Search Results

The AirFit N20 channels airflow non-invasively to a patient from a positive airway pressure (PAP) device such as a continuous positive airway pressure (CPAP) or bilevel device.

The AirFit N20 is:
• to be used by patients weighing more than 66 lb (30 kg) for whom positive airway pressure has been prescribed
• intended for single patient re-use in the home environment and multi-patient re-use in the hospital / institutional environment.

The modified ResMed AirFit N20 is a non-invasive vented respiratory mask that provides a silicone air seal around the patient's nose and upper lip. The mask is held in place with adjustable head straps. Air flow from a positive air pressure (PAP) source is directed to the patient's airway non-invasively. It connects to a conventional PAP device air delivery hose via a standard 22mm swivel.

The modified AirFit N20 comprises 4 subassemblies: headgear, frame, cushion and elbow/short tube. The exhaust port is incorporated into the elbow/short tube assembly. For home use, the mask may be cleaned in warm soapy water.

The AirFit N20 is a prescription device supplied non-sterile.

This document describes the regulatory submission for the ResMed AirFit N20, a non-invasive vented respiratory mask. The submission, K161978, is a modification of a previously cleared predicate device, AirFit N20 (K153673), aiming to demonstrate substantial equivalence.

Based on the provided information, the following can be extracted:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state sample sizes for specific tests (e.g., number of masks tested for CO2 rebreathing, or number of cleaning/reprocessing cycles). It mentions "testing to simulated normal use and reasonable abuse scenarios," suggesting laboratory-based testing.

• Data Provenance: The testing was conducted by ResMed Ltd, an Australian company, for a device intended for international markets (indicated by FDA submission). The data is retrospective in the sense that it's bench testing and verification/validation conducted by the manufacturer, not a prospective clinical trial. There is no mention of data from human subjects in the testing phase beyond what is implicitly covered by biocompatibility standards.

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

Not applicable. This is a medical device submission primarily relying on bench testing and engineering verification/validation against international standards (e.g., ISO 17510:2015, ISO 10993 series) and comparison to a predicate device, rather than human expert-established ground truth for a diagnostic output. The "ground truth" here is the adherence to established engineering specifications and safety standards.

4. Adjudication Method for the Test Set

Not applicable for this type of submission. The evaluation is based on objective measurements against pre-defined engineering and performance criteria and adherence to recognized standards.

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

No. This document explicitly states: "Clinical data was not relied upon to demonstrate Substantial Equivalence to the predicate device. Bench testing demonstrates that the modified AirFit N20 mask device performs in an equivalent manner and is as safe and as effective as the previously cleared predicate AirFit N20 device (K153673)." Therefore, an MRMC study is not relevant to this submission.

6. Standalone Performance (Algorithm Only without Human-in-the-loop Performance)

Yes, in the sense that the device's functional and mechanical performance was evaluated in isolation ("bench testing") against pre-defined specifications and standards. This is not an AI algorithm, but a physical medical device; its "standalone performance" refers to its intrinsic characteristics and operation.

7. Type of Ground Truth Used

The "ground truth" for this device, as described in the submission, is based on:

• International Standards: Primarily ISO 17510:2015 (Medical devices – Sleep apnoea breathing therapy Masks and application accessories) and ISO 10993 series for biocompatibility.
• Engineering Specifications: Predetermined acceptance criteria derived from the device's design requirements and performance characteristics of the legally marketed predicate device (K153673).
• Predicate Device Performance: The original AirFit N20 (K153673) serves as a benchmark for "similar performance."

8. Sample Size for the Training Set

Not applicable. This is a physical medical device, not an AI/ML algorithm that requires a training set.

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

Not applicable. As noted above, there is no AI/ML training set.

Ask a specific question about this device

The Mirage Swift is intended for Multiple Patient Reuse by adult patients (>30 Kg) prescribed continuous positive airway pressure or bilevel therapy for use in home, hospitals or clinics.

The Mirage Swift is designed for adult patients for the delivery of non-invasive ventilatory support using continuous positive airway pressure or bi-level therapy. It is intended for multiple patient re-use and is minimally obtrusive to the user providing a high level of comfort, ease-ofuse and seal.

The provided document is a 510(k) summary for the ResMed Mirage Swift Nasal Mask, seeking clearance for "Multiple Patient Reuse" after initially being cleared as a single patient reuse device.

Based on the provided text, there is no specific performance study with acceptance criteria and a detailed report of device performance as one might expect for a new AI/software device. This document is for a physical medical device (a CPAP mask) and focuses on demonstrating substantial equivalence to predicate devices for an expanded indication for use (multiple patient reuse), not for establishing performance metrics of a novel diagnostic or therapeutic algorithm.

Therefore, many of the requested points regarding acceptance criteria, sample sizes for test/training sets, expert adjudication, MRMC studies, or standalone algorithm performance are not applicable or discoverable from this particular 510(k) summary.

Here's an attempt to answer the questions based only on the provided text:

1. Table of acceptance criteria and the reported device performance

The document does not explicitly state quantitative acceptance criteria or a direct performance report in the context of a new diagnostic/therapeutic device. Instead, the "acceptance criterion" is implicitly demonstrating substantial equivalence to predicate devices that are already cleared for multiple patient reuse. The reported "performance" is that this substantial equivalence has been met.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Not applicable. This is not a study assessing diagnostic performance against a test set. The "performance data" mentioned would likely pertain to cleaning, disinfection, and material compatibility relevant to multiple patient reuse, rather than a clinical outcome study with a "test set" of patients.

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)

Not applicable. "Ground truth" in the context of expert consensus for a diagnostic test is not relevant here. The "ground truth" for multiple patient reuse would be established through testing cleaning efficacy, material degradation after disinfection cycles, and biocompatibility, typically performed in a lab setting rather than by clinical experts establishing a diagnosis.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable. There is no "test set" in the context of expert adjudication for this type of submission.

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

Not applicable. This document is about a physical CPAP mask, not an AI or software-assisted diagnostic device. Therefore, no MRMC study or AI improvement metrics are relevant or present.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Not applicable. This is a physical medical device, not an algorithm.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

The concept of "ground truth" as it applies to diagnostic algorithms is not relevant here. For the "Multiple Patient Reuse" claim, the "ground truth" would be objective evidence from laboratory testing demonstrating that the device can be effectively cleaned and disinfected according to a validated protocol without material degradation or compromising safety/performance, making it suitable for subsequent patient use. The document states that "Performance data and rationale are provided" to support this.

8. The sample size for the training set

Not applicable. This is a physical medical device, not an algorithm that requires a "training set."

9. How the ground truth for the training set was established

Not applicable. As above, this is not an algorithm requiring a "training set" or "ground truth" in that context.

Ask a specific question about this device