K Number
K094040
Date Cleared
2010-04-27

(118 days)

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

The F&P ICON™ Series CPAP is for use on adult patients for the treatment of Obstructive Sleep Apnea (OSA). The device is for use in the home or sleep laboratory.

Device Description

The F&P ICON™ Series CPAP is a non-invasive Continuous Positive Airway Pressure (CPAP) flow generator, incorporating a heated respiratory humidifier. The F&P ICON™ Series CPAP is made up of three main models (Auto, Premo and Novo). Features of each of the F&P ICON™ Series CPAP models vary across the model range. The full-featured Auto model has the ability to operate as both a conventional CPAP and an auto-adjusting CPAP. The Auto model of the F&P ICON™ Series CPAP detects apneas, hypopneas, and flowlimitation in the same way that the predicate HC254 device does. The Auto model of the F&P ICON™ Series CPAP also contains an algorithm, called SensAwake™, which is capable of detecting breathing patterns that are indicative of the "anxious" awake state. The SensAwake™ algorithm is identical to that of the predicate HC254 device. An available treatment efficacy reporting software accessory is InfoSmart™. The package offers detailed reporting on therapy effectiveness, including compliance, AHI, leak and pressure. The supplied SmartStick™ fitted at the side of the device transfers this information via USB technology. The device incorporates a ramp feature whereby the delivered pressure gradually increases over a period of 20 minutes until the set pressure is reached. This allows the user to fall asleep at a lower pressure. The F&P ICON™ Series CPAP also includes features such as the SmartDial™, Clock, Alarm and AlarmTunes™.

AI/ML Overview

Here's an analysis of the provided text regarding the F&P ICON™ Series CPAP's acceptance criteria and studies:

Summary of Acceptance Criteria and Reported Device Performance

The F&P ICON™ Series CPAP's testing primarily focused on demonstrating substantial equivalence to existing predicate devices (Fisher & Paykel Healthcare Sleepstyle™ 200 Auto Series HC254 and HC604 CPAP Humidifier). The acceptance criteria were therefore framed around meeting established safety, performance, and functional requirements, as measured through various non-clinical bench tests and compliance with recognized standards.

Acceptance Criteria CategorySpecific Criteria / Standards MetReported Device Performance
Safety- Mechanical, Electrical & Thermal Safety: Compliance with IEC 60601-1 (General Requirements for Safety)."The F&P ICON™ Series CPAP has been tested and complies with the requirements of the following standards: IEC 60601-1 Medical Electrical Equipment General Requirements for Safety"
- Biocompatibility: Compliance with ISO 10993 series standards (cytotoxicity, sensitization, genotoxicity, implantation, irritation) for relevant components."Biocompatibility testing has been conducted at an external test house on relevant components...as per ISO 10993 series standards, encompassing cytotoxicity, sensitization, genotoxicity, implantation and irritation."
- Heated Breathing Tube Temperature: Surface temperature not to exceed 44°C within 250mm of patient connection, air temperature at patient connection port not to exceed 43°C, heated breathing tube and heaterplate disabled before ambient temperature reaches 37°C."ICON™ Heated Breathing Tube Verification Testing - Determining surface temperature of the heated breathing tube does not exceed 44°C within 250mm of the patient connection. and confirming acceptability to design specifications of condensate formation. Verifying air temperature at patient connection port will not exceed 43℃. Verifying heated breathing tube and heaterplate are disabled before ambient temperature reaches 37°C."
- Heaterplate Safety: Heaterplate power removed when air temperature at patient connection port exceeds 43ºC, and in accordance with internal design and safety requirements."ICON™ Heaterplate Verification Testing - Confirming the heaterplate power is removed when the air temperature at the patient connection port exceeds 43ºC, and in accordance with internal design and safety requirements."
- Heated Breathing Tube Structural Integrity: Not to collapse, occlude, or cause safety hazard when tested per ISO 5356 Annex E."ICON™ Heated Breathing Tube Verification Testing - Ensuring the heated breathing tube would not collapse, occlude or otherwise cause a safety hazard when tested in accordance with ISO 5356 Annex E, including several worst case conditions."
- Cleaning & Disinfection: Ability of components to withstand 20 cycles of high-level disinfection (pasteurisation and Cidex OPA) per AAMI TIR12, TIR30, and ISO14937."Relevant components have been independently assessed against AAMI TIR12 and TIR30, and ISO14937 to confirm cleaning methods outlined achieve high level disinfection. ICON™ components in the humidified airpath were tested for their ability to withstand 20 cycles of high level disinfection via pasteurisation and Cidex OPA."
Performance/Functionality- Electromagnetic Compatibility (EMC): Compliance with IEC 60601-1-2."IEC 60601-1-2 Electromagnetic Compatibility Requirements and Tests (incorporating relevant IEC61000 series reference standards)"
- Sleep Apnea Therapy Devices: Compliance with ISO 17510-1."ISO 17510-1 Sleep Apnea Therapy Devices"
- Respiratory Humidification Systems: Compliance with ISO 8185."ISO 8185 Respiratory Humidification Systems"
- Auto-adjusting Pressure (Auto model): Automatically adjust delivered pressure within stated ranges."ICON™ Product Requirement Verification - Ensuring the Auto model can automatically adjust the delivered pressure within the stated pressure ranges."
- Altitude Compensation (Auto & Premo models): Automatically compensate delivered pressure for ambient pressures within stated operating envelope."Ensuring the Auto and Premo models have means to automatically compensate the delivered pressure for ambient pressures within the stated operating envelope."
- Altitude Setting (Novo model): User can set altitude from 0 to 3000m."Ensuring the Novo models has means to allow the user to set the altitude from 0 to 3000m."
- Chamber Spill Test: Chamber meets spill test requirements."ICON™ Chamber Verification Testing - Confirming chamber meets spill test requirements."
- Condensate Formation (Heated Breathing Tube): Acceptability to design specifications."confirming acceptability to design specifications of condensate formation."
- Conical Connectors: Compliance with ISO 5356-1:2004 gauging requirements."ICON™ ISO 5356-1:2004 Product Verification Testing - Confirming that all the conical connectors of the ICON Series CPAP meet the gauging requirements of ISO 5356-1:2004."
Durability/Environmental- Transportation, Storage & Drop Tests: Maintain functionality after environmental tests."ICON™ Transportation, Storage and Drop Tests Verification - Transportation, storage, and drop tests were carried out on ICON™ units. Functional tests were carried out on each unit before and after each environmental test."
Substantial Equivalence- Overall Safety, Effectiveness & Performance: Substantially equivalent to predicate devices (HC254 and HC604). This implies that the new device performs at least as well as, or better than, the predicate devices without raising new questions of safety or effectiveness."Results from device testing confirm that the F&P ICON™ Series CPAP is substantially equivalent to the Fisher & Paykel Healthcare HC254 and HC604 predicate devices in terms of safety, effectiveness and performance."
"This information indicates that the F&P ICON™ Series CPAP is substantially equivalent to the predicate device in terms of safety, effectiveness and performance."

Study Details from the Provided Text:

The provided document describes non-clinical bench testing rather than clinical studies with human subjects.

  1. Sample size used for the test set and the data provenance:

    • Sample Size: Not explicitly stated as a numerical count of units. The testing involved "relevant components," "ICON™ units," and "all the conical connectors." Implies sufficient units were tested to demonstrate compliance with standards and design specifications.
    • Data Provenance: All testing appears to be internal bench testing performed by Fisher & Paykel Healthcare or designated external test houses, as indicated by phrases like "bench tests have been performed on the F&P ICON™ Series CPAP," and "Biocompatibility testing has been conducted at an external test house." The country of origin of the data is implicitly New Zealand, where Fisher & Paykel Healthcare is located.
    • Retrospective or Prospective: All tests described are prospective, as they were conducted specifically for the 510(k) submission to verify the device's design and performance.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • This question is not applicable as the studies described are non-clinical bench tests. The "ground truth" for these tests is defined by established engineering and medical device standards (e.g., IEC, ISO, AAMI) and the device's own design specifications, rather than by expert clinical opinion or diagnosis on patient data.
  3. Adjudication method for the test set:

    • This question is not applicable for non-clinical bench tests. Adjudication methods like 2+1 or 3+1 are used in clinical studies or expert reviews of data to resolve discrepancies in diagnoses or interpretations. Bench test results are typically objective measurements against predefined pass/fail criteria.
  4. 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. The device (a CPAP machine) is not an imaging or diagnostic AI device that would involve human "readers" interpreting cases. The document explicitly states: "Clinical testing was not required to demonstrate the safety and effectiveness of the F&P ICON™ Series CPAP. Product functionality has been adequately assessed by bench testing as above."
  5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

    • This question is not directly applicable in the context of a CPAP machine as it's a therapeutic device, not an AI diagnostic algorithm. However, its "Auto model" has an algorithm to detect apneas, hypopneas, and flow limitation, and the "SensAwake™" algorithm detects "anxious" awake states. The document states:
      • "The Auto model of the F&P ICON™ Series CPAP detects apneas, hypopneas, and flowlimitation in the same way that the predicate HC254 device does."
      • "The SensAwake™ algorithm is identical to that of the predicate HC254 device."
    • This implies that the performance of these internal algorithms was bench-tested for functionality (e.g., "Ensuring the Auto model can automatically adjust the delivered pressure within the stated pressure ranges") and validated by its equivalence to the predicate device, which would have undergone its own validation. No specific "algorithm-only" performance study is detailed beyond functional verification against design specifications and predicate equivalence.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

    • For the non-clinical tests, the "ground truth" was based on:
      • International and national standards: (e.g., IEC 60601-1, IEC 60601-1-2, ISO 17510-1, ISO 8185, ISO 10993 series, AAMI TIR12, TIR30, ISO14937, ISO 5356-1:2004).
      • Device design specifications: For specific functional requirements like temperature limits, spill test requirements, condensate formation, pressure adjustment ranges, and altitude compensation.
      • Predicate device characteristics: The performance and safety profile of the legally marketed predicate devices (HC254 and HC604) served as an implicit benchmark for "substantial equivalence."
  7. The sample size for the training set:

    • This question is not applicable. CPAP machines are not typically "trained" in the machine learning sense. Their internal algorithms (like those for auto-adjustment or SensAwake™) are engineered and validated through traditional software and hardware verification methods, not typically through a "training set" of data.
  8. How the ground truth for the training set was established:

    • This question is not applicable for the same reason as above. If the internal algorithms were developed using models, their "ground truth" would have been based on physiological principles of breathing and sleep disorders, defined by medical understanding and possibly empirical data gathered during the design phase of the original predicate device, but not described in this submission as a separate "training set" with ground truth establishment in a machine learning context.

§ 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).