Intended Use

Automated machine learning-based decision support system indicated as a screening tool for adult patients aged 65 years and over with heart failure undergoing cardiovascular assessment using echocardiography. Provides information alerting physician for referral to confirmatory investigations. Patient management decisions should not be made solely on the device results.

Technology

EchoGo Amyloidosis 1.0 processes 2D echocardiograms as input and uses a convolutional neural network AI algorithm to output a binary classification decision indicating presence or absence of cardiac amyloidosis. It is a fully automated software-only device without a graphical user interface, receiving DICOM files and interoperating via DICOM standards with ultrasound machines or PACS. The AI was pre-trained on large datasets and independently validated in clinical settings.

Performance

The software underwent extensive verification and validation including safety and performance testing, risk management, usability assessments with clinical users, and cybersecurity testing. Clinical performance was validated on a large multi-site cohort of over 1,100 patients aged 65+ with heart failure from US and international sites, showing sensitivity of 84.5%, specificity of 89.7%, and robust subgroup performance. Uncertainty and repeatability analyses demonstrated trustworthy and reproducible AI outputs.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    3/28/2024

    7 months
  • 2

    FDA Approval

    11/15/2024

Other devices from Ultromics Limited

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.