(150 days)
The Cadwell ApneaTrak device is intended for home sleep testing, including the acquisition of physiological and environmental data. The recorded signals are then transmitted to a PC so that they can be viewed. ApneaTrak is intended for use on patients older than 2 years of age.
ApneaTrak is intended for use in hospitals, sleep centers and other sleep testing environments, including the patient's home. ApneaTrak is intended to be used when prescribed by a qualified healthcare provider for use on patients suspected of sleep disorders, specifically Sleep Disordered Breathing (SDB) and requires review by qualified medical personnel. ApneaTrak is NOT intended to perform automatic diagnosis.
Cadwell's ApneaTrak is a sleep diagnostic system consisting of: (1) acquisition hardware that can acquire, record, store, and transfer up to 3 channels of ExG (including EEG, EMG, ECG, and EOG signals) data, 2 respiratory effort channels, 1 thermistor channel, 1 pressure channel, 1 snore channel, and 1 oximetry channel; (2) a host electronic device (typically a PC) capable of running the software as well as charging and interfacing with the acquisition device; and (3) software that allows for device configuration and data download.
ApneaTrak is connected, by a clinical user, to a host device via USB cable for initialization. After initialization and having been given instruction on correct clinical use of the device, ApneaTrak is then used by the patient at home. The device acquires and stores physiological and/or environmental data to onboard memory. After use, the device is returned to the clinical user, who connects the device to the host PC. The software downloads and stores data from the device in European Data Format (EDF).
The provided document does not contain an acceptance criteria table detailing specific performance metrics and a study describing how the device meets those criteria with clinical data. Instead, it details that the ApneaTrak device underwent performance testing against recognized electrical safety, electromagnetic disturbance, and performance standards for its various signal acquisition functionalities.
The document indicates that the device's technical specifications and intended use are similar to predicate devices (Zmachine Synergy and Nox T3 Sleep Recorder). The testing primarily focuses on demonstrating compliance with standards and equivalence in signal acquisition performance through bench testing rather than a comparative effectiveness study involving human readers or a standalone algorithm-only performance study.
Here's a breakdown of the available information based on your request:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of acceptance criteria with specific performance thresholds for diagnostic accuracy (e.g., sensitivity, specificity for identifying sleep disorders) that the device must meet against a ground truth. Instead, it lists the following performance tests and their outcomes:
| Test | Test Method Summary | Reported Device Performance (Results) |
|---|---|---|
| ExG | ExG functionality validated by complying with essential performance requirements from IEC 60601-2-26 and IEC 60601-2-40. | All test results demonstrate compliance with the standards. |
| Pulse Oximetry | Pulse oximetry functionality validated by complying with ISO 80601-2-61 Particular requirements for pulse oximeters. | All test results demonstrate compliance with the standard. |
| Respiratory Effort | A known oscillating input signal was injected into the respiratory channel of the subject device. The input and output data were plotted and quantitatively compared. | Passing result based on high measure of equivalence between input and output signals. |
| Airflow - Pressure | A known oscillating input signal was input to the airflow pressure channel of the subject device. The input and output data were plotted and quantitatively compared. | Passing result based on high measure of equivalence between input and output signals. |
| Airflow - Thermal | A known oscillating input signal was input to the airflow thermal channel of the subject device. The input and output data were plotted and quantitatively compared. | Passing result based on high measure of equivalence between input and output signals. |
| Snore | A known oscillating input signal was input to the snore channel of the subject device. The input and output data were plotted and quantitatively compared. | Passing result based on high measure of equivalence between input and output signals. |
| Electrical Safety | Compliance with IEC 60601-1:2005 + CORR. 1:2006 + CORR. 2:2007 + A1:2012, AAMI ES60601-1:2005 +C1+A2 [R2012], IEC 60601-2-40:2016, IEC 60601-2-26:2012, ISO 80601-2-61:2017, IEC 60601-1-11:2015, IEC 60601-1-6:2013, IEC 62304:2006 + A1:2015. | All test results demonstrate compliance with the applicable standards. |
| Electromagnetic | Compliance with IEC 60601-1-2:2014. | All test results demonstrate compliance with the applicable standards. |
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 describes "performance bench tests" where "a known oscillating input signal was injected" or "tested in accordance with internal software requirements, system requirements, and usability requirements." This implies laboratory-based testing with simulated data or controlled inputs rather than a clinical test set with patient data. Therefore, there is no sample size of patients or information on data provenance (country, retrospective/prospective) for a clinical test set provided.
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)
Given the nature of the bench testing described (injecting known signals), the concept of "experts establishing ground truth for a test set" as typically understood in AI/clinical validation studies does not apply here. The ground truth for these tests was the "known oscillating input signal" or the performance requirements of the standards themselves.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
No adjudication method is mentioned, as the testing described focuses on device functionality and signal accuracy against known inputs or standards, not on diagnostic interpretations 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 MRMC comparative effectiveness study was done or reported in the provided document. The device is described as a data acquisition system for home sleep testing, and it "is NOT intended to perform automatic diagnosis." The focus is on accurate signal acquisition, not AI-assisted interpretation or improvement of human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document does not describe a standalone algorithm performance study. The device's purpose is to acquire and transmit physiological data for review by qualified medical personnel. It explicitly states, "ApneaTrak is NOT intended to perform automatic diagnosis."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the bench tests, the ground truth was known oscillating input signals or the defined specifications and requirements of the relevant IEC/ISO standards. For the purpose of regulatory substantial equivalence, the ground truth for the device's claims implicitly relies on the predicate devices and their established performance for similar data acquisition.
8. The sample size for the training set
No training set is mentioned as the document does not describe a machine learning or AI-based diagnostic algorithm that would require a training set. The device is an electrophysiological signal acquisition system.
9. How the ground truth for the training set was established
As no training set is discussed, this question is not applicable.
§ 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).