Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K150239
    Device Name
    FibroScan
    Manufacturer
    Date Cleared
    2015-09-01

    (211 days)

    Product Code
    Regulation Number
    892.1560
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The FibroScan® system is intended to provide 50Hz shear wave speed measurements and estimates of tissue stiffness through internal structures of the body.

    FibroScan® is indicated for noninvasive measurement of shear wave speed and estimate of stiffness at 50 Hz in the liver. The shear wave speed may be used as an aid to clinical management of pediatric and adult patients with liver disease.

    Device Description

    FibroScan® system consists of a system unit and a hand-held probe. It is based on Vibration-Controlled Transient Elastography (VCTE™) technology, and is designed to perform non-invasive measurements of liver shear wave speed and estimates of tissue stiffness. The probe containing a mechanical vibrator produces low-amplitude elastic waves that travel through the skin and intercostal space into the liver. Ultrasound is used to track the shear (elastic) wave, measure its speed and provide estimated stiffness. The results are displayed on the system unit.

    The focus of this submission is the expansion of the indications for use for the FibroScan system by Echosens to pediatric patients. In order to address the smaller anatomic size of pediatric patients, a new probe (S+) was developed, and the indications for use of the previously cleared M+ probe were modified. The new probe uses the same principle of operation, intended use and methodology (i.e. application to patient, signal measurement, processing and display), design, materials, manufacturing and testing processes as the previously cleared M+ and XL+ probes. The device specifications are similar to those of the predicate device. The system's software was upgraded to accommodate these changes.

    AI/ML Overview

    The FibroScan® system, specifically the new S+ probe and revised software, aims to expand its indications for use to pediatric patients. The study primarily focused on non-clinical testing to demonstrate that the device meets its specifications and is substantially equivalent to predicate devices.

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria for the FibroScan® system are derived from the performance parameters of its predicate devices, FibroScan® (#K123806) and Aixplorer® (#K132274), particularly concerning bias and precision in shear wave speed measurements.

    Acceptance Criteria CategoryAcceptance Criteria (derived from predicate devices)Reported Device Performance (FibroScan® - Pediatric Use)
    BiasComparable to or better than:(-13.5%) - (3.6%)
    FibroScan® Predicate: (-13.9%) - (1.3%)
    Aixplorer® Predicate: (-7.2%) - (43.4%)
    PrecisionComparable to or better than:(0.7%) - (2.0%)
    FibroScan® Predicate: (0%) - (3.1%)
    Aixplorer® Predicate: (0%) - (3.4%)
    TechnologySame underlying physical phenomenon, methodology, and design principles as predicate devices.Same principle of operation, design, materials, manufacturing, and testing processes as primary predicate.
    Intended UseDiagnostic ultrasound imaging/fluid flow analysis of the human body, specifically liver stiffness measurement.Provides 50Hz shear wave speed measurements and estimates of tissue stiffness in the liver. Aid to clinical management of pediatric and adult patients with liver disease.
    Clinical ApplicationAbdominal (for adults), Pediatric (for Aixplorer).Pediatric
    Probe FrequencyWithin range of frequencies used by predicate devices for pediatric applications.5 MHz (S+ Probe)

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

    The document explicitly states that non-clinical testing was performed on phantoms with known elasticity. It does not specify a sample size for these phantoms or their provenance beyond "known elasticity." There is no mention of a human test set in this section of the document.

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

    As the testing was performed on phantoms with "known elasticity," there were no human experts involved in establishing the ground truth for the test set.

    4. Adjudication method for the test set

    Not applicable, as the testing was performed on physical phantoms with established properties, not on cases requiring expert 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

    No MRMC comparative effectiveness study was done or reported in this document. The device operates as a standalone measurement tool and is not described as an AI-assisted interpretation system for human readers.

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

    Yes, a standalone performance evaluation was done for the device. The reported "bias" and "precision" values were obtained directly from the device's measurements on phantoms without human intervention in the measurement process itself. The document emphasizes the algorithm/device's performance in measuring shear wave speed and estimating stiffness.

    7. The type of ground truth used

    The ground truth used for the non-clinical testing was the known elasticity of the phantoms.

    8. The sample size for the training set

    The document describes non-clinical testing and substantial equivalence claims based on technical characteristics and phantom performance. It does not mention a training set in the context of machine learning or AI algorithm development. The "system's software was upgraded to accommodate these changes," but no details on software training are provided.

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

    Not applicable, as no training set (in the context of machine learning) is mentioned as being used or developed for this submission. The software upgrade is described as accommodating changes related to the new probe and expanded indications, rather than being trained on a specific dataset.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1