Viz ICH

Viz ICH is a software tool that employs an artificial intelligence algorithm to analyze non-contrast CT (NCCT) images of the brain for suspected intracranial hemorrhage (ICH). Its purpose is to provide rapid notification to specialists, operating as a parallel workflow tool to expedite triage and review of critical cases in acute settings.

Viz ICH is a notification-only, parallel workflow software tool designed for hospital networks and trained clinicians. It utilizes an artificial intelligence algorithm to analyze non-contrast CT (NCCT) images of the brain, specifically in acute settings, to identify findings suggestive of intracranial hemorrhage (ICH). Upon detecting a suspected ICH, the system sends a notification to a pre-determined neurovascular or neurosurgical specialist, recommending review of the images. While images can be previewed through a mobile application, these are compressed and intended for informational purposes only, not for diagnostic use beyond notification; clinicians must view non-compressed images on a diagnostic viewer for care-related decisions. The performance of Viz ICH was evaluated in a retrospective study involving 261 NCCT scans. The image analysis algorithm demonstrated a sensitivity of 93% and a specificity of 90% in detecting ICH compared to ground truth established by neuro-radiologists, with an AUC of 0.96. A key finding was the significantly reduced time to specialist notification, averaging 0.49 minutes with Viz ICH compared to 38.2 minutes for standard care. Performance was also stratified by variables including clinical site, patient age, gender, ICH subtype (with SAH showing lower sensitivity), slice thickness, and ICH volume. The device is contraindicated for use with NCCT scans from manufacturers other than General Electric (GE) or its subsidiaries.

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. How does the AI algorithm's performance vary with subtle or atypical presentations of intracranial hemorrhage, and what is its false negative rate for ICH subtypes like Subarachnoid Hemorrhage where sensitivity was lower (60%)?; What are the specific technical reasons for the contraindication against non-GE scanners, and are there plans to validate the algorithm on images from other major CT manufacturers?; How does the Viz ICH system integrate with existing hospital Picture Archiving and Communication Systems (PACS) and Electronic Health Records (EHR) beyond DICOM image transfer?; What is the impact of image compression on the mobile application's preview, and what measures are in place to mitigate potential misinterpretation if clinicians inadvertently use it beyond initial notification awareness?; Beyond time-to-notification, what evidence exists or is being collected regarding the impact of Viz ICH on patient outcomes, such as reduced time to intervention or improved neurological recovery?