Doctors have developed an AI tool capable of detecting signs of heart failure and heart valve disease from a routine electrocardiogram (ECG) in under two seconds. This technology extracts more information from an ECG than the human eye can typically discern.
While traditional ECGs are vital for diagnosing heart attacks and abnormal rhythms, they cannot detect heart disease, which usually requires an echocardiogram. The new AI tool aims to identify patients at risk of heart failure and heart valve disease, two common forms of heart disease, from ECG results.
Details of this development were presented at the European Society of Cardiology annual congress. Early diagnosis of these conditions is crucial for patients to receive timely, potentially life-saving, treatment.
In a trial involving 67,000 US patients, the AI tool identified up to 81% of those with heart failure and up to 90% of those with heart valve disease. Dr. Sonya Babu-Narayan of the British Heart Foundation, which funded the trial, noted that while the AI will not detect every heart condition, it could help prioritise high-risk patients.
The technology provides a strong indication of potential heart conditions, allowing individuals deemed highly likely to have them to be referred for an echocardiogram more quickly, rather than waiting months. This could lead to earlier diagnosis and treatment.
Prof. Fu Siong Ng of Imperial College London highlighted that the tool could also opportunistically diagnose heart failure and heart valve disease in people who undergo ECGs for other reasons, by flagging high-risk individuals.