Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K152276
    Manufacturer
    Date Cleared
    2016-06-03

    (296 days)

    Product Code
    Regulation Number
    868.1860
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    Wing Smart FEVI and Peak Flow Meter

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Wing is intended for monitoring FEV1 (Forced exhalation in the first second) and PEF (Peak Expired Flow Rate) for home use. The device is designed for pediatric to adult users. Wing is not recommended for children under 5 years of age.

    Device Description

    The Wing® Smart FEV1 and Peak Flow Meter (Wing) is an electronic peak flow monitor, that measures Peak Flow and FEV1. Wing is not recommended for children under 5 years of age.

    The Wing Sensor consists of a plastic shell and a detachable electronics module. The plastic shell includes a built-in mouthpiece and an acoustic transducer. The electronics module houses a PCBA with a microphone and a 3.5mm audio cable. The audio cable is plugged into the 3.5mm audio jack (headphone jack) of a smartphone to transmit audio data to the Wing Software. The Wing Software, which includes the Wing Mobile Application (Wing App), the Wing Signal Processing Engine, and the Sparo Labs Data Management System, is used to collect, transmit, manage, store, and calculate FEV1 and Peak Flow measurements.

    When taking a lung function measurement, the user launches the Wing App, which serves as Wing's user interface, on his or her smartphone and connects the Wing Sensor by plugging it into the smartphone's headphone jack. The Wing App prompts the user to perform the lung function test after the user has indicated that they would like to take a lung function measurement. As the user blows through Wing Sensor, the acoustic transducer induces oscillations in the airstream and an acoustic tone is created by the airstream. The microphone, located in the electronics module, detects this acoustic tone. The frequency of the acoustic tone (i.e. the number of oscillations) is proportional to flow rate of the air as it passes through the acoustic transducer. With flow rate and correspondent time, the FEV1 can be calculated. Wing is provided non-sterile.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study information for the Wing Smart FEV1 and Peak Flow Meter, based on the provided document:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Performance MetricAcceptance Criteria (ATS Standard Waveforms)Reported Device Performance (Bench Testing)
    FEV1 AccuracyMet ATS recommendationsPassed ATS 24 & 26 Standard Waveforms
    PEF AccuracyMet ATS recommendationsPassed ATS 24 & 26 Standard Waveforms
    FEV1 PrecisionMet ATS recommendationsPassed ATS 24 & 26 Standard Waveforms
    PEF PrecisionMet ATS recommendationsPassed ATS 24 & 26 Standard Waveforms
    BiocompatibilityCompliant with ISO 10993 standardsPassed Cytotoxicity, Sensitization, Irritation per ISO 10993-5, -10, -12
    Electrical SafetyCompliant with IEC 60601-1System complies with IEC 60601-1
    EMCCompliant with IEC 60601-1-2System complies with IEC 60601-1-2
    Software ValidationFollowed FDA guidance for "moderate" level of concernVerification and validation documentation provided; considered "moderate" level of concern

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

    • Sample Size for Test Set: Not explicitly stated as human subject data was not used for the primary performance assessment. The "test set" for the primary performance claim was a set of "ATS 24 and 26 Standard Waveforms."
    • Data Provenance: The standard waveforms are theoretical or simulated data generated by a "pulmonary waveform generator" to represent various flow patterns. This is a controlled, synthetic environment, not real-world human data.

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

    • This information is not applicable as the ground truth for the primary performance testing (accuracy and precision of FEV1 and PEF) was based on ATS Standard Waveforms, which are established industry standards rather than expert consensus on individual cases.

    4. Adjudication method for the test set:

    • This information is not applicable as human readers or experts were not used to assess the performance against the standard waveforms. The device's measurements were quantitatively compared against the known values of the standard waveforms.

    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

    • No, an MRMC study was not done. The document explicitly states: "The subject of this premarket submission, Wing, did not require animal or clinical studies to support substantial equivalence."

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

    • Yes, a standalone performance assessment was done. The bench testing against ATS standard waveforms evaluates the device's (hardware and software combined) ability to accurately measure FEV1 and PEF without human interpretation or intervention in the measurement process itself.

    7. The type of ground truth used:

    • The ground truth for the primary performance claim (FEV1 and PEF accuracy/precision) was established industry standards (ATS Standard Waveforms).
    • For biocompatibility, the ground truth was the acceptance criteria defined by ISO 10993 standards.
    • For electrical safety and EMC, the ground truth was compliance with IEC 60601 standards.

    8. The sample size for the training set:

    • This information is not provided in the document. Software validation and verification were conducted, suggesting development and testing, but details on a "training set" (if applicable for machine learning components) are absent. Given the device's function as a measurement tool rather than a diagnostic AI, it's possible a traditional "training set" in the machine learning sense wasn't used, or not deemed relevant for this submission.

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

    • As the sample size for the training set is not provided, how its ground truth was established is also not provided in the document.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1