EchoGo Amyloidosis (1.0)

EchoGo Amyloidosis (1.0) is a novel machine learning-based decision support tool designed to aid physicians in screening for Cardiac Amyloidosis in adult heart failure patients aged 65 and over through echocardiography. It leverages an artificial intelligence algorithm to analyze 2D echocardiograms for binary classification, demonstrating robust clinical validation, sensitivity, specificity, and reproducibility to ensure its safety and effectiveness.

A regulatory body has completed its review of a new medical software system, EchoGo Amyloidosis (1.0), developed by Ultromics Limited. This system is an automated, machine learning-based decision support tool designed as a screening aid for adult patients aged 65 and over who have heart failure and are undergoing cardiovascular assessment using echocardiography. Its purpose is to provide information that alerts physicians to the potential need for confirmatory investigations for Cardiac Amyloidosis, though patient management decisions should not be based solely on its analysis. Following a comprehensive evaluation, it has been determined that the device is substantially equivalent to a previously marketed system and may now be commercialized, subject to ongoing regulatory controls.The EchoGo Amyloidosis (1.0) system operates by taking a 2D apical four-chamber echocardiogram as input and uses an artificial intelligence algorithm to produce a binary classification indicating the presence or absence of Cardiac Amyloidosis. Extensive software verification and validation testing, including a clinical validation study on a diverse patient cohort, confirmed its performance. The study demonstrated robust sensitivity and specificity, along with high repeatability and strong reproducibility. The developer asserts that the device is as safe and effective as its predicate device, citing adherence to relevant consensus standards and special controls for software design, validation, usability, and clinical data support.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific echocardiographic features or patterns does the AI algorithm prioritize to classify the presence or absence of Cardiac Amyloidosis, and how does this compare to current expert interpretation?; Given that the system is a screening aid, what are the recommended clinical pathways or follow-up procedures for patients identified as potentially having Cardiac Amyloidosis, and what is the expected impact on time to definitive diagnosis?; How does the performance (sensitivity, specificity, repeatability, reproducibility) of EchoGo Amyloidosis (1.0) vary across different echocardiography machine manufacturers or image qualities, and were these variables accounted for in the clinical validation study?; What are the identified limitations or scenarios where the EchoGo Amyloidosis (1.0) system might produce unreliable results, and how are these communicated to clinicians to prevent misdiagnosis or delayed treatment?; Beyond the initial commercialization, what are the plans for ongoing post-market surveillance and performance monitoring, especially concerning its long-term accuracy and utility in diverse clinical settings?