Search Results

CNS Envision is intended for use by qualified personnel in the review, and analysis of patient data collected using external physiological monitors. These data are: raw and quantitative EEG, recorded video data, generic vital signs, electrocardiography, electromyography, intracranial pressures, transcranial Doppler measurements, and Glasgow Coma Score.

CNS Envision includes the calculation and display of a set of quantitative measures intended to monitor and analyze the EEG waveforms. These include, for example, frequency bands, asymmetry, and burst suppression. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.

The aEEG functionality included in CNS Envision is intended to monitor the state of the brain.

CNS Envision is intended for use by a physician or other qualified medical personnel who will exercise professional judgement in using the information. It is intended for use on patients of all ages.

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

CNS Envision is a Microsoft Windows-based software application that facilitates the review, annotation and analysis of patient data and physiological measurements. Some of these data, such as ECG, are displayed in raw format whereas other types, such as EEG, are analyzed and quantified by the software. The specific type of input data that are reviewable by CNS Envision software are: Raw electroencephalography (EEG) Quantitative EEG trends; density spectral arrays (DSA) spectral edge frequency (SEF), alpha-delta ratio (ADR), and amplitude EEG (aEEG) Video Generic vital signs which are heart rate (HR), respiration rate (RR), pulse oximetry (SpO2), blood pressure, arterial blood pressure (ABP), mean arterial pressure (MAP), and body temperature Electrocardiography (ECG) Electromyography (EMG) Intracranial pressure (ICP) Transcranial Doppler (TCD) measurements (e.g. spectral envelope, peak velocity, and pulsatility index; TCD measurement is collected by the predicate K080217 device's interface module which interfaces with the Spencer TCD device cleared in K002533, which was a predicate to the predicate K080217 Glasgow Coma Score (GCS); this parameter is manually entered on the CNS Monitor (K080217) with 3 total GCS scores by the user; the CNS software automatically sums the 3 scores and stores the data to provide a trend graph

CNS Envision also has several features to enable ease-of-use. For example, users may select customized layouts that provide data displays that can be tailored to their monitoring needs according to data sources. The subject device also offers customizable EEG montages that present raw EEG data to medical personnel for interpretation.

Unlike the predicate device, Component Neuromonitoring System™, the subject device does not perform direct data acquisition. Instead, it offers the ability to review data remotely or adjust the review speed.

The provided text is a 510(k) summary for the CNS Envision device. It describes the device's intended use, technological characteristics, and comparison to predicate devices, but it does not contain information about specific acceptance criteria, device performance metrics (e.g., sensitivity, specificity, accuracy), sample sizes for test or training sets, ground truth establishment details, or any multi-reader multi-case (MRMC) study results.

The document states that "Software verification and validation testing was conducted and documentation provided as recommended by the Guidance for the Content of Software Contained in Medical Devices, issued May 2005. Traceability has been documented between all system specifications to validation test protocols. Verification and validation testing includes module-level testing, integration-level testing, and system-level testing. In addition, tests according to “IEC 62366-1:2015, Medical Devices Part 1—Application of usability engineering to medical devices” were performed."

This indicates that some testing was done to ensure the software functions as intended and meets usability standards, but the specific performance results in terms of clinical accuracy or equivalent metrics are not present in this summary. The summary focuses on establishing substantial equivalence based on intended use and technological characteristics rather than a detailed performance study like those typically expected for AI/ML-based diagnostic devices.

Therefore, I cannot provide a table of acceptance criteria and reported device performance, or details about the sample sizes, expert ground truth, adjudication methods, MRMC studies, or standalone performance for this specific device based on the provided text. The device "CNS Envision" is described as software that analyzes and quantifies EEG, but "does not provide any diagnostic conclusion about the patient's condition to the user" and "does not contain automated detection algorithms," suggesting it's a tool for experts rather than an automated diagnostic AI.

To illustrate what such an answer would look like if the information were available, here's a template:

Hypothetical Example (based on standard AI/ML medical device studies, NOT from the provided text):

Given the provided document does not contain the requested information regarding specific acceptance criteria, performance metrics, training/test set details, or human reader studies, I cannot fill out the detailed table and answer the questions directly from the text.

However, if this were an AI-powered diagnostic device, the requested information would typically be presented as follows:

1. Table of Acceptance Criteria and Reported Device Performance (Hypothetical Example - Data NOT from provided text)

Ask a specific question about this device

The Component Neuromonitoring System™ is intended to monitor the state of the brain by recording and displaying EEG signals, and can also receive and display a variety of vital signs and other measurements from third-party monitoring devices (such as ICP, ECG, SpO2, and others). It also has the optional capability to record and display patient video.

The Component Neuromonitoring System is intended for use by a physician or other qualified medical personnel. It is intended for use on patients of all ages within a hospital or medical environment, including the operating room, intensive care unit, emergency room, and clinical research settings.

The Component Neuromonitoring System (CNS) is a portable, computer based system that can continuously record, display, store, and analyze physiological data from multiple monitoring sources in real-time. Electroencephalographic (EEG) data can be recorded from up to 16 electrode locations using the included EEG amplifier. Video can be recorded using an optional video camera. Other data can be recorded from interfaces to third-party monitoring devices, or can be manually entered.

The CNS Monitor consists of the following main physical components: a color flat-panel touchscreen display, an integrated computer system, a Device Interface Module, and an EEG Arnolifier. All hardware components of the monitor are mounted on a wheeled pole stand to provide a compact design, convenient use, and ease of transportation. An Ethernet port is located at the base of the system to allow the archival of patient data to a network. A storage basket can hold electrone supplies, and can also hold the EEG amplifier when the system is not in use.

The Device Interface Module contains six digital serial interfaces for connecting to external monitoring devices and four MDport™ (USB) interfaces used for connecting to other CNS components (such as the EEG Amplifier) or to electrically isolated, USB-based, external monitoring devices. The Device Interface Module also contains a CD/DVD drive for archiving patient recordings, for updating the system software, and for other data storage or retrieval purposes.

The EEG Amplifier is small and lightweight and connects to the Device Interface Module with a flexible 15' cord. It has 19 inputs (including Reference, Ground, and auxiliary inputs) and can record from up to 16 EEG electrode sites. Up to 6 inputs can be used as differential pairs for other physiological signals (e.g.: ECG, EOG, respiration, etc.). Continuous impedance checking automatically detects any electrodes that become loose or detached.

Data can be viewed on the CNS Monitor using a variety of display types: waveform, trend, numeric readout, compressed spectral array (CSA), and density spectral array (DSA). Combinations of multiple display types can be configured in a variety of screen layouts to allow the comparison of different measurements or different time periods from the recording.

The CNS Monitor can compute processed parameters from the EEG data, including: Amplitude Integrated EEG (aEEG), Total Power, Spectral Edge Frequency, EEG Band Power Percentages (delta, theta, alpha, beta), Envelope Amplitude, % Asymmetry, % Suppression, and Inter-Burst Interval (IBI).

The CNS Monitor also has several features to enable ease-of-use. It employs monitoring protocols that can step the user through a monitoring procedure and configure a group of settings for the recording (including EEG electrode sites & montage, collected measurements, and display settings). Pre-configured protocols are included on the system and the user can also create their own customized protocols. Embedded reference content can be viewed on the CNS Monitor to assist the user with system features, device connections, electrode application, and other topics.

Here's a breakdown of the acceptance criteria and study information for the Moberg Research, Inc. Component Neuromonitoring System, based only on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

Important Note: The document does not provide specific quantitative or qualitative performance metrics (e.g., sensitivity, specificity, accuracy, specific thresholds for signal-to-noise ratio, drift, etc.) that would typically constitute detailed acceptance criteria. The acceptance criteria are described in terms of compliance with regulatory standards and general verification/validation.

Regarding the study that proves the device meets the acceptance criteria:

The document describes the performed testing in a general way, rather than detailing a specific, single study with a defined sample size, ground truth, or adjudication method.

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

• Sample Size: Not specified in the provided text.
• Data Provenance: Not specified in the provided text. It refers to "validation and verification testing" and "comparison testing," but provides no details on the data used.

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

• Not specified in the provided text. The document does not mention the use of experts for establishing ground truth in its performance testing summary.

4. Adjudication method for the test set:

• Not specified in the provided text.

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 comparative effectiveness study is mentioned in the provided text. The device is an "EEG Monitor" that records, displays, stores, and analyzes physiological data. It computes parameters from EEG data, but the submission focuses on its equivalence to other neuromonitoring systems, not on assisting human readers in interpretation. Therefore, a study of this nature would not be directly relevant to the described performance testing.

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

• The document describes the system as continuously recording, displaying, storing, and analyzing physiological data. It "computes processed parameters from the EEG data," such as aEEG, Total Power, Spectral Edge Frequency, etc. The performance testing included "comparison testing to ensure the substantial equivalence of the calculation and display of the aEEG." This implies that the algorithm's output (calculated parameters) was evaluated for equivalence. However, the document doesn't explicitly frame this as a "standalone algorithm performance study" with specific metrics against absolute ground truth. It's more focused on equivalence to predicate devices for the calculation and display.

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

• The document implies a "ground truth" based on the performance of predicate devices for the comparison testing of aEEG calculation and display. For other aspects (safety, EMC, general design requirements), the ground truth is adherence to international standards (IEC 60601 series). There is no mention of expert consensus, pathology, or outcomes data being used as ground truth for the device's analytical outputs.

8. The sample size for the training set:

• Not applicable/Not specified. The document describes a medical device, an EEG monitor, which performs signal acquisition, display, and computation of derived parameters. It does not describe a machine learning or AI model that would typically require a "training set" in the conventional sense. The "analysis" capabilities are likely based on established signal processing algorithms rather than learned models from a training set.

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

• Not applicable/Not specified, as no training set for a machine learning model is mentioned.

Ask a specific question about this device