Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K980646
    Date Cleared
    1998-05-06

    (76 days)

    Product Code
    Regulation Number
    862.1113
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    IL SYNTHESIS--ADDITION OF BILIRUBIN AS A MEASURED PARAMETER FOR NEONATE WHOLE BLOOD SAMPLES

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

    The IL Synthesis™ is a family of fully automatic, microprocessor controlled, blood gas, electrolytes, glucose, hematocrit and co-oximeter analyzers that was cleared for market by K963800. A new measured co-oximeter parameter is being added on the IL Synthesis™ for the semiquantitative determination of total bilirubin in whole blood from neonates. Elevated bilirubin levels in the blood of newborns is used to aid in indicating the risk of bilirubin encephalopathy (kernicterus).

    Device Description

    The IL Synthesis™ is a family of fully automatic, microprocessor controlled, blood gas, electrolytes, glucose, hematocrit and co-oximeter analyzers that was cleared for market by K963800. A new measured co-oximeter parameter is being added on the IL Synthesis™ for the semiquantitative determination of total bilirubin in whole blood from neonates.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study details for the IL Synthesis™ Bilirubin parameter, as presented in the provided document:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document does not explicitly state pre-defined acceptance criteria in terms of specific numerical thresholds for slope, intercept, or correlation coefficient. Instead, it describes what the results "showed" and concludes that they are "statistically similar" to the predicate device. For precision, specific acceptance criteria (e.g., maximum allowable SD) are not provided, only the observed SD values.

    Acceptance Criterion (Implicit)Reported Device Performance
    Comparative Performance (vs. Predicate Device)Linear Regression Analysis:
    Substantially equivalent performance to predicate device.Slope: 0.925
    (Implicit: Results are statistically similar)Intercept: 1.097
    Correlation Coefficient (R): 0.969
    Conclusion: "indicating that the results are statistically similar."
    PrecisionWithin-run Precision (5 replicates per instrument, per level):
    Acceptable precision for clinical use (implicit).Level 1 Bilirubin (mg/dL):
    (Implicit: SDs are within expected ranges for the measurement)Instrument 1: Mean 1.1, SD 0.95
    Instrument 2: Mean 0.6, SD 0.78
    Instrument 3: Mean 1.3, SD 0.38
    Level 2 Bilirubin (mg/dL):
    Instrument 1: Mean 2.3, SD 0.55
    Instrument 2: Mean 1.7, SD 0.49
    Instrument 3: Mean 3.7, SD 0.45

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

    • Sample Size: 309 whole blood samples.
    • Data Provenance: The document does not explicitly state the country of origin or whether the study was retrospective or prospective. It only mentions "In a comparative performance study" and "whole blood samples."

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

    • This device is an in-vitro diagnostic (IVD) device measuring a biomarker (bilirubin). The "ground truth" for the comparative study was established by another analytical method (the predicate device, Sigma's Bilirubin, Total and Direct on a spectrophotometer), not by clinical experts making diagnoses based on the results.
    • Therefore, the concept of "experts establishing ground truth" as it would apply to image interpretation or clinical decision-making is not directly applicable here. The predicate device itself acts as the reference method.

    4. Adjudication Method for the Test Set

    • Not applicable. The study compares the new device's measurements against a reference method (the predicate device) directly. There is no human interpretation or adjudication involved in establishing the "ground truth" values for the bilirubin levels.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

    • No, an MRMC comparative effectiveness study was not done. This study focuses on the analytical performance of an IVD device measuring a biomarker, not on human interpretation of images or data.

    6. 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 IL Synthesis™ analyzes samples automatically, and the performance data presented (comparative and precision) reflects the device's output without human intervention in the measurement process itself.

    7. The Type of Ground Truth Used

    • Comparative Ground Truth: The "ground truth" or reference for the comparative study was the measurement results from the predicate device: Sigma's Bilirubin, Total and Direct on a spectrophotometer. This is a form of reference method comparison or method comparison validation.
    • Precision Ground Truth: For the precision study, the ground truth is simply the intrinsic variability of the device measuring the same sample multiple times.

    8. The Sample Size for the Training Set

    • The document describes a 510(k) submission for an already existing device (IL Synthesis™) with the addition of a new measured parameter (Bilirubin). It does not provide information about a "training set" in the context of machine learning. IVD device development typically involves analytical validation studies rather than machine learning training sets.
    • If we interpret "training set" as the data used to initially develop and optimize the bilirubin measurement method for the IL Synthesis™, that information is not provided in this summary. The 309 samples described are for performance validation against the predicate.

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

    • As noted above, the concept of a "training set" and its "ground truth" in the machine learning sense is not applicable or detailed in this 510(k) summary for an IVD device. The summary focuses on the validation of the new parameter's performance against a legally marketed predicate device.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1