Researchers at Imperial College London have developed an AI tool, Aire-CHB, that can detect early signs of complete heart block from routine electrocardiograms, according to an Aug. 20 news release by the university.
Supported by the National Institute for Health and Care Research Imperial Biomedical Research Centre, the system is set to begin clinical trials in late 2025.
The model was trained on more than 1.1 million ECGs from 190,000 patients at a Boston hospital and validated on 50,000 participants from the UK Biobank, showing 89% accuracy in predicting future heart block, compared with 59% using current methods.
Complete heart block, caused by disrupted electrical signals between the heart’s chambers, is often intermittent and difficult to catch early.
Researchers say the tool could allow earlier monitoring and pacemaker treatment, especially in patients with unexplained fainting episodes, according to the release.
