K Number
K032014
Device Name
N LATEX IGM
Manufacturer
Date Cleared
2003-08-07

(38 days)

Product Code
Regulation Number
866.5510
Panel
IM
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

N Latex IgM is an in vitro diagnostic test for the quantitative determination of IgM in human cerebrospinal fluid (CSF) and in paired CSF/serum samples by means of particle-enhanced immunonephelometry using the BN™ Systems. The determination of IgM aids in the evaluation of the patient's immune system.

Device Description

Polystyrene latex particles coated with antibodies specific to human IgM are agglutinated when mixed with samples containing human IgM. These aggregates scatter a beam of light passed through the sample. The intensity of the scattered light is proportional to the concentration of the relevant protein in the sample. The result is evaluated by comparison with a standard of known concentration.

AI/ML Overview

Here's an analysis of the N Latex IgM device's acceptance criteria and the study used to demonstrate its performance, based on the provided documents:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the N Latex IgM device appear to be tied to its correlation with a legally marketed predicate device (Beckman Coulter IMMAGE® Immunochemistry System Low Concentration Immunoglobulin M (IGMLC) assay). While specific numerical acceptance thresholds for slope, intercept, and correlation coefficient are not explicitly stated, the presented "Correlation" and "Method Comparison Studies" implicitly define the performance considered acceptable for demonstrating substantial equivalence. The reported device performance is as follows:

ParameterAssay TypeSample TypeSample Size (n=)SlopeInterceptCorrelation Coefficient
CorrelationN Latex IgMCSF241.04-0.020.995
CorrelationN Latex IgMSerum500.91+0.020.979
CorrelationN Latex IgMCSF/Serum Ratio241.03-0.010.989

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

The "test set" for the correlation studies consists of the following sample sizes:

  • CSF: 24 samples
  • Serum: 50 samples
  • CSF/Serum Ratio: 24 samples

The documents do not specify the country of origin for the data or whether it was retrospective or prospective.

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

This information is not provided in the submitted documents. For in vitro diagnostic assays like N Latex IgM, "ground truth" is typically established by comparative analysis with a reference method or a legally marketed predicate device. The documents indicate that the predicate device (Beckman Coulter IMMAGE® IGMLC assay) served as the comparator, implying its results were used to establish the "truth" against which the N Latex IgM's performance was measured. However, there's no mention of human experts defining this "ground truth" in the context of this type of quantitative assay comparison.

4. Adjudication Method for the Test Set

Not applicable for this type of quantitative assay comparison. The "adjudication method" typically refers to how discrepancies in human expert interpretations (e.g., in medical image analysis) are resolved to establish a definitive ground truth. Here, the comparison is directly between the quantitative output of two diagnostic assays.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No. An MRMC study is not relevant for this device. MRMC studies are typically used to evaluate the impact of a new diagnostic method (like an AI algorithm) on human reader performance, often in image-based diagnostics. The N Latex IgM is an in vitro diagnostic reagent for quantitative measurement, and its performance is evaluated by direct comparison to another quantitative assay, not by human reader interpretation.

6. Standalone (Algorithm Only) Performance Study

Yes, in a sense. The reported "Correlation" and "Method Comparison Studies" represent the standalone performance of the N Latex IgM assay comparing its quantitative output directly with the quantitative output of the predicate device. There is no "human-in-the-loop" aspect to these measurements; it's the device's output itself being evaluated.

7. Type of Ground Truth Used

The "ground truth" for these studies was established by the results obtained from the legally marketed predicate device, the Beckman Coulter IMMAGE® Immunochemistry System Low Concentration Immunoglobulin M (IGMLC) assay (K993547). The assumption is that the predicate device provides accurate and established measurements of IgM, which then serve as the reference standard for the N Latex IgM device.

8. Sample Size for the Training Set

The documents make no mention of a "training set" in the context of machine learning or AI. This device is an immunoassay, not an AI/ML algorithm that requires training data. The "training" for the device would involve calibrating it according to manufacturer specifications, rather than using a data set to "teach" an algorithm.

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

Not applicable, as there is no "training set" in the AI/ML sense for this type of immunoassay.

§ 866.5510 Immunoglobulins A, G, M, D, and E immunological test system.

(a)
Identification. An immunoglobulins A, G, M, D, and E immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the immunoglobulins A, G, M, D, an E (serum antibodies) in serum. Measurement of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.(b)
Classification. Class II (performance standards).