Researchers presented an artificial intelligence tool that can identify signs of heart failure and heart valve disease from routine electrocardiogram results in less than two seconds. The technology, trained on data from several million ECGs, was discussed at the European Society of Cardiology’s annual conference in Munich, Germany. It could help identify patients who should be prioritised for echocardiogram testing.

In testing involving 67,000 patients in the United States, the AI detected up to 81% of people with heart failure and up to 90% of those with heart valve disease. Conventional ECGs record the heart’s electrical activity and have long been used to identify heart attacks and abnormal rhythms, but they cannot reliably diagnose these conditions. Echocardiograms are usually required, and patients can wait months for the scan.

The British Heart Foundation-funded research does not provide a final diagnosis or reliably rule out disease. Its potential role is to flag people at higher risk for faster follow-up testing and treatment. Researchers are also aiming to develop a portable AI-enabled ECG device for health workers, potentially allowing rapid risk assessment outside hospitals and in primary care settings.