Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K023509
    Date Cleared
    2003-10-30

    (377 days)

    Product Code
    Regulation Number
    876.5860
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    DAVITA CLINICAL RESEARCH (TRRI)

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

    The DBB-05 Hemodialysis Delivery System is indicated for hemodialysis prescribed by physicians for adult and pediatric patients with acute or chronic renal failure. The DBB-05 is intended for hemodialysis performed in hospitals and dialysis clinics by a qualified operator.

    Device Description

    The subject device is composed of a hydraulic unit for the delivery of dialysate and extracorporeal blood circuitry. The permeate is heated and deaerated in the hydraulic section, which is then mixed with concentrate and fed into the dialyser through the dialysate fluid feeder. The closed balancing system assures the amount of dialysate infused corresponds to the amount of dialysate extracted. The interior pressure of the dialyser is controlled automatically by adjustment of the ultra filtration amount and UF rate by the dialyser. Heparinization of the external circulating blood can be done with the heparin pump either by continuous or one-shot injection before it is passed on to the dialyser. The subject device uses both acetate dialysis and bicarbonate dialysis. Using the various functions the device, the conductivity and UF profile can be programmed. In addition, the subject device incorporates all functions necessary for double-needle dialysis as well as single-needle dialysis treatment. The hydraulic unit is cleaned and disinfected using selectable cleaning programs and is equipped with the necessary protective systems for patient safety and correct operation.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information based on the provided document:

    This document is a 510(k) summary for a medical device (DBB-05 Hemodialysis Delivery System) seeking clearance from the FDA. 510(k) submissions typically show substantial equivalence to a predicate device rather than conducting a full clinical trial to establish new efficacy or safety. Therefore, the "study" described focuses on performance testing to demonstrate that the new device functions as intended and is comparable to existing devices.


    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance Criteria (Implied)Reported Device Performance
    Conformance with product specificationsThe device performed as designed and met, or exceeded, all product specifications.
    Electrical SafetySuccessful
    Failure SimulationSuccessful
    Software TestsSuccessful
    Functionality under normal usage conditionsEnsured conformance with product specifications.

    Explanation of the "Implied" Acceptance Criteria: The document states, "Examination of device function was performed under conditions similar to those found in normal usage to ensure conformance with product specifications." This implies that the acceptance criteria were the defined product specifications for various functional and safety aspects of the device.

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

    • Sample Size: Not specified in the document. The testing described appears to be bench testing or in-house performance verification rather than a patient-based test set.
    • Data Provenance: The testing was conducted by Nikkiso Co., LTD, in Japan (where the manufacturer is located). The data is retrospective in the sense that it was generated prior to the 510(k) submission to demonstrate the device's capabilities.

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

    Since this was performance testing against product specifications, there wasn't a "ground truth" established by external experts in the clinical sense (e.g., diagnosis by radiologists). Instead, the "ground truth" was the device's engineering and functional specifications. The qualifications of the individuals who performed or validated these tests are not provided, but they would typically be engineers and quality control personnel from the manufacturer.

    4. Adjudication Method for the Test Set

    Not applicable. There was no clinical test set requiring expert adjudication. The testing involved verifying the device's performance against predefined engineering specifications.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

    No, an MRMC comparative effectiveness study was not performed. This type of study is typically done for diagnostic imaging devices to assess human reader performance with and without AI assistance. This device is a hemodialysis delivery system, not a diagnostic imaging AI. The submission focuses on demonstrating substantial equivalence to a predicate device through functional and safety testing.

    6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

    This question is not directly applicable to a hemodialysis delivery system in the context of an AI algorithm. The DBB-05 is a physical medical device. The "software tests" mentioned would relate to the embedded software controlling the device's functions, and its standalone performance would be its ability to execute its programmed operations correctly. This was done as part of the functional and safety testing.

    7. The Type of Ground Truth Used

    The "ground truth" for this submission was the established product specifications and regulatory standards for electrical safety, failure simulation, software, and general device function under normal usage. The device's performance was measured against these predefined criteria.

    8. The Sample Size for the Training Set

    Not applicable. This device is not an AI algorithm that undergoes a "training set" in the machine learning sense. It's a hardware device with embedded software.

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

    Not applicable, as there was no training set for an AI algorithm.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1