Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K221011
    Device Name
    AI.ME System
    Date Cleared
    2022-12-20

    (259 days)

    Product Code
    Regulation Number
    878.4430
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K160312, K173358

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

    The AI.ME System is indicated for fractional skin resurfacing.

    Device Description

    The AI.ME system is a micro coring device controlled by a robot that removes skin by using a disposable punch assembly containing six (6), hollow needle punches inserted into the skin with a fixed maximum penetration depth of 3 mm to remove up to 10% of skin in the treatment area to excise and/or resurface skin.

    The AI.ME system, which is similar in design and performance as the FDA cleared Venus Concept ARTAS system, consists of a cart, a coring mechanism, single-use vacuum assembly and a sterile single-use disposable punch assembly.

    AI/ML Overview

    This document describes the FDA's 510(k) clearance for the AI.ME System, a microneedling device for aesthetic use. It details the device's substantial equivalency to predicate devices based on non-clinical performance data.

    Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

    Acceptance Criteria and Reported Device Performance

    The document does not present a formal table of quantitative acceptance criteria with corresponding performance metrics like a typical study report might. Instead, it outlines various performance and safety tests conducted and states that they were successfully passed or demonstrated. The acceptance criteria are implicitly linked to compliance with relevant industry standards and guidance documents.

    Here's a table constructed from the information provided, outlining the tested aspects and the stated outcome:

    Acceptance Criteria (Stated Test/Requirement)Reported Device Performance (Outcome)
    Software DocumentationPrepared and submitted for a moderate level of concern device in accordance with FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.
    Electrical SafetyTested and successfully passed all relevant sections of IEC 60601-1 Medical electrical equipment, General requirements for Safety.
    Electromagnetic Interference (EMC)Tested and successfully met all relevant sections (Radiated emissions, Conducted emissions, Harmonic emissions, Flicker emissions, Electrostatic discharge immunity test, radiated radio frequency immunity, Electrical fast transient/burst, lightning surge immunity, conducted RF immunity, electromagnetic field immunity, voltage dips and short interruptions, RFID compatibility, and power frequency magnetic field immunity test) to satisfy compliance with IEC 60601-1-2.
    Accuracy of needle penetration depth and puncture rateTested in a suitable skin substrate model and measured using the Keyence Laser System. (Implicitly passed, as no issues were raised).
    Safety features against cross-contamination & fluid ingress protectionDevice design prevents cross-contamination and includes fluid ingress protection due to needle cartridge design. Design elements include serialized disposable assemblies (to prevent re-use) and a sealed path (to prevent fluid ingress). Testing was performed under worst-case scenarios. (Implicitly passed).
    Identification of max safe needle penetration depthMaximum safe needle penetration depth identified in a suitable skin substrate model. The needle depth is fixed at 3 mm and cannot be adjusted, "thus eliminating the needle depth hazard." (Implicitly passed, as control is fixed).
    Sterility of patient-contacting componentsPerformance data demonstrates sterility according to ANSI/AAMI/ISO 17665-1 and ANSI/AAMI/ISO 14937.
    Shelf life support (sterility, package integrity, device functionality)Disposables supplied non-sterile and sterilized per validated procedure prior to use. Materials are non-degradable, so a labeled shelf life is not required. (This addresses the concern by stating it's not applicable for this device's components).
    Biocompatibility of patient-contacting componentsDemonstrated to be biocompatible, including evaluation of cytotoxicity, irritation, sensitization, acute systemic toxicity, and material-mediated pyrogenicity per ISO 10993-1.
    Cleaning and disinfection instructions for reusable componentsCleaning and disinfection validation performed per AAMI TIR30.
    Software verification, validation, and hazard analysisPerformed for all software components according to FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.
    Labeling contentIncludes operational information, device technical parameters, reprocessing instructions for reusable components, disposal instructions, and (where applicable) shelf life. (This is a statement of inclusion, implying compliance).
    Patient labeling contentIncludes device operation information, typical treatment course, probable risks and benefits, and postoperative care instructions. (This is a statement of inclusion, implying compliance).
    Pre-Clinical (Animal) Performance DataStudy in swine model showed clear time-related progressive healing and full resurfacing of the treated area. Concluded that the system "does not pose any undue or additional risks and is safe and effective for fractional skin resurfacing."

    Study Details

    This document describes a 510(k) premarket notification for a medical device that does not involve an AI algorithm for diagnostic or prognostic purposes, but rather a robotic system that incorporates an "AI.ME System" name. The AI aspect, as described, appears to relate to the robotic control for precision, rather than a data-driven AI model that makes clinical assessments or diagnoses. Therefore, many of the requested details about AI model studies (like sample size for test/training sets, ground truth establishment methods, expert adjudication, MRMC studies) are not applicable to the type of device and testing described in this 510(k) summary.

    The "AI" in "AI.ME System" seems to refer to Artificial Intelligence in the sense of an intelligent, automated system (robotics), rather than a machine learning algorithm for image analysis or clinical decision support that would require extensive data for training and testing as per the typical questions.

    However, based on the provided text, here's what can be inferred about the "performance data" that serves as the "study":

    1. Sample Size Used for the Test Set and Data Provenance:

      • Test Set (Pre-Clinical Study): A "swine model" was used for the pre-clinical study. The exact number of animals is not specified.
      • Data Provenance: The study was "pre-clinical" (animal model), likely conducted in a controlled lab environment by the manufacturer or a contract research organization. The country of origin is not specified. It is a prospective study, as it describes an evaluation over time (7, 14, 28 days post-treatment).
      • Other Performance Data: For non-clinical tests like electrical safety, EMC, software validation, sterility, biocompatibility, etc., these are bench tests and lab validations. No patient data or image data sets were mentioned.
    2. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:

      • For the swine study, "macroscopical and histopathological analysis" was conducted. This implies expert evaluation (e.g., pathologists).
      • However, the number of experts and their specific qualifications are not specified.
      • Ground truth regarding the performance characteristics (e.g., accuracy of needle penetration depth) would have been established by engineering measurements using instruments like the Keyence Laser System, not clinical experts.
    3. Adjudication Method for the Test Set:

      • For the pre-clinical (swine) study, the method of adjudication for macroscopic and histopathological analysis is not specified. It generally implies a consensus or independent review process by qualified personnel, but no details are provided.
      • For other performance tests, adjudication methods are not applicable as they involve objective measurements against standards.
    4. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done:

      • No, an MRMC comparative effectiveness study was not done. This type of study is typically performed for diagnostic imaging AI systems where human readers interpret medical images with and without AI assistance. The AI.ME system is a microneedling device, not a diagnostic imaging AI.
    5. If a Standalone (algorithm only without human-in-the-loop performance) was done:

      • The document describes device performance characteristics and safety validations. While the "AI.ME System" implies an automated aspect (robotics), the testing detailed is on the physical device's mechanics, safety, and biological interaction. It's not a standalone AI algorithm in the sense of a software-only diagnostic tool being evaluated for its performance. The "performance data" reported is for the system as a whole, including its automated functions, but doesn't isolate an AI algorithm's performance in a way that is typically measured for diagnostic AI.
    6. The Type of Ground Truth Used:

      • Pre-Clinical Swine Study: Ground truth was established through "macroscopical and histopathological analysis" of tissue from the treated areas at different time points (7, 14, 28 days). This is pathology-based ground truth indicating tissue response and healing.
      • Other Tests: Ground truth for other aspects (e.g., electrical safety, EMC, sterility, biocompatibility, accuracy of needle depth) was established through objective measurements against recognized industry standards and validated methods.
    7. The Sample Size for the Training Set:

      • Not applicable / not specified. The document describes a medical device clearance based on substantial equivalence and non-clinical performance testing validated against standards. It does not describe the development or training of a machine learning model that would require a distinct "training set" of data in the typical AI sense. The "AI" in AI.ME likely refers to robotic automation/control, not a learned model from a dataset.
    8. How the Ground Truth for the Training Set was Established:

      • Not applicable. As no AI training dataset is explicitly mentioned, the concept of establishing ground truth for a training set does not apply.

    Conclusion Summary from Document:

    The document concludes that the AI.ME System is safe and effective as the legally marketed predicate and reference devices, and that the performance testing data supports the stated indications for use. It asserts that the AI.ME System did not raise new questions of safety or effectiveness.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1