Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K232980
    Manufacturer
    Date Cleared
    2024-03-14

    (175 days)

    Product Code
    Regulation Number
    884.6160
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The SpermAlign Sperm Separation Device is intended for preparing motile sperm from semen for use in the treatment of infertile couples by intracytoplasmic sperm injection (ICSI) and in vitro fertilization (IVF) procedures.

    Device Description

    SpermAlign is a sperm separation device used to prepare motile sperm for assisted reproductive technology (ART) procedures. Separation is achieved through a fluid filled microstructure which guides the motile sperm to the central collection outlet isolating it from the remaining sample. The device utilizes a total processing volume of 180ul of liquefied semen added in 30ul aliquots to each of the six outer wells and sperm washing media added to the central well. Following incubation for 30 minutes, the concentrated motile sperm is withdrawn from the central well and may be used directly in intracytoplasmic sperm injection (ICSI) or in vitro fertilization (IVF) procedures.

    SpermAlign is sterilized using X-Ray irradiation and has a sterility assurance level (SAL) of 10-6. The devices are individually packaged and for single use only.

    AI/ML Overview

    The provided document is a 510(k) summary for the SpermAlign Sperm Separation Device, indicating substantial equivalence to a predicate device. While it details several non-clinical performance tests, it does NOT contain the specific information requested about the acceptance criteria and study proving device meets acceptance criteria for an AI/ML medical device, particularly regarding test sets, expert adjudication, MRMC studies, or standalone algorithm performance. The device described appears to be a physical labware device, not an AI/ML software device.

    Therefore, I cannot extract the requested information (acceptance criteria, study details for AI/ML performance, sample sizes for AI/ML test/training data, expert qualifications, adjudication methods, MRMC studies, standalone performance, or ground truth establishment relevant to AI/ML) directly from this document.

    However, I can extract information regarding the non-clinical performance studies conducted for this physical device:

    A table of acceptance criteria and the reported device performance (for physical device tests):

    TestAcceptance CriterionReported Performance
    Sterilization ValidationSterility Assurance Level (SAL) of 10⁻⁶Met SAL of 10⁻⁶
    Endotoxin Testing< 20 EU/device< 20 EU/device
    Human Sperm Survival Assay (HSSA)≥80% of the control motility at 24 hours after 30 minutes exposure to SpermAlignMet (before and after accelerated aging to support 12-month shelf life)
    Sperm Separation Performance (Motility)Not explicitly stated as an "acceptance criterion" but reported as performance metricAverage percent of progressively motile sperm: Input 57.4% / Output 91.9%
    Transportation SimulationNot explicitly stated (implied to meet a standard)Performed per ASTM D4169-22
    Package Integrity (after accelerated aging to support 12-month shelf-life)Visual inspection, Bubble leak, Seal strength (implied to meet standards)Performed per ASTM F1886/F1886M, ASTM F2096-11 (2019), ASTM F88/F88M-16. (Results implied to be successful as device was cleared.)

    The document does NOT provide information for the following AI/ML specific questions:

    • Sample sizes used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
    • Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
    • Adjudication method (e.g. 2+1, 3+1, none) for the test set
    • 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
    • If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
    • The type of ground truth used (expert consensus, pathology, outcomes data, etc)
    • The sample size for the training set
    • How the ground truth for the training set was established
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1