Intended Use

Software workflow tool designed to aid the clinical assessment of adult chest X-ray cases with features suggestive of pleural effusion and pneumoperitoneum in the medical care environment. It analyzes cases using an AI algorithm to identify findings and provides case-level output to PACS or RIS for worklist prioritization or triage.

Technology

The device uses a deep learning convolutional neural network AI algorithm trained on diverse chest X-ray datasets to identify pleural effusion and pneumoperitoneum. It integrates with image and order management systems like PACS/RIS to automatically analyze studies and notify for triage prioritization. Ground truth for training and validation was established by board-certified radiologists.

Performance

Standalone performance was validated on 1269 independent chest X-rays showing high accuracy (AUC ~0.98 for pleural effusion and 0.97 for pneumoperitoneum) with strong sensitivity and specificity values across operating points. Triage effectiveness showed average turn-around time under 30 seconds. These results demonstrate safety, effectiveness, and substantial equivalence to a predicate device.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    7/22/2022

    8 months
  • 2

    FDA Approval

    3/28/2023

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.