AI detects major heart conditions in under two seconds

A new AI tool can detect signs of heart failure and heart valve disease from routine ECGs in under two seconds, potentially enabling earlier treatment in the United States.

“When it comes to the heart, earlier diagnosis and treatment saves and improves lives,” said Dr Sonya Babu-Narayan, consultant cardiologist and clinical director of the British Heart Foundation.

Trained on millions of patients, the technology extracts information from ECGs that is typically invisible to the human eye, potentially helping doctors identify high-risk patients who need further testing. In a US trial involving 67,000 patients, it identified up to 81% of those with heart failure and up to 90% of those with heart valve disease. With about one billion ECGs performed worldwide each year, the approach could help prioritise patients for echocardiograms and treatment before they become seriously unwell.