Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K070259
    Date Cleared
    2008-02-21

    (391 days)

    Product Code
    Regulation Number
    868.1430
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The EC50 ToxCO+ Breath Carbon Monoxide Monitor and accessories are used by healthcare professionals to determine levels of Carbon Monoxide (CO) poisoning.

    Device Description

    The EC50 ToxCO+ Breath Carbon Monoxide Monitor is a handheld device, which provides a non-invasive means of determining Carbon Monoxide (CO) poisoning and Carboxyhaemoglobin (COHb) when blood testing is not available. The EC50 ToxCO+ Breath Carbon Monoxide Monitor is also ideal for use during triage to ensure suspected cases of CO poisoning are not missed. The EC50 ToxCO+ Breath Carbon Monoxide Monitor is a microprocessor-controlled device powered by 2 AA batteries with an Alphanumerice LCD display housed in a sturdy ABS case with a synthetic rubber boot. The EC50 ToxCO+ Breath Carbon Monoxide Monitor is designed to have an operating temperature between 0-30° C, operating humidity 10-95% non-condensing and has storage temperature requirements of 0-30° C. The sensor sensitivity is 1 pmm, has a warm up time of <10 seconds-90% FSD, an accuracy of ±5% of reading, a concentration range of 0-50% COHb/0-500ppm CO and an H2 Cross Interference of <40% @ 20° C. The sensor operating life is 2-3 years with a company warranty of 6 months and requires calibrations at 6-month intervals. The EC50 ToxCO+ Breath Carbon Monoxide Monitor is an easy to use handheld device that has three clearly marked buttons: ON button, CAL calibration button, RECALL button.

    AI/ML Overview

    Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

    Device: EC50 ToxCO+ Breath Carbon Monoxide Monitor


    1. Table of Acceptance Criteria and Reported Device Performance

    The provided documentation does not explicitly define a formal "acceptance criteria" table with specific thresholds that the device must meet to be deemed acceptable. Instead, it relies on comparison to predicate devices and reported specifications.

    Acceptance Criteria (Implied)Reported Device Performance (EC50 ToxCO+)
    Accuracy: Comparable to predicate devices±5% of reading
    Concentration Range: Comparable to predicate devices0-50% COHb/0-500ppm CO
    Sensor Sensitivity: Comparable to predicate devices1 ppm
    Warm-up Time: Comparable to predicate devices<10 seconds - 90% FSD
    H2 Cross Interference: Comparable to predicate devices<40% @ 20°C
    Operating Temperature: Comparable to predicate devices0-30°C
    Operating Humidity: Comparable to predicate devices10-95% non-condensing
    Storage Temperature: Comparable to predicate devices0-30°C
    Electrical Safety: Compliance with relevant standardsMet IEC 60601-1
    Electromagnetic Compatibility: Compliance with relevant standardsMet IEC 60601-1-2
    Biocompatibility of Mouthpiece: Compliance with relevant standardsSatisfied ISO 10993 (same as predicate)
    Biocompatibility of Facemasks: Compliance with relevant standardsMet ISO 10993 (commercially available)
    Sensor Operating Life: Comparable to predicate devices2-3 years
    Calibration Frequency: Comparable to predicate devices6-month intervals

    2. Sample Size Used for the Test Set and Data Provenance

    The provided document does not specify a sample size for a test set involving human subjects or collected data points. The assessment relies on a comparison to predicate devices and bench testing.

    • Sample Size (Test Set): Not specified.
    • Data Provenance: The document implies "bench testing" was performed to compare performance with predicate devices. No specific geographic origin or retrospective/prospective nature of data is mentioned.

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

    The document does not mention the use of experts to establish ground truth for a test set. This type of device (carbon monoxide monitor) typically relies on instrumental measurements for its core performance evaluation rather than expert interpretation of images or clinical assessments for ground truth.


    4. Adjudication Method for the Test Set

    Since no test set involving human interpretation or subjective assessment is described, no adjudication method (e.g., 2+1, 3+1) is mentioned or applicable.


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

    No MRMC comparative effectiveness study was done or mentioned. This type of study involves multiple human readers and multiple cases to assess the impact of an AI system on reader performance. The EC50 ToxCO+ is a standalone diagnostic device that directly measures CO levels, not an AI-assisted diagnostic tool that aids human interpretation.


    6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance

    The device itself is a standalone measurement instrument. Its reported performance (e.g., accuracy, sensitivity, range) is inherently its standalone performance. There is no "human-in-the-loop" component in the direct measurement of CO by the device. The reported performance metrics in the table above represent the device's standalone capabilities.


    7. Type of Ground Truth Used

    The ground truth for evaluating the EC50 ToxCO+ would have been instrumental reference standards for carbon monoxide concentration. For example, calibrated gas mixtures of known CO concentration would be used to test the device's accuracy. The document implicitly relies on the established performance of the predicate electrochemical gas sensors.


    8. Sample Size for the Training Set

    The document does not mention a training set in the context of machine learning or AI. This device uses a traditional electrochemical sensor, not a machine learning model that requires a training set.


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

    As there is no training set for this type of device, this question is not applicable.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1