DrAid for Radiology v1 is an AI-based software tool that analyzes adult chest X-rays to identify features indicative of pneumothorax. It helps prioritize cases in the radiology workflow by notifying the system of potentially critical images, assisting clinicians in timely review without providing direct diagnoses or replacing clinical judgment.
A radiological computer-assisted triage & notification software product designed to aid the clinical assessment of adult Chest X-Ray cases with features suggestive of pneumothorax in medical care environment. DrAid analyzes cases using an artificial intelligence algorithm to features suggestive of suspected findings. It makes case-level output available to a PACS for worklist prioritization or triage.
DrAid is a software module that receives chest X-ray images from PACS or radiological imaging equipment, de-identifies the images, and uses an AI algorithm to analyze frontal chest X-rays for suspected pneumothorax. It provides passive notification flags via API to the PACS/workstation to prioritize cases. The software does not remove or reorder cases, and results are not intended for stand-alone clinical decision making.
Performance testing was conducted on separate datasets: 565 NIH chest X-rays representing the US population and 285 chest X-rays from four Vietnamese hospitals with different scanner types. The device showed high sensitivity (~94.6%), specificity (~97.6%), and AUC (~96.1%) for pneumothorax detection, comparable to the predicate device. Average processing and notification time is approximately 3.83 minutes.
No predicate devices specified
Submission
4/29/2022
FDA Approval
9/1/2022
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.