Myomics

Myomics is an AI-powered software application designed for the qualitative and quantitative evaluation of cardiovascular magnetic resonance images. It employs semi-automated machine learning algorithms, rigorously validated against diverse datasets, to assist clinicians in assessing cardiac health and identifying lesions in adult patient populations.

Phantomics Inc. has received a determination that its device, Myomics, is substantially equivalent to existing legally marketed devices. Myomics is a software application intended for viewing, post-processing, and conducting qualitative and quantitative evaluations of cardiovascular magnetic resonance (MR) images in a DICOM standard format. It includes various tools, some of which are AI-powered, to assist physicians in assessing cardiac images, performing quantitative measurements of the heart and adjacent vessels, and identifying lesions, with semi-automated machine learning algorithms specifically designed for adult populations. This determination allows the company to market the device.The manufacturer is required to adhere to various ongoing regulatory provisions, including annual registration, device listing, good manufacturing practices, and labeling requirements. The device also underwent comprehensive performance testing, including bench tests comparing it to predicate devices, and software verification and validation in accordance with international standards. Furthermore, its integrated AI modules were rigorously validated using a large, diverse dataset from multiple MR imaging device vendors, with all modules meeting predefined performance acceptance criteria, affirming the device's safety and effectiveness for its intended use.

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 performance metrics were used to validate the AI modules, and how did Myomics compare to human experts or other established methods?; Given its semi-automated nature, what is the required level of physician interaction or oversight for optimal diagnostic accuracy and reliability?; Are there any known limitations or contraindications for Myomics, particularly concerning specific cardiac conditions or patient demographics beyond adult populations?; How does Myomics integrate with existing hospital PACS systems and clinical workflows, and what are the data security measures in place for handling sensitive patient information?; Beyond the substantial equivalence determination, are there plans for post-market surveillance or further clinical trials to demonstrate long-term impact on patient outcomes?