JLK-SDH is an AI-powered software that analyzes non-contrast CT head images to detect suspected subdural hemorrhage (SDH). It assists radiologists by notifying them of potential cases in a parallel workflow to standard care, enabling quicker communication and prioritization for specialist review. This helps clinicians promptly identify and manage patients with SDH, improving workflow efficiency and potentially patient outcomes. The device is intended for notification purposes only and does not replace diagnostic evaluation.
Intended Use
JLK-SDH is a notification-only, parallel workflow tool intended to assist trained radiologists to identify and communicate images of specific patients to a specialist, independent of the standard of care workflow, analyzing non-contrast CT images of the head for subdural hemorrhage (SDH).
Technology
JLK-SDH uses an AI-based convolutional neural network algorithm hosted on JLK servers to analyze DICOM non-contrast head CT images for suspected subdural hemorrhage. It provides notification-only, parallel workflow functionality and includes a mobile app for clinicians to view patient lists and preliminary, non-diagnostic images. The AI was trained on a diverse dataset from multiple countries and manufacturers, ensuring broad applicability.
Performance
Performance validation demonstrated high sensitivity (97.1%) and specificity (97.4%) for detecting SDH on non-contrast CTs using an independent dataset of 560 scans from multiple US clinical sites. Time to notification averaged 11.49 seconds, much faster than the predicate device, Viz SDH. Stratified performance showed consistent accuracy across demographics, scanners, and hemorrhage types. Testing followed FDA guidelines for software verification and validation.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
11/22/2024
3 months - 2
FDA Approval
3/3/2025
Other devices from JLK, Inc.
- JLK-AILink2025 • 510K
- JLK-ICH2025 • 510K
- JLK-PWI2024 • 510K
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.