K Number
K082657
Device Name
RTX RESPIRATOR
Manufacturer
Date Cleared
2008-10-08

(26 days)

Product Code
Regulation Number
868.5935
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use
  1. Ventilation - The RTX Respirator is indicated for external ventilation of the lungs resulting in gas exchange. 2) Secretion Clearance - Also for use in assisting patients with secretion clearance management as indicated by standard medical convention. The RTX Respirator is for use in adult and pediatric patient populations. The RTX is not for use in out-of-hospital transport. For prescription use only.
Device Description

The RTX Respirator is an external high and low frequency respirator, which controls both phases of respiration. It consists of a lightweight flexible cuirass, tubing with a keypad and display screen. The Cuirass is available in eleven (11) sizes for various patient populations and sizes. The Cuirass contains a disposable seal and is attached to the patient via Velcro and nylon straps. The RTX Respirator ventilates by decreasing and then increasing the pressure within the cuirass. The negative pressure creates expansion of the chest bringing about inspiration. The positive phase creates positive pressure on the chest and therefore creates expiration.

AI/ML Overview

Here's an analysis of the provided 510(k) summary for the RTX Respirator, focusing on acceptance criteria and the supporting study:

The provided document, a 510(k) summary for the RTX Respirator, focuses on demonstrating substantial equivalence to predicate devices, not on proving that the device meets specific performance acceptance criteria through a standalone study with detailed metrics. The summary describes an equivalence study rather than a study defining and meeting acceptance criteria for a novel device.

Therefore, many of the requested data points (like sample size for test sets, number of experts, adjudication methods, MRMC studies, specific ground truth types, training set details) are not applicable or not provided in this type of submission which primarily addresses substantial equivalence for a medical device.

However, I can extract the information that is present and indicate where requested information is absent.


Acceptance Criteria and Device Performance (Based on Substantial Equivalence Claim)

The submission doesn't define explicit performance acceptance criteria in numerical terms that the RTX Respirator must meet. Instead, the "acceptance criteria" can be inferred as demonstrating substantial equivalence to a predicate device, meaning it performs similarly and is as safe and effective.

Acceptance Criteria (Inferred from Substantial Equivalence Goal)Reported Device Performance (Summary of Clinical Evaluation)
Device is safe and effective for indicated uses."The RTX Respirator was shown... to exhibit a similar pattern of clinical results."
Performance is comparable to the predicate device (Hayek Oscillator K924341)."A comparative clinical study was performed and the RTX Respirator was shown ... to exhibit a similar pattern of clinical results."
No substantial differences in technological characteristics raise new issues of safety or effectiveness compared to predicates."There are no known substantial differences between the RTX Respirator defined in this 510(k) submission and the predicate devices. They have the same or similar intended indications for use and any differences in technological characteristics do not raise issues of safety and effectiveness."
Compliant with relevant electrical safety and EMC standards."The RTX Respirator was tested and found to be compliant to IEC 60601-1-2, IEC 61000-3-2/3, IEC 61000-4-2/3/4/5/6/8/11, and IEC 60601-1."

Study Details

  1. Sample size used for the test set and the data provenance:

    • Sample Size: Not explicitly stated. The summary refers to "A comparative clinical study was performed" but does not give patient numbers.
    • Data Provenance: Not specified (e.g., country of origin). The study involved a "comparative clinical study" and a "review of recent publications on the RTX Respirator," implying a mix of directly collected data and published literature. It doesn't state if it was retrospective or prospective.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Not Applicable/Not Provided. The clinical evaluation focuses on comparative outcomes to a predicate device. "Ground truth" in the context of device performance metrics (like accuracy for a diagnostic device) is not the focus here. The clinical results observed in the comparative study essentially served as the "truth" for demonstrating similar performance to the predicate.
  3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

    • Not Applicable/Not Provided. This method is typically used in image interpretation or diagnostic studies where expert consensus resolves discrepancies. The described clinical study is a comparative performance study of a therapeutic device.
  4. 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:

    • No. This is a therapeutic device (ventilator), not an AI-assisted diagnostic or imaging device. Therefore, MRMC studies and "human readers improving with AI assistance" are not relevant to this submission.
  5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

    • Not Applicable/Not Provided. The RTX Respirator is a medical device, not an algorithm. Its performance is inherent to the device's function, not a computational output.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Clinical Outcomes/Performance Data: The study relied on "clinical results" to demonstrate a "similar pattern" between the RTX Respirator and the predicate Hayek Oscillator. This would involve physiological measurements and patient well-being outcomes, but specific metrics are not detailed.
  7. The sample size for the training set:

    • Not Applicable/Not Provided. This is not an AI/machine learning device that requires a training set.
  8. How the ground truth for the training set was established:

    • Not Applicable/Not Provided. As it's not an AI/ML device, there is no training set.

§ 868.5935 External negative pressure ventilator.

(a)
Identification. An external negative pressure ventilator (e.g., iron lung, cuirass) is a device chamber that is intended to support a patient's ventilation by alternately applying and releasing external negative pressure over the diaphragm and upper trunk of the patient.(b)
Classification. Class II (performance standards).