(89 days)
Sleepiz One+ is a contactless medical device intended to measure heart rate and respiration rate in adult patients, at rest or during sleep (in non-motion condition) and to detect patient presence and body movements.
The Sleepiz One+ hardware unit is intended to be used by a healthcare professional when the recordings are performed in a clinical setting, or by patients or their caregivers when the recordings are performed in a home environment. The Sleepiz One+ cloud software is intended for use by healthcare professionals.
This device is not indicated for active patient monitoring, as it does not provide alarms for timely response in life-threatening situations. It is not indicated for use on pregnant women or patients with active implantable devices.
Sleepiz One+ is a contactless medical device that uses radar technology to measure respiration rate and heart rate from a resting or sleeping patient.
The Sleepiz One+ consists of a hardware unit and cloud-based software The hardware unit can be positioned on a bedside table, mounted on a stand, or attached to the wall behind the patient's bed. It is designed to monitor physiological signals by detecting small body movements, such as those caused by breathing and heartbeat, using Doppler radar. The recorded signals are then transmitted via Wi-Fi to cloud-based software, where they are analyzed to obtain respiration rate, heart rate, and body movement. These outputs can be exposed via the Application Programming Interfaces (APIs) to allow healthcare professionals the review and annotation of the data and compilation of results into reports.
Outputs
- Breathing pattern
- Instantaneous breathing rate [breaths per minute]
- Breathing rate statistics (10th, 50th, and 90th quantiles) [breaths per minute]
- Body movement
- Time in bed [hours]
- Presence detection
- Heart rate [beats per minute]
- Heart rate statistics (10th, 50th, and 90th quantiles) [beats per minute]
The overall system can be grouped into 4 major components, which are classified on the basis of the logical component interfaces where data exchange is occurring.
- Sleepiz Hardware - This is a hardware component serving as primary data acquisition device.
- Embedded Software - This encompasses the firmware running of the Sleepiz Hardware. This, together with Sleepiz hardware, is responsible for data acquisition. The embedded software forms the crux of the Sleepiz hardware such that it defines and controls the data acquisition process. The security aspects related to the operation of the device are incorporated in the design and implementation of embedded software.
- Sleep Analytics Software - The sleep analytics software is responsible for processing data from the Sleepiz Hardware and returning its analytics (e.g., breathing rate, heart rate), as well as its statistics (e.g., mean breathing rate, total recording time, etc.). This refers to the ML model deployed within the cloud software. By itself, the Sleep Analytics Software does not have an external interface. It is wholly encapsulated by the cloud software component Data Processing Layer.
- Cloud Software - The cloud software can be divided into the backend service and the analytics service. The backend service includes modules for data ingestion, a public API, a private API, and a module for sending analysis process requests. The analytics service is responsible for receiving analysis requests and interacting with the sleep analytics software.
The FDA 510(k) clearance letter for Sleepiz One+ (2.5) indicates that the device's substantial equivalence to a predicate device (Sleepiz One+) was established primarily through non-clinical performance testing, focusing on software verification and validation, electrical safety, and electromagnetic compatibility. The document states that the subject device and the predicate device have the same intended use, principle of operation, and similar technological characteristics. The minor modifications (API-based data access instead of web interface and plug-in power instead of battery) were assessed for safety and effectiveness without requiring extensive new clinical studies.
The provided document does not detail specific acceptance criteria for the accuracy of heart rate and respiration rate measurements, nor does it provide a study proving the device meets these specific performance criteria. The clearance is based on the conclusion that "The verification and validation tests performed on the subject device confirm that the device performs as intended in the specified use conditions and comparably to the predicate device. The performance testing conducted shows comparable results between the two models, thereby, demonstrating the safety and performance of the Sleepiz One+ (V.2.5)."
Therefore, based solely on the provided text, a comprehensive table of acceptance criteria and the detailed study proving the device's accuracy against those criteria cannot be constructed. The document infers that the device performs as intended and comparably to the predicate, but it does not present the raw performance data or the specific acceptance thresholds for heart rate and respiration rate accuracy.
Here's a breakdown of the requested information based on the provided text, with clear indications where the information is NOT available.
1. A table of acceptance criteria and the reported device performance
Information NOT available in the provided text. The 510(k) summary states that "performance testing conducted shows comparable results between the two models," but it does not quantify these results or list specific acceptance criteria for heart rate and respiration rate accuracy. The testing primarily focused on software validation, electrical safety, and EMC.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Information NOT available in the provided text. The document mentions "non-clinical performance tests" and "verification and validation tests," but it doesn't specify any sample sizes for a test set related to the accuracy of vital sign measurements, nor the provenance of any data used for such testing.
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)
Information NOT available in the provided text. There is no mention of external experts or ground truth establishment in the context of vital sign accuracy, as the clearance seems to rely on comparability to a predicate device and engineering verification/validation. For devices measuring physiological parameters, ground truth is typically established via reference medical devices (e.g., ECG, capnography) rather than expert consensus on subjective data.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Information NOT available in the provided text. Since no details on a clinical or performance study involving human subjects and expert review are provided, there is no mention of an adjudication method.
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
Information NOT available in the provided text. The Sleepiz One+ is a vital signs monitor, not typically an AI-assisted diagnostic imaging device that would undergo MRMC studies. The device primarily measures heart rate and respiration rate via radar and processes this data in cloud software (Sleep Analytics Software contains the ML model). The interaction is between the device and the patient, not a "human reader" interpreting AI outputs in a MRMC context. The cleared device provides raw data and statistics (like quantiles), which healthcare professionals would then interpret.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device's core function, measuring heart rate and respiration rate from radar signals using its Sleep Analytics Software (which contains the ML model), operates in a standalone manner to generate these outputs. The outputs themselves (instantaneous rates, statistics) are generated by the algorithm without human intervention in the loop of the measurement process itself. Healthcare professionals then access and interpret these results via API. The non-clinical performance testing would have validated the output of this standalone algorithm against internal specifications or a reference.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Information NOT explicitly stated in the provided text regarding vital sign accuracy. For devices measuring heart rate and respiration rate, ground truth is typically established using established reference medical devices (e.g., synchronously recorded ECG for heart rate, capnography or impedance pneumography for respiration rate). While not stated, it can be inferred that if accuracy was evaluated, it would be against such objective physiological measurements rather than subjective expert consensus or pathology.
8. The sample size for the training set
The device uses an "ML model deployed within the cloud software" for "Sleep Analytics Software." However, the provided 510(k) summary does NOT provide any details about the training set size or methodology for this ML model. The focus of the substantial equivalence claim is on the overall system's safety and performance comparability to the predicate, with modifications primarily linked to data access and power source.
9. How the ground truth for the training set was established
Information NOT available in the provided text. As with the training set size, the 510(k) summary does not provide details on how the ground truth for the training set (if any specific to the ML model) was established.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).