AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Blue Rhino G1-Multi Percutaneous Tracheostomy Introducer Set/Tray is intended for percutaneous dilational tracheostomy for management of the airway in adults only. Tube the technique described herein, should be performed in a controlled setting (e.g., ICU or operating room) with the assistance of trained personnel.

Blue Rhino G2-Multi Percutaneous Tracheostomy Introducer Set/Tray is intended for percutaneous dilational tracheostomy for management of the airway in adults only. Tube the technique described herein, should be performed in a controlled setting (e.g., ICU or operating room) with the assistance of trained personnel.

Weinmann-Multi Tracheostomy Exchange Set is intended for adult tracheostomy tube exchange.

Device Description

The subject devices Blue Rhino G1-Multi Percutaneous Tracheostomy Introducer Set/Tray and the Blue Rhino G2-Multi Percutaneous Tracheostomy Introducer Set/Tray are designed for percutaneous dilational tracheostomy for management of the airway. The devices allow for single-stage dilation, which is achieved with a single rhino-horn-shaped dilator using an in-andout motion. Sets and trays include a Blue Rhino G1 Dilator or Blue Rhino G2 Dilator, loading dilators (6.5, 7.0, 7.5, 8.0, 8.5, 9.0, and 10.0 mm) an 8 Fr guiding catheter, a 14 Fr access dilator, and a wire guide. Sets and trays are available in multiple configurations, which include various set and tray components (Table 1) associated with the procedure and/or for gaining percutaneous access.

The subject device Weinmann-Multi Tracheostomy Exchange Set is comprised of a Blue Rhino G1 Dilator, loading dilators (7.0, 7.5, 8.0, 8.5, and 9.0 mm), an 8 Fr Cook Airway Exchange Catheter, and two Rapi-Fit Adapters.

AI/ML Overview

This document is a 510(k) Premarket Notification from the FDA, focusing on the substantial equivalence of medical devices. It primarily compares new devices to previously cleared predicate devices. Therefore, the information typically requested about acceptance criteria and detailed study designs for performance evaluation of AI/ML-based medical devices (like training/test set sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance) is not present for this specific type of device and submission.

The document states that the safety and/or effectiveness of the subject device for modifications (new sizes, OD changes, package/labeling changes) are supported by performance testing and biocompatibility testing. However, it does not provide the detailed acceptance criteria and study results in the format requested for an AI/ML device.

Based on the provided text, here's what can be extracted and what is missing:


1. Table of acceptance criteria and the reported device performance

The document lists several tests performed and states that "The pre-determined acceptance criteria were met" for some mechanical tests. However, it does not provide specific numerical acceptance criteria or the reported performance data.

Acceptance Criteria (Not explicitly stated numerically)Reported Device Performance (Summary)
Not explicitly stated (e.g., tensile strength value)"The pre-determined acceptance criteria were met."
Not explicitly stated (e.g., compression force value)"The pre-determined acceptance criteria were met."

2. Sample size used for the test set and the data provenance

Not provided. The document mentions "performance testing" and "biocompatibility testing" but does not specify sample sizes for these tests, nor the data provenance (e.g., country of origin, retrospective/prospective). This type of detail is typical for detailed clinical or AI/ML performance studies, not for the manufacturing and material changes of a device like this.


3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable/Not provided. This information is relevant for studies involving human interpretation or clinical outcomes used as ground truth, particularly in AI/ML performance evaluations. For physical medical devices undergoing performance and biocompatibility testing for manufacturing changes, this concept of "ground truth" established by experts in a test set is not directly relevant in the same way.


4. Adjudication method for the test set

Not applicable/Not provided. Similar to point 3, adjudication methods are used in studies where there's variability in interpretation (e.g., expert readers reviewing medical images). This is not applicable to the types of performance and biocompatibility tests described for this device.


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

No. An MRMC study is not mentioned. This type of study is specific to evaluating AI/ML systems that assist human readers in tasks like image interpretation. This submission is for a physical medical device (tracheostomy introducer/exchange set) and does not involve AI assistance.


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

No. This is not applicable as the submission is for a physical medical device, not an algorithm.


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

Not explicitly provided in specific detail for each test. For the physical performance tests (like security of attachment, compression force, tensile strength, verification of outer diameter), the "ground truth" would be the engineering specifications and established standards (e.g., BS EN ISO 5366:2016 for security of attachment). For biocompatibility, the ground truth is defined by the biological response assays and limits set by ISO standards (ISO 10993-5, -7, -10, -11, -12). The document states compliance with these standards, implying that the results met the requirements dictated by these standards for safety.


8. The sample size for the training set

Not applicable/Not provided. This concept is specific to AI/ML models. The devices here are physical medical devices, not AI algorithms, so there is no training set in this context.


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

Not applicable/Not provided. As there is no training set for an AI/ML model, this question is not applicable.

§ 868.5800 Tracheostomy tube and tube cuff.

(a)
Identification. A tracheostomy tube and tube cuff is a device intended to be placed into a surgical opening of the trachea to facilitate ventilation to the lungs. The cuff may be a separate or integral part of the tracheostomy tube and is, when inflated, intended to establish a seal between the tracheal wall and the tracheostomy tube. The cuff is used to prevent the patient's aspiration of substances, such as blood or vomit, or to provide a means for positive-pressure ventilation of the patient. This device is made of either stainless steel or plastic.(b)
Classification. Class II.