K Number
K013568
Manufacturer
Date Cleared
2001-12-21

(56 days)

Product Code
Regulation Number
866.6010
Panel
IM
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

This in vitro immunoassay is intended to quantitatively measure CEA in human serum using ADVIA IMS CEA Assay on a Bayer ADVIA® IMS™. Carcinoembryonic Antigen (CEA) is a protein polysaccharide normally present at very low concentrations in the blood of healthy adults. Colorectal cancer and a variety of neonlantic and other disease processes cause significant elevation of CEA, thus issued as a tumor marker. CEA assay is designed to aid in the management and prognosis of cancer patients in whom changing concentrations of CEA are observed.

The Bayer ADVIA® IMS™ CEA assay is an in vitro diagnostic device intended to qualitatively measure carcinoembryonic antigen (CEA) in human serum. CEA test results are to be used as an aid in the management of cancer patients by monitoring CEA concentrations. CEA testing is not recommended as a screening procedure to detect cancer in the general population.

Device Description

Not Found

AI/ML Overview

Here's an analysis of the acceptance criteria and study details based on the provided text, formatted to address your specific points:

Acceptance Criteria and Device Performance

Acceptance CriteriaReported Device Performance (ADVIA IMS CEA Assay)
Imprecision (Total CV%)Level 2.05 ng/mL: 3.0%
Level 10.76 ng/mL: 2.2%
Level 16.85 ng/mL: 1.8%
Correlation (R value)0.998
Correlation (Syx)1.019 ng/mL
Interference (Hemoglobin)0.4% change at 1000 mg/dL concentration
Interference (Lipids)1.8% change at 1000 mg/dL concentration
Interference (Bilirubin)1.2% change at 25 mg/dL concentration
Interference (IgG)1.2% change at 6.0 mg/dL concentration
Interference (Albumin)2.5% change at 6.5 mg/dL concentration
Analytical Range0.2 – 100 ng/mL
Minimum Detectable Conc.0.2 ng/mL

The acceptance criteria are implicitly defined by the performance of the predicate device (Immuno 1) which the ADVIA IMS CEA Assay aims to be substantially equivalent to. The provided table directly compares the performance of the ADVIA IMS to the Immuno 1 for imprecision and minimum detectable concentration. For other metrics like correlation and interference, specific thresholds are not explicitly stated, but the reported values demonstrate acceptable performance relative to the predicate device and expected analytical specifications for such assays, leading to the conclusion of substantial equivalence.

Study Details

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

    • Sample Size: 89 serum specimens were used for the correlation study.
    • Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document indicates "human serum" samples were used.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • This is an in vitro diagnostic (IVD) assay for quantitative measurement of a biomarker. The "ground truth" for such assays is established through comparison to a well-characterized reference method or predicate device. Human experts are generally not involved in establishing the ground truth for an IVD's quantitative measurements in the same way they would be for image interpretation.
  3. Adjudication method for the test set:

    • Not applicable. As this is a quantitative measurement compared to a predicate device, adjudication by multiple human readers is not relevant.
  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:

    • Not applicable. This is an in vitro diagnostic (IVD) device, not an AI-assisted diagnostic tool for image interpretation or similar applications where MRMC studies are typically conducted.
  5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    • Yes, the performance data presented (imprecision, correlation, interference, analytical range, minimum detectable concentration) represent the standalone performance of the ADVIA IMS CEA Assay device itself. It's a fully automated analytical system once the sample is loaded.
  6. The type of ground truth used:

    • Predicate Device Comparison: The primary "ground truth" or reference for establishing the performance of the ADVIA IMS CEA Assay was the Immuno 1 CEA Assay. The study demonstrates correlation and comparative performance against this legally marketed predicate device.
  7. The sample size for the training set:

    • Not specified. For an in vitro diagnostic assay, there isn't typically a "training set" in the machine learning sense. Assay development involves optimizing reagents, protocols, and instrument parameters, but not usually in a data-driven training paradigm like AI. The reported data pertains to the validation of the final developed assay.
  8. How the ground truth for the training set was established:

    • Not applicable, as there isn't a "training set" in the context of an IVD assay's analytical performance validation. The performance characteristics are inherent to the assay's chemical and instrumental design.

§ 866.6010 Tumor-associated antigen immunological test system.

(a)
Identification. A tumor-associated antigen immunological test system is a device that consists of reagents used to qualitatively or quantitatively measure, by immunochemical techniques, tumor-associated antigens in serum, plasma, urine, or other body fluids. This device is intended as an aid in monitoring patients for disease progress or response to therapy or for the detection of recurrent or residual disease.(b)
Classification. Class II (special controls). Tumor markers must comply with the following special controls: (1) A guidance document entitled “Guidance Document for the Submission of Tumor Associated Antigen Premarket Notifications (510(k)s) to FDA,” and (2) voluntary assay performance standards issued by the National Committee on Clinical Laboratory Standards.