JLK-ICH is an AI-powered software that analyzes non-contrast CT scans of the head to detect suspected intracranial hemorrhage. It provides automated notifications to clinicians to prioritize review, allowing faster communication and potentially improving patient outcomes. The software works alongside standard care without replacing diagnostic evaluations.
Intended Use
A radiological computer-aided triage and notification software indicated for use in the analysis of non-contrast CT images of the head to detect intracranial hemorrhage, providing notification to clinicians to assist hospital networks in identifying and communicating images to specialists, parallel to standard workflow.
Technology
Utilizes an AI/ML algorithm hosted on servers to analyze non-contrast CT scans of the head, compatible with DICOM standards, with results sent through a mobile application for notification. The system enables non-diagnostic image preview on mobile and supports efficient triage with a mean notification time of 0.19 minutes.
Performance
Performance validation included a retrospective study of 376 NCCT head scans (188 positive, 188 negative) compared against ground truth by US board-certified neuroradiologists, yielding sensitivity of 97.3%, specificity of 97.9%, and AUC of 0.978. Time-to-notification averages 0.19 minutes, surpassing the predicate device (Viz ICH). Performance was consistent across patient age, gender, race-ethnicity, scanner manufacturer, slice thickness, ICH subtype, and ICH volume categories.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
10/29/2024
2 months - 2
FDA Approval
1/3/2025
Other devices from JLK, Inc.
Ready to Sharpen Your Edge?
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.