Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K211309
    Device Name
    endomina system
    Date Cleared
    2021-12-07

    (221 days)

    Product Code
    Regulation Number
    876.1500
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    endomina system

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

    The endomina® system, composed of a triangulation (endomina® platform) and an instrument for tissue piercing and approximation (TAPES), is intended for endoscopic placement of suture(s) and approximation of soft tissue in the gastrointestinal tract. The system is to be used on an adult population.

    Device Description

    The endomina® system is intended for endoscopic placement of suture(s) and approximation of soft tissue in the gastrointestinal tract utilizing an endoscope. The system is comprised of a triangulation platform (endomina® platform) and an instrument for tissue piercing and approximation (TAPES). The endomina® system is sterile packaged and designed for single use and is manufactured from various thermoplastic, silicone, stainless steel materials, biocompatible 3D printing materials and other medical grade materials.

    endomina® platform:
    The endomina® platform can be assembled on a regular flexible endoscope inside the stomach. It includes a bendable therapeutic channel meant for the endoscopic tool TAPES. This channel can be deployed perpendicular to the axis of the endoscope, thereby ensuring the triangulation, leaving the channel of the endoscope free for other instruments.

    TAPES:
    TAPES is an instrument intended to be used with the endomina® platform and a flexible endoscope for tissue approximation in the gastrointestinal tract. TAPES is inserted in the bendable arm of endomina®'s platform. TAPES enables piercing and approximation of two, internal tissues with a needle which are then linked by releasing anchors connected with suture. These anchors create a stitch that can then be tightened, generating interrupted stitches in the gastrointestinal tract.

    AI/ML Overview

    The provided document describes the 510(k) premarket notification for the endomina® system, an endoscopic tissue approximation device. It details the device's characteristics, intended use, and the non-clinical performance data used to demonstrate its substantial equivalence to a predicate device.

    However, the document does not contain the kind of information typically found in an FDA submission for an AI/ML-driven device, which would include specific acceptance criteria like precision, recall, or AUC, or details about the study design (e.g., sample size, expert consensus, MRMC study, ground truth establishment) for validating such an algorithm.

    The endomina® system is a mechanical device for endoscopic suturing. Its performance evaluation focuses on physical attributes (dimensions, material properties, mechanical integrity, sterility, shelf-life, biocompatibility) and functional aspects like "suture delivery accuracy," "pull-off force," "force needed to approximate tissue," and "needle piercing force." The "Non-clinical Performance Data" section confirms "Appropriate product testing was performed on endomina® system to evaluate conformance with standard requirements and substantial equivalence to the predicate device."

    Therefore, I cannot extract the specific information requested in the prompt (acceptance criteria for an AI/ML device, details of an AI/ML study, MRMC study, standalone performance, training set details) because the provided text pertains to a medical device, not an AI/ML algorithm.

    The closest equivalent information regarding "acceptance criteria" and "proof" in this document is found under "Non-clinical Performance Data," which lists various bench tests and animal testing:

    Relevant Information from the Document:

    • Acceptance Criteria (implicit for a mechanical device): Conformance with standard requirements and substantial equivalence to the predicate device. This implies meeting pre-defined mechanical and functional specifications.
    • Reported Device Performance (as described in the "Non-clinical Performance Data"):
      • Bench testing included:
        • Suture delivery accuracy
        • Needle attachment
        • Pull-off force to remove the distal tip from the endoscope
        • Size of approximated tissue fold
        • Force needed to approximate the tissue
        • Ease of insertion into a patient gastrointestinal tract
        • Suture strength
        • Force needed to separate anchors and suture
        • Needle piercing force
      • Sterility: SAL 10-6 confirmed by sterilization validation according to EN ISO 11135:2014 /A1:2019.
      • Packaging and Shelf-life: Packaging integrity confirmed by ASTM F1929-15 and ASTM F1886-16. Shelf-life claims confirmed by functional testing on aged products.
      • Biocompatibility: Testing performed on all components per ISO 10993-1: 2018, including chemical characterization (ISO 10993-18: 2020), cytotoxicity (ISO 10993-5: 2009), sensitization (ISO 10993-10: 2010), irritation (ISO 10993-10: 2010), acute systemic toxicity (ISO 10993-11: 2017), material mediated pyrogenicity (USP ), and implantation (ISO 10993-6: 2016).
      • Animal Testing: Performed to demonstrate substantial equivalence regarding ease of use, efficacy, and safety during endoscopic tissue approximation for suturing in a minipigs' stomach.

    Regarding the specific questions in the prompt, based on the provided text, the answers are:

    1. A table of acceptance criteria and the reported device performance: This is not presented as a formal table with precise numerical criteria and outcomes, as one would expect for an AI/ML device's performance metrics. Instead, the "Non-clinical Performance Data" section lists the types of tests performed and the successful validation of these tests to establish conformance and substantial equivalence.

      Acceptance Criteria (Implicit for non-AI device)Reported Device Performance (from "Non-clinical Performance Data")
      Conformance to standard requirementsBench testing (suture delivery accuracy, forces, etc.) performed
      Substantial equivalence to predicateAnimal testing demonstrated substantial equivalence
      Sterility (SAL 10-6)Confirmed by EN ISO 11135:2014 /A1:2019
      Packaging IntegrityConfirmed by ASTM F1929-15 and ASTM F1886-16
      Shelf-lifeConfirmed by functional testing on aged products
      BiocompatibilityPerformed as per ISO 10993 standards
    2. Sample size used for the test set and the data provenance: Not applicable in the context of an AI/ML test set. The document mentions "minipigs" for animal testing, which is a "sample" but not an AI test set. No country of origin for generic "data" is mentioned, and the nature is pre-market testing, not retrospective/prospective clinical data for an algorithm.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for a mechanical device's function is typically established through engineering specifications, physical measurements, and animal/cadaveric studies, not expert consensus on image interpretation.

    4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. This refers to AI/ML ground truth 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, as this is a mechanical device, not an AI-assisted diagnostic tool.

    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as there is no algorithm described.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For this mechanical device, ground truth would be based on engineering specifications, physical measurements, and histological/observational results from animal studies concerning tissue approximation, rather than expert interpretation of a dataset.

    8. The sample size for the training set: Not applicable, as there is no AI/ML algorithm requiring a training set.

    9. How the ground truth for the training set was established: Not applicable, as there is no AI/ML algorithm requiring a training set.

    In summary, the provided document describes the regulatory clearance of a mechanical medical device, not an AI/ML device. Therefore, the questions related to AI/ML specific acceptance criteria, study design, ground truth, and training data cannot be answered from the given text.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1