Search Results

The Neuron-Spectrum-AM system with Neuron-Spectrum.NET software is intended for use as a digital neurophysiological system for recording, processing, and displaying biopotential signals such as Electroencephalography (EEG) and Polysomnography (PSG) derived from Electroencephalography (EEG) by the means of a dedicated software module and dedicated electrodes.

The device is portable and can register up to 21 EEG channels, 4 polygraphic channels, and 1 direct current channel.

The device does not provide alarms, does not provide automated event marking and does not provide to the user any diagnostic conclusion about the patient's condition. They are in patient care institutions, diagnostics centers, neurosurgical hospitals, experimental laboratories. The device can also be used as a home use device under supervision of qualified personnel. The patient group includes all ages and sexes.

The Neuron-Spectrum-AM with Neuron-Spectrum.NET Software (Subject device) is an ambulatory wireless digital neurophysiological device capable of recording, processing, and displaying electroencephalography (EEG), video EEG, long-term monitoring (LTM), and polysomnography (PSG) biopotential signals.

As listed in Table 1, The NS-AM device comprises an Electronic Unit, a Battery Adaptor, an External Rechargeable Battery Bank, a Carrying Pouch and the Neuron-Spectrum.NET desktop application software. The Neuron-Spectrum.NET Software application was cleared in the Predicate's 510(k) submission (K133995).

The Subject device supports up to 21 EEG channels, 4 wide-band polygraphic channels, 1 breath channel, and 1 direct current channel for a total of 27 analog input channels.

The Electronic Unit acquires, records and transmits biopotential signals such electroencephalography (EEG) and polysomnography (PSG). The built-in 2.4GHz Wi-Fi radio allows real-time transfer of the collected biopotential signals to the computer running the Neuron-Spectrum.NET software. The biopotential signals are also recorded onto a removable SD memory card as back up for later post analysis.

The Electronic Unit includes a front panel ON/OFF power button, a light sensor and a User Interface (UI). The UI consist of a liquid crystal display and three menu navigation buttons. Figure 4 shows the UI main functions. The Electronic Unit can be powered by replaceable internal AA batteries or by the External Rechargeable Battery Bank.

The Electronic Unit and the External Rechargeable Battery Bank reside side-by-side inside the Carrying Pouch. The pouch is strapped and worn over the patient clothing while in use.

The Neuron-Spectrum.NET software is a computer application that receives, records, processes, and displays the biopotential signals collected by the electronic unit on the PC display. The main operations provided by the Neuron-Spectrum.NET software are:

• EEG Acquisition
• · EEG Review, Editing, Storing, Exporting.
• EEG Analysis
• Creation of Exam Reports
• · Program Setup

The electronic unit measures (141 H x 96 W x 36 D) mm and weighs about 270 grams. The External Rechargeable Battery Bank unit measures (165 H x 106 W x 25 D) mm and weighs about 570 grams. The combined weight for the electronic unit, the battery adaptor and the External Rechargeable Battery Bank is approximately 880 grams.

The provided FDA 510(k) summary (K220254) for the Neurosoft Ltd. Neuron-Spectrum-AM with Neuron-Spectrum.NET Software describes the device and its claimed substantial equivalence to a predicate device (K133995). Given the information, here's a breakdown of the requested details:

1. Table of Acceptance Criteria and Reported Device Performance

This 510(k) summary does not explicitly state specific, quantifiable acceptance criteria (e.g., "sensitivity must be > X%") for the device's diagnostic performance, nor does it report specific performance metrics like sensitivity, specificity, accuracy, etc., for the device's clinical efficacy.

Instead, the acceptance criteria are implicitly met through demonstrating substantial equivalence to a predicate device by showing that it "is as safe, as effective, and performs as well as or better than the Neuron-Spectrum-4/P with Neuron-Spectrum.NET Predicate device".

The "reported device performance" is focused on passing various non-clinical engineering and software tests to demonstrate this substantial equivalence.

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

The 510(k) summary explicitly states under "8.2. Clinical Testing": "The substantial equivalence for the Subject device will not be demonstrated by results of clinical testing. Therefore, no clinical testing was performed."
This means there was no test set of patient data used for clinical performance evaluation. The data provenance is therefore not applicable as no clinical data was used in the assessment for this submission.

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

Since no clinical testing was performed and no test set of patient data was used, this information is not applicable.

4. Adjudication Method for the Test Set

As no clinical testing was performed, an adjudication method for a test set is not applicable.

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

No MRMC study was done, as explicitly stated that "no clinical testing was performed." Therefore, information on the effect size of human readers improving with AI vs. without AI assistance is not applicable. The device does not include an AI diagnostic component for interpretation; it is a signal acquisition and processing system.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

No standalone performance study was done for an algorithm's diagnostic capability, as the device's function is to record, process, and display biopotential signals (EEG/PSG), not to provide automated diagnostic conclusions or interpretations. The device "does not provide automated event marking and does not provide to the user any diagnostic conclusion about the patient's condition."

7. The Type of Ground Truth Used

Given that no clinical testing was performed, there was no clinical ground truth (expert consensus, pathology, outcomes data, etc.) established for the purpose of demonstrating clinical performance. The "ground truth" for the engineering performance tests would be defined by the known specifications of the test equipment and the expected outputs under controlled conditions.

8. The Sample Size for the Training Set

Since this is a medical device for recording and processing biopotential signals and not a machine learning/AI diagnostic algorithm that requires training on patient data for clinical interpretation, there is no training set in the context of typical AI algorithm development. The device's "training" refers to its engineering design and manufacturing processes.

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

As there is no training set as typically understood for an AI algorithm, this information is not applicable. The "ground truth" for the device's development lies in engineering specifications, regulatory standards, and the functional performance of the predicate device.

Ask a specific question about this device

Neuro-IOM system with Neuro-IOM.NET software is a medical device intended for intraoperative neurophysiologic monitoring: the device provides information to assess a patient's neurophysiological status.

The system allows to monitor the functional integrity and/or mapping of central and peripheral nervous system including motor and sensory pathways.

It is provided in III different configurations:

I. 32/B

II. 32/S

III. 16/S

The system ensures the following IOM modalities: free-run EMG (electromyography), direct nerve stimulation including pedicle screw test, SSEP (somatosensory evoked potentials), MEP (motor evoked potentials), EEG (electroencephalography), AEP (auditory evoked potentials), VEP (visual evoked potentials), direct cortical stimulation. Also the train-of-four (TOF) stimulation is performed.

The system is not intended to measure the vital signs. It records the data to be interpreted by the neuromonitoring specialist.

Neuro-IOM system with Neuro-IOM.NET software is a medical device intended for intraoperative neurophysiologic monitoring: the device provides information to assess a patient's neurophysiological status.

The system allows to monitor the functional integrity and/or mapping of central and peripheral nervous system including motor and sensory pathways. It is provided in III different configurations:

I.32/B 32/8 II. III. ાર્ભદ્ર

The system ensures the following IOM modalities: free-run EMG (electromyography), direct nerve stimulation including pedicle screw test, SSEP (somatosensory evoked potentials), MEP (motor evoked potentials), EEG (electroencephalography), AEP (auditory evoked potentials), VEP (visual evoked potentials, direct cortical stimulation. Also, the train-of-four (TOF) stimulation is performed.

The system is not intended to measure the vital signs. It records the data to be interpreted by the neuromonitoring specialist.

The systems can be used in operating rooms, intensive care units of different health care facilities (including clinics, hospitals, health centers, ambulance centers, etc.), specialized medical facilities (including prevention centers, medicine centers for emergency, military and medical expertise centers), research and educational medical and biological facilities where the neuromonitoring is required, only by qualified operators who have received training on these devices.

The provided text is an FDA 510(k) summary for the Neuro-IOM system. It details the device's technical specifications and compares them to a predicate device (Xltek Protektor 32) to demonstrate substantial equivalence, rather than providing the results of a specific clinical study with defined acceptance criteria and human reader performance.

Therefore, many of the requested details about acceptance criteria, clinical study design, sample sizes, expert ground truth, and MRMC studies are not present in this document because they are not typically required for a 510(k) clearance based on substantial equivalence for this type of device. The focus is on demonstrating that the new device is as safe and effective as a legally marketed predicate through non-clinical testing and comparison of specifications.

However, I can extract the information that is available and note what is not provided.

Acceptance Criteria and Device Performance:

The document does not present specific "acceptance criteria" for a clinical performance study in the typical sense of metrics like sensitivity, specificity, accuracy, or AUC. Instead, the "acceptance criteria" are implied by the demonstration of substantial equivalence to the predicate device, primarily through comparison of technical specifications and non-clinical performance testing (biocompatibility, electrical safety, EMC, performance tests, and software verification/validation).

The "reported device performance" is demonstrated by showing that the Neuro-IOM system's technical attributes are either identical or sufficiently similar to the predicate device, or where differences exist, they do not adversely affect safety and effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance

As noted, there isn't a direct table of clinical acceptance criteria and performance metrics. Instead, the document provides detailed comparison tables between the subject device (Neuro-IOM system) and the predicate device (Xltek Protektor 32) across various attributes. The acceptance is implied if the differences are found to not adversely affect safety and effectiveness.

Here's a summary of the technical performance comparison, which serves as the basis for the "acceptance" of substantial equivalence:

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

• Sample Size: This document does not describe a clinical study with a "test set" sample size in terms of patient data. The evaluation for 510(k) clearance was based on non-clinical testing (e.g., electrical safety, EMC, performance tests, software verification/validation) and comparison to a predicate device.
• Data Provenance: Not applicable as no clinical patient data set was used for performance evaluation described here. The company, Neurosoft Ltd, is based in the Russian Federation.

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

• Not applicable. There was no clinical "test set" and thus no ground truth established by experts for that purpose. The ground truth for this submission is implicitly the established safety and effectiveness of the predicate device and the adherence to relevant medical device standards.

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

• Not applicable. There was no clinical "test set" requiring adjudication.

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 MRMC study was done. This device is an intraoperative neurophysiological monitoring system, not an AI-powered diagnostic imaging tool that would typically undergo such a study. The product description does not indicate AI assistance that would augment human reader performance in interpreting findings beyond displaying physiological data.

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

• The device functions as a physiological monitoring system that "records the data to be interpreted by the neuromonitoring specialist." It is not a standalone diagnostic algorithm that operates without human interpretation. Its performance is demonstrated through its hardware and software specifications for signal acquisition and display, similar to the predicate device.

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

• The "ground truth" for this 510(k) submission is the demonstrated safety and effectiveness of the predicate device (Xltek Protektor 32) and compliance with relevant industry standards (e.g., AAMI/ANSI ES 60601-1, IEC 60601-1-2, IEC 62366-1, ISO 10993 series). The testing focused on functional equivalence and safety conformance, not diagnostic accuracy against a clinical ground truth.

8. The sample size for the training set:

• Not applicable. This document is a 510(k) summary for a physiological monitoring device, not an AI/ML device 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.

Ask a specific question about this device

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