(46 days)
Natus NeuroWorks is EEG software that displays physiological signals. The intended user of this product is a qualified medical practitioner trained in Electroencephalography who will exercise professional judgment in using the information. The NeuroWorks EEG software allows acquisition, display, archive, review and analysis of physiological signals. · The Seizure Detection component of NeuroWorks is intended to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic seizures, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with full scalp montage according to the standard 10/20 system. · The Spike Detection component of NeuroWorks is intended to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with full scalp montage according to the standard 10/20 system. · aEEG, Burst Suppression, Envelope, Alpha variability, Spectral Entropy trending functionalities included in NeuroWorks are intended to assist the user while monitoring the state of the brain. The automated event marking function of Neuroworks is not applicable to these analysis features. · Neuro Works also includes the display of a quantitative EEG plot, Density Spectral Array (DSA), which is intended to help the user to monitor and analyze the EEG waveform. The automated event marking function of NeuroWorks is not applicable to DSA. · This device does not provide any diagnostic conclusion about the patient's condition to the user.
Natus NeuroWorks is electroencephalography (EEG) software that displays physiological signals. The software platform is designed to work with Xltek and other select Natus amplifiers (headboxes). Software add-ons and optional accessories let you customize your system to meet your specific clinical EEG monitoring needs.
The provided document describes the Natus NeuroWorks software, an EEG software with functionalities including seizure and spike detection, and various trending capabilities.
Here's an analysis of the acceptance criteria and the study that proves the device meets them:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of quantitative acceptance criteria and corresponding reported device performance with specific metrics (e.g., sensitivity, specificity, accuracy thresholds for seizure/spike detection). Instead, the demonstration of equivalence for the new trend features relies on qualitative comparison to a predicate device.
The "Comments" column in Table 1: Substantial Equivalence, Trends and other features implicitly states the performance goal for the newly added or enhanced features: to be "Equivalent" or "Same" as the specified predicate device. For example, for Burst Suppression, Envelope Trend, Spectral Entropy, Spectral Edge, Alpha Variability, and R-R interval trend, the comment is "Equivalent: Feature added to Natus NeuroWorks Subject device. With this implementation the Natus NeuroWorks Subject device is now equivalent to NicoletOne and Moberg Predicate devices."
For the DSA / Spectrogram feature, the comment indicates that the feature was already available but improved in terms of common naming, additional color scales for better contrast, and improved spectral resolution (64Hz vs 30Hz), making it "equivalent to NicoletOne predicate device."
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not specify a separate "test set" for performance evaluation of the trend features as typically understood in a clinical study context. Instead, for the newly added or improved trend features (Burst Suppression, Envelope, Spectral Entropy, Spectral Edge, Alpha Variability, DSA), the performance evaluation involved showing that the "resulting graphs are identical" when using the same study data as examples from the NicoletOne predicate device.
The document does not provide information on the country of origin of this "same study data" or whether it was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not specify the number or qualifications of experts used to establish ground truth for the trend feature comparison. The comparison relies on visual identity of trend plots against a predicate device.
For the Seizure Detection and Spike Detection components, the indications for use state they are "intended to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic seizures/spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces." This implies that the 'ground truth' for these features is ultimately the interpretation by "qualified clinical practitioners," but the document doesn't detail how this was established for the performance study.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe any formal adjudication method for the performance evaluation of the trend features. The comparison relies on direct graphical comparisons.
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
A multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described. The document states: "There were no clinical studies performed for this submission."
The device functions as "computer-assisted tools" for marking electrographic events to "assist qualified clinical practitioners." However, no study measuring improvement in human reader performance with this assistance is presented.
6. If a standalone (i.e. algorithm only, without human-in-the-loop performance) was done
While the document doesn't explicitly refer to "standalone performance" metrics for seizure and spike detection (e.g., sensitivity, specificity of the algorithm alone), the performance testing for the trend features was essentially a standalone comparison: the algorithm's output (trend graph) was compared to the predicate's algorithm output using the same input data. The "identical" nature of the graphs suggests successful replication of the predicate's standalone trending functionality.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the trend features (Burst Suppression, Envelope, Spectral Entropy, Spectral Edge, Alpha Variability, DSA), the "ground truth" implicitly used for comparison was the output of the predicate device's algorithms on the same raw EEG data. The goal was to demonstrate that the Natus NeuroWorks algorithms produced graphically identical or equivalent trends.
For the Seizure Detection and Spike Detection, the ground truth is ultimately "electrographic seizures/spikes" as interpreted by "qualified clinical practitioners," but the method of establishing this ground truth for validation is not detailed.
8. The sample size for the training set
The document does not provide information on the sample size for the training set for any of the algorithms. It states that the software was "designed and developed according to a robust software development process" and "rigorously verified and validated," but omits details about machine learning model training.
9. How the ground truth for the training set was established
The document does not provide information on how the ground truth for the training set was established. Given the lack of details on training data and methods, this information is not available in the provided text.
§ 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).