Search Results

The digital systems Neuron-Spectrum-1, Neuron-Spectrum-2, Neuron-Spectrum-3, Neuron-Spectrum-4 and Neuron-Spectrum- 4/P with Neuron-Spectrum.NET software are intended for use as digital neurophysiological systems intended for recording, processing and display biopotential signals such as Electroencephalography (EEG) and long-latency Evoked Potential (EP). Polysomnography (PSG) derives from Electroencephalography (EEG) by the means of a dedicated software module and dedicated electrodes.

The devices are portable and can register up to 8 (Neuron-Spectrum-1), 16 (Neuron-Spectrum-2), 19 (Neuron-Spectrum-3), 21 (Neuron-Spectrum-4, Neuron-Spectrum-4/P) EEG channels, 1 (Neuron-Spectrum-1, Neuron-Spectrum-2, Neuron-Spectrum-3 and Neuron-Spectrum-4) or up to 4 polygraphic channels (Neuron-Spectrum-4/P: ECG, EOG), 1 breath channel and 2 direct current channels (Neuron-Spectrum-4/P).

Neuron-Spectrum.NET includes the Evoked potentials averaging function and Quantitative electroencephalography (qEEG) , including specific parameters such as Rhythmicity, FFT power ratio and amplitude metrics.

The devices do not provide alarms, do not provide automated event marking and do not provide to the user any diagnostic conclusion about the patient's condition. They are intended for use in the patient care institutions, diagnostics centers, neurosurgical hospitals experimental laboratories and sleep laboratories.The patient group includes all ages and sexes.

The digital systems Neuron-Spectrum-1, Neuron-Spectrum-2, Neuron-Spectrum-3, Neuron-Spectrum-4 and Neuron-Spectrum- 4/P with Neuron-Spectrum.NET software are intended for use as digital neurophysiological systems intended for recording, processing and display biopotential signals such as Electroencephalography (EEG) and long-latency Evoked Potential (EP). Polysomnography (PSG) derives from Electroencephalography (EEG) by the means of a dedicated software module and dedicated electrodes.

The devices are portable and can register up to 8 (Neuron-Spectrum-1), 16 (Neuron-Spectrum-2), 19 (Neuron-Spectrum-3), 21 (Neuron-Spectrum-4, Neuron-Spectrum-4/P) EEG channels, 1 (Neuron-Spectrum-1, Neuron-Spectrum-2, Neuron-Spectrum-3 and Neuron-Spectrum-4) or up to 4 polygraphic channels (Neuron-Spectrum-4/P: ECG, EOG), 1 breath channel and 2 direct current channels (Neuron-Spectrum-4/P).

Neuron-Spectrum.NET includes the Evoked potentials averaging function and Quantitative electroencephalography (qEEG) , including specific parameters such as Rhythmicity, FFT power ratio and amplitude metrics.

The devices do not provide alarms, do not provide automated event marking and do not provide to the user any diagnostic conclusion about the patient's condition. They are intended for use in the patient care institutions, diagnostics centers, neurosurgical hospitals experimental laboratories and sleep laboratories-The patient group includes all ages and sexes

The provided text describes a 510(k) premarket notification for the Neurosoft Neuron-Spectrum series of devices (Neuron-Spectrum-1, -2, -3, -4, and -4/P) with Neuron-Spectrum.NET software. The primary purpose of the submission is to demonstrate substantial equivalence to previously cleared predicate devices, rather than to establish new acceptance criteria through a clinical study. Therefore, the document does not contain a typical "acceptance criteria" table with specific performance metrics (e.g., sensitivity, specificity, AUC) and reported device performance against those criteria as would be expected for an AI/ML device seeking de novo authorization or a PMA.

Instead, the submission focuses on comparing the technological characteristics of the subject device to predicate devices to argue for substantial equivalence. The "acceptance criteria" can be inferred to be that the device performs functionally and safely at least as well as the predicate devices, as demonstrated through technical comparisons and compliance with relevant safety and performance standards.

Here's an attempt to structure the information based on the provided text, acknowledging the limitations due to the nature of a 510(k) submission primarily focused on substantial equivalence:

Inferred Acceptance Criteria and Device Performance (Based on Substantial Equivalence to Predicate Devices)

Study Details:

The provided document describes a 510(k) premarket notification, which relies on demonstrating substantial equivalence to a legally marketed predicate device, rather than a clinical study establishing new performance claims. Therefore, the details requested about sample sizes, ground truth establishment, expert adjudication, and comparative effectiveness studies are not typically found in this type of submission for this class of device.

Here's what can be inferred or stated based on the document's content:

1. Sample size used for the test set and the data provenance:

   • Test Set Description: The document does not describe a clinical test set of patient data used to evaluate the device's performance against specific acceptance criteria. The evaluation is primarily based on technical specification comparisons and compliance with recognized standards (e.g., IEC tests for electrical safety and electromagnetic compatibility).
   • Data Provenance: Not applicable as a traditional clinical test set was not used. The "performance data" refers to validation tests on the device itself (hardware and software) and compliance with standards. The document mentions "Validation tests (Section 16.3), the Software Requirements Specifications (Section 16.4)" but these sections are not provided in the extract.

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

   • Not applicable. As no clinical test set with ground truth was described for independent device evaluation (beyond the intrinsic safety and performance of the device's components and software features), no experts were involved in establishing ground truth for such a test. The evaluation is against predicate device specifications and regulatory standards.

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

   • Not applicable as no clinical test set requiring expert adjudication for ground truth was used.

4. 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 MRMC study was done. This device is an Electroencephalograph system for recording, processing, and displaying biopotential signals. It "does not provide alarms, do not provide automated event marking and do not provide to the user any diagnostic conclusion about the patient's condition." Therefore, it does not involve AI for interpretation or diagnostic assistance to human readers, and thus such a study would not be relevant.

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

   • No standalone algorithm performance study was done. The device's software (Neuron-Spectrum.NET) performs functions such as signal acquisition, review, editing, storing, and analysis (including quantitative EEG parameters like Rhythmicity, FFT power ratio, and amplitude metrics). However, the document explicitly states that the device "does not provide to the user any diagnostic conclusion about the patient's condition." Its functions are presented as tools for trained medical professionals, implying a human-in-the-loop workflow, where the human interprets the displayed signals and analysis. The document does not describe autonomous algorithmic diagnostic output.

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

   • Not applicable for a clinical test set. The "ground truth" for this submission would relate to whether the device's technical specifications and functional performance meet the engineering and safety standards, and are comparable to predicate devices. This involves engineering measurements and comparisons rather than clinical ground truth diagnoses.

7. The sample size for the training set:

   • Not applicable. The document does not describe a machine learning algorithm that underwent a training phase with a specific dataset.

8. How the ground truth for the training set was established:

   • Not applicable, as no training set for a machine learning algorithm is described.

Ask a specific question about this device