(28 days)
The device is intended to record the physiological data required for EEG and sleep studies (Polysomnography or PSG). These data, may be used by clinicians in Sleep Disorders, Epilepsies and other disorders as a diagnostic aid.
The device is intended to record cerebral, extracerebral and other bio-potential activities for EEG and Sleep Studies via legally marketed PSG reading software. These data may be used by clinicians in sleep disorders, Epilepsies and other related disorders as a diagnostic ald.
The device is intended to record the physiological data required for EEG and sleep studies (Polysomnography or PSG).
The provided text describes a Special 510(k) Notification for the Nihon Kohden PSG Input Box, Model JE-912AK. However, the document primarily focuses on regulatory compliance, substantial equivalence to a predicate device, and general performance testing rather than a detailed study with specific acceptance criteria and performance metrics described in the way you've outlined.
Based on the provided text, I can infer the following:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of specific quantitative acceptance criteria or detailed reported device performance in the format of accuracy, sensitivity, specificity, or similar metrics typically associated with AI/algorithm performance. Instead, it states:
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Regulatory Compliance & Standards adherence | The device complies with IEC 601-1 sub-clause 56.3(c) implemented by 21 CFR Part 898. It also conforms to voluntary industrial standards: IEC 60601-1 (1988), Amendment 1 (1991), Amendment 2 (1995), IEC 60601-1-1 (1992), Amendment 1 (1995), IEC 60601-1-2 (1993), CISPR11 Group 1, Class B, IEC 60601-2-26 (1994). |
| Product Specifications | "The completed testing showed that the device met its product specifications." |
| Safety & Reliability | Verified conformance to safety and reliability. |
| Software Functionality | "Software verification and validation tested the operation of the software functions of the device. The results confirmed that the device performed within specifications." |
| Environmental Testing | Subjected to temperature/humidity stress testing. |
| Electromagnetic Compatibility | Subjected to electromagnetic interference / electromagnetic compatibility testing. |
| Design Controls | Developed in accordance with design controls. |
2. Sample size used for the test set and the data provenance
The document does not specify a "test set" with a particular sample size for evaluating algorithmic performance. The testing described is for hardware and software functionality, safety, and compliance, not for diagnostic accuracy evaluated against a specific dataset of patient cases. Thus, data provenance (country, retrospective/prospective) is not applicable in this context.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. The ground truth concept as described (e.g., expert consensus for diagnostic accuracy) does not apply to the type of performance testing reported in this submission for an EEG/PSG amplifier. The ground truth for electrical and safety performance would be established by engineering standards and test equipment.
4. Adjudication method for the test set
Not applicable, as there is no mention of a diagnostic performance 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 such study was conducted or reported. This device is an amplifier for recording physiological data, not an AI-powered diagnostic tool. It records data that may be used by clinicians as a diagnostic aid with "legally marketed PSG reading software."
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
No standalone algorithm performance was conducted or reported. The device itself is hardware.
7. The type of ground truth used
For the reported performance testing (safety, electrical, software functionality), the ground truth is based on engineering specifications, regulatory standards (e.g., IEC), and design control documents. There is no mention of expert consensus, pathology, or outcomes data being used as ground truth for this device's performance evaluation as described.
8. The sample size for the training set
Not applicable. This device is not an AI/ML algorithm that requires a training set.
9. How the ground truth for the training set was established
Not applicable for the same reason as above.
§ 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).