The Behold.ai Red Dot device is an AI-powered software platform that assists radiologists by automatically analyzing adult chest X-ray images to identify suspected pneumothorax cases. It integrates into clinical workflows by notifying radiologists through PACS or workstation systems to prioritize these cases for faster review. It is intended to support, but not replace, clinical decision-making.
The red dot™ software platform is a software workflow tool designed to aid the clinical assessment of adult Chest X-Ray cases with features suggestive of Pneumothorax in the medical care environment. It analyzes cases using an artificial intelligence algorithm to identify suspected findings. It makes case-level output available to a PACS/workstation for worklist prioritization or triage. It is not intended for standalone clinical decision-making or to rule out pneumothorax.
The device uses Artificial Intelligence and pattern recognition technology to analyze frontal chest X-rays. It receives DICOM images, validates and anonymizes them, and then applies a visual recognition AI algorithm to detect suspected pneumothorax findings. Results are sent in a JSON message to PACS/workstation systems for case prioritization without altering the original image or marking specific areas.
Performance testing involved retrospective evaluation of 888 chest X-rays from multiple clinical sites in the US and UK, with 299 pneumothorax-positive cases. The device achieved an AUROC of 0.975, accuracy of 90.20%, sensitivity of 94.65%, and specificity of 87.95%. Processing time averaged 13.8 seconds, with total notification time (including transmission) averaging 29.3 seconds, comparable to the predicate device.
No predicate devices specified
Submission
6/12/2019
FDA Approval
2/28/2020
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.