(67 days)
The SNAP Model 8 device is indicated for use in the diagnostic evaluation of patients for apnea and snoring and to provide quantitative and qualitative analysis of apnea and snoring.
The SNAP Model 8 system is not intended as a substitute for full polysomnography when additional parameters such as sleep stages or EEG activity are required.
The target population consists of patients who are suspected of apnea and/or complain about snoring. The majority of the test procedures will take place at the patient's home, although some may take place in a sleep laboratory. Both pediatric and adult patients may be tested.
The SNAP Model 8 system consists of several components. The Model 8 data recorder and associated sensors and accessories, the SNAP application software which run on a PC in the physician's office, and the SNAP data analysis software located on computers at the SNAP Diagnostics central location.
The SNAP Model 8 Data Recorder is a small DC powered device designed to be simple and easy to use by a patient. It is self-contained, with integrated microcontroller and LCD display and all necessary interface electronics to perform all system recording functions. It does not require connection to a host computer in order to perform the recording functions. The data recorder consists of the physical hardware and firmware that interfaces to the patient to collect the physiological data. The recorder has sensors to collect sound, pulse oximetry, respiration effort (belt), and body position. The information is digitized and stored on a removable solid state memory card (SD card). The data on the removable data card is accessed through a USB port on the device, connecting to a PC running the SNAP application software. The recorder is made from flame retardant ABS plastic and has the following specifications.
Respiratory Channels: 4
Sample Rate: 14 Hz (flow, effort), 2240 Hz (audio)
Measurements: Air Flow, Effort(2), Audio
Oximeter Channels: 2
Measurements: SaO2, Pulse (both sampled at 14 Hz)
Body Position Channel (optional): 1 (sampled at 14 Hz)
Height: 1.375 inches (34.925 mm)
Width: 5.5 inches (139.7 mm)
Depth: 4 inches (101.6 mm)
Weight (with power adapter): 15.9 ounces (0.45 kg)
Power: AC 100-240v 50-60Hz, Battery backup 3.6v Lithium Ion
The SNAP application software consists of a DLL (dynamic link library) and GUI (graphical user interface) and provides the interface for all communication between the recorder and the computer in the doctor's office. The GUI calls DLL functions to interact with the data recorder. The GUI also interacts through the Internet with the central website to transfer the patient data, and provides various data entry functions. The GUI calls DLL functions to program the recorder, check status, clear memory, check USB connectivity, retrieve serial number, retrieve patient data, get time, etc.. The GUI interacts with the website to identify the patient for the programming step and to transfer the collected patient data to the web server.
The data analysis follows a pre-existing procedure that is already in place for earlier models. The patient data from the website is securely downloaded to analysis workstations at SNAP Diagnostics for analysis and processing. The SNAP data analysis software, which runs on PC computers at the SNAP Diagnostics central location, consists of a GUI and algorithms that allow SNAP to display the recorded data and mark the recorded events that are characteristic of sleep and respiratory disorders such as apnea. The software summarizes the events and provides the data necessary to generate a report. The resulting report is then securely uploaded back to the website so it can be made available to the referring physician by a transfer mechanism of their choice.
Here's a breakdown of the acceptance criteria and study information for the SNAP Model 8, as extracted from the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Criteria | Reported Device Performance |
|---|---|---|
| Electromagnetic Compatibility (EMC) | Compliance with CISPR 11:2009 (Radio-frequency emission requirements) | The SNAP Model 8 recorder meets the radio interference Power Line Conducted and Radiated emission requirements of CISPR 11 Group 1, Class B, Industrial, Scientific and Medical (ISM) Radio-Frequency Equipment. |
| Safety | Compliance with IEC 60601-1-2 and any applicable particular standards in this family of international safety standards (General Requirements for Basic Safety and Essential Performance Collateral Standard Electromagnetic Compatibility Requirements and Tests using the test procedures IEC 61000-4-2; IEC 61000-4-3; IEC 61000-4-4; IEC 61000-4-5; IEC 61000-4-6; IEC 61000-4-8; and IEC 61000-4-11). | The SNAP Model 8 recorder meets the requirements of European Standard EN 60601-1-2. |
| Clinical Equivalence (Data Recording) | Signals recorded by the Model 8 are clinically equivalent in every respect to those signals recorded by the predicate device (SNAP Model 7). | The data recorded by the Model 8 was compared to data recorded from the predicate device and analyzed by qualified technicians. The result of the comparison is that the signals recorded by the Model 8 are in every respect clinically equivalent to those signals recorded by the predicate device. |
| Clinical Equivalence (Analysis and Reports) | Presentation, analysis, and reports generated by the analysis software are clinically equivalent in every respect to those of the predicate device (SNAP Model 7). | The presentation, analysis and reports generated by the analysis software were compared to those of the predicate device. The result of the comparison is that the analysis software is in every respect clinically equivalent to the presentation, analysis and reports generated by the predicate device. |
| General Compliance | All tests verified to meet the required acceptance criteria as a result of product requirements and risk analysis; compliance with applicable standards referenced in "Guidance for the Content of Pre-market Submissions for Software Contained in Medical Devices", May 2005. | All tests were verified to meet the required acceptance criteria. The device complies with the applicable standards referenced in the Guidance for FDA Reviewers and Industry "Guidance for the Content of Pre-market Submissions for Software Contained in Medical Devices", May 2005. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the numerical sample size used for the head-to-head comparison between the SNAP Model 8 and the predicate device. The provenance is not specified, though it can be inferred that the comparison was likely conducted with existing data or new data collected specifically for this purpose. The study design described (comparison to predicate) implies a prospective or retrospective collection of data for comparison, but the specifics are not given.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document states that the data was "analyzed by qualified technicians" but does not specify the number of technicians or their specific qualifications (e.g., years of experience, specific certifications).
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1). The "qualified technicians" analyzed the data, but no mention of multiple readers or an adjudication process for discrepancies is provided.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
No MRMC study was performed or described. The SNAP Model 8 is a recording and analysis system, and the "analysis software" mentioned is the algorithm, not an AI assistant for human readers. The study focuses on the equivalence of the device's outputs to a predicate device, not on human reader performance with or without AI.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone comparison was done. The document states:
- "The data recorded by the Model 8 was compared to data recorded from the predicate device and analyzed by qualified technicians." (This highlights the recording accuracy of the hardware.)
- "The presentation, analysis and reports generated by the analysis software were compared to those of the predicate device." (This specifically evaluates the algorithm's output without human intervention for the analysis part.)
The "analysis software" for both the Model 8 and predicate device operates in a standalone fashion to process recorded data and generate reports. The 510(k) summary focuses on the equivalence of the outputs of these standalone algorithms.
7. The Type of Ground Truth Used
The ground truth for the clinical equivalence study was implicitly the data and analysis from the predicate device (SNAP Model 7). The study aimed to show that the Model 8's recorded signals and analysis outputs were "clinically equivalent" to those of the predicate device, which presumably was already accepted as providing valid measurements. No external "gold standard" such as pathology or outcomes data is mentioned beyond comparison to the predicate.
8. The Sample Size for the Training Set
The document does not provide any information about a training set or its sample size. The focus is on demonstrating equivalence to a predicate device, implying that the algorithms in the SNAP Model 8 are "essentially unchanged" from the predicate or are evolutionary modifications, rather than a new algorithm requiring a distinct training and validation paradigm as might be seen with novel AI/ML models.
9. How the Ground Truth for the Training Set Was Established
Since no specific training set is mentioned, there is no information on how its ground truth was established. The existing "pre-existing procedure" and "algorithms are essentially unchanged" from the predicate suggest a reliance on established methods rather than a novel machine learning approach requiring a separate training ground truth.
§ 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).