K Number
K983875
Date Cleared
1999-05-14

(193 days)

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

The Vitros® CA 125 II is an in vitro assay intended for the quantitative measurement of OC 125 defined antigen in the serum or plasma (EDTA or heparin). The Vitros CA 125 II assay is to be used as an aid in monitoring response to therapy for patients with epithelial ovarian cancer. Serial testing for patient CA 125 assay values should be used in conjuction with other clinical methods used for monitoring ovarian cancer.

Device Description

The VITROS Immunodiagnostic System uses luminescence as the signal in the quantitative and semi-quantitative determination of selected analytes in human body fluids, commonly serum and plasma. Coated microwells are used as the solid phase separation system. The system is comprised of three main elements: 1. The VITROS Immunodiagnostic Products (in this case VITROS Immunodiagnostic Products CA 125 II Reagent Pack, VITROS Immunodiagnostic Products CA 125 II Calibrators, which are combined by the VITROS Immunodiagnostic System to perform the VITROS CA 125 II assay). 2. The VITROS Immunodiagnostic System instrumentation, which provides automated use of the immunoassay kits. 3. Common reagents used by the VITROS System in each assay. The VITROS System and common reagents are dedicated specifically only for use with the VITROS Immunodiagnostic Products range of immunoassay products.

AI/ML Overview

The provided text describes a 510(k) premarket notification for the VITROS CA 125 II assay, which is an in vitro diagnostic device. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than conducting a de novo study with strict acceptance criteria and a detailed study design as might be seen for novel AI/ML software.

Therefore, many of the requested categories are not applicable or cannot be determined from the provided document, as the FDA 510(k) process for this type of device does not typically require the same level of detail regarding acceptance criteria linked to specific performance endpoints, or a standalone study as would be required for a novel AI device addressing diagnostic performance (e.g., sensitivity, specificity, AUC) against a clinical ground truth.

However, I can extract the information that is present and indicate where information is missing or not applicable based on the nature of the submission.


Acceptance Criteria and Device Performance for VITROS CA 125 II assay

The primary "acceptance criterion" for a 510(k) submission like this is substantial equivalence to a predicate device. For in vitro diagnostic assays, this typically involves demonstrating comparable analytical performance, including correlation, precision, and other assay characteristics.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criterion (Implicit for 510(k) Equivalence)Reported Device Performance
Correlation with Predicate DeviceVITROS CA 125 II assay = 0.963 x [Boehringer Mannheim Elecsys CA 125 II] + 0.654 (U/mL)
Coefficient of Correlation0.946
Analytical SensitivityTests performed, but specific values not reported in summary.
SpecificityTests performed, but specific values not reported in summary.
PrecisionTests performed, but specific values not reported in summary.
DilutionTests performed, but specific values not reported in summary.
Expected ValuesTests performed, but specific values not reported in summary.

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

  • Sample Size for Test Set: Samples from "a variety of clinical categories" were used for comparison. The exact number of samples is not specified in this summary document.
  • Data Provenance: The origin of the clinical samples (e.g., country) is not specified. The document implies these were clinical samples ("samples from a variety of clinical categories"). It does not specify if the data was retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth and Qualifications of Experts

  • Not Applicable. For an in vitro diagnostic assay demonstrating analytical equivalence with a predicate, the "ground truth" for the test set is typically established by the measurement of the analyte by the predicate device itself, and potentially by reference methods for analytical performance characteristics. Expert interpretation of images or clinical outcomes is not the primary ground truth method for this type of device.

4. Adjudication Method for the Test Set

  • Not Applicable. See point 3. Performance is based on quantitative analytical results, not adjudicated interpretations.

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

  • No. This is an in vitro diagnostic (IVD) assay, not an AI/ML imaging or diagnostic software that typically involves human readers. Therefore, an MRMC study is not applicable.

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

  • Yes, effectively. As an IVD assay, the device operates autonomously to measure CA 125 II antigen in serum or plasma. Its performance is evaluated independently of human interpretation of its measurement to establish analytical equivalence. While the results are used by clinicians, the "performance" of the assay itself is standalone.

7. The Type of Ground Truth Used

  • Comparative Measurement against Predicate Device (Boehringer Mannheim Elecsys CA 125 II). For analytical correlation, the predicate device's measurements served as the reference. For other analytical characteristics (sensitivity, specificity, etc.), standard laboratory reference methods or purified analytes would typically be used, but the specifics are "Refer to the VITROS CA 125 II assay package insert."

8. The Sample Size for the Training Set

  • Not Applicable/Not Specified. This is a traditional immunoassay, not an AI/ML model that requires a distinct "training set" in the machine learning sense. The assay development and calibration process would involve extensive experimentation and optimization, but it's not described as a "training set" like in AI/ML.

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

  • Not Applicable/Not Specified. See point 8. The "ground truth" for developing such an assay would relate to accurate measurement of the CA 125 analyte using established analytical chemistry principles and reference materials, rather than a "ground truth" of patient outcomes or expert consensus.

§ 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.