Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K190030
    Date Cleared
    2019-03-05

    (57 days)

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

    Embrella Endoscopic Distal Attachment

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

    Embrella™ Endoscopic Distal Attachment is intended to the distal end of the endoscope to facilitate endoscopic therapy and maintain an appropriate endoscopic field of view.

    Device Description

    The proposed device Embrella™ Endoscopic Distal Attachment is an additional device, made of medical grade silicone rubber designed to attach to the distal end of the endoscope. Its shape is umbrella shaped, with six flexible wings that easily to fold backwards and forwards. It can be used to facilitate endoscopic therapy and maintain an appropriate endoscopic field of view.

    Embrella™ Endoscopic Distal Attachment has two models, one is EM-S-01, which is compatible with endoscopy distal diameter 12.8-14.5mm; the other is EM-S-02, which is compatible with endoscopy distal diameter 11.5-13.0mm.

    AI/ML Overview

    The provided text is a 510(k) Summary for the Embrella™ Endoscopic Distal Attachment. It states that the device is substantially equivalent to a predicate device (EndoRing™ K133359) and lists various tests performed. However, it does not contain specific acceptance criteria or detailed results of a study that proves the device meets specific performance metric acceptance criteria in the way one would expect for a detailed AI/ML device performance study.

    Instead, the document focuses on demonstrating substantial equivalence through:

    • Comparison of technological characteristics (materials, design, configuration, indications for use, sterilization, etc.).
    • Performance Bench Testing: "Dimension; Operating Performance; Matching Performance; Tension Performance;"
    • Animal Testing: "Endoscopy View Testing."

    The document explicitly states: "No clinical study is included in this submission." This means there is no multi-reader multi-case (MRMC) study, standalone algorithm performance study, or human-in-the-loop study with detailed metrics like sensitivity, specificity, or AUC, as might be expected for an AI/ML diagnostic device.

    Therefore, many of the requested points cannot be directly answered from the provided text. I will address the points based on the information available and note where information is not present.


    Summary of Acceptance Criteria and Study Performance for Embrella™ Endoscopic Distal Attachment

    Based on the provided 510(k) summary, the acceptance criteria and study proving device performance are primarily centered around demonstrating substantial equivalence to a predicate device (EndoRing™ K133359) through bench testing and animal testing, rather than a clinical trial with statistical metrics, given that this is a mechanical accessory device, not an AI/ML diagnostic.

    1. Table of Acceptance Criteria and Reported Device Performance

    The document broadly states that bench tests and animal tests were performed to demonstrate equivalence to the predicate device. Specific quantitative acceptance criteria (e.g., "Tension performance must be > X Newtons") and exact numerical results are not provided in this summary. The acceptance criterion implied is "equivalent to the predicate device."

    Test CategoryAcceptance Criteria (Implied)Reported Device Performance (Implied)
    Dimension PerformanceDimensions meet specified requirements and are equivalent to predicate."The testing performed demonstrated that the proposed device and predicate device are equivalent."
    Operating PerformanceDevice operates as intended and equivalent to predicate."The testing performed demonstrated that the proposed device and predicate device are equivalent."
    Matching PerformanceDevice properly matches with endoscope and is equivalent to predicate."The testing performed demonstrated that the proposed device and predicate device are equivalent."
    Tension PerformanceDevice withstands specified tension and is equivalent to predicate."The testing performed demonstrated that the proposed device and predicate device are equivalent."
    Endoscopy View TestingMaintains appropriate endoscopic field of view, equivalent to predicate."The testing performed demonstrated that the proposed device and predicate device are equivalent." (Performed on animals.)

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

    • Test Set Sample Size: The document does not specify exact sample sizes for the bench tests or the "Endoscopy View Testing" on animals. Details like the number of devices tested or the number of animals used are not provided.
    • Data Provenance: Not explicitly stated, but the submission is from a Chinese company (Micro-Tech (Nanjing) Co., Ltd.) to the FDA. The tests would presumably have been conducted in a controlled environment to support regulatory submission. The document implies these were retrospective tests conducted specifically for this submission.

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

    • No information is provided regarding the number or qualifications of experts involved in establishing "ground truth" for the performance tests. Given these are bench and animal tests for a mechanical device, formal expert adjudication in the sense of image interpretation (like for AI/ML) is not mentioned.

    4. Adjudication method for the test set:

    • Not applicable/Not described. The tests appear to be physical/mechanical performance validations rather than subjective interpretation requiring adjudication.

    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs. without AI assistance:

    • No MRMC study was done. The document explicitly states: "No clinical study is included in this submission." Therefore, there is no information on human reader improvement with AI assistance (as this is not an AI device).

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

    • Not applicable. This device is a mechanical endoscope accessory, not an algorithm or AI system.

    7. The type of ground truth used:

    • For the bench tests (Dimension, Operating, Matching, Tension), the "ground truth" would be engineering specifications and measurements.
    • For the "Endoscopy View Testing" (animal testing), the "ground truth" would be direct observation and assessment of the endoscopic field of view during the procedure. The "truth" is established by the observed physical performance of the device itself.

    8. The sample size for the training set:

    • Not applicable. This device is a mechanical accessory, not an AI/ML system that requires training data.

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

    • Not applicable. As above, no training set for an AI/ML model.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1