Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K181108
    Date Cleared
    2018-05-24

    (27 days)

    Product Code
    Regulation Number
    876.5630
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Fresenius Liberty Select Cycler is indicated for acute and chronic peritoneal dialysis.

    Device Description

    The Liberty Select Cycler is an electro-mechanical medical device. Software controls the functions of the machine during peritoneal dialysis treatment, including fluid flow, heating, and alarms. Like the predicate device, the modified Liberty Select Cycler is a software-controlled electromechanical medical device designed as a table-top unit to deliver Automated Peritoneal Dialysis (APD) therapy for the treatment of end-stage renal disease (ESRD). The Liberty Select Cycler is used to perform continuous and intermittent peritoneal dialysis therapies. Treatment settings are programmed based on a physician's prescription.

    AI/ML Overview

    Acceptance Criteria and Device Performance for Fresenius Liberty Select Cycler (K181108)

    This submission (K181108) is for a modification to the Fresenius Liberty Select Cycler, specifically concerning software updates. The key point is that the essential performance characteristics, indications for use, materials, and other technological aspects remain the same as the predicate device (K171652). Therefore, the acceptance criteria and performance data presented here are based on the essential performance characteristics outlined for the device.

    1. Table of Acceptance Criteria and Reported Device Performance

    FeatureAcceptance CriteriaReported Device Performance (from K171652, essentially unchanged)
    Inflow45–316 mL/min45–316 mL/min
    OutflowMinimum: 30 mL/min, Maximum: 286 mL/minMinimum: 30 mL/min, Maximum: 286 mL/min
    Temperature37°C ± 1°C37°C ± 1°C
    Volume Accuracy, Fill± 2% of the fill volume± 2% of the fill volume
    Volume Accuracy, Drain± 3% of the drain volume± 3% of the drain volume

    2. Sample Size Used for the Test Set and Data Provenance

    The provided document does not specify a separate "test set" in the context of a clinical study with human subjects for this particular submission (K181108). This submission primarily focuses on software modifications to an already cleared device. The testing described is software verification and validation testing, which would typically involve testing on the device itself (hardware-in-the-loop) and simulated environments, rather than a human patient test set.

    • Sample Size: Not applicable in the context of a human patient test set for this submission. The "sample size" would relate to the number of test cases or scenarios executed during software testing.
    • Data Provenance: Not applicable in the context of clinical data provenance for this submission. The "data" comes from internal software testing and verification activities.

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

    Not applicable. This submission focuses on software changes and mechanical/electrical device performance, not on diagnostic accuracy based on expert interpretation. The "ground truth" for software testing would be the expected behavior or outcome defined by design specifications and requirements.

    4. Adjudication Method for the Test Set

    Not applicable. Adjudication methods are typically used in studies involving human interpretation or clinical outcomes where discrepancies among readers or evaluators need to be resolved. This submission describes software and mechanical performance testing.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    No. An MRMC comparative effectiveness study was not done. This type of study is relevant for assessing the impact of AI on human reader performance in diagnostic tasks, which is not the purpose of this device or its modifications.

    6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

    Not explicitly a "standalone study" in the common sense of an AI algorithm making a diagnosis. However, the software verification and validation testing described can be considered a form of standalone performance evaluation for the software's intended functions within the device. The software controls functions like fluid flow, heating, and alarms independently, and its modifications were tested to ensure these functions operate correctly.

    7. Type of Ground Truth Used

    The ground truth for the performance characteristics listed in the table (Inflow, Outflow, Temperature, Volume Accuracy) would be established by engineering specifications, calibration standards, and validated measurement techniques. For the software verification, the ground truth would be the defined software requirements and expected outputs based on those requirements.

    8. Sample Size for the Training Set

    Not applicable. This device is an electro-mechanical medical device with software controls, not a machine learning or AI algorithm that requires a "training set" in the traditional sense. The software is programmed based on defined logic and parameters, rather than trained on data.

    9. How the Ground Truth for the Training Set Was Established

    Not applicable. As there is no "training set" in the context of a machine learning algorithm, there is no ground truth established for it. The software's correct functioning is verified against its predefined specifications and requirements.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1