K Number
K071346
Date Cleared
2007-09-24

(133 days)

Product Code
Regulation Number
862.1810
Panel
IM
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

An enzyme linked immunoassay (ELISA) for the detection and semi-quantitation of intrinsic factor antibodies in human serum to aid in the diagnosis of pernicious anemia.

Device Description

An enzyme linked immunoassay (ELISA)

AI/ML Overview

This FDA 510(k) clearance letter for the ImmuLisa Intrinsic Factor Antibody ELISA does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and study design. The document is primarily an approval letter, not a full summary of the performance study.

However, based on the information provided, here's what can be extracted and what cannot:

1. A table of acceptance criteria and the reported device performance

This information is not available in the provided document. The 510(k) clearance letter confirms that the device was deemed substantially equivalent to a predicate device, but it does not detail specific acceptance criteria (e.g., sensitivity, specificity thresholds) or the exact performance metrics reported in the submission.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not available in the provided document.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not available in the provided document. For an ELISA test, the "ground truth" would typically come from a reference method or clinical diagnosis based on a combination of factors, not necessarily based on expert interpretation of images.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not available in the provided document. Adjudication methods are more relevant for subjective interpretations (e.g., radiology reads) than for quantitative ELISA results.

5. 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

This information is not applicable and not available in the provided document. The ImmuLisa Intrinsic Factor Antibody ELISA is an in-vitro diagnostic (IVD) test, not an AI-powered diagnostic imaging device that assists human readers. Therefore, an MRMC study and
AI-assisted improvement metrics are irrelevant for this type of device.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not applicable in the provided document in the way it's framed. The device is a laboratory assay. Its performance is inherent to the assay procedure and relies on laboratory technicians performing the test correctly. There isn't an "algorithm only" component in the sense of a software-driven interpretation without human interaction typically found in AI devices. The "standalone" performance would be the analytical performance of the ELISA system itself (e.g., its sensitivity, specificity, accuracy against a reference method). These specific analytical performance metrics are not detailed in the clearance letter.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

For an ELISA diagnostic test like this, the ground truth for evaluating its performance would typically be based on:

  • Clinical diagnosis of pernicious anemia: This would involve a comprehensive clinical assessment (e.g., B12 levels, clinical symptoms, other lab tests).
  • Reference method/gold standard for intrinsic factor antibody detection: This might involve a different, already validated, and often more complex assay for intrinsic factor antibodies.

The specific type of ground truth used is not detailed in the provided document.

8. The sample size for the training set

This information is not available in the provided document. For an ELISA kit, "training set" is not typically a concept used in the same way as machine learning. Instead, there would be studies for assay development, optimization, and validation, but these wouldn't be referred to as a "training set" in the context you're asking.

9. How the ground truth for the training set was established

This information is not applicable and not available in the provided document. See the explanation for point 8.

§ 862.1810 Vitamin B

12 test system.(a)
Identification. A vitamin B12 test system is a device intended to measure vitamin B12 in serum, plasma, and urine. Measurements obtained by this device are used in the diagnosis and treatment of anemias of gastrointestinal malabsorption.(b)
Classification. Class II.