(78 days)
The intended use of the PLV Continuum II ventilator is to provide continuous or intermittent ventilatory support for the care of individuals who require mechanical ventilation. The intended patient population includes pediatric and adult patients who weigh at least 5 kg (11 lbs). The PLV Continuum II ventilator is intended for use in home, institutional and portable settings and may be used for invasive as well as non-invasive ventilation.
The PLV Continuum ventilator is a microprocessor controlled, compressor-based, ventilator that provides ventilatory support by delivering room air to the patient. PLV Continuum utilizes an internal compressor to generate compressed air for delivery to the patient. Breath delivery is controlled by software. The PLV Continuum has a membrane keypad with indicator Light Emitting Diodes (LED) for the selection and acceptance of patient settings. The PLV Continuum is capable of providing the following types of ventilatory support:
- Positive Pressure Ventilation, delivered either invasively (via endotracheal or tracheostomy tube) or non-invasively (via mask or mouthpiece).
- Assist Control, Synchronized Intermittent Mandatory Ventilation (SIMV) or Spontaneous Pressure (CPAP) modes of ventilation.
- Volume-Controlled (VC). Available in A/C and SIMV.
- Pressure-Controlled (PC). Available in A/C and SIMV.
- Pressure Support (PS). Available in SIMV and SPONT.
The provided document is a 510(k) Premarket Notification for a modification to the PLV Continuum Ventilator, now referred to as the PLV Continuum II Ventilator. This document concerns a medical device (ventilator) and its regulatory approval process, rather than a clinical study evaluating an AI/ML powered device. As such, many of the requested fields (e.g., sample size for test/training sets, number of experts, adjudication methods, MRMC studies, standalone performance) are not applicable to this type of submission.
The document primarily focuses on establishing substantial equivalence to predicate devices rather than proving the performance against specific acceptance criteria in the context of an AI/ML algorithm.
However, I can extract information related to the performance testing conducted for the device.
Here's a summary of the information that can be extracted, with notes for the fields that are not applicable:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria / Standard | Reported Device Performance (Summary) |
|---|---|
| ASTM F 1100-90 (Ventilators) | Performance testing was conducted per the applicable sections and results demonstrate that all design and system requirements for the modified PLV Continuum have been met. |
| ASTM F 1246-91 (Ventilators) | Performance testing was conducted per the applicable sections and results demonstrate that all design and system requirements for the modified PLV Continuum have been met. |
| IEC 60601-1-2 (EMC) | EMC testing was performed per this standard. |
| FDA Draft Reviewer Guidance for Premarket Notification Submissions (1993) (Electrical, mechanical, environmental testing) | Electrical, mechanical, and environmental testing was performed in accordance with this guidance. |
| FDA Guidance for the Content of Premarket Submissions for Software contained in Medical Devices (1998) (Software validation testing) | Software validation testing was performed per this guidance. |
Study Proving Device Meets Acceptance Criteria:
The study that proves the device meets the acceptance criteria is described as a series of performance tests, rather than a single clinical study.
- Study Name/Description: "Summary of Performance Testing" (Section 16.5)
- Study Objective: To demonstrate that all design and system requirements for the modified PLV Continuum have been met and to support substantial equivalence to predicate devices.
- Key Finding: "The results of all testing demonstrate that all design and system requirements for the modified PLV Continuum have been met." (Section 16.5) and "The technological characteristics of the modified PLV Continuum ventilator and the results of the performance testing do not raise new questions of safety and effectiveness when compared to the legally marketed predicate devices." (Section 16.6)
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not Applicable. This is a hardware/software medical device modification submission, not an AI/ML study with a distinct "test set" of patient data. The "testing" refers to engineering and regulatory compliance testing of the device itself.
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 patient data adjudicated by experts, is not relevant to this type of device submission. Performance was assessed against engineering standards and specifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not Applicable. See point 3.
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 is not an AI-powered device, nor is it a diagnostic device being evaluated with human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not Applicable. While the device is microprocessor-controlled with software algorithms, the "standalone" performance requested typically refers to the performance of an AI algorithm in isolation from a human user, which is not the subject of this document. The device's performance was evaluated as a complete system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not Applicable as traditionally defined for AI/ML studies. The "ground truth" here is adherence to engineering specifications and regulatory standards (e.g., flow rates, pressure delivery, safety alarms, EMC compliance).
8. The sample size for the training set
- Not Applicable. There is no "training set" in the context of an AI/ML algorithm development described in this document. The software algorithms are described as "equivalent to those used on the currently marketed Respironics PLV Continuum ventilator (K022750)".
9. How the ground truth for the training set was established
- Not Applicable. See point 8.
§ 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).