(83 days)
The VPAP ADAPT is intended to provide non-invasive ventilatory support to treat adult patients with OSA and Respiratory Insufficiency caused by central and/or mixed apneas and periodic breathing.
The VPAP ADAPT is a non-invasive flow generator device designed to provide adaptive servo-ventilation therapy (ASV) to stabilize a patient's ventifation. The device continually measures the patient's instantaneous ventilation, and calculates a target ventilation equal to 90% of the patient's recent average ventilation (time constant 100 seconds). It then adjusts the degree of support to servo-control the patient's ventilation to at least equal the target ventilation.
The VPAP ADAPT is fitted with alarms to alert the user to changes that will affect the treatment. Some of the alarms are pre-set (fixed) whereas others are clinically selectable. Also, a graphic user interface displays clinical data and enables the user (patient/clinician) to set and adjust certain parameters.
Here's a breakdown of the acceptance criteria and study information for the VPAP ADAPT device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Bench Testing | |
| Minute Ventilation | Behaved similar to predicate device (VPAP III ST-A) |
| Tidal Volume | Behaved similar to predicate device (VPAP III ST-A) |
| Clinical Study | |
| Apnea/Hypopnea Index (AHI) | Clinically equivalent to predicate device (VPAP III ST-A) |
| Respiratory-related Arousal Index (RAI) | Clinically equivalent to predicate device (VPAP III ST-A) |
| Effectiveness for central, mixed apnea, or periodic breathing | Demonstrated effective |
| Superiority over predicate device | VPAP ADAPT device was statistically significantly superior (p=0.001) to the VPAP III ST-A for providing effective therapy (based on non-equivalent AHI results) |
| All secondary endpoints | Provided further evidence of equivalency of devices |
2. Sample Size Used for the Test Set and Data Provenance
The text explicitly mentions "Predicate bench testing and clinical studies were used to show substantial equivalence." However, it does not specify the sample size for either the bench test or the clinical test set.
Regarding data provenance:
- The text does not explicitly state the country of origin.
- The text refers to the study as "clinical studies" and "equivalence study," which are typically prospective in nature.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not provide information on the number of experts used or their qualifications for establishing ground truth in the clinical study. It refers to "clinical studies" and "findings," implying expert interpretation of data like AHI and RAI, but no specifics are given.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method used for the test set in the clinical study.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted in the typical sense for algorithm evaluation. Instead, a comparative clinical study was performed between the new device (VPAP ADAPT) and a predicate device (VPAP III ST-A) in human patients.
- Effect size of how much human readers improve with AI vs without AI assistance: This metric is not applicable as the study compares device performance on patients, not human reader performance with or without AI assistance. The study found that the VPAP ADAPT device itself was, in one aspect (non-equivalent AHI results), superior (statistically significant p=0.001) in providing effective therapy compared to the predicate device.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The study described is a standalone device performance study, not an algorithm-only study. The device, VPAP ADAPT, is a physical medical device that provides "adaptive servo-ventilation therapy" and includes "processing electronics." The performance data relates to the device's ability to treat patients, rather than the isolated performance of an algorithm within it. The "servo-control" mechanism is essentially an algorithm embedded in the device.
7. Type of Ground Truth Used
The ground truth for the clinical study was based on clinical parameters such as:
- Apnea/Hypopnea Index (AHI)
- Respiratory-related Arousal Index (RAI)
These are standard metrics used in sleep medicine to assess the severity of breathing disorders and the effectiveness of therapies. While not explicitly stated, these metrics are typically derived from polysomnography studies, which involve expert interpretation.
8. Sample Size for the Training Set
The document does not mention a separate training set or its sample size. This suggests that the device's "adaptive servo-ventilation therapy" mechanism might have been developed and refined using internal methods, but no external "training set" with ground truth is referenced in the context of this 510(k) submission. The device continually measures ventilation and calculates a target ventilation, which is inherent to its real-time operation, not a pre-trained model in the sense of modern AI.
9. How the Ground Truth for the Training Set Was Established
As no separate training set is mentioned as part of the submission documentation, there is no information on how its ground truth would have been established. The device design and verification activities were performed based on risk analysis and product requirements, implying internal R&D processes rather than training on a specific external dataset with pre-established ground truth.
§ 868.5895 Continuous ventilator.
(a)
Identification. A continuous ventilator (respirator) is a device intended to mechanically control or assist patient breathing by delivering a predetermined percentage of oxygen in the breathing gas. Adult, pediatric, and neonatal ventilators are included in this generic type of device.(b)
Classification. Class II (performance standards).