BraveCX
Bering LtdBraveCX is an AI-based software that analyzes adult chest X-ray images to detect pleural effusion and pneumothorax. It helps radiologists prioritize cases with suspected critical findings by flagging suspicious images in the PACS worklist, enhancing workflow efficiency without providing direct diagnostic decisions.
Intended Use
BraveCX is a radiological computer-assisted triage and notification software that analyzes adult (≥18 years old) chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax). The software provides case-level outputs available in the PACS/workstation for worklist prioritization or triage and does not send proactive alerts directly to specialists.
Technology
BraveCX uses deep learning AI to analyze DICOM chest X-ray images, is deployable as an API either on cloud or on-premises, and integrates with PACS or other DICOM storage. Outputs are flags in the worklist indicating suspicion of pleural effusion or pneumothorax, with no image markup, and notifications generated within 15 minutes after interpretation.
Performance
BraveCX achieved high performance in detecting pleural effusion and pneumothorax with ROC AUC >0.95, sensitivities around 82-89%, and specificities around 90-97% in both internal and external non-clinical validation datasets. Testing included diverse datasets and compared favorably to the predicate device Lunit INSIGHT CXR Triage. Average notification time is approximately 10 seconds, faster than the predicate.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
12/15/2022
10 months - 2
FDA Approval
11/9/2023
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.