Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K100992
    Device Name
    NEURALMAS
    Date Cleared
    2010-09-24

    (168 days)

    Product Code
    Regulation Number
    874.1820
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K031510, K072736, KO62996, K000722

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

    This device is intended for use in surgical procedures to assist in locating and mapping motor nerves through the use of mechanomyographic (MMG) signals and electrical stimulus of nerves. This device is indicated for locating and identifying spinal nerve roots and peripheral motor nerves originating from spinal levels C3-T1 and L2-S2.

    Device Description

    The NeuralMAS™ system is a multichannel intraoperative monitor for use during surgeries in which a motor nerve is at risk. The NeuralMAS™ system records mechanomyographic (MMG) signals from muscles innervated by the affected nerve, which may originate from operator applied electrical stimulus or from direct or indirect mechanical stimulus occurring during the course of surgery. The monitor will assist early nerve identification by providing the surgeon with a tool to help locate and identify the particular nerve at risk to minimize trauma by alerting the surgeon when a particular nerve has been activated.

    The NeuralMAS™ system consists of a reusable Patient Module, a Control Unit comprised of a touch-screen PC and an assortment of disposable conductive probes, stimulators, sensors, electrodes and electrode leads.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study details for the NeuralMAS™ device, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided text does not explicitly state pre-defined acceptance criteria in terms of specific performance metrics (e.g., minimum sensitivity or specificity targets). Instead, the study's acceptance was based on demonstrating "statistical agreement" and "correlation" with a predicate device.

    Acceptance Criteria (Implied)Reported Device Performance
    Statistical agreement with predicate deviceResults for positive and overall percent agreement established that:
    1. The NeuralMAS™ system's principle functions are effective for ascertaining and monitoring spinal nerve status and location.
    2. Data acquired by NeuralMAS™ during simulated surgical use in an animal model correlate well with data acquired simultaneously by a predicate device. |
      | Effectiveness of principle functions | Demonstrated effectiveness in ascertaining and monitoring spinal nerve status and location. |
      | Correlation of acquired data with predicate device | Good correlation between data acquired by NeuralMAS™ and data acquired simultaneously by a predicate device in an animal model. |
      | Safety and effectiveness comparable to predicate device | Concluded to be "as safe, as effective and performs as well as the legally marketed predicate device." |
      | Substantial equivalence in function to predicate device | Concluded to be "substantially equivalent in function to the legally marketed predicate device." |

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

    • Sample Size: Not explicitly stated. The study mentions a "comparative performance evaluation was conducted in the sheep," implying a limited animal study, but the specific number of sheep or cases is not provided.
    • Data Provenance: Prospective animal study conducted in "sheep" (animal model). The country of origin is not specified, but the submission is to the US FDA, so it's likely a US-based study or one adhering to US regulatory standards.

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

    Not applicable. The study was a comparative performance evaluation between the subject device and a predicate device in an animal model, not an assessment against human-established ground truth. The "ground truth" was essentially the synchronous readings from the predicate device and the physiological responses observed during the animal experiment.

    4. Adjudication Method for the Test Set

    Not applicable. There was no mention of human expert adjudication for the animal study. The comparison was statistical agreement and correlation between the two devices.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

    No. The study described is a non-clinical animal study comparing the device to a predicate, not an MRMC study involving human readers.

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

    Yes, in essence. The "comparative performance evaluation" in the sheep assessed the device's ability to ascertain and monitor nerve status and location, and its data acquisition, in direct comparison to the predicate device. This is a standalone assessment of the device's functional performance in a simulated surgical environment. Human interpretation or intervention as part of the performance measurement itself (beyond setting up and operating the devices) is not indicated.

    7. The Type of Ground Truth Used

    The "ground truth" for the test set was the data simultaneously acquired by the predicate device and the directly observable physiological responses in the animal model. The study aimed to show correlation and agreement between the NeuralMAS™ and the predicate device's readings. It did not rely on a separate, independent "gold standard" or pathology.

    8. The Sample Size for the Training Set

    Not applicable. This is a 510(k) submission for a medical device that records mechanomyographic signals and uses electrical stimulation. The device itself is not described as involving a machine learning algorithm that requires a "training set" in the traditional sense. The "training" for the device would have involved engineering development and calibration, not a data-driven machine learning training set as would be found in AI/ML device submissions.

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

    Not applicable, as there's no mention of a traditional machine learning training set for this device.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1