Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K972688
    Date Cleared
    1997-09-08

    (63 days)

    Product Code
    Regulation Number
    866.1640
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    To determine gram-positive bacterial susceptibility against the antimicrobial agent Levofloxacin. Organisms with indications for testing* include:

    Levofloxacin Gram-Positive Bacteria Enterococcus faecalis Staphylococcus aureus Streptococcus pyogenes

    • As taken from the Indications and Usage section of the manufacturers' package insert (Ortho-McNeil).
    Device Description

    Microdilution Minimum Inhibitory Concentration (MIC) Panels, MicroScan® Dried Gram-Positive MIC/Combo Panels

    AI/ML Overview

    Acceptance Criteria and Device Performance for MicroScan® Dried Gram-Positive MIC/Combo Panels with Levofloxacin

    This report details the acceptance criteria and the study demonstrating the performance of the MicroScan® Dried Gram-Positive MIC/Combo Panels with Levofloxacin, as described in the 510(k) submission K972688.

    1. Acceptance Criteria and Reported Device Performance

    The acceptance criteria for this device are based on the FDA DRAFT document "Review Criteria for Assessment of Antimicrobial Susceptibility Devices" (dated May 31, 1991). The primary metric used is Essential Agreement.

    Acceptance Criteria (Essential Agreement)Reported Device Performance (Essential Agreement)
    Defined by FDA DRAFT document99.4%

    Note: The specific numerical threshold for "acceptable" Essential Agreement from the FDA DRAFT document is not explicitly stated in the provided text, but the reported 99.4% was deemed acceptable by the FDA.

    2. Sample Size and Data Provenance for the Test Set

    • Sample Size: The exact number of isolates used in the "external evaluations" (test set) is not specified. However, the evaluation included "fresh and stock Efficacy isolates and stock Challenge strains."
    • Data Provenance: The document does not explicitly state the country of origin. The study was conducted by Dade MicroScan Inc. in West Sacramento, CA, suggesting the data was likely generated within the United States. The study appears to be retrospective for the stock isolates and challenge strains, and possibly includes prospective components for "fresh" efficacy isolates.

    3. Number, Qualifications, and Adjudication Method of Experts for Ground Truth

    • Number of Experts: The document does not specify the number of individual experts used to establish ground truth.
    • Qualifications of Experts: Not specified.
    • Adjudication Method: Not applicable. The ground truth was established by comparing the device's performance to an NCCLS frozen Levofloxacin Reference Panel, which serves as the gold standard, rather than relying on human expert consensus.

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

    An MRMC comparative effectiveness study was not performed as this device is an automated in vitro diagnostic for determining antimicrobial susceptibility, not a device requiring human interpretation of complex cases. Therefore, the effect size of human readers improving with AI vs. without AI assistance is not applicable.

    5. Standalone Performance Study

    Yes, a standalone performance study was done. The entire premise of the 510(k) submission and the "external evaluations" was to demonstrate the performance of the MicroScan® Dried Gram-Positive MIC/Combo Panel with Levofloxacin (the algorithm/device) against a reference standard without human intervention in the result interpretation.

    6. Type of Ground Truth Used

    The type of ground truth used was a reference standard: an NCCLS frozen Levofloxacin Reference Panel. This panel is considered the gold standard for susceptibility testing for comparison purposes.

    7. Sample Size for the Training Set

    The document does not specify a separate "training set" or its sample size. The product being validated is a panel for susceptibility testing, and the development process likely involved internal optimization and validation, but specific data used for "training" in the modern AI sense is not described. The provided information focuses on the validation of the final product.

    8. How Ground Truth for the Training Set Was Established

    As a distinct "training set" is not explicitly mentioned, the method for establishing its ground truth is also not described. For the overall development and validation, the ground truth would have been established by comparison to reference methods, similar to the validation process itself (e.g., NCCLS reference panels).

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1