(76 days)
The MediByte™ is a portable sleep data recorder used to record physiological signals during sleep while the patient is either at home or in a clinical environment. The data is downloaded after the recording is completed and the assist software enables the trained human professional typically a Registered Sleep Technologist or Medical Doctor - to verify the results of the study and generate a report.
Target Population: Children and adult patients who are screened during sleep disorder studies.
Environment of Use: The majority of the screenings occur either in the home at in a clinical setting.
The MediByte™ is intended to be used only by or on the order of a physician.
The MediByte™ is a palm-sized recording device capable of acquiring and storing physiological signals from FDAcleared sensors and transmitting the physiological data to a computer through the Universal Serial Bus (USB) port.
The MediByte™ records up to 8 channels of physiological signals: either electromyogram (EMG), or electrocardiogram (EKG); as well as chest effort; abdominal effort; airflow pressure; snoring; body position; arterial oxygen saturation (SpO2); and pulse rate. The signals cannot be viewed in real time, but can be downloaded after collection for assisted analysis by a human professional trained in the analysis and reporting of sleep disorders medicine.
The MediByte™ is powered by one ½ AA battery and connects to a computer via the MediByte™ USB communication cable. The MediByte™ and sensors are both typically worn by the patient during the recording and all patient contact materials consist of latex-free biocompatible material.
The provided text describes the acceptance criteria and performance of the MediByte™ device, primarily through comparison to a predicate device, the MediPalm®.
Here's an analysis based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Functional Performance | Capable of meeting stated performance specifications and producing readable output. (Passed all tests) |
| Software Compliance | Compliance with "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 2005). (Passed all tests) |
| Software Verification/Validation | Compliance with "General Principles of Software Validation: Final Guidance for Industry and FDA Staff" (Jan 11, 2002). (Passed all tests) |
| Environmental & Electrical Safety | Compliance with "Electroencephalograph Devices Guidance for 510(k) Content" (Nov 03, 1997). (Passed all tests) |
| Signal Quality/Equivalence | Recorded readable and appropriate signals. Performance was "identical" to the predicate device (MediPalm®) in simulation tests. |
2. Sample size used for the test set and the data provenance:
- Sample Size: The document mentions "Analysis of overnight studies" and "Simulation tests" without specifying the exact number of patients or samples used for these tests. Therefore, the sample size for the test set is not explicitly stated.
- Data Provenance: The studies appear to be internal tests conducted by BRAEBON Medical Corporation to demonstrate equivalence. The document does not specify country of origin for the data (e.g., patient demographics from a specific country) or whether the data was retrospective or prospective clinical data. It primarily describes internal testing and simulations.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document implies that "Assisted analysis by a human professional trained in the analysis and reporting of sleep disorders medicine" for verifying results the software generates. However, it does not specify the number of experts used for establishing the ground truth of the test set, nor their specific qualifications (e.g., years of experience) beyond "trained human professional typically a Registered Sleep Technologist or Medical Doctor."
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- The document does not specify any formal adjudication method (like 2+1 or 3+1) for establishing ground truth within the context of performance testing or a clinical study. It implies that a "trained human professional" verifies the results but doesn't detail a consensus or arbitration process.
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, an MRMC comparative effectiveness study was not done. The device description indicates that "assisted software enables the trained human professional... to verify the results of the study and generate a report," suggesting a human-in-the-loop system. However, the performance testing section focuses on the device's functional integrity and signal equivalence to a predicate device, not on the comparative effectiveness of human readers with vs. without AI assistance. Therefore, no effect size for human reader improvement is reported.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The device's intended use explicitly states: "The data is downloaded after the recording is completed and the assist software enables the trained human professional... to verify the results of the study and generate a report." This clearly indicates a human-in-the-loop system, not a standalone (algorithm only) performance evaluation. The device is a "portable sleep data recorder," where the software assists a human professional, implying the algorithm is not intended for standalone diagnostic decisions.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the core performance assessment related to signal quality and equivalence, the ground truth appears to be based on comparison to the established performance of the legally marketed predicate device, MediPalm®. The statement "The performance of the BRAEBON Medical Corporation MediByte™ (subject device) was identical to that of MediPalm® (predicate device)" suggests that the MediPalm's output served as the reference for signal accuracy. For the "overnight studies," the ground truth for interpreting the physiological signals would presumably come from standard sleep study analysis by qualified professionals, but this isn't explicitly detailed as an expert consensus process for setting a definitive "ground truth" for the test set itself.
8. The sample size for the training set:
- The document does not mention a "training set" in the context of machine learning or AI development. The device appears to be a signal acquisition and recording device with "auto assist software," rather than a deep learning model that requires explicit training data. The testing described is primarily functional and comparative to a predicate device, not an evaluation of an AI algorithm's learned performance.
9. How the ground truth for the training set was established:
- Since there's no mention of a training set or an AI algorithm that was "trained," there's no information on how a ground truth for such a set would have been established.
§ 868.2375 Breathing frequency monitor.
(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).