Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K251108
    Date Cleared
    2025-08-29

    (140 days)

    Product Code
    Regulation Number
    878.4400
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    Erbe ESU Model VIO**®** 3n with Accessories

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

    The Erbe Electrosurgical Unit (ESU/Generator) model VIO 3n with instruments and accessories is intended to deliver high frequency (HF) electrical current for the cutting and/or coagulation of tissue.

    Device Description

    The Erbe ESU Model VIO® 3n is an electrosurgical unit (ESU) that delivers high-frequency (HF) electrical current for cutting and/or coagulation of tissue. The unit can be mounted/secured to a cart/system carrier or on a ceiling mount. Different footswitches are available for activating the ESU. The ESU VIO® 3n has several clearly defined monopolar and bipolar cutting and coagulation modes with different electrical waveforms and electrical parameters that are programmed with defined effect levels. Each effect level corresponds to a defined maximum power output and a voltage limitation. In combination with the compatible argon plasma coagulation unit APC 3 (K191234), it offers monopolar modes for argon plasma coagulation and argon-supported modes. The ESU has a touchscreen monitor that provides the user with an onscreen tutorial as well as settings and operational information. It also provides a small number of physical controls, such as the power switch, instrument sockets and a neutral electrode receptacle. Connections for the central power supply, for footswitches, for potential equalization of the operating theatre and Erbe Communication Bus (ECB) connections to other Erbe modules are located at the rear. The ESU emits sounds when instruments are activated, and messages are signaled. The actual application is carried out using compatible electrosurgical instruments that are connected to the generator. The VIO® 3n can be combined with matching Erbe devices and modules, instruments, and accessories.

    To address various clinical needs, the ESU is available in 5 different configurations which are called "Fire", "Metal", "Stone", "Water" and "Timber". Whereas the configuration "Fire" includes all available modes and functionalities, the other configurations only offer a reduced number of modes and functionalities.

    AI/ML Overview

    The provided FDA 510(k) clearance letter and summary for the Erbe ESU Model VIO® 3n with Accessories do not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a specific study proving the device meets those criteria, particularly for an AI/software as a medical device (SaMD).

    This document pertains to an electrosurgical unit, which is a hardware device for cutting and coagulating tissue using high-frequency electrical current. The "software" mentioned in the document refers to the operating software of the ESU itself, not an AI or diagnostic algorithm, and thus the type of performance metrics, ground truth, and study designs you're asking about (e.g., MRMC, standalone performance, expert consensus on diagnostic images) are not applicable to this type of device submission.

    Therefore, I cannot provide a table of acceptance criteria and device performance in the context of an AI/SaMD, nor detailed information on test set sample sizes, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, or specific training set details, because this document describes a hardware device.

    However, I can extract the information that is present about the non-clinical performance testing and what it aims to demonstrate:


    1. Table of Acceptance Criteria and Reported Device Performance

    As this is a hardware electrosurgical unit, the "acceptance criteria" are generally related to compliance with electrical safety, EMC, and functional performance standards for tissue cutting/coagulation. The document does not provide specific quantitative acceptance criteria values or detailed performance metrics in a table. It states that the device "performs as intended per the product specifications and requirements."

    Acceptance Criteria Category (Inferred from testing)Reported Device Performance (Summary from submission)
    Functional Performance (Cutting and Coagulation Mode)"Validated the cutting and coagulation mode performance compared to the predicate device(s)." "Performs as intended and meets design specifications."
    Electromagnetic Compatibility (EMC)"Tested in compliance with IEC 60601-1-2 and FDA Guidance 'Electromagnetic Compatibility (EMC) of Medical Devices'."
    Electrical Safety"Tested in compliance with IEC 60601-1 and IEC 60601-2-2, as applicable."
    Software Verification"Provided for an enhanced documentation level in compliance with IEC 62304 and FDA Guidance 'Content of Premarket Submissions for Device Software Functions'."
    Cybersecurity"Tested and assessed according to FDA Guidance 'Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions'."

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

    • Test Set Sample Size: Not specified for any of the non-clinical tests.
    • Data Provenance: Not specified, but the tests were performed "non-clinical," implying laboratory or bench testing rather than clinical patient data. The manufacturer is Erbe Elektromedizin GmbH (Germany).

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

    • This question is not applicable to the non-clinical testing of an electrosurgical hardware device. Ground truth, in the context of AI/SaMD, usually refers to labeled diagnostic data. For this device, "ground truth" would be the measurable physical parameters and effects on tissue.

    4. Adjudication method for the test set

    • This question is not applicable. Adjudication methods like 2+1 or 3+1 are used for expert consensus on ambiguous diagnostic cases in AI/SaMD studies. For an ESU, performance is measured against engineering specifications and observed physical effects.

    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 was not done. This type of study is relevant for diagnostic AI tools that assist human readers (e.g., radiologists interpreting images). The Erbe ESU Model VIO® 3n is an interventional hardware device, not a diagnostic AI.

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

    • The term "standalone performance" for an AI algorithm is not directly applicable here. However, the non-clinical performance testing (functional, EMC, electrical safety) can be considered "standalone" in the sense that the device's technical capabilities were tested independently against specifications without a human operator's diagnostic interpretation loop. The device directly performs an action (cutting/coagulation) rather than providing information for human interpretation.

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

    • For the functional testing, the "ground truth" would be the observable physical effects on tissue (e.g., degree of cutting, coagulation depth, eschar formation) and measured electrical parameters (power output, voltage, current) compared to established engineering specifications and the performance of predicate devices.
    • For safety and EMC, the "ground truth" is compliance with international standards (e.g., IEC 60601 series).

    8. The sample size for the training set

    • This question is not applicable. The Erbe ESU Model VIO® 3n is an electrosurgical hardware device. It does not use a "training set" in the machine learning sense to learn and develop an algorithm. Its operating software is developed through traditional software engineering processes, not machine learning model training.

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

    • This question is not applicable as there is no machine learning training set for this device.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1