Search Results

ClearRead Xray Pneumothorax is a notification-only triage workflow tool for use by trained professionals to help prioritize chest X-rays. The device operates in parallel to and independent of standard of care image interpretation workflow. Specifically, the device uses an artificial intelligence algorithm to analyze images for features suggestive of a pneumothorax 5 mm or larger; it makes case-level output available to a PACS/workstation for worklist prioritization or triage. Identification of cases suspected of containing a pneumothorax is not for diagnostic use beyond notification. ClearRead Xray Pneumothorax is limited to analysis of imaging data as a guide to possible urgency of adult chest X-ray image review and should not be used in lieu of full patient evaluation or relied upon to make or confirm diagnoses. The device does not replace review and diagnosis of the Xrays by trained professionals. The device is not intended to be used with plain film X-ray.

ClearRead Xray Pneumothorax is comprised of a computer assisted triaging tool, designed to prioritize chest X-rays based on the suspected presence of a pneumothorax (PTX) 5mm or larger. ClearRead Xray Pneumothorax requires both lungs to be in the field of view. ClearRead Xray Pneumothorax provides adjunctive information and is not intended to be used for diagnosis. ClearRead Xray Pneumothorax receives images according to the DICOM® protocol (via a standard IEEE 802.3 network connection), processes the image, and delivers the resulting information through the same DICOM network interface. Image inputs are limited to adult, digital frontal chest radiographs. The output results are sent to facilitate prioritization of chest Xrays for radiologist review on one or more devices that conform to the ClearRead Xray Pneumothorax DICOM Conformance Statement. ClearRead Xray Pneumothorax does not support printing or DICOM media.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Device: ClearRead Xray Pneumothorax (K213566)

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" per se. However, it indicates key performance metrics that were measured and met through the clinical evaluation. The primary objective was to demonstrate the device meets or exceeds expected performance. The specific metrics, measured on an independent test set, and their reported values are:

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

• Test Set Sample Size:

  • Clinical Evaluation: A total of 1138 cases were used.
    • 1028 cases from MIMIC-CXR (419 PTX positive, 609 PTX negative)
    • 110 cases from Georgetown University Medical Center (GUMC) (40 PTX positive, 70 PTX negative)
  • Internal Test Set (Benchmarking): 600 cases (300 negatives and 300 positives). This test set was separate from the internal "development set."

• Data Provenance:

  • MIMIC-CXR: Collected from 2011 to 2016 at Beth Israel Deaconess Medical Center, USA. This is a controlled online dataset.
  • Georgetown University Medical Center (GUMC): Collected between 2002 to 2013, USA.
  • The clinical evaluation used retrospective adult patient images from multiple sources. The data was explicitly stated to be independent data, not used for training or internal validation.

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

• Number of Experts: Three (3)
• Qualifications: Senior board-certified radiologists with expertise in thoracic radiology.

4. Adjudication Method for the Test Set

The ground truth for the test set was established by a majority voting rule from the expert panel. Each expert independently reviewed the PA/AP image and associated radiology reports. The final image label (PTX positive/negative) and associated annotations (bounding boxes for PTX) were derived from this majority vote. If a true positive case, the associated annotation bounding boxes were replaced with a single box that enclosed all bounding boxes agreed upon by the majority. This resembles a "3-reader majority" consensus.

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

No MRMC comparative effectiveness study was described in the provided text. The study focused on the standalone (algorithm-only) performance of the device as a triage tool. The "Indications for Use" explicitly state it is a "notification-only triage workflow tool" and "operates in parallel to and independent of standard of care image interpretation workflow." It also states, "The device does not replace review and diagnosis of the X-rays by trained professionals." Therefore, it's not designed for human-in-the-loop performance improvement but rather for workflow prioritization.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance study was done. The reported AUC, Sensitivity, Specificity, and Time to Notification are all measures of the algorithm's performance without human intervention. The study describes "The ClearRead Xray Pneumothorax system was run on all selected images... Machine indications were transferred to the statistical analysis team and used as the basis for performance assessment."

7. Type of Ground Truth Used

The ground truth used for the clinical evaluation (test set) was expert consensus.

• This was based on the visual inspection of image data by three expert radiologists.
• It was further supported by available radiology reports.
• For true positive cases, annotations (bounding boxes) were included.

8. Sample Size for the Training Set

The document does not specify an exact numerical sample size for the training set. It mentions:

• "All models used by the ClearRead Xray Pneumothorax system were trained with cases that were clinically validated as negative for pneumothorax, and cases labeled as positive via a simulated data construction process."
• "This included the publicly available data from the NIH, as hosted by Kaggle, wherein experts outlined proven pneumothoraces for thousands of images."
• "Importantly, this also included over 7000 confirmed negatives cases."

Therefore, the training set included:

• Thousands of images with expert-outlined pneumothoraces from NIH/Kaggle.
• Over 7000 confirmed negative cases.
• Simulated data: Synthetically generated positive cases by inserting pneumothoraces into negative cases.

9. How Ground Truth for the Training Set Was Established

The ground truth for the training set was established using a hybrid approach:

• Real Data:
  • For real positive cases (pneumothoraces), ground truth was established by clinical experts who "hand-drew outlines" of proven pneumothoraces (e.g., from the NIH/Kaggle dataset).
  • For real negative cases (no pneumothoraces), ground truth was established by being "clinically validated as negative." (This likely implies expert review or clinical reports confirming absence of PTX).
• Simulated Data:
  • For simulated positive cases, the ground truth was arrived at via construction. This means the synthetic pneumothoraces were digitally inserted into negative cases, and their location and size were precisely known by design.

Ask a specific question about this device