K Number
K193600
Date Cleared
2020-06-26

(186 days)

Product Code
Regulation Number
876.5010
Panel
GU
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The EndoGI Biliary Stent System is intended for delivery of stent(s) to the biliary tract for drainage of the bile ducts, for splinting of a bile duct during healing, or for providing bile duct patency in a stricture or past a stone.

Device Description

The EndoGI System incorporates two preloaded stents. Both stents are identical in design with a straight body and one end incorporating a 65° bend (duodenal bend). The stents are comprised of a biocompatible radiopaque plastic which allows visualization of the stents post deployment. Both stents are pre-mounted on the delivery system and are delivered via near-the-wire and over-the-wire methods. The EndoGI System is available 10 Fr and includes two 110 mm stents. The system is compatible with a guidewire of up to 0.035". The safety lock mechanisms are incorporated within the delivery device handle.

AI/ML Overview

The provided text describes the EndoGI Biliary Stent System and its substantial equivalence to a predicate device, primarily through bench and animal testing. It does not contain information about an AI/ML powered device, therefore, many requested sections about human readers, ground truth establishment for training, and sample sizes for training/test sets are not applicable.

However, I can extract information related to the performance testing and acceptance criteria as presented for the non-AI medical device.

1. Table of Acceptance Criteria and Reported Device Performance

Feature/TestAcceptance CriteriaReported Device Performance
Material (Biocompatibility)Biocompatibility tests for stent and delivery system.Stent and delivery system successfully passed: Systemic Toxicity (Implant Method), Implant Evaluation Test in Rabbits, Systemic Toxicity (Dual Route Repeated Exposure Method) Test, Material Mediated Pyrogenicity Test, Acute Systemic Toxicity Test, Guinea Pig Maximization Test, Intracutaneous Reactivity Test, Mouse Lymphoma Assay, Ames Bacterial Reverse Mutation Assay, MEM Elution Cytotoxicity Assay.
Mechanical EvaluationMeets performance standards for: Kink Resistance, Flow Rate, Bond Strength, Dimensional Verification, Compression Force (Bile), Tensile Test (Bile).EndoGI Biliary Stent System device successfully passed all listed mechanical evaluation tests. Obtained results supports substantial equivalency claim for Tensile test, Compression test, and Flow Rate.
Two Stent DeploymentSystem able to successfully deliver 2 stents utilizing a one-step procedure, no local tissue reaction, and successful stent removal.Animal study (GLP-like on porcine model) demonstrated successful delivery of 2 stents in one-step, no local tissue reaction, and successful stent removal across 6 repeats. Average procedure duration was 20 minutes; second stent deployment within 1 minute.

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

The document does not explicitly define a "test set" in the context of an AI/ML device. For the animal study, the sample size was 6 repeats on a porcine model. The provenance is an animal model, specifically a "GLP-like animal study on porcine model," which implies a controlled, prospective study designed to evaluate product performance.

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

Not applicable as this is not an AI/ML powered device requiring expert ground truth for image interpretation or diagnosis. The "ground truth" for this device's performance is derived from physical and biological observations during bench and animal testing.

4. Adjudication method for the test set

Not applicable. The "test set" here refers to the physical and biological tests, not a dataset requiring adjudication.

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/ML powered device.

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

Not applicable. This is not an AI/ML powered device. The device's "standalone" performance is evaluated through the specified bench and animal tests.

7. The type of ground truth used

For the bench testing (e.g., mechanical evaluations), the ground truth is based on engineering specifications and measurable physical properties.
For the animal study, the ground truth is based on direct observation of successful stent delivery, absence of local tissue reaction, and successful stent removal by the study investigators.

8. The sample size for the training set

Not applicable as this is not an AI/ML powered device.

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

Not applicable as this is not an AI/ML powered device.

§ 876.5010 Biliary catheter and accessories.

(a)
Identification. A biliary catheter and accessories is a tubular flexible device used for temporary or prolonged drainage of the biliary tract, for splinting of the bile duct during healing, or for preventing stricture of the bile duct. This generic type of device may include a bile collecting bag that is attached to the biliary catheter by a connector and fastened to the patient with a strap.(b)
Classification. Class II (special controls). The device, when it is a bile collecting bag or a surgical biliary catheter that does not include a balloon component, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 876.9.