Key points from article :
Doctors have developed an artificial intelligence tool that can identify signs of heart failure and heart valve disease from a routine electrocardiogram (ECG) in less than two seconds. The technology analyses electrical signals from the heart to detect patterns that may be difficult for clinicians to recognise unaided. By extracting additional information from a test already widely used in healthcare, the system could help identify heart problems earlier and speed up access to further investigations.
In a US trial involving 67,000 patients, the AI system identified up to 81% of people with heart failure and up to 90% of those with heart valve disease. The research, funded by the British Heart Foundation, was presented at the European Society of Cardiology’s annual congress in Munich. The findings are particularly promising because ECGs are performed around a billion times worldwide each year, potentially offering a way to screen large numbers of people without requiring an additional initial test.
Currently, suspected heart failure and valve disease are usually investigated using an echocardiogram, an ultrasound scan of the heart. Patients can face waits of several months for these scans. The AI system could help prioritise those most likely to have a serious condition, allowing them to receive further testing and treatment sooner. Researchers also suggest it could be used to analyse ECGs taken for other reasons, flagging possible heart disease in people who might otherwise go undiagnosed.
However, the technology is not intended to replace doctors or provide a definitive diagnosis. It can miss some cases, and patients flagged as high-risk still need further assessment, including an echocardiogram. The next steps include developing portable AI-enabled ECG devices and exploring how the technology could be integrated into routine hospital care. Researchers are also investigating whether AI can detect other conditions, including high blood pressure and type 2 diabetes, by analysing short videos of people’s faces.
