LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K220499
    Device Name
    Rapid PE Triage and Notification (PETN)
    Manufacturer
    iSchemaView Inc.
    Date Cleared
    2022-05-17

    (84 days)

    Product Code
    QAS
    Regulation Number
    892.2080
    Type
    Traditional
    Panel
    Radiology
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Device Name :

    Rapid PE Triage and Notification (PETN)

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Rapid PE Triage and Notification (PETN) is a radiological computer aided triage and notification software indicated for use in the analysis of CTPA images. The device is intended to assist hospital networks and trained clinicians in workflow triage by flagging and communication of suspected positive findings of central pulmonary embolism (PE) pathology in adults. The software is only intended to be used on single-energy exams.

    Rapid PETN uses an artificial intelligence algorithm to analyze images and highlight cases with detected findings on a server or standalone desktop application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected findings. Notifications include compressed preview images that are meant for informational purposes only and not intended for diagnostic use beyond notification. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

    The results of Rapid PETN are intended to be used in conjunction with other patient information and based on ther professional judgment, to assist with trage/proritization of medical images. Notified clinicians are responsible for viewing full images per the standard of care. Rapid PETN is validated for use on GE, Siemens and Toshiba scanners.

    Device Description

    Rapid PETN is a radiological computer-assisted triage and notification software device. The Rapid PETN module is a contrast enhanced CTPA processing module which operates within the integrated Rapid Platform to provide triage and notification of suspected Central Pulmonary Emboli (PE). The PETN module is an AI/ML module. The output of the module is a priority notification to clinicians indicating the suspicion of central PE based on positive findings. The Rapid PETN module uses the basic services supplied by the Rapid Platform including DICOM processing, job management, imaging module execution and imaging output including the notification and compressed image.

    AI/ML Overview

    Here's a summary of the acceptance criteria and study details for iSchemaView Inc.'s Rapid PE Triage and Notification (PETN) device, based on the provided text:

    1. Acceptance Criteria and Reported Device Performance

    The acceptance criteria were defined by the primary endpoint of the standalone performance validation study.

    Acceptance Criteria (Primary Endpoint)Reported Device Performance
    Sensitivity ≥ 0.96 (presumably lower bound of CI)0.96 (95% CI: 0.92 - 0.98)
    Specificity ≥ 0.89 (presumably lower bound of CI)0.89 (95% CI: 0.83 - 0.93)
    Processing Time (Secondary Endpoint)2.64 minutes (2.34-4.80 min)

    2. Sample Size and Data Provenance

    • Test Set (Final Performance Validation): 306 CTPA cases.
    • Data Provenance: The text does not explicitly state the country of origin. It mentions "multiple sites" for the development data. The study appears to be retrospective as it uses existing CTPA cases.

    3. Number of Experts and their Qualifications for Ground Truth

    • Number of Experts: 3 experts
    • Qualifications: The document does not explicitly state the qualifications (e.g., radiologist with specific experience) of these experts.

    4. Adjudication Method for the Test Set

    • The ground truth was established by "3 experts using a 2:3 confirmation." This indicates a consensus-based approach where at least two out of three experts had to agree for a particular finding to be considered ground truth.

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

    • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned. The study focused on the standalone performance of the AI algorithm for triage and notification, not on how human readers' performance improved with AI assistance.

    6. Standalone Performance (Algorithm Only)

    • Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The "Final device validation included standalone performance validation."

    7. Type of Ground Truth Used

    • The ground truth was established by expert consensus (3 experts using a 2:3 confirmation).

    8. Sample Size for the Training Set

    • Algorithm Development (Training and Development Validation): 600 CTPA cases (300 Positive, 300 Negative).
    • Training Cases: 480 cases (240 Positive, 240 Negative).
    • Additionally: An extra 276 negative cases were included to further assess specificity. It's not explicitly stated if these were solely for development validation or also incorporated into a later training phase, but their purpose was for model assessment.

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

    • The document implies that the ground truth for the 600 cases used in algorithm development (training and initial validation) was established in a similar manner to the final validation, but it doesn't explicitly detail the method (e.g., number of experts, adjudication) for the training set itself. Given the context of medical device development, it is highly probable that ground truth for the training set was also established by expert review, likely with a consensus process, to ensure high-quality labels for model training.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1