Search Results

The EUROIMMUN Anti-PLA2R ELISA (IgG) test kit is intended for the qualitative or semiquantitative determination of IgG class autoantibodies against phospholipase A2 receptor (PLA2R) in human serum. It is used as an aid in the diagnosis of primary membranous glomerulonephritis (pMGN), in conjunction with other laboratory and clinical findings.

Device Description

The EUROIMMUN Anti-PLA2R ELISA (IgG) consists of a microwell ELISA plate coated with PLA2R antigen, 5 calibrators, positive and negative control, peroxidase-labelled anti-human IgG conjugate, sample buffer, wash buffer concentrate, TMB chromogen/substrate solution and stop solution.

AI/ML Overview

The acceptance criteria and study proving the device meets them are detailed below for the EUROIMMUN Anti-PLA2R ELISA (IgG).

1. Table of Acceptance Criteria and Reported Device Performance

Performance Characteristic	Acceptance Criteria	Reported Device Performance
Reproducibility
Intra-Assay CV	< 12% for positive and borderline samples; all qualitative results for negative samples to be negative; all qualitative results (positive, borderline, negative) of ratio-based samples to be in line with expected result.	RU/ml: CVs range from 2.6% to 10.9%. Ratio: All qualitative results in line with expected (e.g., 0% positive for negative, 100% positive for positive).
Inter-Assay CV	< 12% for positive and borderline samples; all qualitative results for negative samples to be negative; all qualitative results (positive, borderline, negative) of ratio-based samples to be in line with expected result.	RU/ml: CVs range from 4.2% to 10.3%. Ratio: All qualitative results in line with expected (e.g., 100% negative for negative, 100% positive for positive, 73% borderline for a borderline sample).
Repeatability (Total Imprecision)	< 12% for positive and borderline samples; all qualitative results for negative samples to be negative; all qualitative results (positive, borderline, negative) of ratio-based samples to be in line with expected result.	RU/ml: Total CVs range from 3.6% to 14.8% (Sample 1 above 12%). Ratio: All qualitative results largely in line with expected (e.g., 100% negative for negative, 100% positive for positive, 97-99% borderline for borderline samples).
Lot-to-Lot Reproducibility	< 12% for positive and borderline samples; all qualitative results for negative samples to be negative; all qualitative results (positive, borderline, negative) of ratio-based samples to be in line with expected result.	RU/ml: Total CVs range from 4.0% to 11.2% (Sample 1 is 11.2%). Ratio: All qualitative results largely in line with expected (e.g., 100% negative for negative, 100% positive for positive, 72-94% borderline for borderline samples).
Linearity/Assay Reportable Range	Sufficiently linear from 2 to 1500 RU/mL.	The assay was shown to be sufficiently linear from 2 to 1500 RU/mL.
Limit of Detection (LoD)	LoD should be approximately 2.2 RU/ml (or lower to functional sensitivity).	LoD was found to be 2.2 RU/ml.
Limit of Blank (LoB)	Not explicitly stated an acceptance criterion, but investigated.	LoB was found to be 1.8 RU/ml.
Limit of Quantitation (LoQ)/Functional Sensitivity	LoQ = LoD, or approximately 1.4 RU/ml if using functional sensitivity.	Functional sensitivity was approx. 1.4 RU/ml. LoQ = LoD = 2.2 RU/ml.
Analytical Specificity (Cross-reactivity)	No significant cross-reactivity with tested disease states.	All 65 sera (thyroiditis, SLE, Sjögren's, SSc, RA, cANCA, pANCA, GBM, HBsAg) were negative, indicating no cross-reactivity.
Analytical Specificity (Interference)	Individual recovery within 70-130%; mean recovery within 85-115%.	No significant interference for hemoglobin (up to 1000 mg/dl), triglyceride (up to 2000 mg/dl), and bilirubin (up to 40 mg/dl).
Method Comparison (Predicate Device)	Not explicitly stated with numerical values, but implied substantial agreement.	RU/mL: Positive Agreement (borderline as negative): 86.79% (95% CI: 81.5%-91.0%). Negative Agreement: 99.71% (95% CI: 98.4%-100.0%).RU/mL: Positive Agreement (borderline as positive): 89.62% (95% CI: 84.7%-93.4%). Negative Agreement: 99.71% (95% CI: 98.4%-100.0%).Ratio: Positive Agreement (borderline as negative): 86.79% (95% CI: 81.5%-91.0%). Negative Agreement: 99.71% (95% CI: 98.4%-100.0%).Ratio: Positive Agreement (borderline as positive): 92.45% (95% CI: 88.0%-95.6%). Negative Agreement: 99.71% (95% CI: 98.4%-100.0%).
Clinical Sensitivity	Within the expected range of approximately 70% as reported in scientific literature.	66.9% (95% C.I.: 61.0 - 72.4%) for pMGN, using 5-point calibrated analysis and 20 RU/ml cut-off (borderline samples counted as negative). 68.7% (95% C.I.: 62.9 - 74.2%) for pMGN (borderline samples counted as positive).
Clinical Specificity	Not explicitly quantified, but demonstrated high specificity against various control groups.	99.6% (95% C.I.: 98.1 - 100.0%) against all control groups combined (borderline samples counted as negative or positive).

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

Reproducibility (Intra-Assay): 20 determinations for RU/ml based results, 20 determinations for Ratio based results.
Reproducibility (Inter-Assay): 30 determinations for RU/ml based results, 30 determinations for Ratio based results.
Repeatability (Total Imprecision): 150 determinations per sample for RU/ml and Ratio based results.
Reproducibility (Lot-to-Lot): 18 determinations per sample for RU/ml and Ratio based results.
Linearity/Assay Reportable Range: Five sets of 11-step-wise dilutions (totaling 55 samples).
Limit of Blank (LoB), Limit of Detection (LoD), Limit of Quantitation (LoQ): Investigated following CLSI standard EP17-A.
Analytical Specificity (Cross-reactivity): Panel of 65 clinically characterized sera.
Analytical Specificity (Interference): Sera with anti-PLA2R concentrations spiked with potential interfering substances.
Method Comparison and Clinical Study:
- Test Set Size: 560 samples in total; 275 from pMGN patients and 285 from control groups.
- Data Provenance: The document states "Clinical studies were performed in cooperation with different sites." While specific countries are not mentioned, it implies multiple clinical sites. The studies are prospective in nature in the sense that samples were collected for analysis by the new device against established clinical diagnoses. The clinical diagnoses were based on renal biopsy and clinical/laboratory criteria, and samples were drawn within 8 weeks after biopsy before treatment.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

The document does not explicitly state the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") used to establish the ground truth for the clinical study samples.
However, the clinical study section states: "pMGN diagnosis was based on renal biopsy and was considered to be idiopathic/primary when no secondary cause of MN was suspected on the basis of clinical and laboratory criteria." This implies a standard clinical diagnostic process involving medical professionals (e.g., nephrologists, pathologists) who interpret biopsies and clinical data.

4. Adjudication Method for the Test Set

The document does not describe an explicit adjudication method for the clinical study's ground truth beyond stating that pMGN diagnosis was "based on renal biopsy and was considered to be idiopathic/primary when no secondary cause of MN was suspected on the basis of clinical and laboratory criteria." This suggests that the clinical diagnosis, informed by biopsy and other findings, served as the ground truth. There is no mention of a process like "2+1" or "3+1" for reaching a consensus diagnosis for individual cases.

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 to the EUROIMMUN Anti-PLA2R ELISA (IgG) device. This is an in vitro diagnostic (IVD) assay, not an AI-powered image analysis or diagnostic support system that would involve human readers and AI assistance. The performance is measured directly through laboratory analysis of patient samples.

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

This is an in vitro diagnostic (IVD) assay (ELISA), not an algorithm or AI system. The performance characteristics (sensitivity, specificity, reproducibility, etc.) are inherent to the assay and its protocol when performed in a laboratory setting. Therefore, a "standalone algorithm performance" study is not relevant in this context. The results are generated by the assay itself, following the prescribed procedure, and then interpreted based on established cut-off values.

7. The Type of Ground Truth Used

Clinical Study: The ground truth for the clinical study samples was based on clinical diagnosis, primarily established by:
- Renal biopsy for confirmation of primary membranous glomerulonephritis (pMGN).
- Clinical and laboratory findings to rule out secondary causes of membranous nephropathy.
Analytical Studies (e.g., Reproducibility, Linearity, Cross-reactivity, Interference): The ground truth for these studies was based on:
- Known concentrations or expected relative values of analytes in prepared samples or controls.
- Known clinical characteristics of patient panels (e.g., positive for thyroiditis, negative for anti-PLA2R antibodies, etc.).

8. The Sample Size for the Training Set

This is an in vitro diagnostic (IVD) assay, not a machine learning or AI model that requires a distinct "training set" in the traditional sense. The device's performance characteristics are established through various analytical and clinical studies, but there isn't a "training phase" to optimize an algorithm with a specific dataset.

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

As explained above, this device is not an AI/ML algorithm requiring a training set. The "ground truth" equivalent for the development and validation of an IVD assay involves:
- Reference materials/calibrators: Precisely prepared solutions with known concentrations of the analyte.
- Clinically characterized samples: Sera from patients with confirmed diagnoses (e.g., pMGN by biopsy, specific autoimmune diseases) and healthy controls, used to determine the assay's clinical performance. These samples are analogous to validation data for an algorithm.

Ask a Question

Ask a specific question about this device

Page 1 of 1