AI Model Predicts Heart Valve Disease Years in Advance from ECG

July 16, 2025

An AI algorithm uses ECG data to accurately predict risk of future regurgitant heart valve diseases before symptoms or ultrasound changes appear.

Key Details

  • International team trained AI on nearly 1 million ECG and echocardiogram records from 400,000+ patients in China.
  • The model predicted risk of mitral, tricuspid, or aortic valvular regurgitation within years, with 69-79% accuracy.
  • High-risk patients identified by AI were up to 10 times more likely to develop valve disease.
  • Validation was conducted on 34,000+ US patients, supporting generalizability across populations.
  • Trials with the NHS are scheduled for late 2025 to evaluate real-world performance.
  • Research funded by British Heart Foundation, published in European Heart Journal.

Why It Matters

This research demonstrates how AI can leverage routinely acquired ECGs to flag patients at high risk for heart valve disease before traditional imaging reveals abnormalities, potentially transforming screening and management. It highlights the potential of integrating imaging and non-imaging clinical data in AI models to enable earlier and more proactive cardiac care.

Read more

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.