Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K142032
    Date Cleared
    2015-05-07

    (286 days)

    Product Code
    Regulation Number
    870.2300
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    MRI PATIENT MONITORING SYSTEM TESLA M3

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

    The MRI Patient Monitoring System Tesla M3 is intended for monitoring of vital signs during MRI examinations (MRI procedures) of patients.

    The Tesla M3 is intended for use in the Adult, Pediatric and Neonatal populations for the continuous monitoring of Electrocardiogram (ECG), Non-Invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP), Temperature, Respiration, Capnography (etCO₂), Oxygen and Anesthetic Agents.

    The Tesla M3 is intended for use in the Adult and Pediatric populations for the continuous monitoring of Pulse Oximetry (SpO2).

    The Tesla M3 is intended for use by health care professionals.

    Device Description

    The Tesla M3 is a MRI Patient Monitoring System that is intended to monitor and display vital signs during MRI examinations (MRI procedures) of patients. It is capable for continuous monitoring and displaying data from the following sensors/measurement modules in graphic and numeric form:

    • Electrocardiogram (ECG),
    • Pulse Oximetry (SpO2),
    • . Non-Invasive Blood Pressure (NIBP),
    • . Invasive Blood Pressure (IBP),
    • Temperature, Respiration,
    • Capnography (etCO2), and
    • . Oxygen and Anesthetic Agents
    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information for the MRI Patient Monitoring System Tesla M3, based on the provided FDA 510(k) summary:

    1. Table of Acceptance Criteria and Reported Device Performance

    TestAcceptance CriteriaReported Device Performance
    Electrical safetyCompliance to IEC 60601-1:2012Passed
    Electromagnetic compatibilityCompliance to EN/IEC 60601-1-2: 2007Passed
    Multifunction Patient MonitorCompliance to IEC 60601-2-49: 2011-02Passed
    AlarmsCompliance to IEC 60601-1-8:2006+A1:2012-11Passed
    BiocompatibilityCompliance to ISO 10993-1Passed
    Risk ManagementCompliance to ISO 14971:2007Passed
    SoftwareCompliance to IEC 62304:2006Passed
    Pulse OximeterCompliance to ISO 80601-2-61: 2011Passed
    Respiratory Gas MonitorCompliance to ISO 80601-2-55: 2011-12Passed
    IBP (Invasive Blood Pressure)Compliance to IEC 60601-2-34:2011-05Passed
    NIBP (Non-Invasive Blood Pressure)Compliance to IEC 80601-2-30:2009-01 (ed.1.0)Passed
    ECG (Electrocardiogram)Compliance to IEC 60601-2-27:2011-03 (ed.3.0)Passed
    ThermometersCompliance to ISO 80601-2-56: 2009 (ed. 1.0)Passed

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

    The provided summary does not mention specific sample sizes for any clinical test sets. The testing conducted was primarily non-clinical compliance testing to established international standards. The provenance of data is not specified beyond being "non-clinical testing" conducted by the manufacturer, MIPM.

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

    This information is not provided in the 510(k) summary. Since the testing was non-clinical and focused on compliance to international standards, it's unlikely that "experts" in the sense of medical professionals establishing a ground truth for a test set were used in the same way they would be for an AI-driven diagnostic device. The ground truth would be defined by the specifications of the standards themselves (e.g., a known electrical signal for ECG accuracy, a calibrated pressure source for NIBP accuracy).

    4. Adjudication Method for the Test Set

    This information is not provided. Given the nature of compliance testing against objective standards, a formal adjudication method like "2+1" or "3+1" used in clinical studies with subjective assessments would not be applicable. The results are typically "Pass" or "Fail" based on whether the device meets the quantitative requirements of the standard.

    5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Readers Improve with AI vs. Without AI Assistance

    No, an MRMC comparative effectiveness study was not done. The device is a physiological patient monitor, not an AI-assisted diagnostic tool, and the submission explicitly states that "no clinical testing was required to support the medical device."

    6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

    The device is a physiological patient monitor; therefore, it's an "algorithm only" device in the sense that its measurements are generated by internal algorithms without human interpretation being part of its performance determination. However, it's important to differentiate this from AI-driven diagnostic algorithms. The "standalone" performance here refers to the device's ability to accurately measure vital signs against established standards, independent of human interpretation or intervention in the measurement process itself. The non-clinical performance testing summarized in the table above represents its standalone performance against these technical standards.

    7. The Type of Ground Truth Used

    The ground truth used for these tests is based on the objective specifications and requirements outlined in the referenced international standards (e.g., IEC, ISO). For example:

    • For ECG: known electrical signals or waveforms.
    • For NIBP: calibrated pressure sources.
    • For Pulse Oximetry: simulated oxygen saturation levels.

    It is not expert consensus, pathology, or outcomes data.

    8. The Sample Size for the Training Set

    This information is not applicable and not provided. The Tesla M3 is a hardware-based physiological monitor with embedded software/firmware for data acquisition and processing, not a machine learning or AI device that requires a "training set" in the context of deep learning or similar algorithms. Its development and validation are based on engineering principles and compliance with medical device standards.

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

    This information is not applicable as there is no "training set" in the context of an AI/ML algorithm being trained. The "ground truth" for the device's functioning, as mentioned above, is established by adherence to the specifications of recognized international medical device standards.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1