(139 days)
The Mirage Vista™ mask is an accessory to a non-continuous ventilator (respirator), intended for multiple-patient use for adult patients prescribed continuous positive airway pressure (CPAP) and bi-level therapy in hospital, clinical, and home environments.
The Mirage Vista™ mask has an unobtrusive design, which increases the patient's field of vision and allows wearing of glasses whilst the mask is in use. The new design reduces the perceived size and weight of the mask when compared to the predicate mask.
The Mirage Vista™ mask is strapped to the patient's face covering the nose, and connected via tubing to a CPAP or bi-level flow generator. Positive pressure ventilation is thus applied to the lungs in a non-invasive manner.
Mirage Vista™ mask comes in one frame size and two cushion sizes (standard and deep).
This document is a 510(k) summary for the ResMed Mirage Vista™ Mask. It focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed performance study with acceptance criteria and specific statistical results for a device like an AI algorithm.
Therefore, many of the requested categories for describing an AI algorithm study cannot be directly answered from the provided text. The device in question is a physical medical device (a mask for ventilation), not a software or AI-driven diagnostic tool.
Here's an attempt to extract relevant information and explain why other points cannot be addressed:
1. Table of Acceptance Criteria and Reported Device Performance
The submission states the device was tested to determine certain characteristics and that the results show substantial equivalence to the predicate mask. It doesn't present specific numerical acceptance criteria or performance metrics in the format you might expect for an AI algorithm (e.g., sensitivity, specificity thresholds).
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Pressure-flow characteristic | Substantially equivalent to predicate mask | Substantially equivalent to predicate mask |
| Functional dead space (CO2 re-breathing) | Substantially equivalent to predicate mask | Substantially equivalent to predicate mask |
| Flow impedance | Substantially equivalent to predicate mask | Substantially equivalent to predicate mask |
| Multiple-patient use | Validation for multiple-patient use | Validated for multiple-patient use |
| Biocompatibility | Compliant with ISO 10993 standards or predicate materials | Materials are predicate or compliant with ISO 10993 |
2. Sample Size Used for the Test Set and Data Provenance
This information is not provided in the document. The submission references "performance data" and "validation for multiple-patient use" but does not detail the specific test methodologies, number of subjects/masks tested, or the origin of any data (e.g., country, retrospective/prospective).
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
This information is not applicable/not provided. The device is a physical mask; its performance is assessed through engineering and clinical testing, not by establishing a ground truth label for data using human experts as would be done for an AI diagnostic.
4. Adjudication Method for the Test Set
This information is not applicable/not provided. Adjudication typically refers to resolving disagreements among experts when labeling data for AI, which is not relevant here.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
This information is not applicable/not provided. An MRMC study is designed for diagnostic algorithms evaluated by human readers. This submission concerns a physical medical device.
6. If a Standalone (algorithm only without human-in-the-loop performance) was done
This information is not applicable/not provided. This is not an algorithm, so the concept of standalone performance does not apply.
7. The Type of Ground Truth Used
The "ground truth" here is the physical and functional performance of the mask, compared against established standards for medical devices and the performance of the predicate device. This is evaluated through:
- Engineering tests (pressure-flow, dead space, flow impedance).
- Biocompatibility testing against ISO 10993 standards.
- Validation for its stated use (multiple-patient use).
It is not "expert consensus, pathology, or outcomes data" in the context of an AI diagnostic.
8. The Sample Size for the Training Set
This information is not applicable/not provided. This device is a physical product, not an AI model that requires a training set.
9. How the Ground Truth for the Training Set was Established
This information is not applicable/not provided. As above, this is not an AI model requiring a training set.
Summary of Limitations:
The provided text is a 510(k) summary for a physical medical device (a mask) seeking clearance based on substantial equivalence to a predicate device. It is structured to meet regulatory requirements for such a device, focusing on intended use, technological characteristics, and a high-level summary of performance testing to support equivalence. It does not contain the detailed statistical analysis, reader studies, ground truth establishment, or dataset specifics that would be present in a submission for an AI/software as a medical device (SaMD).
§ 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).