K Number
K984619
Date Cleared
1999-02-23

(56 days)

Product Code
Regulation Number
866.5660
Panel
IM
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

For the in-vitro measurement of specific IgG autoantibodies against the glomerular basement membrane (GBM) specifically the C-terminal end of type IV collagen, present in human serum. It is intended as an aid in the diagnosis of Goodpast's syndrome, in conjunction with other clinical findings.

Device Description

BINDAZYME Anti-GBM EIA Diagnostic Test Kit

AI/ML Overview

This document is a 510(k) clearance letter from the FDA for an in vitro diagnostic test kit, specifically the "Binding Site BINDAZYME® Anti-GBM Enzyme Immunoassay Diagnostic Test Kit."

It's important to understand that a 510(k) clearance for an in vitro diagnostic (IVD) device is fundamentally different from the regulatory process for AI-powered medical image analysis devices. The information requested in your prompt (e.g., sample size for test set, number of experts, adjudication methods, MRMC studies, standalone performance, training set details) is typically associated with the comprehensive clinical validation studies required for AI devices, especially those that provide diagnostic insights from medical images.

For an IVD like the one described in this document, the "performance" typically refers to analytical performance (sensitivity, specificity, precision, accuracy relative to a reference method) and clinical performance (how well the test results correlate with the presence or absence of the disease in a patient population, and its utility in diagnosis). The document provided is not a study report; it's an FDA clearance letter affirming substantial equivalence to a predicate device. Therefore, it does not contain the detailed study information you are asking for regarding acceptance criteria, sample sizes, expert involvement, or AI-specific validation methods.

However, I can infer and state what would typically be expected for such a device and what some of the closest information might be, based on the nature of a 510(k) submission for an IVD.


Absence of Specific Information:

The provided document (FDA 510(k) clearance letter) does not contain the detailed study information required to answer most of your questions about acceptance criteria and study design as it pertains to AI/ML devices. This document is a regulatory approval letter based on a separate submission, not the submission itself or a study report.

Inferences Based on IVD Nature and 510(k) Process (General Expectation, Not from Document):

For an in-vitro diagnostic (IVD) device, the "acceptance criteria" and "study" would typically refer to analytical and clinical performance studies, which are evaluated against a predicate device or accepted standards for diagnosing a specific condition.


Based on the provided document and general understanding of IVD 510(k) clearances, here's what can be stated or inferred:

  1. Table of Acceptance Criteria and Reported Device Performance:

    • Acceptance Criteria: Not specified in the provided document. For an IVD like this, acceptance criteria would typically relate to analytical performance (e.g., sensitivity, specificity, precision, linearity, range) and clinical performance (e.g., agreement with a gold standard or predicate device in patient populations).
    • Reported Device Performance: Not explicitly detailed in the provided document. The FDA's letter states that "we have determined the device is substantially equivalent... to legally marketed predicate devices." This implies that the device's performance, as demonstrated in its 510(k) submission, was deemed comparable to that of a predicate device already on the market. Specific metrics (e.g., sensitivity, specificity, accuracy values) are not present in this clearance letter.
  2. Sample Size Used for the Test Set and Data Provenance:

    • Not specified in the provided document. For an IVD, the test set would typically involve patient samples (sera in this case) from individuals with and without the condition of interest. The size and characteristics of this sample set would have been part of the 510(k) submission.
    • Data Provenance: Not specified in the provided document. Typically, clinical studies for IVDs involve samples collected from various clinical sites. Whether these were prospective or retrospective samples is not mentioned.
  3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:

    • Not applicable in the typical sense for this IVD. The "ground truth" for an IVD like the Anti-GBM EIA would be established through a combination of:
      • Clinical diagnosis: Based on patient symptoms, imaging, biopsy, and other laboratory tests.
      • Reference method(s): Comparison to other established laboratory tests or panels for GBM autoantibodies.
      • Pathological confirmation: In some cases, kidney biopsy findings would be definitive "ground truth."
    • Therefore, it's not about "experts establishing ground truth for a test set" in the context of image interpretation, but rather clinical and pathological confirmation of disease status.
  4. Adjudication Method for the Test Set:

    • Not applicable as typically understood for AI evaluation. Adjudication (e.g., 2+1, 3+1) is common in reader studies for AI devices. For an IVD, the "ground truth" is established via clinical diagnosis and/or reference laboratory methods, not by multiple expert readers interpreting the test output for ground truth.
  5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

    • No, this is highly unlikely for an IVD kit. MRMC studies are primarily designed for evaluating the performance of imaging devices or AI algorithms that assist human readers in interpreting medical images. This device is a laboratory assay.
  6. If a Standalone Performance was done:

    • Yes, in spirit, for an IVD. An IVD kit's performance is inherently "standalone" in that it provides a quantitative or qualitative result based directly on the patient sample. Its performance (e.g., sensitivity, specificity, positive predictive value, negative predictive value) would have been evaluated relative to the true disease status or a reference method. It operates without human interpretation of complex outputs in the way an AI image analysis algorithm does.
  7. The Type of Ground Truth Used:

    • Likely a combination of clinical diagnosis, other established laboratory methods, and possibly pathology (e.g., kidney biopsy results) for the presence or absence of Goodpasture's syndrome. The device measures IgG autoantibodies against GBM, which is a specific marker for the disease. Ground truth would confirm the actual pathological or clinical state of the patient.
  8. The Sample Size for the Training Set:

    • Not specified in the provided document. For an IVD, internal development and validation would involve numerous samples, but it's not referred to as a "training set" in the same way as for AI algorithms. It's more about assay optimization and internal validation samples.
  9. How the Ground Truth for the Training Set Was Established:

    • Not specified in the provided document. For an IVD's internal development and optimization, ground truth would be established similarly to the test set: through well-characterized patient samples with known clinical and/or pathological diagnoses, or through spiked samples for analytical validation.

Summary:

The provided document is an FDA 510(k) clearance letter for an in vitro diagnostic test kit, not a detailed study report for an AI-powered device. Therefore, it does not contain the specific information about acceptance criteria, sample sizes, expert involvement, and AI-specific validation methods that your questions are structured around. The "study" for this device would have focused on analytical and clinical performance to demonstrate substantial equivalence to a predicate device, which is a different paradigm from AI device validation.

§ 866.5660 Multiple autoantibodies immunological test system.

(a)
Identification. A multiple autoantibodies immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the autoantibodies (antibodies produced against the body's own tissues) in serum and other body fluids. Measurement of multiple autoantibodies aids in the diagnosis of autoimmune disorders (disease produced when the body's own tissues are injured by autoantibodies).(b)
Classification. Class II (performance standards).