AI Platform (AIP001) by Exo Inc is a software tool designed to help medical professionals assess ultrasound images of the heart and lungs in adult patients. It uses AI to detect and measure features of these images, aiding in quantification and reporting of important clinical parameters such as ejection fraction and lung artifacts, thus supporting diagnosis and treatment decisions in a clinical setting.
The AI Platform is intended for noninvasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of adult patients with suspected disease. The device is intended to be used on images from adult patients.
The device is a software as a medical device (SaMD) that imports DICOM ultrasound images, uses deep convolutional neural networks for segmentation or landmark detection, and provides tools for image viewing, landmark placement, and report generation specifically for cardiac and lung ultrasound imaging.
Performance was validated with clinical test data from multiple sites including diverse demographics. The cardiac function AI had 151 subjects, lung function AI had 125 subjects, and testing used independent datasets not involved in training. Performance metrics included intraclass correlation coefficients up to 0.95 for ejection fraction and reliability measures for lung artifact detection. Device performed consistently across subgroups and with various clinical confounders such as COPD and COVID-19.
No predicate devices specified
Submission
8/17/2023
FDA Approval
11/17/2023
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.