LogoFDA 510(k) Search
Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K001763
    Device Name
    CRIT-LINE MONITOR III (CLM III)
    Manufacturer
    IN-LINE DIAGNOSTICS CORP.
    Date Cleared
    2000-12-20

    (191 days)

    Product Code
    MQS
    Regulation Number
    876.5820
    Type
    Traditional
    Panel
    Gastroenterology/Urology
    Reference & Predicate Devices
    N/A
    Predicate For
    K093834
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    Device Description
    AI/ML Overview
    Ask a Question

    Ask a specific question about this device

    K Number
    K992227
    Device Name
    CRIT-LINE MONITOR III (CLM III)
    Manufacturer
    IN-LINE DIAGNOSTICS CORP.
    Date Cleared
    1999-07-30

    (28 days)

    Product Code
    MQS
    Regulation Number
    876.5820
    Type
    Special
    Panel
    Gastroenterology/Urology
    Reference & Predicate Devices
    K972470,K982412
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The CRIT-LINE MONITOR III, (CLM III) is a non-invasive hematocrit, oxygen saturation and percent change in blood volume monitor used in the treatment of hemodialysis patients. In addition, the CLM III estimates access recirculation and access blood flow in hemodialysis patients.

    Device Description

    The CLM III consists of a state-of-the-art microprocessor which has all of the chip select logic, serial communication, timing and watchdog circuits incorporated within it. The CLM III is used in conjunction with the In-Line Diagnostics Blood Chamber. The blood chamber is connected to and becomes part of the dialysis tubing circuit. The sensor from the CLM III is connected to the blood chamber which reads critical blood parameters as blood passes through the blood chamber.

    AI/ML Overview

    Here's an analysis of the provided text regarding the CRIT-LINE MONITOR III, structured to answer your questions:

    Acceptance Criteria and Device Performance Study for CRIT-LINE MONITOR III

    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance Criteria (Stated Goal)Device Performance (Reported Result)
    Correlation coefficient value near 1 (i.e., .90 or greater) for internally calculated ABF vs. externally calculated ABF.Correlation coefficient: 0.94
    -Average difference between methods: 46 ml/min
    -Standard deviation of difference: 200 ml/min

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

    • Sample Size: 29 data points
    • Data Provenance: Retrospective (though collected specifically for this validation, it's not a prospective interventional trial based on the description).
      • 16 data points from Victoria Hospital in London Ontario, Canada (April 8th and April 9th, 1999)
      • 13 data points from Central Valley Dialysis in Salt Lake City, Utah (June 22nd and June 24th, 1999)

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

    The document does not mention the use of experts to establish ground truth. The "ground truth" (or reference method) was established by calculating Access Blood Flow (ABF) values externally using CRIT-LINE MONITOR III hematocrit measurements fed into a formula via a calculator or spreadsheet program (which was the previously approved method, K982412).

    4. Adjudication Method for the Test Set

    No adjudication method is described. The comparison was statistical between two calculated values (one internally by the device, one externally using device-generated hematocrit data and a formula).

    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 comparative effectiveness study was not done. This device is a monitor measuring physiological parameters; it's not an AI system for image interpretation or diagnosis that would typically involve human readers.

    6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

    Yes, in a way. The study's purpose was to validate the internal calculation of ABF by the CRIT-LINE MONITOR III. This internal calculation is essentially the "algorithm only" performance, compared against the established external calculation method which uses data generated by the same device (CLM III hematocrit measurements) but processes it outside the device. The study is evaluating the device's self-contained ABF calculation capability.

    7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

    The "ground truth" was the previously approved method of ABF measurement, which involved:

    • Measuring hematocrit values using the CLM III.
    • Calculating ABF values externally via a calculator or spreadsheet program using these measured hematocrit values.
    • This method itself had a 510(k) clearance (K982412).

    Essentially, the ground truth was a reference calculation method using device-generated data.

    8. The Sample Size for the Training Set

    The document does not mention a separate training set. The CRIT-LINE MONITOR III is a physical device with a software modification for internal calculation. The description implies the software was developed based on existing understanding of the ABF formula and then validated with the 29 data points as the "test set" against the established external calculation method. It's unlikely that machine learning or a training set in the modern sense was used for this type of device in 1999.

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

    As no explicit training set is mentioned, this question is not applicable. The device's internal ABF calculation functionality was evaluated against a pre-existing, legally marketed method of calculating ABF.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1