(273 days)
The CRI Zmachine is a single-channel, EEG acquisition and analysis system, designed for use in the home or clinical environments. This device is intended to be used by qualified healthcare practitioners to monitor the wake and sleep states of adult patients and as an adjunct to their diagnosis of sleep disorders.
The CRI Zmachine is a battery-operated, single-channel, EEG acquisition and analysis system. The Zmachine system includes the Zmachine device, disposable EEG sensor cable, and a wall charger. The device operates on data from the differential-mastoid EEG channel to determine the wake and sleep states of the patient every 30 seconds.
Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:
Zmachine® Acceptance Criteria and Performance Study
The Zmachine® is a single-channel EEG acquisition and analysis system designed to monitor wake and sleep states in adult patients and as an adjunct to the diagnosis of sleep disorders. Its performance was evaluated against human scoring consensus.
1. Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Threshold for "high association") | Reported Device Performance |
|---|---|---|
| Zmachine Specificity (Wake) | Not explicitly stated, but implied by overall Kappa | 91.6% |
| Zmachine Sensitivity (Sleep) | Not explicitly stated, but implied by overall Kappa | 95.8% |
| Overall Kappa Agreement | 0.75 | 0.8275 |
2. Sample Size and Data Provenance for Test Set
- Sample Size: 99 subjects.
- Data Provenance: Not explicitly stated, but implied to be from a clinical study where polysomnographic (PSG) data was acquired. The location (country) is not specified. The study was prospective in the sense that the Zmachine data was acquired simultaneously with PSG data for the purpose of the study.
3. Number and Qualifications of Experts for Ground Truth
- Number of Experts: At least two (2) certified polysomnographic technologists per PSG record (3 records scored by 2, 16 records scored by 3, and 80 records scored by 4 technologists).
- Qualifications: Certified polysomnographic technologists. No specific experience level (e.g., "10 years of experience") is mentioned.
4. Adjudication Method for Test Set
The adjudication method used was a consensus of human scorers. Specifically:
- 3 records were scored by 2 technologists.
- 16 records were scored by 3 technologists.
- 80 records were scored by 4 technologists.
The consensus was then used as the ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, an MRMC comparative effectiveness study examining the effect size of human readers improving with AI vs. without AI assistance was not conducted or reported. The study focused on the standalone performance of the Zmachine algorithm against human consensus.
6. Standalone (Algorithm Only) Performance Study
Yes, a standalone performance study was conducted. The performance metrics (specificity, sensitivity, and Kappa agreement) directly reflect the Zmachine algorithm's ability to determine wake/sleep states without human intervention, compared to the expert ground truth.
7. Type of Ground Truth Used
The ground truth used was expert consensus based on visual sleep scoring rules (Rechtschaffen & Kales R&K, 1968) of polysomnographic (PSG) data.
8. Sample Size for the Training Set
The document does not specify the sample size used for the training set. It only describes the clinical study for performance testing.
9. How Ground Truth for Training Set Was Established
The document does not provide details on how the ground truth for the training set was established. It describes the Zmachine's EEG analysis methodology as a "Proprietary adaptive algorithm using time and frequency domain features," but offers no information regarding its development or the data used for training.
§ 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).