Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K103631
    Manufacturer
    Date Cleared
    2011-07-21

    (220 days)

    Product Code
    Regulation Number
    868.2375
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    BIANCAMED LIMITED

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

    The device is intended to be used for the spot measurement of respiration rate of an adult patient in a hospital and clinical setting. It is not a vital signs monitor or an apnea monitor.

    The device is indicated for use as suitable for use on adult patients. It should not be used on patients that exhibit uncontrolled limb movement.

    Device Description

    The SleepMinder Breathing Frequency Indicator BM07 consists of

    • A small sensor unit that can stand on a desk top or shelf. The sensor . unit emits a very low power radio signal that is aimed at the patient. The sensor utilizes the reflected radio signal to measure the chest movement of the patient, and thus discern the respiration rate. The sensor has no part that is in contact with the patient.
    • The sensor data is transmitted to a PC running a proprietary display . program. The validated transmission method to the PC is a BlueTooth wireless link.
    • . The PC display program runs a proprietary algorithm to extract the respiration rate from the sensor movement data. The program displays
      • The respiration rate, and o
      • Indicates whether there is a valid target, whether the o target is moving too much for a breathing signal to be indentified or the signal is clear enough for a breathing rate to be calculated.
    AI/ML Overview

    This submission focuses on establishing substantial equivalence to previously cleared predicate devices rather than defining specific acceptance criteria for a new device and then proving the device meets those criteria through a detailed study with quantitative performance metrics. While "Performance Data" is mentioned, the description provided is general and qualitative.

    Here's an analysis based on the provided text, highlighting the limitations due to the nature of the 510(k) summary:


    1. Table of Acceptance Criteria and Reported Device Performance

    As specific quantitative acceptance criteria are not explicitly stated in the provided text (e.g., "accuracy must be within X breaths per minute"), a typical table format cannot be generated. Instead, the performance is described in relation to a predicate device.

    Acceptance Criteria (Implied / Qualitative)Reported Device Performance
    Device functions as intended and breathing rate observed is as expected (comparable to predicate)."In all instances, the SleepMinder Breathing Frequency Indicator BM07 functioned as intended and breathing rate observed was as expected."
    Satisfactory performance in presence of typical RF interference."Validation testing was also carried out to confirm that the BM07 sensor continued to perform satisfactorily in the presence of typical potential RF interference emitters."
    Breathing rate calculation stable across multiple devices."...and also that the breathing rate calculation was stable across a number of individual examples of the device."
    Meets general market and scientific expectations of accuracy."Performance data collected against the SOMNOscreen predicate device demonstrate that the SleepMinder Breathing Frequency Indicator BM07 meets general market and scientific expectations of accuracy, as does the Kai R-Spot 100."

    2. Sample Size for the Test Set and Data Provenance

    • Sample Size for Test Set: 24 volunteer subjects.
    • Data Provenance: Not explicitly stated, but the company is BiancaMed Ltd, located in Dublin, Ireland. The study involved "volunteer subjects," implying prospective data collection for the validation testing. It is not specified if the subjects represented diverse geographical locations or were all from Ireland.

    3. Number of Experts Used to Establish Ground Truth and Qualifications

    • The ground truth for the test set was established using a predicate device, the SOMNOscreen Plus RC Easy [K060708]. This device uses chest effort bands to measure breathing rate.
    • The text does not mention the use of human "experts" (e.g., radiologists) to establish ground truth; rather, it relies on the established measurement capabilities of a cleared medical device.

    4. Adjudication Method for the Test Set

    • No explicit adjudication method (like 2+1 or 3+1) is described. The comparison was directly between the SleepMinder BM07 and the SOMNOscreen Plus RC Easy. The SOMNOscreen's data was processed after the recording session to display a breathing rate against time, and the BM07's recordings were similarly processed for comparison.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    • No MRMC comparative effectiveness study was done. The study was a comparison of a new device (BM07) against a predicate device (SOMNOscreen) for stand-alone performance, not an assessment of human readers with vs. without AI assistance. Therefore, no effect size for human reader improvement is provided.

    6. Standalone Performance Study

    • Yes, a standalone study was done. The "Validation testing" and "overall performance" testing described were for the SleepMinder Breathing Frequency Indicator BM07 itself, directly comparing its output to the SOMNOscreen Plus RC Easy. This evaluates the algorithm's performance without a human in the loop for interpreting the raw sensor data. The PC program displays the respiration rate, which a human then reads.

    7. Type of Ground Truth Used

    • The ground truth used was measurement from a predicate medical device (SOMNOscreen Plus RC Easy [K060708]) using chest effort bands, which is considered a direct and established method for measuring breathing rate. This could be interpreted as a form of "reference standard" or "gold standard" for breathing rate measurement in this context.

    8. Sample Size for the Training Set

    • The provided text does not mention a training set or its sample size. The document describes validation testing against a predicate device, which implies evaluation of a complete, already-developed algorithm. If the algorithm involves machine learning, information about its training would typically be in an earlier development stage document, not necessarily explicitly detailed in a 510(k) summary focused on substantial equivalence.

    9. How the Ground Truth for the Training Set Was Established

    • As no training set is mentioned, there is no information provided on how its ground truth was established.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1