K Number
K173193
Device Name
F&P SleepStyle
Date Cleared
2018-08-08

(310 days)

Product Code
Regulation Number
868.5905
Panel
AN
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The device is for use on adult patients for the treatment of Obstructive Sleep Apnoea (OSA). The device is for use in the home or sleep laboratory.

Device Description

The F&P SleepStyle™ is a non-invasive, auto adjusting Continuous Positive Airway Pressure (CPAP) flow generator, incorporating a heated respiratory humidifier. The device is intended to treat Obstructive Sleep Apnea (OSA) by delivering a flow of positive airway pressure at a level prescribed by a physician to splint open the airway and prevent airway collapse.

The F&P SleepStyle™ system is comprised of the following devices/accessories:

  • F&P SleepStyle™ models SPSAAN and SPSCAN: .
  • . Breathing tubes:
    • ThermoSmart™ heated breathing tube; o
    • Standard breathing tube, i.e. non-heated, and elbow connector; O
  • Water chamber and water chamber seal; .
  • USB stick (F&P InfoUSB) .

The F&P SleepStyle™ system is available in two modes, fixed and auto-adjusting CPAP.

Similar to the predicate device, the SleepStyle™ works by pressurizing room air which is then transported to a patient interface. The delivery of positive air pressure to the patient holds the soft tissue in the throat open, preventing airway collapse and thus disruptions to the patient's breathing and sleep.

Humidified CPAP devices include a water chamber which holds water that is heating element in the CPAP device, thus adding water vapor to the gas prior to delivery to the patient. This is integrated into the device. The humidifier reduces nasal dryness and improves patient comfort.

An optional heated breathing tube (ThermoSmart) reduces condensation and improves humidity delivery to the patient.

The proposed device has integrated Bluetooth which allows therapy data to be sent to general wellness applications which can be used by patients for self-assessment and monitoring of therapy progress.

The proposed device also has an integrated modem which automatically uploads therapy data to the software reporting tool InfoSmart (K161686) managed by the healthcare provider. Alternatively data from the device can be stored onto an USB stick and uploaded to the software reporting tool InfoSmart (K161686).

AI/ML Overview

The Fisher & Paykel Healthcare F&P SleepStyle™ device, a non-invasive auto-adjusting CPAP flow generator for treating Obstructive Sleep Apnea (OSA) in adults, underwent both non-clinical and clinical testing to demonstrate substantial equivalence to its predicate device, the F&P ICON (K094040).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly state quantitative acceptance criteria for clinical performance that can be directly mapped to reported performance in a table. However, it indicates that the clinical study aimed to validate the device for the treatment of OSA using APAP and CPAP modes with and without pressure relief technologies. The overall conclusion demonstrates that SleepStyle™ is substantially equivalent to the predicate device F&P ICON (K094040), implying that its performance regarding OSA treatment was considered acceptable.

For non-clinical performance, the acceptance criteria are adherence to various international standards (e.g., ANSI/AAMI ES60601-1, IEC 60601-1-2, ISO 8185, ISO 10993 series, ISO 80601-2-70, ISO 5356-1, ISO 5367). The device has been tested according to these standards, and the non-clinical performance data demonstrates substantial equivalence, indicating it met the requirements of these standards.

Acceptance Criteria CategorySpecific Criteria (Implicit or Explicit from Standards/Validation Goals)Reported Device Performance (Implicit from Conclusion)
Clinical PerformanceDevice effectively treats Obstructive Sleep Apnea (OSA) using APAP and CPAP modes, with and without pressure relief technologies (expiratory relief and SensAwake), demonstrating substantial equivalence to the predicate device.Device validated for OSA treatment using various modes and features; deemed substantially equivalent to predicate.
Non-Clinical PerformanceAdherence to numerous safety and performance standards (e.g., ANSI/AAMI ES60601-1, IEC 60601-1-2, ISO 8185, ISO 10993 series, ISO 80601-2-70, ISO 5356-1, ISO 5367). Functional performance (e.g., pressure accuracy, flowrate, noise, water chamber integrity, transport testing, altitude adjustment, pull test). Biocompatibility. Software safety and lifecycle processes (IEC 62304, ISO 14971).Non-clinical testing carried out covering mechanical, electrical, thermal safety, environmental conditions, EMC, and functional verification. Device has been tested according to listed standards. Biocompatibility testing conducted (cytotoxicity, sensitization, intracutaneous reactivity, acute systemic toxicity, chemical characterization, VOCs, CO, CO2, ozone). Software level of concern moderate; testing done as per IEC 62304 and ISO 14971.

2. Sample Size Used for the Test Set and Data Provenance

  • Sample Size: 50 patients
  • Data Provenance: The clinical validation study was conducted at the Fisher & Paykel Sleep Laboratory in New Zealand following GCP (Good Clinical Practice) guidelines. This indicates a prospective study design as it's a validation study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

This information is not explicitly provided in the document. The study was conducted at a "Sleep Laboratory," which implies involvement of sleep specialists, but the number or specific qualifications of experts establishing ground truth (e.g., for diagnoses or assessment of treatment efficacy beyond automated device data) are not detailed.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (such as 2+1 or 3+1) for establishing ground truth within the clinical study.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No, an MRMC comparative effectiveness study was not explicitly mentioned or performed. The clinical study focused on validating the device's efficacy for OSA treatment, not on directly comparing human reader performance with and without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done

Yes, the testing described appears to include standalone algorithm performance testing as part of the functional bench testing and validation of the device's algorithms. The document mentions:

  • "Functional Bench Testing" was conducted, including "Static and Dynamic Pressure Accuracy," "Flowrate at Maximum Pressure," "Max Pressure Single Fault," "Noise Verification," etc.
  • The device has a "revised auto adjusting CPAP algorithm" and "revised AHI measurement algorithm," which would have been evaluated algorithm-only.
  • The "Software" section confirms that software testing was done as per IEC 62304 and ISO 14971, indicating validation of the embedded algorithms' performance.

7. The Type of Ground Truth Used

For the clinical validation study, the ground truth for OSA treatment efficacy would likely be based on clinical outcomes like changes in Apnea-Hypopnea Index (AHI) or other sleep study parameters, observed and interpreted by sleep clinicians. While not explicitly stated, this is standard for sleep apnea treatment validation.

For the non-clinical testing, ground truth for performance characteristics would be established by measurement against known standards and specifications (e.g., pressure calibration using reference instruments, humidity output measurements against ISO 8185 requirements).

8. The Sample Size for the Training Set

The document does not specify a separate training set or its sample size. This submission is for a medical device (CPAP machine), not a machine learning model that would typically have a distinct training and test set in that context. The "revised algorithms" imply development, but specific training set details are not provided in this regulatory submission summary.

9. How the Ground Truth for the Training Set was Established

As no specific training set is mentioned in the context of a machine learning workflow, the method for establishing its ground truth is not provided. If the algorithms were developed using internal data, their ground truth would have been established through methods standard to the development of such medical device algorithms, likely involving physiological data and expert analysis, but this is not detailed in the provided text.

§ 868.5905 Noncontinuous ventilator (IPPB).

(a)
Identification. A noncontinuous ventilator (intermittent positive pressure breathing-IPPB) is a device intended to deliver intermittently an aerosol to a patient's lungs or to assist a patient's breathing.(b)
Classification. Class II (performance standards).