Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K053462
    Manufacturer
    Date Cleared
    2006-01-18

    (36 days)

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

    3160 MRI PATIENT MONITORING SYSTEM

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

    The 3160 MRI Patient Monitoring System is intended to monitor vital signs for patients undergoing MRI procedures and to provide signals for synchronization for the MRI scanner. The 3160 MRI Patient Monitoring System is intended for use by health care professionals.

    Device Description

    The 3160 MRI Patient Monitoring System is intended to monitor vital signs for patients undergoing MRI procedures and to provide signals for synchronization for the MRI scanner. It is designed to assist clinicians in monitoring patient vital signs in the MRI the dynamic and evolving Magnetic Resonance environment. A combination of wireless communication, radio frequency (RF) shielding, digital signal processing (DSP), and adaptable mounting technologies address the challenges associated with patient monitoring in the MRI area. Built on Invivo's strong heritage in MRI patient vital signs monitoring, the 3160 MRI Patient Monitoring System provides accurate, continuous, and reliable performance during all phase of MRI applications.

    AI/ML Overview

    This document describes the 3160 MRI Patient Monitoring System, a device intended to monitor vital signs for patients during MRI procedures. The submission focuses on demonstrating substantial equivalence to previously cleared predicate devices rather than a standalone clinical study with expert ground truth or AI performance metrics.

    Here's a breakdown of the requested information based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The device's acceptance criteria are presented as "Specification" and the reported performance as "Pass" within the tables below.

    ParameterSpecificationReported Device Performance
    End Tidal CO2 Monitoring (Capnometer)
    Measurement Range0-76 mmHgPass
    Accuracy±2mmHg + 5% of readingPass
    Flow Rate50 mL/minPass
    Respiration Rate0 to 100 BPMPass
    Zero Drift Rate0.5 mmHg/hr; 1.5 mmHg/24hrPass
    Alarm LimitsLower: Off, 5 to 60 mmHg; Upper: Off, 5 to 80 mmHgPass
    Inspired CO225 mmHgPass
    Invasive Pressure Monitoring
    Channels1 or 2 simultaneous channelsPass
    Bandwidth (-3dB)0 to 12 HzPass
    Range-10 to +248 mmHgPass
    Sensitivity5 uV/V/mmHgPass
    Gain Accuracy± 0.5 %Pass
    Auto Zero FeatureZeroes with +/- 300 mmHg offset to 0+/- 5 mmHg within 1 secondPass
    Waveform Display Scales0 to 45, 0 to 75, 0 to 150, 0 to 200, 0 to 250 mmHgPass
    High Pressure Alarm5 to 248 mmHg range; 1 mmHg resolutionPass
    Low Pressure Alarm5 to 248 mmHg range; 1 mmHg resolutionPass
    Temperature Monitoring
    Temperature Range25 to 44°C (77° to 111.2°F)Pass
    Accuracy± 0.5°C (± 0.5°F)Pass
    Resolution± 0.1°C (± 0.18°F)Pass
    Respiration Monitoring
    Range4 to 150 BPMPass
    Resolution1 BPMPass
    Accuracy2% to 60 BPM, 3.4% at 87 BPM, 5.6% at 142 BPMPass

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

    The document does not specify a distinct "test set" in the context of human-reviewed data or a training/validation split common in AI/machine learning studies. The performance data is based on "Validation and Verification Testing" using simulators and test equipment.

    • Sample Size: Not applicable in the context of distinct patient data sets. The testing involved "simulators and test equipment under actual use conditions" and two specific MRI scans (TRUE-FISP and PLANAR-ECHO) in a 3.0T MRI system.
    • Data Provenance: Not human-derived patient data. The testing was conducted using simulators and test equipment within a specific (3.0T) MRI environment. It is a non-clinical, controlled laboratory/engineering testing environment, not retrospective or prospective patient data from a specific country.

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

    Not applicable. The performance testing described is engineering verification and validation against specified technical parameters, not a clinical study requiring expert interpretation of medical images or patient outcomes. The "ground truth" here is the known output of the simulators and test equipment against which the device's measurements are compared.

    4. Adjudication Method for the Test Set

    Not applicable. There was no clinical ground truth established by experts requiring adjudication. The device's measurements were compared against known values from test equipment.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

    No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This submission focuses on the technical performance of a vital sign monitoring device and its substantial equivalence to predicate devices, not on the improvement of human reader performance with AI assistance. The device itself is a physiological monitoring system, not an AI diagnostic tool for interpreting medical images.

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

    Yes, the performance data presented is effectively a standalone evaluation of the device's functional modules (e.g., capnometer, invasive pressure, temperature, respiration) against established technical specifications using test equipment. There is no "human-in-the-loop" component in this performance testing as described. The performance data assesses the accuracy of the device's sensors and algorithms in measuring vital signs under simulated conditions.

    7. The Type of Ground Truth Used

    The ground truth used for the performance testing was derived from simulators and test equipment under controlled, actual-use (MRI environment) conditions. This is a technical or engineering ground truth, where the expected values are known and precisely controlled by the testing apparatus.

    8. The Sample Size for the Training Set

    Not applicable. This submission describes the performance of a physiological monitoring device, not an AI or machine learning algorithm that requires a training set of data.

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

    Not applicable, as there was no training set for an AI/machine learning algorithm.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1