AI spots heart valve disease risk years before symptoms, study finds

An AI algorithm could identify people at risk of dangerous heart valve disease years before symptoms appear, researchers say.

‘Our work is harnessing AI to detect subtle changes at the earliest stage from a simple and common test’, said Dr Arunashis Sau, study lead from Imperial College London. ‘Rather than waiting for symptoms, or relying only on expensive and time-consuming imaging tests, we could use AI-enhanced ECGs to spot those most at risk earlier than ever before.’

Published in The European Heart Journal, the study found the AI could predict significant leaks in the heart’s valves, known as regurgitant valvular heart diseases, with 69-79% accuracy. People flagged ‘high-risk’ were up to 10 times more likely to develop the condition.

How was the research conducted?

Researchers trained the AI on almost one million ECG and ultrasound records from over 400,000 patients in China, then tested it on more than 34,000 US patients.

For you

Be part of something bigger, join BCS, The Chartered Institute for IT.

‘By training the model in an almost exclusively Chinese population and then testing in a US cohort, we can show that our AI tool has the potential to be applied in various countries and settings’, said Dr Fu Siong Ng, clinical senior lecturer in cardiac electrophysiology for Imperial College London.

The team says early detection could transform care for the estimated 41 million people worldwide living with valve disease. ‘This means that many more people could get the care they need before their hidden condition affects their quality of life or becomes life-threatening’, Dr Sau added.

Read more about the study on the Imperial College Healthcare NHS Trust website.