Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K202331

    Validate with FDA (Live)

    Date Cleared
    2021-02-02

    (169 days)

    Product Code
    Regulation Number
    878.4040
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Medical Face Masks are intended to be worn to protect both the patient and healthcare personnel from transfer of microorganisms, body fluids and particulate material. These face masks are intended for use in infection control practices to reduce the potential exposure to blood and body fluids. The Medical Face Masks are single use, disposable device, provided non-sterile.

    Device Description

    The Medical Face Mask is composed of three layers and is flat-pleated. The mask materials consist of an outer layer (spun-bond polypropylene), a middle layer (meltblown polypropylene), and an inner layer (spun-bond polypropylene). Each mask contains tie strings (spun-bond polypropylene) or ear loops (spandex elastic cord) to secure the mask over the users' mouth and face and includes a malleable nose piece (iron wire with white plastic covering) to provide a firm fit over the nose.

    AI/ML Overview

    The provided text describes the acceptance criteria and performance data for a Medical Face Mask, not an AI-powered diagnostic device. Therefore, the questions related to AI device performance metrics, such as human reader improvement with AI assistance, standalone algorithm performance, AI training/test set details, and expert adjudication, are not applicable to this document.

    However, I can extract the information relevant to the medical device's performance as described in the provided text.

    Here's a breakdown of the requested information based on the document:

    1. A table of acceptance criteria and the reported device performance

    Performance CharacteristicsAcceptance CriteriaTest Result
    Bacterial Filtration Efficiency Performance (%)≥9899.9%
    Differential Pressure (Delta-P) (mm H2O/cm²)<6.02.11mmH2O/cm²
    Particulate Filtration Efficiency at 0.1 micron Performance (%)≥9899.35%
    Resistance to penetration by synthetic blood, Minimum pressure in mmHg for pass results12032/32 passed at 120 mmHg
    Flammability ClassClass 1Class 1
    CytotoxicityIf viability is reduced to < 70% of the blank, it has a cytotoxic potential.Non-cytotoxic
    Irritation(0-0.4) negligible;(0.5-1.9) slight;(2-4.9) moderate;(5-8) severeNon-sensitizing
    SensitizationMagnusson and Kingman grades of 1 or greater in the test group generally indicate sensitization.Non-irritating

    2. Sample size used for the test set and the data provenance

    The document does not specify general "sample sizes" for the test sets in the typical sense of a clinical trial. Instead, it references specific test methodologies with their own inherent sample requirements. For example:

    • Resistance to penetration by synthetic blood (ASTM F1862): The result is "32/32 passed," indicating a sample size of 32 masks were tested.
    • For other tests (BFE, PFE, Delta-P, Flammability, Biocompatibility), the specific sample sizes used for the tests are not explicitly stated, but the methodology standards (e.g., ASTM F2101, F2299, etc.) would define these.

    Data Provenance: The document does not explicitly state the country of origin of the data for these performance tests. It mentions the manufacturer is Gemtier Medical (Shanghai) Inc. in China. The testing was non-clinical. The document implies these tests were conducted as part of the submission to the FDA. It does not mention if the data was retrospective or prospective, as these terms are typically reserved for clinical studies.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

    This question is not applicable. The device is a medical face mask, and its performance acceptance is based on objective, standardized laboratory tests (e.g., filtration efficiency, fluid resistance, biocompatibility), not on expert interpretations of data like in an AI diagnostic setting.

    4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

    Not applicable. This is a non-clinical device performance study based on standardized test methodologies, not a study involving human readers or subjective interpretations that would require adjudication.

    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

    Not applicable. This document pertains to the regulatory submission for a medical face mask, not an AI-assisted diagnostic device. No human reader studies (MRMC) were conducted or are relevant.

    6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

    Not applicable. This is not an algorithmic device. The performance data presented is for the physical medical face mask.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

    The "ground truth" for the device's performance is established by adherence to recognized international and national standards for medical face masks and biological evaluation. These standards define the specific methodologies and acceptance criteria for measuring characteristics like bacterial filtration efficiency, particulate filtration efficiency, fluid resistance, flammability, and biocompatibility. For example:

    • ASTM F2100, ASTM F1862, ASTM F2299, ASTM F2101, MIL-M-36954C, 16 CFR Part 1610 (for physical properties)
    • ISO 10993-1, ISO 10993-5, ISO 10993-10 (for biological evaluation)

    The performance results are objectively measured against these predefined thresholds, rather than based on subjective expert consensus, pathology, or outcomes data.

    8. The sample size for the training set

    Not applicable. This is a physical medical device, not an AI system that requires a training set.

    9. How the ground truth for the training set was established

    Not applicable. As this is not an AI system, there is no training set or associated ground truth establishment process.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1