(266 days)
The DiscoverEEG System, Model DE-401 is intended to be used for measuring and recording the electrical activity of a subject's brain, obtained by placing non-invasive electrodes on the head. The DiscoverEEG, DE-401 is indicated for use in acquiring electroencephalographic (EEG) signals in the OR, ICU, ER, clinical settings and at home and for clinical research. The medical use of data acquired by the DiscoverEEG is to be performed under the direction and interpretation of a licensed medical professional. The DiscoverEEG, Model DE-401 does not provide any diagnostic conclusion about the subject's condition.
The DiscoverEEG System, Model DE-401, is a wearable, medical-grade EEG device that acquires and stores up to four electroencephalograms (EEGs) obtained from noninvasive electrodes placed on a subject's head. The acquired EEG waveforms, as well as, processed EEG spectral variables are continuously stored by the system for later retrieval. The data can be transferred from the DiscoverEEG hardware to a computer for review. The DiscoverEEG System, Model DE-401 has four main components: Acquisition Module, Memory Module, Disposable Electrode Array, and Data Viewer Software.
The provided text does not contain specific acceptance criteria for performance metrics (like sensitivity, specificity, accuracy) related to the interpretation of EEG signals by the DiscoverEEG System, Model DE-401 for diagnostic purposes. This is explicitly stated in the Indications for Use: "The DiscoverEEG, Model DE-401 does not provide any diagnostic conclusion about the subject's condition."
Instead, the non-clinical testing sections focus on the device meeting its design and functional requirements, safety standards (UL, IEC60601-1, IEC60601-1-11, IEC60601-2-26), and electromagnetic compatibility (IEC60601-1-2). The substantial equivalence claim is based on similar intended use, technological characteristics, and principles of operation to predicate devices, with bench testing demonstrating functional performance without providing specific quantitative metrics for diagnostic accuracy.
Therefore, for the aspects requested, here's what can be extracted from the document:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of performance-based acceptance criteria (e.g., sensitivity, specificity) for diagnostic accuracy. The "reported device performance" is primarily qualitative, stating that the device "meets its design and functional requirements" and "performed as expected."
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Design & Functional Requirements | Meets design and functional requirements; performed as expected; no unexpected behavior observed. |
| Safety Standards | Will comply with IEC60601-1, IEC60601-1-11, IEC60601-2-26, and UL medical electrical equipment standards. |
| Electromagnetic Compatibility | Will comply with IEC60601-1-2 and IEC60601-2-26. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable. The document states "Laboratory testing, performed on identical hardware to the DiscoverEEG subject of this submission, demonstrated that the DiscoverEEG, Model DE-401 meets its design and functional requirements." This indicates bench testing rather than a clinical human subject test set. There's no mention of sample size or data provenance in this context.
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)
Not applicable. The testing described is non-clinical bench testing, not involving human interpretation for ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. There was no test set requiring expert adjudication for ground truth.
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
Not applicable. The device "does not provide any diagnostic conclusion about the subject's condition" and the submission states "further clinical data is not required to demonstrate performance for the DiscoverEEG, Model DE-401 for the indication for use subject to this submission." Therefore, no MRMC study was performed to assess human reader improvement with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
Not applicable in the context of diagnostic performance. The device's function is to "measure and record the electrical activity of a subject's brain" and provide "processed EEG spectral variables." The medical use and interpretation are explicitly "to be performed under the direction and interpretation of a licensed medical professional." While the device itself processes signals, the "standalone" performance for diagnostic purposes is not claimed or evaluated. The non-clinical testing focused on hardware functionality and adherence to standards.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable. The testing described is non-clinical/bench testing against design specifications and functional requirements, not against clinical ground truth like expert consensus, pathology, or outcomes data.
8. The sample size for the training set
Not applicable. The document does not describe an AI/ML component that requires a training set for diagnostic or interpretative tasks. The device acquires and processes EEG signals, but its output is for interpretation by a medical professional, not a standalone diagnostic conclusion.
9. How the ground truth for the training set was established
Not applicable, as there is no described training set.
§ 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).