Search Results

The Zebra Pneumothorax device 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. HealthPNX 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. HealthPNX is not intended to direct attention to specific portions or anomalies of an image. Its results are not intended to be used on a stand-alone basis for clinical decision-making nor is it intended to rule out Pneumothorax or otherwise preclude clinical assessment of X-Ray cases.

Zebra's HealthPNX is a radiological computer-assisted triage and notification software system. The software automatically analyzes PA/AP chest x-rays and alerts the PACS/workstation once findings suspicious of pneumothorax are identified.

The following modules compose the HealthPNX software system:

Data input and validation: After a chest x-ray has been performed, a copy of the study is automatically retrieved and processed by the HealthPNX device. Following retrieval of a study, the validation feature assesses the input data (i.e. age, modality, view) to ensure compatibility for processing by the algorithm.

HealthPNX algorithm: Once a study has been validated, the algorithm analyzes the frontal chest x-ray for detection of suspected findings suggestive of pneumothorax.

IMA Integration feature: The study analysis and the results of a successful study analysis is provided to IMA, that notifies the PACS/workstation through the worklist interface.

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.

The radiologist is then able to review the study earlier than in standard of care workflow.

In summary, the HealthPNX device is intended to provide a passive notification through the PACS/workstation to the radiologists indicating the existence of a case that may potentially benefit from the prioritization. It doesn't output an image and therefore it does not mark, highlight, or direct users' attention to a specific location on the original chest X ray.

The device aim is to aid in prioritization and triage of radiological medical images only.

Here's a breakdown of the acceptance criteria and study details for the HealthPNX device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size for Test Set: 588 anonymized Chest X-Ray cases (146 pneumothorax positive, 442 pneumothorax negative).
• Data Provenance: Retrospective cohort from the USA and Israel.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Three (3) US Board Certified Radiologists.
• Qualifications: US Board Certified Radiologists. Years of experience are not specified.

4. Adjudication Method for the Test Set

The provided text states that "The validation data set was truthed (ground truth) by three US Board Certified Radiologists (truthers)." It does not explicitly detail an adjudication method like 2+1 or 3+1. This implies that the consensus of these three radiologists established the ground truth, but the specific rules (e.g., majority vote, unanimous) are not described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

• Yes, an MRMC-like study was done. The text states: "The triage effectiveness was evaluated by three different US Board Certified Radiologists (readers) that read these cases prospectively in real time with the HealthPNX device (HealthPNX prioritized work-list) and without (standard of care, 'First-in-First-out' or 'FIFO' queue) with a washout period separating between the two read periods with and without the HealthPNX device."
• Effect Size of Human Readers' Improvement:
  • Without AI (Standard of Care): Mean triage time of 68.98 minutes (95% CI: [60.53, 77.43] minutes).
  • With AI (HealthPNX): Mean triage time of 8.05 minutes (95% CI: [5.93, 10.16] minutes).
  • Improvement (Reduction): 60.93 minutes. This represents a statistically significant reduction in triage time for time-sensitive images.

6. If a Standalone Study (Algorithm Only) Was Done

• Yes, a standalone study was done. The text explicitly states: "The stand-alone detection accuracy was measured on this cohort respective to ground truth." and "Overall, the HealthPNX was able to demonstrate an area under the curve (AUC) of 98.3% (95% CI: [97.40%, 99.02%])".

7. The Type of Ground Truth Used

• Expert Consensus: The ground truth for the test set was established by three (3) US Board Certified Radiologists.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size for the training set. It only discusses the validation/test set.

9. How the Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for the training set was established. It only describes the process for the validation/test set.

Ask a specific question about this device