Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K203624
    Date Cleared
    2022-06-16

    (552 days)

    Product Code
    Regulation Number
    872.5470
    Panel
    Dental
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Custom-made Invisible Aligners is indicated for the treatment of tooth malocclusion in patients with permanent dentition (i.e., all second molars). The Custom-made Invisible Aligner positions teeth by way of continuous gentle force.

    Device Description

    The Custom-made Invisible Aligners System is a series of dental aligners that are fabricated of clear, thin thermoformed Polyethylene terephthalate (PETG) plastic to progressively reposition the teeth. Corrective force to reposition the teeth is delivered via minor changes into a position in each subsequent aligner.

    AI/ML Overview

    The provided text describes a 510(k) premarket notification for a medical device, the "Custom-made Invisible Aligners." This type of submission aims to demonstrate that a new device is substantially equivalent to a legally marketed predicate device. For this submission, the manufacturer primarily relies on non-clinical performance testing and biocompatibility testing, rather than clinical studies or AI algorithm performance studies. Therefore, many of the requested items related to AI and human reader studies are not applicable.

    Here's an analysis based on the provided document:

    Acceptance Criteria and Reported Device Performance

    1. Table of acceptance criteria and the reported device performance:

    Test ItemTest Standard/MethodAcceptance CriteriaResult
    ThicknessInternal standard≤1.2mmPass
    Appearance"ZMT-FD-SS-052"No crack or bubbling; No defectsPass
    OdorInternal standardOdorlessPass
    DensityASTM D792-2013≤2.6g/cm³Pass
    Water absorptionISO20795.1-2013≤32 μg/mm³Pass
    DissolutionISO20795.1-2013≤1.6 μg/mm³Pass
    Color stabilityISO20795.1-2013No changePass
    Tear resistanceISO6383.1-2015>200N/cmPass
    Wear resistanceISO9352-2012<0.25g/1000rPass
    Flexural modulus of elasticityISO20795.1-2013≥600MpaPass
    Biocompatibility (Cytotoxicity)ISO 10993Non-cytotoxicPass
    Biocompatibility (Irritation)ISO 10993Not an intracutaneous irritantPass
    Biocompatibility (Sensitization)ISO 10993Non-sensitizingPass
    Manufacturing AccuracyPre-established specifications3D molding and aligner molding meet specs; suitability, function, form comply with specsPass
    Shelf LifeReal-time aging testingPerformance maintained after 30 monthsPass

    The tests demonstrate that the subject device (Custom-made Invisible Aligners) meets the pre-established quality, safety, and performance criteria, aligning with or improving upon the predicate device.


    Study Details:

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

    • Performance Testing (Physical/Mechanical properties): The document does not specify the exact sample size for each performance test (e.g., thickness, density, etc.). It states that "A comparison testing was performed in combination with the subject and predicate device." This suggests multiple samples were tested for each characteristic but does not provide a number.
    • Manufacturing Accuracy Validation: 12 different patient cases were evaluated at the beginning, middle, and end of the treatment sequence.
    • Shelf Life Testing: Performance testing was conducted after 30 months of real-time aging under commercial storage conditions.
    • Data Provenance: The document does not explicitly state the country of origin for the data or whether it was retrospective or prospective. Given the manufacturer's location (Zhejiang, China), the testing was likely conducted in China. The non-clinical nature of these tests means "retrospective" or "prospective" as typically applied to patient data is less relevant.

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

    • Not Applicable. The ground truth for the non-clinical performance and biocompatibility tests is based on established international standards (e.g., ASTM, ISO) and internal specifications, rather than expert human interpretation or diagnosis. For manufacturing accuracy, it's evaluated against pre-established specifications and the treatment design in software.

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

    • Not Applicable. As the tests are non-clinical and compliance-based, there is no human adjudication process involved in establishing "ground truth" errors. The results are objective measurements against defined criteria.

    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. No MRMC study was conducted. This submission does not involve an AI algorithm intended for human interpretation or diagnostic assistance. The device is a physical medical device (aligners).

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

    • Not Applicable. This is not an AI algorithm. While there is software involved in ordering and processing, its verification and validation are described as supporting the device's safety and effectiveness, not as an AI-driven diagnostic or treatment planning tool being evaluated for standalone performance.

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

    • Objective Test Standards and Specifications: The ground truth for the non-clinical tests (material properties, biocompatibility, manufacturing accuracy, shelf-life) is based on:
      • Established international standards (e.g., ASTM, ISO).
      • Internal specifications and methods.
      • Pre-established specifications and the treatment design in the software for manufacturing accuracy.

    8. The sample size for the training set:

    • Not Applicable. This submission does not involve a machine learning algorithm that requires a training set.

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

    • Not Applicable. No training set was used.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1