K Number
K993433
Manufacturer
Date Cleared
1999-10-27

(15 days)

Product Code
Regulation Number
868.5905
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Virtuoso Smart LX CPAP System delivers continuous positive airway pressure therapy for the treatment of Obstructive Sleep Apnea.

Device Description

The Virtuoso LX Smart CPAP System is a blower-based system that generates positive airway pressures from 3 to 20 cm H.O. The device is intended for use with a patient circuit that connects to the CPAP device to route the air to patient via a nasal mask. The patient circuit consists of six-foot 20 mm tubing, an exhalation device and a nasal mask. These basic characteristics of the Virtuoso LX Smart CPAP device have not changed as compared to the predicate device, the Virtuoso Smart CPAP System K953930.

The Virtuoso LX Smart CPAP System is a microprocessor-controlled device that produces Continuous Positive Airway Pressure known as CPAP. One of the primary components in the CPAP device is the blower that generates airflow. The blower assembly consists of an impeller coupled to a brushless DC motor assembled in a plastic housing. When encrgized, the blower draws ambient air through an air filter, pressurizes it, and provides the Therapeutic Pressure to the patient via the patient circuit.

AI/ML Overview

The provided text describes modifications to the Respironics® Virtuoso LX Smart CPAP System and asserts its substantial equivalence to a predicate device (Virtuoso Smart CPAP System K953930). However, it does not contain details of a specific study that explicitly outlines acceptance criteria and subsequently reports on the device's performance against those criteria in a quantitative manner as requested.

The document states: "Design verification tests were performed on the Virtuoso LX Smart CPAP System as a result of the risk analysis assessment, and acceptance criteria were met." This is a general statement and does not provide the specific data requested in the prompt.

Therefore, much of the requested information cannot be extracted from the provided text.

Here's a breakdown of what can and cannot be answered based on the provided text:

1. A table of acceptance criteria and the reported device performance

  • Cannot be provided. The document states that "acceptance criteria were met" for design verification tests, but it does not specify what those criteria were nor does it report the device's actual performance metrics against them.

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

  • Cannot be provided. The document refers to "design verification tests" but offers no details on sample size, data provenance, or whether the tests involved human subjects or just device-level testing. The data card modification facilitates data retrieval, but no study based on this retrieval is described.

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)

  • Cannot be provided. No information about a "test set" with established ground truth or expert involvement is present. The device is a CPAP system, and the modifications relate to data management and user questionnaires, not to diagnostic image interpretation or similar tasks requiring expert ground truth establishment.

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

  • Cannot be provided. No adjudication method is mentioned as there is no described test set requiring expert review.

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

  • Cannot be provided. This is not a diagnostic imaging device involving "human readers" or AI assistance in interpretation. The device itself is a CPAP system for treating sleep apnea, and the modifications are for data management.

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

  • Cannot be provided. The document discusses a "microprocessor-controlled device" and "Encore Data Management Software" but does not describe any standalone performance studies of an algorithm separate from the device's primary function or data handling. The software explicitly states it "does not perform any scoring or diagnosing."

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

  • Cannot be provided. No specific "ground truth" is mentioned as there is no reported study requiring it for performance evaluation. The "Functional Outcomes of Sleep Questionnaire" (FOSQ) is mentioned as a way to "determine if CPAP therapy has improved a patient's quality of life," but this is an outcome measure facilitated by the device, not a ground truth for device performance as typically understood in regulatory submissions for AI/diagnostic devices.

8. The sample size for the training set

  • Cannot be provided. There is no mention of a "training set" or any machine learning model being trained as part of the modifications or device development process described.

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

  • Cannot be provided. As no training set is mentioned, its ground truth establishment is also not discussed.

§ 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).