(151 days)
The VPAP III™ is intended for the treatment of Obstructive Sleep Apnea (OSA) in adult patients. The optional integrated humidifier (HUMIDAIRE® 2I™) is indicated for the humidification and warming of air from the VPAP III™ flow generator. The VPAP III™ flow generator and HUMIDAIRE 2I™ are for home and hospital use.
The VPAP III is a microprocessor-controlled blower-based positive airway pressure flow generator for the treatment of OSA. The device is based on the S7 Elite with an additional therapy mode (bi-level), derived from the VPAP II ST, to provide pressure relief during exhalation. The flow generator is used in combination with patient tubing and a mask. For additional humidification, an optional integrated humidifier, the HUMIDAIRE 2i, is compatible with the flow generator.
This 510(k) summary for the ResMed VPAP III does not contain a study that proves the device meets specific acceptance criteria in the way a clinical performance study would for an AI/ML device.
Instead, this submission is for a modified device (a CPAP/Bi-level flow generator) and focuses on demonstrating substantial equivalence to predicate devices already on the market. Therefore, the "acceptance criteria" and "study" are not presented in the typical format you'd expect for an AI/ML diagnostic or therapeutic device.
However, I can extract information related to design validation and verification, which serves a similar purpose in demonstrating the device performs as intended and is safe/effective.
Here's an analysis based on the provided text, structured to align with your request where possible, but with important caveats due to the nature of the submission:
1. Table of Acceptance Criteria and Reported Device Performance
The 510(k) summary does not list specific, quantifiable acceptance criteria with corresponding performance metrics like sensitivity, specificity, or AUC, as would be typical for an AI/ML device. Instead, the "acceptance criteria" are implied by the successful completion of "Design Verification and Validation tests" which confirmed that modifications had "no impact on the safety or effectiveness of the device."
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| No impact on safety of the device due to modifications | All tests confirmed no impact on safety |
| No impact on effectiveness of the device due to modifications | All tests confirmed no impact on effectiveness |
| Same intended use as predicate devices | Yes, "Same Intended Use" |
| Same operating principle as predicate devices | Yes, "Same Operating Principle" |
| Same technologies as predicate devices | Yes, "Same Technologies" |
| Same manufacturing line as predicate devices | Yes, "Same Manufacturing Line" |
| Device functions as a microprocessor-controlled blower-based positive airway pressure flow generator for OSA treatment | Device described as such |
| Bi-level therapy mode provides pressure relief during exhalation (new feature) | Device incorporates bi-level therapy mode for pressure relief |
| Compatibility with optional integrated humidifier | Yes, HUMIDAIRE 2i is compatible |
2. Sample Size Used for the Test Set and Data Provenance
This information is not provided in the 510(k) summary. The document states "Design Verification and Validation tests were performed," but it does not detail the specifics of these tests, including sample sizes for any test sets (e.g., number of patients, test cases, or simulated scenarios) or the provenance of any data used (e.g., country of origin, retrospective/prospective). This is typical for a device like a CPAP machine where performance is often evaluated through engineering bench testing, simulated use, and compliance with recognized standards, rather than large-scale clinical trials measuring outcomes in patients directly for equivalence claims.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not applicable/provided in this 510(k) summary. "Ground truth" established by experts (like radiologists for imaging devices) is typically relevant to AI/ML diagnostic devices where human interpretation is being augmented or replaced. For a CPAP device, performance is evaluated against engineering specifications, physiological principles, and clinical outcomes that are not typically determined by a panel of expert "readers" establishing a "ground truth" for a test set in the same way.
4. Adjudication Method for the Test Set
This information is not applicable/provided for the reasons stated above. Adjudication methods like 2+1 or 3+1 are used when reconciling disagreements among expert readers for ground truth generation in AI/ML validation studies.
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
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed or mentioned in this 510(k) summary. Such studies are specific to AI-assisted diagnostic tools where the impact on human reader performance is being evaluated. The VPAP III is a therapeutic device (flow generator), not an AI diagnostic tool.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
This concept is not applicable here. The VPAP III is a physical medical device (a flow generator) for therapy, not a standalone algorithm. While it contains a microprocessor and likely algorithms for pressure delivery, these are integral to the device's function as a "human-in-the-loop" isn't a relevant paradigm for its primary function. Its performance is its intrinsic output of airflow and pressure, not an interpretation or prediction.
7. The Type of Ground Truth Used
The "ground truth" for a device like the VPAP III would primarily be:
- Engineering Specifications: Compliance with predefined pressure, flow, and timing specifications.
- Physiological Principles: The device's ability to maintain positive airway pressure at specified levels, which is the mechanism for treating OSA.
- Clinical Efficacy (established by predicates): The understanding that CPAP and bi-level therapy are effective for OSA, as demonstrated by the predicate devices and general medical knowledge.
The submission confirms that "Design Verification and Validation tests were performed... in accordance with the risk analysis and product requirements," implying that the device was tested against its intended performance specifications.
8. The Sample Size for the Training Set
This information is not applicable/provided. "Training set" refers to data used to train AI/ML algorithms. The VPAP III is a hardware device with embedded software/firmware; it does not explicitly describe a "training set" in the context of machine learning.
9. How the Ground Truth for the Training Set Was Established
This information is not applicable/provided for the reasons stated in point 8.
§ 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).