LogoFDA 510(k) Search
K Number
K241390
Device Name
NeuroMatch
Manufacturer
LVIS Corporation
Date Cleared
2024-11-26

(195 days)

Product Code
OMB,OLT,OMA
Regulation Number
882.1400
Type
Traditional
Panel
NE
Reference & Predicate Devices
K182181
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

  1. LVIS NeuroMatch Software is intended for the review, monitoring and analysis of electroencephalogram (EEG) recordings made by EEG devices using scalp electrodes and to aid neurologists in the assessment of EEG. The device is intended to be used by qualified medical practitioners who will exercise professional judgement in using the information.

  2. The Seizure Detection component of LVIS NeuroMatch is intended to mark previously acquired sections of adult EEG recordings from patients greater than or equal to 18 years old that may correspond to electrographic seizures, in order to assist qualified medical practitioners in the assessment of EEG traces. EEG recordings should be obtained with a full scalp montage according to the electrodes from the International Standard 10-20 placement.

  3. The Spike Detection component of LVIS NeuroMatch is intended to mark previously acquired sections of adult EEG recordings from patients >18 years old that may correspond to spikes, in order to assist qualified medical practitioners in the assessment of EEG traces. LVIS NeuroMatch Spike Detection performance has not been assessed for intracranial recordings.

  4. LVIS NeuroMatch includes the calculation and display of a set of quantitative measures intended to monitor and analyze EEG waveforms. These include Artifact Strength, Asymmetry Spectrogram, and Fast Fourier Transform (FFT) Spectrogram. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.

  5. LVIS NeuroMatch displays physiological signals such as electrocardiogram (ECG/EKG) if it is provided in the EEG recording.

  6. The aEEG functionality included in LVIS NeuroMatch is intended to monitor the state of the brain.

  7. LVIS NeuroMatch Artifact Reduction (AR) is intended to reduce muscle and eye movements, in EEG signals from the International Standard 10-20 placement. AR does not remove the entire artifact signal and is not effective for other types of artifacts. AR may modify portions of waveforms representing cerebral activity. Waveforms must still be read by a qualified medical practitioner trained in recognizing artifacts, and any interpretation or diagnosis must be made with reference to the original waveforms.

  8. This device does not provide any diagnostic conclusion about the patient's condition to the user.

Device Description

NeuroMatch is a cloud-based software as a medical device (SaMD) intended to review, monitor, display, and analyze previously acquired and/or near real-time electroencephalogram (EEG) data from patients 18 years old or older. The device is not intended to substitute for real-time monitoring of EEG. The software includes advanced algorithms that perform artifact reduction, seizure detection, and spike detection.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study details for the NeuroMatch device, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

For Seizure Detection:

MetricAcceptance Criterion (Non-Inferiority)NeuroMatch Performance (Mean [95% CI])Predicate (Persyst 14) Performance (Mean [95% CI])Met Criterion?
SensitivityUpper limit of 95% CI for (Persyst 14 - NeuroMatch) -4 per 24hr3.74 [2.59, 5.44]4.26 [3.15, 7.39]Yes

For Spike Detection:

MetricAcceptance Criterion (Non-Inferiority)NeuroMatch Performance (Mean [95% CI])Predicate (Persyst 14) Performance (Mean [95% CI])Met Criterion?
SensitivityUpper limit of 95% CI for (Persyst 14 - NeuroMatch) -1.5 per minute3.24 [2.15, 4.33]3.61 [2.68, 4.53]Yes

2. Sample Sizes and Data Provenance

For Seizure Detection Validation:

  • Test Set Sample Size:
    • Patients: 181 patients with at least 1 verified seizure event, and 10 control patients with 0 verified seizure events.
    • EEG Hours: 979.40 hours from seizure patients, 80 hours from control patients.
    • Events: 504 events used for sensitivity calculation (capped at 6 events per patient).
  • Data Provenance: Data collected from three independent and geographically diverse medical institutions. The document indicates this data was "completely separate and independent from the data used to design and train the algorithm," implying it is retrospective data. Country of origin is not explicitly stated but implied to be the US based on the FDA submission.

For Spike Detection Validation:

  • Test Set Sample Size:
    • Patients: 149 patients with at least 1 verified spike event.
    • Total EEG minutes (hours): 2752.72 minutes (~45.9 hours).
  • Data Provenance: Data collected from three independent and geographically diverse medical institutions. This dataset was also "completely separate and independent from the data used to design and train the algorithm," indicating retrospective data. Country of origin is not explicitly stated.

3. Number and Qualifications of Experts for Ground Truth

  • Number of Experts: Three independent EEG-trained neurologists.
  • Qualifications of Experts: EEG trained neurologists. More specific details like years of experience are not provided.

4. Adjudication Method for the Test Set

  • Seizure Detection: A reference standard was established by a panel of three independent EEG trained neurologists. Seizures were identified based on a 2 out of 3 majority rule.
  • Spike Detection: The reference standard was established by a panel of three independent EEG trained neurologists. Spikes were identified with majority consensus among the annotating physicians (i.e., consensus of at least 2 out of the 3 physicians).

5. MRMC Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study evaluating human reader improvement with AI assistance versus without AI assistance was not explicitly described in the provided text. The study compares the algorithm's performance (NeuroMatch) to a predicate algorithm's performance (Persyst 14), not human performance.

6. Standalone Performance Study

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done for both seizure and spike detection. The results presented in the tables are direct comparisons between the NeuroMatch algorithm and the Persyst 14 predicate algorithm, both run on the validation dataset against a ground truth established by experts.

7. Type of Ground Truth Used

The ground truth used for both seizure and spike detection was expert consensus, specifically "consensus of at least 2 out of the 3 physicians" (majority rule) from independent EEG-trained neurologists.

8. Sample Size for the Training Set

The sample size for the training set is not explicitly provided in the given document. The document states that the validation dataset "was completely separate and independent from the data used to design and train the algorithm," but it does not specify the details of the training data.

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

The method for establishing ground truth for the training set is not explicitly provided in the document. It only states that the validation set was independent of the data used for training and design.

§ 882.1400 Electroencephalograph.

(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).