Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K193460
    Manufacturer
    Date Cleared
    2020-05-26

    (162 days)

    Product Code
    Regulation Number
    872.5570
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The iNAP One Sleep Therapy System is indicated for home use in the treatment of obstructive sleep apnea (OSA) in adults in whom positive airway pressure is not the preferred treatment choice.

    Device Description

    The iNAP One Sleep Therapy System consists of six (6) main components. The components are a console, a saliva container, a saliva absorbent (iNAP DryPad), a flexible polymer tubing (iNAP Tubing Set), a soft polymer oral interface (iNAP Oral Interface) and a software application for mobile devices (iNAP Care). One additional accessory is Oral Interface with Tubing, which is a combination of the Oral Interface and Tubing Set. The function of iNAP One Sleep Therapy System is developing a negative pressure gradient in the user's oral cavity, which is set as -40 mmHg.

    AI/ML Overview

    Please find below the requested information about the acceptance criteria and study proving the device meets these criteria:

    1. Table of Acceptance Criteria and Reported Device Performance

    CategoryAcceptance CriteriaReported Device Performance (iNAP One Sleep Therapy System)
    BiocompatibilityCompliance with ISO 10993-1 series for patient contact materials.All biocompatibility tests (Cytotoxicity, Skin Sensitization, Oral Mucosa Irritation, Pyrogenicity, Leechable & Extractables) passed for all relevant components (Oral Interface, Tubing Set, Oral Interface with Tubing Set).
    Bench TestingSubstantial equivalence to predicate device (Winx) in negative pressure application and maintenance.Substantially equivalent to Winx device in negative pressure application and maintenance.
    AcousticsAcoustic power < 30 dB per ISO 7779.Acoustic power < 30 dB per ISO 7779:2010.
    SoftwareSoftware verification and validation (FDA Guidance for Industry and FDA Staff "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices"). Level of concern: "major".Software verification and validation conducted; documentation provided as recommended by FDA guidance.
    Clinical PerformanceNon-inferiority to predicate device (Winx mouthpiece) regarding clinical performance; lower incidence of adverse events; durable beneficial effect over 28-30 days.Clinical performance non-inferior to Winx mouthpiece. Incidence of adverse events and serious adverse events was lower compared to Winx/Winx+ mouthpieces. Beneficial effect durable over 28-30 days.
    Negative Pressure Setting & Accuracy40 mmHg (±10%)40 mmHg (±10%)
    Electrical SafetyCompliance with IEC 60601-1: Class II Equipment, Type BF, IP22, Continuous Operation.Compliance with IEC 60601-1: Class II Equipment, Type BF, IP22, Continuous Operation. (Note: Predicate device was IPX0, but no additional risks induced).
    Electromagnetic Compatibility (EMC)Compliance with IEC 60601-1-2.Compliance with IEC 60601-1-2.
    Safety for Home EnvironmentCompliance with IEC 60601-1-11.Compliance with IEC 60601-1-11.

    2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    The document mentions two randomized studies for clinical testing:

    • One performed in Taiwan.
    • The other, a multicenter international study with sites in Germany, Taiwan, and the United States.

    The specific sample size (number of participants) for these clinical studies, nor whether they were retrospective or prospective, is not explicitly stated in the provided text. However, randomized studies are generally prospective.

    3. 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)

    The provided text does not explicitly state the number of experts used or their specific qualifications for establishing ground truth in the clinical studies. The clinical studies likely used objective measures (e.g., polysomnography data for OSA severity, adverse event reports) rather than expert consensus on diagnostic images.

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

    The document does not specify any adjudication method for the clinical test set data. Given the nature of OSA treatment effectiveness and adverse event reporting, it's more likely that predefined clinical endpoints and safety criteria were used rather than a consensus-based adjudication for subjective interpretations.

    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

    A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed as this device (iNAP One Sleep Therapy System) is a treatment device for Obstructive Sleep Apnea, not a diagnostic imaging device involving human readers or AI assistance in image interpretation. The study focused on the effectiveness of the physical device compared to a predicate device.

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

    This question is not applicable as the iNAP One Sleep Therapy System is a physical medical device for treating OSA, not an algorithm, and it operates with a human user (the patient). The software component (iNAP Care mobile app) is for tracking usage records and sealing-leakage time ratio, not for standalone diagnostic or therapeutic action.

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

    For the clinical studies, the ground truth would have been established through outcomes data, including:

    • Measures of Obstructive Sleep Apnea severity (though specific metrics like AHI are not detailed in this summary, they are standard for OSA studies).
    • Adverse event data for safety comparison.
    • Patient compliance and usage data.

    8. The sample size for the training set

    The document does not mention a training set in the context of device performance evaluation. The clinical studies were randomized trials comparing the subject device to a predicate, not machine learning model training.

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

    This question is not applicable as there is no mention of a training set for machine learning or AI algorithm development in the provided text.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1