LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K980242
    Device Name
    IL TEST HEPARIN
    Manufacturer
    INSTRUMENTATION LABORATORY CO.
    Date Cleared
    1998-03-19

    (55 days)

    Product Code
    KFF
    Regulation Number
    864.7525
    Type
    Traditional
    Panel
    Hematology
    Reference & Predicate Devices
    K935212
    Why did this record match?
    Device Name :

    IL TEST HEPARIN

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

    IL Test™ Heparin is an in vitro diagnostic test for the quantitative determination of unfractionated heparin (UFH) and low molecular weight heparin (LMWH) activity in human plasma. It is an automated heparin assay based on a synthetic chromogenic substrate and Factor Xa inactivation.

    Device Description

    IL Test™ Heparin is an in vitro diagnostic test for the quantitative determination of unfractionated heparin (UFH) and low molecular weight heparin (LMWH) activity in human plasma. It is an automated heparin assay based on a synthetic chromogenic substrate and Factor Xa inactivation.

    AI/ML Overview

    Here's an analysis of the provided information regarding the acceptance criteria and study for the IL Test™ Heparin device:

    Acceptance Criteria and Device Performance

    Acceptance Criteria CategoryAcceptance CriteriaReported Device Performance
    Method ComparisonCorrelation (r) to predicate device should demonstrate substantial equivalence.ACL 300: r = 0.988 (n=98)
    ACL Futura: r = 0.989 (n=91)
    Within-Run Precision (UFH)Not explicitly stated, but typically a low Coefficient of Variation (CV) is desired.ACL 300:
    • 1.84% CV at 0.77 U/mL
    • 7.76% CV at 0.23 U/mL
    ACL Futura:
    • 4.06% CV at 0.81 U/mL
    • 14.27% CV at 0.21 U/mL

    Note: The document states that the new device "is substantially equivalent in performance, intended use and safety and effectiveness" to the predicate device. The presented performance data (correlation and precision) are intended to support this claim of substantial equivalence. Specific numerical acceptance thresholds for r and CV are not explicitly listed in the provided text, but the reported values are presented as evidence of meeting the general requirement for substantial equivalence.

    Study Details

    1. Sample sizes used for the test set and the data provenance:

      • Method Comparison Sample Sizes:
        • ACL 300: n = 98 samples
        • ACL Futura: n = 91 samples
      • Data Provenance: The samples were "from patients treated with UFH and LMWH." No specific country of origin is mentioned, but it can be inferred that it's likely from a medical setting in the USA, given the submission to the FDA. The study is retrospective in nature, using existing patient samples.

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

      • Not applicable. This is an in vitro diagnostic device for quantitative determination of substances in plasma. The "ground truth" for method comparison is the result obtained from the predicate device, not expert consensus interpretation.

    3. Adjudication method for the test set:

      • Not applicable. As this is an in vitro diagnostic device measuring chemical substances, there is no human adjudication process involved in establishing ground truth for the test set.

    4. 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. This is an in vitro diagnostic device. MRMC studies are typically for imaging or other diagnostic tools where human interpretation plays a role and AI assistance might be integrated. This device is an automated assay.

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

      • Yes, this study is inherently a standalone performance evaluation of the device (the automated assay) compared to a predicate device. The results (correlation and precision) demonstrate the algorithm's performance without direct human intervention in the result generation or interpretation beyond operating the instrument.

    6. The type of ground truth used:

      • For the method comparison studies, the "ground truth" was the quantitative result obtained from the predicate device (IL Test™ Heparin Xa). For precision studies, the ground truth was the expected concentration of the 4th Heparin International Standard.

    7. The sample size for the training set:

      • Not applicable / Not specified. For in vitro diagnostic assays of this type, a "training set" in the machine learning sense is not typically used or reported. The assay's chemical/biological principles are established, and the "training" would involve optimization and calibration of the assay parameters during development, not a data-driven model training.

    8. How the ground truth for the training set was established:

      • Not applicable. See point 7. The device's underlying principles are based on established biochemical reactions (synthetic chromogenic substrate and Factor Xa inactivation), not a learned model from a ground-truth-labeled training set. Calibration might use reference materials like the Heparin International Standard, but this is distinct from "training data" for an AI algorithm.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1