Search Results

The Menai self-adjusting system is indicated for the treatment of Obstructive Sleep Apnea (OSA) in patients (female patients with mild to moderate OSA when using AfH treatment mode) weighing more than 66 lb (30 kg). It is intended for home and hospital use.

Monte Carlo is a mobile application for patients to remotely operate a prescribed compatible ResMed machine and transfer, and display usage and therapeutic information. Monte Carlo also allows healthcare professionals to remotely configure compatible OSA therapy devices.

The Menai FFM is a non-invasive accessory used for channeling airflow to a patient from a compatible ResMed machine such as a continuous positive airway pressure (CPAP) system.

The Menai FFM is:
• to be used by patients weighing more than 66 lb (30 kg) for whom positive airway pressure therapy has been prescribed
• intended for single-patient reuse in the home and hospital/institutional environment.

The Menai system CPAP device retains similar hardware and performance features of the predicate device(s). It is provided in a portable smaller footprint than the predicate for user convenience in the home environment. Key features include mask, tubing, humidification system, and software controls. The Menai System contains a Micro-processor controlled blower system that generates Continuous Positive Airway Pressure (CPAP) from 4-20 cmH2O as required to maintain an "air splint" for treatment of OSA. Included is an optional humidifier component for patients who experience dryness in the upper airways such as mouth or nasal areas.

The Menai system flow generator includes CPAP, AutoSet for Her (AfH) modes. These modes and their treatment parameters are only settable by the Clinician via the Clinician accessible menu of the software. In addition to Patient and Clinician settable features, the software can display patient sleep data and treatment pressures, similar to that found on the predicate S9 Elouera (K140124). The Menai system includes Cheynes Stokes Respiration (CSR) breathing pattern recognition and reporting, this feature remains unchanged as cleared S9 Elouera (K140124).

Here's a breakdown of the acceptance criteria and study information based on the provided text, keeping in mind that the document is a 510(k) summary and not a full clinical study report, so some details (like specific statistical results or full ground truth methods for all tests) may not be explicitly stated.

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't provide a consolidated table of acceptance criteria with numerical performance targets and reported results for all aspects of the device. Instead, it describes various tests and states that the device "met the predetermined acceptance criteria" or "demonstrated compliance."

However, we can infer some criteria and reported performance from the "Non-Clinical Testing" section for the core therapeutic performance:

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

• Test Set Sample Size:
  • Therapeutic Performance (Bench Testing): Not explicitly stated. It mentions "patient breathing patterns" and "digitized breathing patterns" for CSR detection, suggesting a collection of such patterns, but no number is given.
  • Biocompatibility, Electrical Safety, Mechanical, Acoustic, Software V&V: These are generally conducted on device units or software builds, not "patient test sets" in the same way clinical or diagnostic studies are. The sample size for these types of tests would typically refer to the number of devices or components tested, which is not specified.
  • Clinical Study (Humidifier): Not specified.
• Data Provenance: The document does not specify the country of origin for any data cited.
  • Therapeutic Performance (Bench Testing): Retrospective, as it used "digitized breathing patterns" and "patient script file" data.
  • Clinical Study (Humidifier): Prospective for the "clinical study" focusing on bio-burden and impedance.

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

• Therapeutic Performance (Bench Testing), CSR Detection: Not specified. The "Clinical Pass/Fail criteria" were predefined, implying expert input into their establishment, but the number or qualifications of experts used to establish the ground truth for the digitized breathing patterns themselves is not mentioned. Many such patterns are often derived from polysomnography interpreted by sleep specialists, but this is not stated here.
• Other Testing (Biocompatibility, Electrical, Mechanical, Software): Ground truth for these types of engineering and safety tests is established by adherence to recognized international standards and regulatory guidance, rather than expert consensus on individual cases.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for any specific test set. For the CSR detection, it states the Menai system's results were "compared to the predicate S9 Elouera (K140124)" and met "predefined Clinical Pass/Fail criteria." This implies a comparison to an established reference or a standard of performance, but not an independent expert adjudication process on the test cases themselves.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was mentioned. The device being reviewed is a noncontinuous ventilator (CPAP machine), not typically an imaging or diagnostic AI requiring an MRMC study to assess human reader improvement. The "Clinical Study" was focused on the humidifier component's characteristics (bioburden, impedance, replacement interval).

6. Standalone Performance Study (Algorithm Only)

Yes, standalone performance was implicitly studied for the core therapeutic functions and CSR detection:

• Therapeutic Performance (Bench Testing): "A breathing machine simulates patient breathing patterns, which results in the Flow Generator responding in a manner consistent with maintaining the CPAP treatment pressure... or adjusting the CPAP pressure..." This indicates the algorithm's performance in responding to simulated physiological conditions.
• CSR Detection and Reporting: "Side-by-side testing using the same digitised breathing patterns was used for both predicate and Menai system. This test executes patient script file is treated as an individual scenario, which the Menai reports either: No CSR, CSR, CSR + OSA, OSA." This is a standalone test of the algorithm's ability to detect and report these patterns.

7. Type of Ground Truth Used

• Therapeutic Performance (Bench Testing): The ground truth for these tests would be the expected or ideal physiological response to the simulated breathing patterns, as defined by the device's specification and comparison to the predicate device's known performance. This is essentially an engineering-defined "ground truth."
• CSR Detection and Reporting: The ground truth for this was established by the "same digitized breathing patterns" used for both the predicate and new device, which were likely derived from actual patient data previously interpreted and labeled, forming the "patient script files." This would be closer to an "expert consensus" or "polysomnography-derived" ground truth for the underlying physiological events.
• Clinical Study (Humidifier): Laboratory analysis (for bacterial accumulation/proliferation) and direct measurement (for impedance).

8. Sample Size for the Training Set

The document does not provide details about a training set for any algorithms. This is a 510(k) summary, often focused on verification and validation against pre-defined requirements and predicate devices, rather than the developmental aspects of AI/ML algorithms which would typically involve training sets. While there's a "Software Verification and Validation Testing" section, it focuses on general software lifecycle processes rather than machine learning specifics.

9. How Ground Truth for the Training Set Was Established

Since no training set details are provided, the method for establishing its ground truth is also not described.

Ask a specific question about this device