When complete heart block occurs, it can initially be intermittent and therefore difficult to identify; yet by the time it becomes permanent, it is far more dangerous for the patient,” said Dr. Arunashis Sau, Academic Clinical Lecturer at Imperial College London’s National Heart and Lung Institute, and cardiology registrar at Imperial College Healthcare NHS Trust. “If we doctors can better identify patients early on with this condition, we’ll be able to monitor them more closely or progress to treating them with a pacemaker - avoiding their serious injury, emergency hospital admission, or even their death.”

Related Links:
Imperial College Healthcare NHS Trust