Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K240593
    Manufacturer
    Date Cleared
    2024-08-23

    (175 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The VEEGix EEG System, is intended to be used for measuring and recording the electrical activity of a patient's brain, obtained by placing electrodes on the forehead and wirelessly transmitting the electroencephalographic (EEG) signals for storage and display.

    The VEEGix EEG System, is intended for use in the acquisition of EEG signals, displaying them in real time and storing them for later review and analysis.

    The VEEGix EEG System, is intended for use in a hospital Operating Room. Post Anesthesia Care Unit, Intensive Care Unit, Emergency Department, or in other medical facilities such as inpatient and outpatient (ambulatory) surgery settings.

    The VEEGix EEG System is indicated for use on patients 18 years of age or older and is to be used by licensed medical professionals who have been adequately trained in the use and interpretation of EEG data for determination of brain state.

    The VEEGix EEG System does not provide any diagnostic conclusion about the patient's condition.

    The VEEGix EEG System is not to be used as a stand-alone in the evaluation or diagnosis of a disease or other condition.

    The VEEGix EEG System is not intended for use in life support systems.

    Device Description

    The VEEGix™ EEG system (subject device) is a Electrocochleographic (EEG) device to allow healthcare practitioners, nurses, neurologists and qualified technicians working in hospital Operating Room, Post Anesthesia Care Unit, Intensive Care Unit, Emergency Department, or in other medical facilities such as inpatient and outpatient (ambulatory) surgery settings to observe a patient's EEG signals and its derivatives.

    The use of the subject device is a straight-forward procedure of applying the VEEGix Electrode, which is a lightweight band, onto the patient's scalp in which the electrodes acquire the patient's EEG signals. Those signals are transmitted via the VEEGix EEG module) to the VEEGix iOS app (application) which display the patient's EEG measurements in real-time to allow healthcare practitioners, nurses, neurologists and qualified technicians to monitor and record those EEG measurements.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study details for the VEEGix EEG System, based on the provided FDA 510(k) summary:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document doesn't explicitly list a table of quantitative acceptance criteria with corresponding performance values for the software component of the device. Instead, the "Technology Comparison" table highlights specific technical characteristics where the VEEGix EEG System aligns with or exceeds its predicates, implying these are the implicit acceptance criteria for technical equivalence. The clinical performance section describes the methodology used to demonstrate comparable EEG signal quality to a conventional clinical EEG system, which serves as the overarching performance goal.

    Implicit Acceptance Criteria and Reported Device Performance (based on "Technology Comparison" and "Clinical Performance Testing" sections):

    Acceptance Criteria (Implied)Reported Device Performance (VEEGix EEG System)Reference/Context
    Technical Equivalence
    Classification RegulationClass II per 882.1400Same as primary predicate
    Product Code(s)OLT, OMC, ORT, GXYSame as primary predicate
    Indications for UseSubset of primary, same as secondary predicateNo new safety/effectiveness questions
    ModalitiesEEGSame as predicates
    Environment of UseHospital OR, PACU, ICU, ED, inpatient/outpatient surgery settingsSame as primary predicate, included in secondary
    Number of EEG Channels1 bipolarSame as secondary predicate, substantially equivalent to primary
    Number of Electrodes3 (Fp1, Fpz, Fp2)Same as secondary predicate, substantially equivalent to primary
    Sensing ElectrodesSilver, disposableSubstantially equivalent
    Power SourceBatterySame as predicates
    System ComponentsElectrode Array, Sensor module, acquisition, Tablet for memory and data viewingSame as primary predicate, similar to secondary
    Screen Display DetailsRaw EEG Waveforms; Signal Quality (Channel Connection, Artifact, Noise, Interference); Spectral Parameters (EEG power spectrum, SEF 95%, DSA, α, Β, δ, θ, γ)Substantially equivalent to primary (missing 10/20 Hz markers, B band division not raising new questions), secondary display capabilities included
    Storage for offline recordingYes, in the tablet displaySame as primary predicate
    Electrode ImpedanceYesSame as primary predicate
    Detection for Leads OffYesSame as predicates
    File output capabilityYesSame as predicates
    Real-time EEG DisplayYes, wireless to tabletSame as predicates
    Processed EEG Bandwidth0.5 Hz to 80 HzSubstantially equivalent as primary predicate (0.5 Hz to 45 Hz)
    Automatic Artifact IdentificationYesSame as primary predicate
    Common Mode Rejection> 100 dBSubstantially equivalent as primary predicate (> 90 dB)
    Amplifier Input Impedance200 GΩSubstantially equivalent as primary predicate (> 500 M Ohm)
    Electrode Impedance TestYesSame as primary predicate
    Patient Contains IsolationReinforced Insulation (2 MOPP), battery poweredSubstantially equivalent as primary predicate
    Event MarkersYes, artifact detectionSame as primary predicate
    Burst Suppression DisplayYes, Suppression Ratio (%)Substantially equivalent as primary predicate (Burst Suppression Probability)
    Display InterfaceTablet display indicates connection and operationSame as primary predicate
    BiocompatibilityTested per ISO 10993 (cytotoxicity, irritation, sensitization)Substantially equivalent
    Clinical Performance
    Comparable EEG signal quality to conventional clinical EEG systemsPearson's correlation coefficient (r=0.84, p<0.0001) between time-aligned NS and N1 waveforms. Substantial overlap visually.Bench testing in ICU setting

    2. Sample size used for the test set and the data provenance

    The document states: "Bench testing was performed in hospital to compare the quality and medical EEG feature similarity of electroencephalography (EEG) signals obtained by the NeuroServo (NS) device and those recorded with a conventional clinical EEG system (N1) (NicoletOne, Natus Medical Inc., Pleasanton, CA) in an ICU setting."

    • Sample Size for Test Set: Not explicitly stated as a number of patients or recordings. The description focuses on signal processing and comparison, implying data was collected from one or more patients, but a specific count is missing.
    • Data Provenance:
      • Country of Origin: Not explicitly stated, but the study was performed "in hospital" in an "ICU setting," suggesting prospective data collection.
      • Retrospective or Prospective: Prospective, as the testing was described as being "performed in hospital" to compare signals.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

    The document mentions "experts" in the context of "10-second epochs as this is a common temporal range used by experts for the offline or online visualization of data." However, it does not state the number of experts used to establish the ground truth for the test set, nor their specific qualifications. The comparison was primarily quantitative (Pearson's correlation) and visual ("substantial overlap between the waveforms").


    4. Adjudication method for the test set (e.g., 2+1, 3+1, none)

    No explicit adjudication method (e.g., 2+1 or 3+1 for clinical consensus on ground truth) is mentioned for the test set. The comparison relies on a quantitative statistical measure (Pearson's correlation coefficient) and visual assessment of waveform overlap against a predicate device.


    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

    No multi-reader multi-case (MRMC) comparative effectiveness study involving human readers or AI assistance effect size is reported. The VEEGix EEG System "does not provide any diagnostic conclusion about the patient's condition" and "is not to be used as a stand-alone in the evaluation or diagnosis of a disease or other condition." Its purpose is to measure, record, and display EEG signals for interpretation by licensed medical professionals.


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

    The clinical performance test described is a standalone (algorithm only) performance evaluation, although it's comparing the VEEGix system's signal acquisition and processing directly against a predicate system. The study quantified the similarity of EEG signals obtained by the VEEGix system with a conventional clinical EEG system (NicoletOne, N1) using Pearson's correlation coefficient. The output of the VEEGix system (processed EEG signals) was directly compared to the output of the N1 system.


    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

    The "ground truth" for the clinical performance testing was the EEG signals obtained from a "conventional clinical EEG system (NicoletOne, Natus Medical Inc., Pleasanton, CA)". This predicate device's output served as the reference standard against which the VEEGix device's signal quality was compared.


    8. The sample size for the training set

    The document does not provide any information regarding a training set sample size. The VEEGix EEG System appears to be a signal acquisition and display system without explicit mention of deep learning or AI models that would require a dedicated training set in the conventional sense. The "Automatic Artifact Identification" feature might implicitly involve some learned algorithms, but no details on training data are provided.


    9. How the ground truth for the training set was established

    As no training set is mentioned or detailed, there is no information provided on how ground truth for a training set was established.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1