HealthVCF is a software solution that uses artificial intelligence to analyze chest and abdominal CT scans to detect suspected vertebral compression fractures. It helps clinicians prioritize these cases for review within bone health programs by flagging them in a dedicated workstation application without interfering with the standard radiology workflow. The product aims to improve the speed of identifying at-risk patients but does not provide a diagnosis itself.
HealthVCF is a passive notification software tool used by clinicians to prioritize patients for suspected vertebral compression fractures via AI analysis of chest and abdominal CT scans. It flags exams suggestive of vertebral compression fractures for clinician review in Bone Health and Fracture Liaison Service programs, viewed via PACS worklist, without providing diagnostic information or replacing full patient evaluation.
HealthVCF uses an AI algorithm to analyze chest and abdominal CT scans, operates as a parallel workflow tool to standard radiology, and provides passive notification of suspected vertebral compression fractures through a standalone Zebra Worklist application. It validates data inputs, processes studies for suspected fractures, and sends flagged results for clinician prioritization without altering the radiology workflow or providing diagnosis.
A retrospective study of 611 anonymized chest and abdominal CT cases (306 positive for vertebral compression fractures, 305 negative) was used to validate HealthVCF. Ground truth was established by three board-certified radiologists. The system achieved an AUC of 0.9504, sensitivity of 90.20%, and specificity of 86.89%, meeting accuracy goals and demonstrating substantial equivalence to its predicate device. The average analysis time was 61.36 seconds, comparable to the predicate.
No predicate devices specified
Submission
10/15/2019
FDA Approval
5/12/2020
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.