Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K221638
    Date Cleared
    2022-09-19

    (105 days)

    Product Code
    Regulation Number
    874.4760
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    Rhino-Laryngo Videoscope Olympus ENF-VH, Rhino-Laryngo Videoscope Olympus ENF-V3

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

    RHINO-LARYNGO VIDEOSCOPEs OLYMPUS ENF-V3 and ENF-VH are intended to be used with an Olympus video system center, light source, document, display monitor, and other ancillary equipment for endoscopic diagnosis. RHINO-LARYNGO VIDEOSCOPEs OLY MPUS ENF-V3 and ENF-VH is indicated for use within the nasal lumens and airway anatomy (including nasopharynx and trachea).

    Device Description

    Rhino-Laryngo Videoscopes Olympus ENF-VH, ENF-V3 are intended to be used with an Olympus video system center, light source, documentation equipment, display monitor, and other ancillary equipment for endoscopic diagnosis. Rhino-Laryngo Videoscopes Olympus ENF-VH, ENF-V3 are indicated for use within the nasal lumens and airway anatomy (including nasopharynx and trachea).

    AI/ML Overview

    The provided text describes a 510(k) premarket notification for two new medical devices, the Olympus RHINO-LARYNGO VIDEOSCOPE ENF-VH and ENF-V3. The primary goal of this submission is to demonstrate that these new devices are substantially equivalent to already legally marketed predicate devices (Olympus ENF-VH2 and ENF-V4).

    It is crucial to understand that this document describes a submission for substantial equivalence of new endoscopes to existing predicate endoscopes. It is not a study proving the performance of an AI-powered diagnostic device against specific acceptance criteria for diagnostic accuracy. Therefore, many of the requested elements for an AI/ML-based device will not be found in this document.

    The document focuses on demonstrating that the new endoscopes (ENF-VH and ENF-V3) have similar technological characteristics, intended use, and safety/effectiveness profiles to their respective predicate devices (ENF-VH2 and ENF-V4). The "performance testing" described is primarily bench testing to ensure the new endoscopes meet established medical device standards and perform comparably to the predicates in terms of physical and optical properties.

    Here's an attempt to answer your questions based on the provided text, highlighting where the requested information for an AI/ML diagnostic study is not applicable or not present in this type of device submission:


    1. Table of acceptance criteria and the reported device performance

    For these endoscopes, the "acceptance criteria" are generally based on meeting established medical device standards and demonstrating performance comparable to the predicate devices. The "reported device performance" refers to the results of various bench tests.

    Acceptance Criteria (Implied)Reported Device Performance
    Substantial Equivalence to Predicate Device
    - Similar Indications for UseStated as "Similar to predicate. Device name and model number are now included in the Indications for Use statement. The actual intended use is identical." (Tables 5-1 and 5-2)
    - Similar Mode of ActionStated as "Same as predicate" (Tables 5-1 and 5-2)
    - Similar Optical System Parameters (Field of View, Direction of View, Depth of Field)Stated as "Same as predicate" (Tables 5-1 and 5-2)
    - Similar Imaging System (Type of Chip, No. of Image Sensor Chip, NBI observation)Stated as "Same as predicate" (Tables 5-1 and 5-2)
    - Similar Physical Dimensions (e.g., Insertion Tube Diameter, Working Length)Stated as "Same as predicate" for most. Minor total length difference noted for control section design change, but deemed not to alter indications for use or safety/effectiveness. (Tables 5-1 and 5-2)
    - Similar Sterilization CompatibilityStated as "Available, Same as predicate" for EO, STERRAD NX, STERRAD 100S. (Tables 5-1 and 5-2) Reprocessing validation was conducted and devices validated as safe and effective for listed methods.
    Compliance with Voluntary Standards (Section 10)Stated "The following voluntary standards have been applied to the subject devices respectively" with a comprehensive list of standards met (e.g., IEC 60601 series, ISO 10993 series, ISO 14971).
    Specific Performance Bench Testing (Section 12)
    - Thermal SafetyVerified compliance to IEC 60601-2-18:2009-08 ("Protection against excessive temperature and other safety hazards").
    - Composite DurabilityDemonstrated subject device retains safety and effectiveness against expected use-life stresses.
    - Noise and Dynamic RangeConfirmed "substantially equivalent to the predicate device" and "compliant to ISO 15739:2017."
    - Color PerformanceConfirmed "substantially equivalent to the predicate devices in the WLI and NBI observation mode."
    - Image Intensity UniformityConfirmed "substantially equivalent to the predicate devices."
    - ResolutionConfirmed "substantially equivalent to the predicate device."
    - Photobiological SafetyVerified compliance to IEC 32471:2006-07; confirmed light emitted is low enough not to cause injury.
    - Biocompatibility"Successfully validated by testing on the subject devices according to ISO 10993-1" for mucosal membrane contact. "Biological Risk associated with this device is acceptable."
    - Electrical Safety and EMCFound to be in compliance with relevant IEC 60601 series requirements.
    - Software Verification and Validation TestingPerformed and documented to be in compliance with relevant FDA guidance.
    - Risk AnalysisPerformed in accordance with ISO 14971:2007. Outcomes considered acceptable.

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

    • Sample Size: Not applicable in the context of an "AI test set." The testing described is primarily bench testing of physical device properties and adherence to manufacturing and safety standards. For example, durability tests would involve a certain number of units, but this is not a "data set" in the AI sense.
    • Data Provenance: Not applicable for an AI data set. The "data" here comes from results of physical and electrical safety testing, as well as characterization of optical properties, performed by Olympus. The countries of origin for manufacturing facilities are listed as Japan (Shirakawa Olympus Co., Ltd. and Aizu Olympus Co., Ltd.). The testing is presumably prospective as it's for a new product submission.

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

    • This is not applicable as there is no "ground truth" to be established by experts for a diagnostic AI model. The device is a direct visualization endoscope, not an AI diagnostic tool. The "truth" is whether the physical and optical properties meet specifications and are comparable to predicate devices, verified through engineering and laboratory testing.

    4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    • Not applicable. This concept applies to human reader studies or expert labeling for AI training/testing data, neither of which are described for these endoscopes.

    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 device is an endoscope for direct visualization, not an AI-assisted diagnostic tool. No MRMC study or assessment of human reader improvement with AI assistance was performed or needed for this type of submission.

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

    • Not applicable. This refers to AI algorithm performance. The device is a traditional endoscope.

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

    • Not applicable. For a medical device like an endoscope, "ground truth" relates to its physical, optical, and safety specifications being met, and its performance being comparable to a legally marketed predicate. This is confirmed through engineering testing and compliance with recognized standards.

    8. The sample size for the training set

    • Not applicable. There is no AI model or "training set" for this submission as it's for a physical endoscope.

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

    • Not applicable. See point 8.

    In summary, the provided document is a regulatory submission for medical device clearance (510(k)) that focuses on demonstrating "substantial equivalence" of new endoscopes to existing ones. It is not about an AI/ML-based diagnostic device, and therefore the criteria for evaluating such a device (e.g., AI performance, expert ground truth, reader studies) are not present or applicable here.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1