NeuroICH is a software tool designed to analyze non-contrast CT scans of the head using artificial intelligence to detect signs of intracranial hemorrhage. It provides notifications to specialist clinicians via a mobile app, helping to prioritize patient care without replacing standard diagnostic procedures.
NeuroICH is a notification-only, parallel workflow tool for hospital networks and trained clinicians to identify and communicate images of suspected intracranial hemorrhage (ICH) patients to specialists, independent of standard of care workflow. It uses an AI algorithm to analyze non-contrast CT images of the head acquired in the acute setting to detect findings suggestive of ICH and notify clinicians with non-diagnostic preview images via a mobile application, without altering original images or serving as a diagnostic device.
NeuroICH is a software-only tool consisting of a cloud-hosted image analysis deep learning AI algorithm analyzing non-contrast head CT studies for ICH features and a mobile application for notifications and preview images. It operates in parallel to standard care without altering or removing original medical images and does not segment or highlight specific image areas. It is substantially equivalent to the predicate device Viz ICH with similar workflow and notification functionality.
Performance was evaluated retrospectively on 376 non-contrast head CT studies with 35.9% ICH positive cases. Sensitivity was 94.81% and specificity 92.53%, meeting pre-specified goals and comparable to the predicate device. Time to notification averaged 0.37 minutes, much faster than standard care's 18.3 minutes. Sub-analyses showed consistent performance across age, gender, scanner models, hemorrhage subtypes, and CT slice thicknesses.
No predicate devices specified
Submission
6/14/2024
FDA Approval
11/7/2024
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.