A routine heart test can now catch disease early

A new AI tool developed in the UK can spot early signs of two common forms of heart disease from a standard electrocardiogram, potentially cutting the months-long wait many patients face for further testing. Details were presented this week at the European Society of Cardiology's annual congress in Munich. Trained on millions of patients, the model reads the ECG, a test that measures the heart's electrical activity and has never been able to detect heart disease on its own. In a trial of 67,000 patients in the US, it flagged 81% of heart failure cases and 90% of heart valve disease cases. The first outward sign of heart failure, for anyone who is not an experienced cardiologist, is often cardiac arrest. "When it comes to the heart, earlier diagnosis and treatment saves and improves lives," said Dr. Sonya Babu-Narayan of the British Heart Foundation, which funded the work. Roughly a billion ECGs are ordered worldwide every year. The machine reads them in the blink of an eye.