LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K242292
    Device Name
    uAI Easy Triage ICH
    Manufacturer
    Shanghai United Imaging Intelligence Co., Ltd.
    Date Cleared
    2024-09-24

    (53 days)

    Product Code
    QAS
    Regulation Number
    892.2080
    Type
    Traditional
    Panel
    Radiology
    Reference & Predicate Devices
    K221716
    Why did this record match?
    Device Name :

    uAI Easy Triage ICH

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

    uAl Easy Triage ICH is a radiological computer-assisted triage and notification software device indicated for analysis of non-enhanced head CT images. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and prioritizing studies with suspected positive findings of Intracranial Hemorrhage (ICH).

    Device Description

    uAI Easy Triage ICH is a radiological computer-assisted triage and notification software intended to assist radiologists by flagging potential intracranial hemorrhage (ICH) in non-contrast head CT images. The Triage Software is a component of the uAI Easy Triage platform, a comprehensive medical imaging communication system designed to integrate and deploy specialized image processing applications.

    The uAI Easy Triage ICH algorithm uses artificial intelligence CNN (convolutional neural networks) and advanced image processing to triage the non-contrast CT images for suspicious intracranial hemorrhage.

    The uAI Easy Triage ICH alerts users to new studies with suspicious ICH findings via pop-up notifications. The software provides both active and passive notification mechanisms. Active notifications are presented as an alert icon with a count of pending cases, and an alert status bar displaying patient details, suspected findings, and the time of examination. Passive notifications are represented by an icon beside the patient's name in the list for cases with detected ICH findings. Additionally, the application offers a DICOM image preview feature for radiologists to review. This preview is strictly informational, devoid of diagnostic markers, and is not to be used for definitive diagnosis.

    The uAI Easy Triage ICH embodies the core algorithmic technology that identifies image characteristics consistent with intracranial hemorrhage. The application reads DICOM files, verifies their compatibility with the prescribed acquisition protocols, executes the triage algorithm, and communicates findings in DICOM format, compatible with the uAI Easy Triage Platform.

    AI/ML Overview

    Acceptance Criteria and Study Details for uAI Easy Triage ICH

    1. Acceptance Criteria and Reported Device Performance

    MetricAcceptance CriteriaReported Device Performance (95% CI)
    Sensitivity≥ 80%92% (86%-96%)
    Specificity≥ 80%95% (90%-98%)
    Time to NotificationNot explicitly stated as a numerical criterion, but noted as "similar to the predicate device's time"41.1 seconds (40.1, 42.1) (mean with 95% CI)

    Note: The document does not explicitly state a numerical acceptance criterion for "Time to Notification" but indicates that the device's performance is similar to the predicate device. The 80% acceptance criteria for sensitivity and specificity are mentioned in the text "exceeding the acceptance criteria of 80%."

    2. Sample Size for Test Set and Data Provenance

    • Sample Size: 295 non-contrast CT scans (studies)
      • 147 positive for ICH
      • 148 negative for ICH
    • Data Provenance: Retrospective data obtained from different zip codes across four U.S. states.

    3. Number of Experts and Qualifications for Ground Truth Establishment

    • Number of Experts: 3 U.S.-board-certified neuroradiologists.
    • Qualifications: U.S.-board-certified neuroradiologists. Specific years of experience are not mentioned.

    4. Adjudication Method for the Test Set

    • Adjudication Method: Majority read of the 3 U.S.-board-certified neuroradiologists. (Implies a "3+1" or similar consensus approach where at least two out of three experts agreed to establish the ground truth).

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

    • The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to assess human reader improvement with AI assistance. The study focuses on the standalone performance of the AI algorithm.

    6. Standalone Algorithm Performance

    • Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The reported sensitivity, specificity, and time to notification are for the uAI Easy Triage ICH software itself, compared to the expert-established ground truth.

    7. Type of Ground Truth Used

    • Expert Consensus: The ground truth was established by the majority read of 3 U.S.-board-certified neuroradiologists.

    8. Sample Size for the Training Set

    • Sample Size: 9791 data points (cases) were collected for training and internal testing.

    9. How Ground Truth for the Training Set was Established

    • The ground truth for the training set was established in the form of ICH positive/negative by radiologists. Specific details on the number or qualifications of these radiologists, or the adjudication method, are not provided for the training set.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1