Search Results

HealthVCF is a passive notification for prioritization-only, parallel-workflow software tool used by clinicians to prioritize specific patients within the standard-of-care bone health setting for suspected vertebral compression fractures. HealthVCF uses an artificial intelligence algorithm to analyze chest and abdominal CT scans and flags those that are suggestive of the presence of at least one vertebral compression at the exam level. These flags are viewed by the clinician in Bone Health and Fracture Liaison Service programs in the medical setting via a worklist application on their Picture Archiving and Communication System (PACS). HealthVCF does not send a proactive alert directly to the user.

Health VCF does not provide diagnostic information beyond triage and prioritization, it does not remove cases from the radiology worklist, and should not be used in place of full patient evaluation, or relied upon to make or confirm diagnosis.

Zebra's HealthVCF solution is a software product that automatically identifies suspected findings suggestive of vertebral compression fractures on chest and abdominal CT scans and provides a passive notification to the workstation of the presence of this finding in the scan. This notification is received by the standalone desktop Zebra Worklist application which flags the identified scan and assists clinicians engaged in bone-health management in viewing the scan ahead of others. The device aim is to aid in prioritization and triage of radiological medical images only and does not provide diagnostic information beyond triage.

The software uses an artificial intelligence algorithm to automatically analyze chest and abdominal CT scans. If a suspected vertebral compression fracture is found in a scan, the alert is automatically sent to the Zebra Worklist application on the workstation used by the bone-health clinician in parallel with the ongoing standard of care within the bone health setting. The standard of care radiology workflow (i.e. reviewing and reporting the findings that initiated the request for CT) continues unaffected by the parallel workflow of the bone health program. For clarity, the HealthVCF device does not flag/prioritize cases within this radiology workflow. The standalone desktop application, Zebra Worklist, includes three sagittal preview images meant for informational purposes only and is not intended for diagnostic use. The Zebra Worklist presents all cases processed by the algorithm, and flags those with a suspected finding.

Zebra's HealthVCF device works in parallel to and in conjunction with the standard care of workflow within bone health programs, and completely independent of the standard of care workflow within the radiology department. After a chest or abdominal CT scan has been performed, a copy of the study is automatically retrieved and processed by the HealthVCF device. The device performs the analysis of the study and returns a notification about a suspected vertebral compression fractures to the Zebra Worklist to notify the clinicians in Bone Health and Fracture Prevention Programs reviewing the chest and abdominal CTs for at-risk patients. The clinician is then able to review the study earlier and recall the patient for further evaluation.

The primary benefit of the product is the ability to reduce the time it takes to alert physicians to the presence of a finding such as a vertebral compression fracture. The software does not recommend treatment or provide a diagnosis. It is meant as a tool to assist in improved workload prioritization of cases in bone health and fracture prevention programs. The final diagnosis is provided by a clinician after reviewing the scan itself.

The following modules compose the HealthVCF software:

Data input and validation: Following retrieval of a study, the validation feature assessed the input data (i.e. age, modality, view) to ensure compatibility for processing by the algorithm.
HealthVCF algorithm: Once a study has been validated, the algorithm analyzes the chest and abdominal CT scans for detection of suspected finding suggestive of vertebral compression fracture.
IMA Integration feature: The study analysis and the results of a successful study analysis is provided to IMA, to then be sent to Zebra Worklist application for triaging.
Error codes feature: In the case of a study failure during data validation or the analysis by the algorithm, an error is provided to the system.

Here's a breakdown of the acceptance criteria and the study proving the HealthVCF device meets them, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states the AUC performance goal was >95%, and the device achieved 0.9504, indicating it met this goal. The sensitivity and specificity figures were reported for "this operating point" but the specific thresholds for these points as acceptance criteria are not explicitly stated, beyond the general concept of "accuracy performance goals."

2. Sample Size and Data Provenance for the Test Set

• Sample Size: A retrospective cohort of 611 anonymized Chest and abdominal CT cases.
  • 306 cases positive for vertebral compression fractures (severe and moderate fractures).
  • 305 cases negative for vertebral compression fractures (mild or no fracture), including confounding imaging factors.
• Data Provenance: Retrospective, from the USA and Israel.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three experts were used to establish ground truth.
• Qualifications: All three experts were US Board-Certified Radiologists. Their years of experience are not specified in the provided text.

4. Adjudication Method for the Test Set

The document explicitly states that the validation data set was "truthed (ground truth) by three US Board-Certified Radiologists." It does not specify the exact adjudication method (e.g., 2+1, 3+1 consensus, majority vote) beyond stating that three radiologists established the ground truth. There is no mention of "none" for adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was mentioned. The study focused on the standalone performance of the HealthVCF device against ground truth, not on how human readers' performance improved with AI assistance.

6. Standalone Performance (Algorithm Only)

Yes, a standalone (i.e., algorithm only without human-in-the-loop performance) study was conducted. The document states, "The standalone detection accuracy was measured on this cohort respective to the ground truth."

7. Type of Ground Truth Used

The type of ground truth used was expert consensus (from three US Board-Certified Radiologists).

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set. It only describes the validation/test set.

9. How Ground Truth for the Training Set Was Established

The document does not specify how ground truth for the training set was established. It only details the ground truthing process for the independent validation/test set.

Ask a specific question about this device