Heart Failure Diagnosis with AI Handheld Echo

Article | Jul 29, 2025

A new study published in the European Journal of Heart Failure showcases the power of artificial intelligence to transform how heart failure is diagnosed. Researchers tested fully automated AI analysis (Us2ai) on images acquired using handheld echocardiography in 867 real world patients with suspected heart failure.

The AI accurately detected left ventricular ejection fraction (LVEF ≤40 percent) with a diagnostic accuracy of 0.93, closely matching expert human analysis of standard cart based echocardiograms.

Remarkably, LVEF measurements from AI analyzed scans were statistically interchangeable with those from human experts.

These findings suggest AI powered handheld echocardiography could bring faster, more accessible heart failure diagnosis to primary care and community settings, potentially reshaping heart failure care pathways around the world.

Heart Failure Diagnosis with AI Handheld Echo

Download and read the full manuscript here →

Campbell, R. T., Petrie, M. C., Docherty, K. F., Brooksbank, K. J. M., McKinley, G., Haig, C., McConnachie, A., Lam, C. S. P., Adamson, C., Butler, E., Curtain, J. P., Hartshorne‐Evans, N., Graham, F. J., Hainey, H., Jarvie, J., Lee, M. M. Y., Macklin, L., Mangion, K., McCoubrey, A., & McDowell, K. (2025). Artificial intelligence fully automated analysis of handheld echocardiography in real‐world patients with suspected heart failure. European Journal of Heart Failure. https://doi.org/10.1002/ejhf.3783