Search Results

The Anti-Neutrophil Cytoplasmic Antibodies (Ethanol-fixed) test system is an indirect immunofluorescence assay (IFA) for the qualitative and semi-quantitative determination of anti-neutrophil cytoplasmic antibodies (ANCA) of the IgG isotype in human serum by manual fluorescence microscopy or with dIFine. The presence of ANCA in conjunction with other clinical and laboratory findings can be used to aid in the diagnosis of ANCA associated vasculitis (AAV). All suggested results obtained with dIFine must be confirmed by a trained operator.

The Anti-Neutrophil Cytoplasmic Antibodies (Formalin-fixed) test system is an indirect immunofluorescence assay (IFA) for the qualitative and semi-quantitative determination of anti-neutrophil cytoplasmic antibodies (ANCA) of the IgG isotype in human serum by manual fluorescence microscopy or with dIFine. The presence of ANCA in conjunction with other clinical and laboratory findings can be used to aid in the diagnosis of ANCA associated vasculitis (AAV). All suggested results obtained with dIFine must be confirmed by a trained operator.

Not Found

The provided FDA 510(k) clearance letter for "Anti-Neutrophil Cytoplasmic Antibodies (Ethanol-Fixed)" and "Anti-Neutrophil Cytoplasmic Antibodies (Formalin-Fixed)" from ZEUS Scientific does not contain the detailed information necessary to describe the acceptance criteria and the study that proves the device meets those criteria.

This document is primarily a clearance letter, confirming that the device is substantially equivalent to a predicate device and outlining regulatory guidelines and requirements. It mentions the "dIFine" system, which likely refers to an automated interpretation component, but it does not provide any specific performance data, study design, or methodology for demonstrating the device's accuracy or effectiveness.

Therefore, I cannot fulfill your request for the following information based solely on the provided text:

1. A table of acceptance criteria and the reported device performance: This information is not present.
2. Sample sized used for the test set and the data provenance: Not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
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: Not mentioned. The letter states that "All suggested results obtained with dIFine must be confirmed by a trained operator," implying a human-in-the-loop, but no study details are provided.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not mentioned, although the statement about human confirmation suggests the primary use case is not standalone.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not mentioned.
8. The sample size for the training set: Not mentioned.
9. How the ground truth for the training set was established: Not mentioned.

To obtain this information, you would typically need to refer to the 510(k) Summary or the full 510(k) submission document, which often includes a detailed description of the validation studies conducted. The clearance letter itself is a summary of the FDA's decision, not the full technical dossier.

Ask a specific question about this device

The EUROIMMUN IFA Granulocyte Mosaic EUROPattern is intended as an indirect immunofluorescence test for the qualitative or semi-quantitative determination of immunoglobulin class IgG anti-neutrophil cytoplasmic antibodies (ANCA) in human serum. It is used as an aid in the diagnosis of ANCA associated vasculitides, in conjunction with other laboratory and clinical findings. The EUROIMMUN IFA Granulocyte Mosaic EUROPattern test kit is intended for use with the EUROPattern microscope and software system. All suggested results obtained with the EUROPattern system must be confirmed by trained personnel.

The EUROIMMUN EUROPLUS Granulocyte Mosaic EUROPattern is intended as an indirect immunofluorescence test for the qualitative or semi-quantitation of immunoglobulin class IgG anti-neutrophil cytoplasmic antibodies (ANCA) and the qualitative determination of IgG anti-MPO, and, if included, anti-GBM antibodies in human serum. It is used as an aid in the diagnosis of ANCA associated vasculitides, in conjunction with other laboratory and clinical findings. The EUROIMMUN EUROPLUS Granulocyte Mosaic EUROPattern test kit is intended for use with the EUROPattern microscope and software system. All suggested results obtained with the EUROPattern system must be confirmed by trained personnel.

Not Found

The provided text is a 510(k) premarket notification decision letter from the FDA. It does not contain information about the acceptance criteria and study details for the device's performance. The letter primarily focuses on the regulatory determination of substantial equivalence and general device regulations.

Therefore, I cannot provide the requested table and study details based on the given input.

Ask a specific question about this device

AESKUSLIDES® ANCA is an indirect immunofluorescence assay utilizing human neutrophil granulocyte coated slides, fixed with Ethanol or Formalin, as a substrate for the qualitative and semi-quantitative determination of anti-neutrophil cytoplasmic autoantibodies (ANCA) in human serum by manual microscopy or with the HELIOS® AUTOMATED IFA SYSTEM.

This in vitro diagnostic assay is used as an aid for the diagnosis of ANCA-associated vasculitides (AAV) in conjunction with other clinical and laboratory findings. All suggested results obtained with the HELIOS AUTOMATED IFA SYSTEM must be confirmed by trained personnel.

AESKUSLIDES ANCA is an indirect immunofluorescence assay utilizing human neutrophil granulocyte coated slides, fixed with Ethanol or Formalin, as a substrate for the qualitative and semi-quantitative determination of anti-neutrophil cytoplasmic autoantibodies (ANCA) in human serum by manual microscopy or with the HELIOS® AUTOMATED IFA SYSTEM.

This in vitro diagnostic assay is used as an aid for the diagnosis of ANCA-associated vasculitides (AAV) in coniunction with other clinical and laboratory findings. All suggested results obtained with the HELIOS AUTOMATED IFA SYSTEM must be confirmed by trained personnel.

Slides coated with human neutrophil granulocytes for autoantibody detection are fixated by two different methods: ethanol (EtOH) fixation or formalin fixation. Ethanol fixation allows cell components to move through the cells after the fixation process. Formalin fixation causes cellular components to cross-link (a movement of cellular components is abrogated and the patterns are distinct). By processing serum on both Ethanol and Formalin-fixed slides, the user can confirm if the pattern is C-, P-, or A-ANCA, according to the table below.

This document outlines the acceptance criteria and supporting studies for the AESKUSLIDES® ANCA Ethanol and AESKUSLIDES® ANCA Formalin devices, which are indirect immunofluorescence assays for the qualitative and semi-quantitative determination of anti-neutrophil cytoplasmic autoantibodies (ANCA).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document details various performance studies with corresponding acceptance criteria and results. Below is a summary of these:

Note on Borderline Samples: Several studies (e.g., Within-Lab Precision, Between-Lab Precision, Accelerated Stability, In Use Stability) explicitly mention the handling of "borderline" samples (very low positive samples that can be evaluated as negative). For certain calculations, results are presented both including and excluding these samples, with justification for lower agreement when included. This indicates a robust statistical approach for handling results near the decision threshold.

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

Total Clinical Samples: 630 clinical samples were used for the Clinical Evaluation and Method Comparison studies.

Provenance:

• 510 clinical samples were sourced from 10 BioBanks in the US (BioChain, BioReclamationIVT, Bioserve, ConversantBio, Cureline, DiscoveryLifeSciences, iSpecimen, Precision for Medicine, ProMedDx, and Vitrologic). These samples were selected based on diagnosis to reflect important conditions for the study.
• 120 serum samples were sourced from a German University Hospital to complement rare but important diagnoses (70 Wegener's Granulomatosis, 25 MPA, 25 Churg-Strauss Syndrome).
• Retrospective/Prospective: The document does not explicitly state whether the studies were retrospective or prospective. However, the nature of acquiring samples from biobanks and the use of de-identified diagnoses strongly suggests a retrospective data collection approach for the main clinical sample set.
• Healthy Donor Samples: An additional panel of 150 sera from healthy donors was used for the Expected Values/Reference Range study: 100 from Germany and 50 from the US.

The document states that the diagnosis criteria of the samples were in agreement with diagnostic standards used in the U.S and Germany (e.g., ACR criteria), and that the US sample set was selected to contain different ethnic groups to reflect the US population. All samples were checked for purity, volume, and contaminations and deemed suitable for the study.

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

The ground truth for the clinical sample set was established based on the "diagnosis criteria of the different samples [that] have been made in agreement with diagnostic standards used in the U.S and Germany." A written statement from different serum suppliers is available on request. This implies that the initial diagnosis (ground truth) was established by medical professionals (e.g., clinicians) at the originating institutions (biobanks, university hospital) based on clinical and laboratory findings, prior to their inclusion in this study. The document does not specify the number or specific qualifications of these initial diagnosing experts.

For the subsequent "reading" or "evaluation" of slides within the various performance studies (e.g., Within-Lab, Between-Lab, Method Comparison, Stability studies), two independent readers/experts were consistently used. The qualifications of these readers are generally referred to as "trained personnel" or "trained operator." For instance, the intended use statement explicitly says "All suggested results obtained with the HELIOS AUTOMATED IFA SYSTEM must be confirmed by trained personnel." and "The device is for use by a trained operator in a clinical laboratory setting." Specific details on years of experience or board certification (e.g., "radiologist with 10 years of experience") are not provided for these internal study readers.

4. Adjudication Method for the Test Set

For the "reading" or "evaluation" of slides in the various performance studies:

• The studies consistently involved two independent readers.
• The results of these two readers were often calculated and presented separately as well as combined.
• There is no explicit mention of an "adjudication" process (e.g., a 2+1 or 3+1 method) where a third, senior expert would resolve discrepancies between the two initial readers to establish a final ground truth for the study. Instead, the analysis focuses on the agreement between the readers and their agreement with either the expected reference values (for analytical studies) or comparison methods (for clinical studies). The concept of "User Confirmation" (Method B) implies that human oversight is always required for the automated results, but not necessarily a formal adjudication of discordant human reads.

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

Yes, a multi-reader, multi-case (MRMC) comparative effectiveness study was done. This is evident in the "Method Comparison of Method A, B, and C and clinical study" section (pages 85-96). This study compared:

• Method C (Manual): Manual processing and manual reading by two independent readers.
• Method B (Reader Confirmation): Automated processing/imaging by HELIOS, with manual reading of digital images by two independent readers.
• Method A (HELIOS): Automated processing/imaging by HELIOS, with automated positive/negative classification by the HELIOS Vasculitis Pattern Plus software.

The study was conducted at three different study sites (two US, one German) using the entire 630-sample set, with two independent readers at each site for manual and reader confirmation methods.

Effect Size (AI vs. Human-in-the-Loop):
The document does not present the effect size in terms of how much human readers improve with AI vs. without AI assistance. Instead, it compares the performance (agreements and diagnostic sensitivities/specificities) between:

1. Human reading of traditionally processed slides (Method C).
2. Human reading of AI-processed images (Method B).
3. AI-only classification (Method A).

The statement that "All suggested results obtained with the HELIOS AUTOMATED IFA SYSTEM must be confirmed by trained personnel" (intended use) and the acceptance criteria for Method A (lower agreement accepted for automated-only results, e.g., >70% compared to >90% for human reads) consistently emphasize that the AI is an aid that requires human confirmation. The data implicitly supports that humans (Methods B and C) perform better than the standalone AI (Method A) in certain aspects (higher agreement percentages, higher diagnostic performance metrics for Human vs HELIOS in Formalin especially). For example, in ANCA Formalin, Method C vs A pattern agreement was only 69.7% while C vs B was 82.1-87.5%, highlighting the current limitations of standalone AI pattern recognition and the value of human reading (even with automated imaging).

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

Yes, standalone performance of the algorithm (HELIOS Vasculitis Pattern Plus software, referred to as Method A) was evaluated.

• Method A processed slides automatically, acquired images, and performed automated reading/interpretation.
• Its performance was compared against manual reading (Method C) and human reading of automated images (Method B) in the "Method Comparison of Method A, B, and C" study.
• As noted in point 5, the acceptance criteria for Method A were lower (e.g., ≥ 70% agreement) compared to the human-in-the-loop methods (≥ 90%). The results show that Method A generally achieved these lower thresholds but performed less ideally for pattern recognition.

7. The Type of Ground Truth Used

The ground truth used several types throughout the studies:

• Clinical Diagnosis (Outcomes Data / Expert Consensus): For the diagnostic sensitivity and specificity calculations (Method comparison against predicate, and Method A, B, C comparison), the ground truth for patient samples was their established "diagnosis" (e.g., ANCA-associated vasculitis (AAV), other diseases like SLE, RA, etc.). This diagnosis was made in agreement with US and German diagnostic standards (e.g., ACR criteria), implying a form of expert consensus based on clinical and laboratory findings.
• Expected Results/Reference Values (Expert Consensus): For analytical performance studies (e.g., Precision, Stability, Carry Over, Time Extension, Interfering Substances), ground truth was often defined as "expected results" or "expected values" for specific samples (e.g., positive/negative status, specific pattern, fluorescence intensity). These expected values were likely established by experienced operators / experts during the initial characterization of the control and study samples. The repeated use of "correctly found" implies agreement with a pre-established reference.
• Negative Healthy Donor Panel: For the "Expected Values/Reference Range" study, healthy donor samples confirmed to be negative for ANCA were used to establish a reference range, implicitly serving as a negative ground truth.

There is no mention of pathology or direct biopsy results as ground truth, which is typical for diagnoses like vasculitis given the nature of ANCA testing.

8. The Sample Size for the Training Set

The document does not provide a specific sample size for the "training set" of the HELIOS AUTOMATED IFA SYSTEM. The provided information focuses on the validation of the device, particularly the performance evaluation of the final device using various test sets. The software's pattern recognition uses "SVM (Support Vector Machine) technology," which implies a machine learning approach. However, details on the dataset used to train this SVM model are not disclosed in this document.

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

Similarly, since the training set details are not provided, the method for establishing its ground truth is also not explicitly described. For machine learning models like SVMs used in pattern recognition, the training data would typically be images with associated labels (ground truth) that are a result of expert annotation or consensus. Given the context of manual reading by "trained personnel" and the need for "confirmation by trained personnel," it is highly probable that the ground truth for any training set would have been established by multiple expert pathologists or laboratory professionals specializing in indirect immunofluorescence interpretation, likely through a consensus or adjudication process. However, this is an inference based on industry practice and the provided context, not a direct statement in the document.

Ask a specific question about this device

EliA PR3s is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to proteinase 3 (PR3) in human serum and plasma (Li-heparin, EDTA) as an aid in the clinical diagnosis of Granulomatosis with Polyangiitis (GPA, formerly called Wegener's Granulomatosis) in conjunction with other laboratory and clinical findings. EliA PR3s uses the EliA IgG method on the instrument Phadia 2500/5000.

EliA MPOs is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to myeloperoxidase (MPO) in human serum and plasma (Li-heparin, EDTA) as an aid in the clinical diagnosis of microscopic polyangiitis (MPA) in conjunction with other laboratory and clinical findings. EliA IgG method on the instrument Phadia 2500/5000.

EliA GBM is intended for the in vitro semi-quantitative measurement of IgG antibodies to a3 chain of collagen IV in human serum and plasma (Li-heparin, EDTA) as an aid in the clinical diagnosis of Goodpasture syndrome in conjunction with other laboratory and clinical findings. EliA GBM uses the EliA IgG method on the instrument Phadia 2500/5000.

The method-specific reagents are identical with K140225, but are filled in containers specific for the Phadia® 2500/5000 instrument. Each device consists of:

• Test Wells: -
  EliA PR3S Wells are coated with human PR3 protein – 4 carriers (12 wells each), ready to use:

EliA MPOS Wells are coated with human MPO protein – 4 carriers (12 wells each), ready to use;

EliA GBM Wells are coated with human recombinant α3 chain of collagen IV – 2 carriers (12 wells each), ready to use;

• EliA Sample Diluent: PBS containing BSA, detergent and 0.095% (w/v) sodium azide - 6 bottles, 48 mL each, ready to use; or 6 bottles, 400 mL each, ready to use:
• -EliA IgG Conjugate 50 or 200: ß-Galactosidase labeled anti-IgG (mouse monoclonal antibodies) in PBS containing BSA and 0.06% (w/v) sodium azide – 6 wedge shaped bottles, 5 mL each, ready to use; or 6 wedge shaped bottles, 19 mL each, ready to use
• -EliA IgG Calibrator Strips: Human IgG (0, 4, 10, 20, 100, 600 µg/L) in PBS containing BSA, detergent and 0.095% (w/v) sodium azide - 5 strips, 6 singleuse vials per strip, 0.3 mL each, ready to use;
• EliA IgG Curve Control Strips: Human IgG (20 µg/L) in PBS containing BSA, detergent and 0.095% (w/v) sodium azide – 5 strips, 6 single-use vials per strip, 0.3 mL each, ready to use;
• EliA IgG Calibrator Well: Coated with mouse monoclonal antibodies 4 carriers (12 wells each), ready to use.
• -EliA ANCA/GBM Positive Control 2500/5000: Human serum containing IgG antibodies to PR3, MPO and GBM in PBS containing BSA, detergent and 0.095% (w/v) sodium azide - 6 single use vials, 0.3 mL each, ready to use;
• -EliA IgG/IqM/IgA Negative Control 2500/5000: Human sera from healthy donors in PBS containing BSA, detergent and 0.095% (w/v) sodium azide -6 single-use vials, 0.3 mL each, ready to use;

The Phadia EliA Immunodiagnostic System is an automated system for immunodiagnostic testing. The EliA reagents are available as modular packages, each purchased separately. Apart from the EliA ANCA/GBM Positive Control 2500/5000 and the EliA IgG/ IgM/IgA Negative Control 2500/5000, all packages listed above are required to carry out an EliA PR3°, EliA MPOS and EliA GBM tests.

The provided text describes the acceptance criteria and study results for the EliA PR3s, EliA MPOs, and EliA GBM immunoassays when used on the Phadia 2500/5000 instrument. This submission is to add these previously cleared assays to a new instrument platform, so the focus is on method comparison rather than clinical studies.

Here's the breakdown of the requested information:

1. Table of acceptance criteria and reported device performance for Instrument Comparison (Method Comparison):

The acceptance criteria for method comparison (comparing Phadia 2500/5000 to the predicate Phadia 250) were:

• Slope for the regression lines should be between 0.9 and 1.1 for single replicate to single replicate.
• Intercept close to 0.

The performance is reported for each immunoassay (EliA PR3s, EliA MPO®, EliA GBM) and for each of the three Phadia 2500/5000 instruments (A, B, C) tested against the Phadia 250.

EliA PR3s on Phadia 2500/5000 (vs. Phadia 250):

EliA MPO® on Phadia 2500/5000 (vs. Phadia 250):

EliA GBM on Phadia 2500/5000 (vs. Phadia 250):

2. Sample size used for the test set and the data provenance:

• Sample Size: More than 100 samples for each EliA test (PR3s, MPO®, GBM). The submission also specifies "≥20% of the samples within ±25% of the medical decision point."
• Data Provenance: Not explicitly stated as "country of origin," but implies clinical samples used for method comparison. The samples are referred to as "patient serum samples." It is a prospective study as the comparison aims to show equivalence of the new instrument platform with the predicate.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

This information is not provided in the given text. The study is a method comparison between two instruments (Phadia 250 and Phadia 2500/5000) using the same assays, not a clinical study to establish diagnostic accuracy against a clinical gold standard determined by experts. The "ground truth" for the method comparison is the measurement value obtained from the predicate Phadia 250 instrument.

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

This information is not applicable as the study is a method comparison of quantitative measurements, not a diagnostic study requiring expert adjudication of cases. The comparison is based on numerical results from two instruments.

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 is not applicable. The device described is an immunoassay system for semi-quantitative measurement of antibodies, not an AI-assisted diagnostic imaging device used by human readers.

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

The device (EliA immunoassays on Phadia 2500/5000) operates as a standalone automated system for measuring antibody levels. The results are semi-quantitative measurements that are an aid in clinical diagnosis, meaning a human clinician interprets the results in conjunction with other findings. However, the performance data presented (precision, linearity, detection limits, method comparison) is reflective of the standalone performance of the algorithm/instrument system. Therefore, the analytical performance studies (precision, linearity, detection limit) and method comparison effectively represent standalone algorithmic performance.

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

For the method comparison study, the "ground truth" for evaluating the performance of the EliA assays on the Phadia 2500/5000 instrument was the results obtained from the predicate device, Phadia 250 instrument.

8. The sample size for the training set:

This information is not applicable as the devices are immunoassays, not machine learning algorithms that require a specific training set in the typical sense. The underlying EliA IgG method and its associated reagents were previously reviewed (K140225), implying that analytical performance of the assay itself was established in prior submissions. This current submission focuses on instrument equivalence.

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

This is not applicable for the same reasons as point 8. The assays do not involve machine learning with a distinct training set. The "ground truth" for establishing the analytical parameters and clinical performance of the immunoassays themselves would have been established through extensive analytical validation (e.g., against reference methods, known positive/negative samples, clinical samples with confirmed diagnoses) in their original clearance (K140225).

Ask a specific question about this device

NOVA Lite® DAPI ANCA (Ethanol) Kit is an indirect immunofluorescence assay for the qualitative detection and semiquantitative determination of anti-neutrophil cytoplasmic antibodies (ANCA) of IgG isotypes in human serum by manual fluorescence microscopy or with NOVA View Automated Fluorescence Microscope. The presence of ANCA, in conjunction with other serological, radiological, histological, and clinical findings aids in the diagnosis of ANCA associated vasculitides. A trained operator must confirm results when generated with the NOVA View device.

NOVA Lite® DAPI ANCA (Formalin) Kit is an indirect immunofluorescence assay for the qualitative detection and semi-quantitative determination of anti-neutrophil cytoplasmic antibodies (ANCA) of IgG istoypes in human serum by manual fluorescence microscopy or with NOVA View Automated Fluorescence Microscope. The presence of ANCA, in conjunction with other serological, radiological, histological, and clinical findings aids in the diagnosis of ANCA associated vasculitides. A trained operator must confirm results when generated with the NOVA View device. ANCA Formalin test is not intended to be used by itself, but in conjunction with ANCA Ethanol test.

The NOVA Lite DAPI ANCA (Ethanol) and ANCA (Formalin) Kits are indirect immunofluorescence assays for the qualitative detection and semi-quantitative determination of anti-neutrophil cytoplasmic antibodies of IgG isotypes in human serum

Kit components:

• . ANCA (Formalin Fixed Human Neutrophils) Slides; 12 wells/slide, with desiccant, or ANCA (Ethanol Fixed Human Neutrophils) Slides; 12 wells/slide, with desiccant
• FITC IgG Conjugate with DAPI, containing 0.09% sodium azide; ready to use. ●
• Positive Controls: cANCA and pANCA; human serum with antibodies to PR3 and MPO antigen, ● containing 0.09% sodium azide; pre-diluted, ready to use.
• Negative Control: IFA System Negative Control, diluted human serum with no ANCA present, containing 0.09% sodium azide; pre-diluted, ready to use.
• PBS II (40x) Concentrate, sufficient for making 2000 mL of 1x PBS II.
• Mounting Medium, containing 0.09% sodium azide
• Coverslips

This document outlines the acceptance criteria and study results for the NOVA Lite Dapi ANCA Ethanol Kit and Formalin Kit. This is a medical device, and the information is presented in the context of an FDA 510(k) premarket notification.

Acceptance Criteria and Reported Device Performance

The device is evaluated based on its precision performance (within laboratory imprecision, between lots reproducibility, between sites/instruments reproducibility, and between operators reproducibility), interference resistance, cross-reactivity with other conditions, and clinical sensitivity and specificity.

Precision Performance:

The acceptance criteria for precision studies consistently revolve around:

• Qualitative agreement: ≥ 90% (for NOVA View, Digital, and Manual readings)
• Grade agreement: ≥ 90% within ± 1 reactivity grade (for Digital and Manual readings)
• Pattern agreement: ≥ 90% (for Digital and Manual readings), or ≥ 80% after excluding positive/negative discrepancies for NOVA View

The studies generally show the device meets these targets. For example:

• Within-laboratory imprecision: "grades were within ± one reactivity grade within one run (within triplicates), and the average grade was no more than one reactivity grade different between runs."
• Between lots reproducibility: All qualitative agreements for Ethanol ANCA (NOVA View, Manual, Digital) were ≥ 97.0%. For Formalin ANCA, agreements ranged from 90.9% to 100%. Grade agreements were 100% within ± 1 grade for both Ethanol and Formalin ANCA for manual and digital readings. Pattern agreements were 100% for manual and digital Ethanol ANCA, and ranged from 90.9% to 100% for manual and digital Formalin ANCA.
• Between sites/instruments reproducibility:
  • Ethanol ANCA: Qualitative agreement (Total) ranged from 90.9% to 96.1% for NOVA View, 86.4% to 91.5% for Manual, and 90.1% to 96.1% for Digital. Grade agreement was ≥ 96.0% for both Manual and Digital. Pattern agreement (excluding pos/neg disagreement) was ≥ 90.0% for NOVA View, ≥ 98.0% for Manual, and ≥ 98.0% for Digital.
  • Formalin ANCA: Qualitative agreement (Total) ranged from 93.7% to 94.8% for NOVA View, 90.2% to 91.3% for Manual, and 92.7% to 95.5% for Digital. Grade agreement was ≥ 91.0% for both Manual and Digital. Pattern agreement (excluding pos/neg disagreement) was ≥ 93.0% for NOVA View, ≥ 98.0% for Manual, and ≥ 99.0% for Digital.
• Between operators reproducibility: Overall agreement (Positive/Negative) for Ethanol ANCA ranged from 94.4% to 100% for Manual reading and 97.2% to 100% for Digital Image Reading. For Formalin ANCA, it ranged from 94.0% to 100.0% for Manual reading and 91.6% to 99.6% for Digital Image Reading.

Interference:

• Acceptance Criteria: Grades obtained on samples with interfering substances are within ± 1 reactivity grade of those obtained on the control samples, spiked with diluent.
• Reported Performance: "No interference was detected with bilirubin up to 100 mg/dL, hemoglobin up to 200 mg/dL, triglycerides up to 1000 mg/dL, cholesterol up to 224.3 mg/dL, RF IgM up to 56 IU/mL, Human Immunoglobulin up to 35 mg/dL, Rituximab up to 7.6 mg/mL, Methylprednisolone up to 0.85 mg/mL, Cyclophosphamide up to 4.1 mg/mL, Methotrexate up to 0.01 mg/mL and Azathioprine up to 0.03 mg/mL. Reactivity grades of samples containing the interfering substance were within ± one grade of the control samples with both manual and digital reading."

Cross-reactivity:

The document reports cross-reactivity rates for various autoimmune and infectious conditions (e.g., Infectious Disease, Autoimmune thyroid disease, Celiac, Rheumatoid Arthritis). It also specifically examines cross-reactivity with known ANA positive samples. This is presented as information rather than having explicit numerical acceptance criteria in the provided text. The document acknowledges that ANA can interfere and states: "ANA positive samples may react with the nuclei of ethanol-fixed neutrophils, masking or mimicking ANCA. Positive IIF results should be confirmed by antigen specific solid phase assay for anti-MPO and anti-PR3."

Conjugate Comparison (to predicate device):

• Acceptance Criteria: Qualitative agreement: ≥ 90%, Grade agreement: ≥ 90% within ± 1 reactivity grade, Endpoint dilution is within ±1 dilution step between the two conjugates.

• Reported Performance: "The qualitative agreement and the grade agreement between the result obtained with the predicate and the new conjugate was 100% on both Ethanol and Formalin ANCA slides." Endpoint titers were within ±1 dilution step.

• Method Comparison (to predicate device):

  • Acceptance Criteria: Qualitative agreement: ≥ 80% (for manual and digital), Grade agreement: ≥ 90% within ± 1 reactivity grade, Pattern agreement: ≥ 80% between manual and digital interpretation.
  • Reported Performance: Ethanol ANCA qualitative agreement ranged from 80.3% to 91.8% for manual and digital vs. predicate manual. Grade agreement (within ±2 grades) was 99.6%. Pattern agreement was ≥ 80.1%. Formalin ANCA qualitative agreement ranged from 79.0% to 94.4%. Grade agreement (within ±2 grades) was 100%. Pattern agreement was ≥ 86.9%.

Clinical Sensitivity and Specificity:

These are reported for various ANCA Associated Vasculitides (AAV) subgroups (GPA, MPA, eGPA) and overall AAV, as well as for control populations across multiple sites and interpretation methods (Digital, Manual, NOVA View). No explicit numerical acceptance criteria are given for these performance characteristics in this document, but the results are presented as the device's performance.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample sizes used for the test set and data provenance

• Precision (within lab): 16 samples (3 negative, 13 positive - 7 anti-MPO, 6 anti-PR3) tested in triplicates across 10 runs (30 data points per sample). (p. 11) Data provenance is in-house (Inova Diagnostics). This was a prospective study.
• Precision (between lots): 33 clinically and/or analytically characterized samples. (p. 16) Data provenance is in-house (Inova Diagnostics). This was a prospective study.
• Precision (between sites/instruments): 287 clinically characterized samples were tested at three sites (Inova's laboratory and two external US clinical laboratories). Additionally, the two external sites each tested 100 routine clinical samples. The internal study uses 287 samples, with a clinical cohort of n=238 after excluding 49 analytically characterized samples. (p. 21) Data provenance includes US clinical laboratories (prospective, as samples were "tested").
• Precision (between operators): 10 samples (2 negative, 4 P-ANCA, 4 C-ANCA positive) tested at each of three sites, for 5 days in 5 replicates (25 data points per sample). (p. 28) Data provenance includes US clinical laboratories (prospective).
• Interference: 5 specimens (1 negative, 1 low MPO, 1 strong MPO, 1 low PR3, 1 strong PR3). These were spiked with various interferents and tested in triplicates. (p. 34) Data provenance is likely in-house. This was a prospective study.
• Cross-reactivity: 151 clinical patient samples (Infectious Disease, Autoimmune thyroid disease, Celiac, Rheumatoid Arthritis) and 25 analytically characterized ANA positive samples. (p. 35) Data provenance includes a clinical patient population. This was likely a retrospective analysis from collected samples.
• Conjugate Comparison: 36 specimens (analytically characterized serum samples and controls) plus a diluent blank. Endpoint titration on 6 positive samples. (p. 37) Data provenance is likely in-house. This was a prospective study.
• Method Comparison (vs. predicate): 100 samples (50 P-ANCA, 50 C-ANCA) and various disease control groups (Infectious Disease, Systemic Lupus Erythematosus, Progressive Systemic Sclerosis, Rheumatoid arthritis and Chronic Kidney Disease) for a total of 267 samples. (p. 38) Data provenance is in-house (Inova Diagnostics), likely retrospective from collected samples.
• Clinical Performance (Sensitivity/Specificity): 653 clinically or analytically characterized serum samples. A subset of 287 samples was also tested across three sites, with a clinical cohort of 238 after excluding analytically characterized samples. (p. 41) Data provenance covers a combined population, including US clinical samples and characterized samples. Likely a mix of retrospective and prospective.
• Expected Values: 89 samples from apparently healthy subjects. (p. 45) Data provenance is not explicitly stated as US or international but is part of the broader clinical validation. Likely a retrospective analysis.

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 test sets.

For "clinically characterized samples" and "analytically characterized MPO/PR3" samples, it is implied that a reference standard (e.g., diagnosis of ANCA Associated Vasculitis, characterized anti-MPO/PR3 status) was used as ground truth. However, the exact process of how this ground truth was established, who established it, and their qualifications are not detailed.

The manual readings and digital image interpretations are performed by "trained operators."

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

The document does not describe an explicit adjudication method like "2+1" or "3+1" for discrepancies in the test sets.

• For manual and digital readings in precision and method comparison studies, results from different operators/sites are compared.
• The "NOVA View interpretation" results are expected to be reviewed and confirmed by a "trained operator." (p. 9, 45) This implies a human-in-the-loop confirmation process as a form of adjudication for the automated 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

While there are studies involving multiple sites and operators comparing manual reading, digital image reading (human reading of images captured by the automated system), and NOVA View software interpretation, the document does not describe a formal MRMC comparative effectiveness study in the sense of measuring the improvement of human readers with AI assistance vs. without AI assistance.

The studies compare the performance of human readers (manual and digital) and the NOVA View software alone, but not the synergistic effect or comparative effectiveness of AI-assisted human reading against unassisted human reading. The "digital image reading" is human reading of images captured by the NOVA View, which is an output of the system, but the document does not present data on how this assistance (providing the images) improves human readers compared to traditional manual microscopy.

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

Yes, a standalone performance (algorithm only) was done. The "NOVA View software interpretation" is explicitly compared throughout the document to "Manual reading" (traditional microscopy) and "Digital reading" (human interpretation of the NOVA View generated digital images).

For example, in the Clinical Sensitivity and Specificity section (p. 42-44), separate results are provided for "NOVA View" (software interpretation), "Digital" (human interpretation of digital images), and "Manual" (traditional microscopy). This clearly indicates a standalone performance evaluation of the NOVA View software. The statement "A trained operator must confirm results when generated with the NOVA View device" (p. 2-3, 45) specifies the intended use model, but the software's performance without this confirmation step is also reported.

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

The types of ground truth used include:

• Analytically characterized samples: These are identified as "anti-MPO/PR3 positive" (p. 41), implying a biochemical or molecular characterization. This forms a strong ground truth for the presence of specific antibodies.
• Clinically characterized serum samples: These are often categorized by "Diagnosis" (e.g., ANCA Associated Vaculitidies (AAV), Infectious Disease, Rheumatoid Arthritis, etc.) (p. 21-23, 41). The establishment of these diagnoses would likely be based on a combination of clinical findings, laboratory tests, histology, and possibly expert consensus from treating physicians. The document does not specify the exact diagnostic criteria or who established these clinical diagnoses.
• Apparently healthy subjects: Used as a negative control group. (p. 41, 45)

8. The sample size for the training set

The document does not explicitly state the sample size for a "training set" for the NOVA View AI algorithm itself. It mentions that the "SWT function was established on 10 anti-MPO (P-ANCA) and 10 anti-PR3 (C-ANCA) positive samples" to establish LIU curves, which could be considered a form of training or calibration data for that specific function. However, a general training set size for the core ANCA detection and pattern recognition algorithm is not provided.

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

As the document does not explicitly detail a separate "training set" and its ground truth establishment, the information is limited. For the 20 samples (10 anti-MPO, 10 anti-PR3) used to establish the SWT function's LIU curves, the ground truth was "manually titrated" and "results were interpreted by NOVA View and by manual reading." (p. 47) This implies that the manual titration and reading served as the reference for establishing the LIU curves.

Ask a specific question about this device

EliA PR3s is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to proteinase 3 (PR3) in human serum and plasma (heparin, EDTA, citrate) to aid in the clinical diagnosis of Granulomatosis with Polyangiitis (GPA; formerly known as Wegener's granulomatosis) in conjunction with other laboratory and clinical findings. EliA PR3s uses the EliA IgG method on the instrument Phadia 100.

EliA PR3s is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to proteinase 3 (PR3) in human serum and plasma (heparin, EDTA, citrate) to aid in the clinical diagnosis of Granulomatosis with Polyangitis (GPA; formerly known as Wegener's granulomatosis) in conjunction with other laboratory and clinical findings. EliA PR3s uses the EliA IgG method on the instrument Phadia 250.

EliA MPOs is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to myeloperoxidase (MPO) in human serum and plasma (heparin, EDTA, citrate) as an aid in the clinical diagnosis of microscopic polyangitis (MPA) in conjunction with other laboratory and clinical findings. EliA IgG method on the instrument Phadia 100.

EliA MPOs is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to myeloperoxidase (MPO) in human serum and plasma (heparin, EDTA, citrate) as an aid in the clinical diagnosis of microscopic polyangitis (MPA) in conjunction with other laboratory and clinical findings. EliA IgG method on the instrument Phadia 250.

EliA GBM is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to alpha3 chain of collagen IV in human serum and plasma (heparin, EDTA, citrate) as an aid in the clinical diagnosis of Goodpasture syndrome in conjunction with other laboratory and clinical findings. EliA GBM uses the EliA IgG method on the instrument Phadia 100.

EliA GBM is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to alpha3 chain of collagen IV in human serum and plasma (heparin, EDTA, citrate) as an aid in the clinical diagnosis of Goodpasture syndrome in conjunction with other laboratory and clinical findings. EliA GBM uses the EliA IgG method on the instrument Phadia 250.

EliA ANCA/GBM Positive Control 100 is intended for laboratory use in monitoring the performance of in vitro measurement of ANCA/GBM antibodies with Phadia 100 using the EliA IgG method.

EliA ANCA/GBM Positive Control 250 is intended for laboratory use in monitoring the performance of in vitro measurement of ANCA/GBM antibodies with Phadia 250 using the EliA IgG method.

The new devices belong to a fully integrated and automated system for immunodiagnostic testing. It comprises a Fluorescence-Immunoassay test system using EliA single wells as the solid phase and is intended to be performed on the instruments Phadia 100 and Phadia 250.

The conjugate for the EliA IgG method is mouse anti-human IgG beta-galactosidase, which uses 4-Methylumbelliferyl-ß-D-Galactoside as substrate.

The total IgG calibration is based on a set of six WHO-standardized IgG Calibrators derived from human serum. They are used to establish an initial calibration curve, which may be used for up to 28 days on additional assays and can be stored by the instrument. Each additional assay includes calibrator (curve) controls that have to recover in defined ranges to ensure that the stored calibration curve is still valid. The Fluorescence-Immunoassay test system includes test-, method-specific and general reagents that are packaged as separate units.

The Phadia US, Inc. EliA™ PR3s, EliA™ MPOs, and EliA™ GBM immunoassays are intended for the semi-quantitative measurement of IgG antibodies to PR3, MPO, and alpha3 chain of collagen IV, respectively. These tests aid in the clinical diagnosis of Granulomatosis with Polyangiitis (GPA), microscopic polyangitis (MPA), and Goodpasture syndrome when used in conjunction with other laboratory and clinical findings. The EliA ANCA/GBM Positive Controls are for monitoring the performance of these immunoassays.

Here's an analysis of the provided information regarding acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific quantitative acceptance criteria (e.g., sensitivity, specificity thresholds) for the new devices (EliA PR3s, EliA MPOs, EliA GBM). Instead, it focuses on demonstrating "laboratory equivalence" to predicate devices.

The study indicates:

• Results obtained within a comparison study between new and predicate device.
• Results obtained for clinically defined sera.
• Results obtained for samples from apparently healthy subjects (normal population).

The overarching conclusion is: "In summary, all available data support that the new devices are substantially equivalent to the predicate devices."

Without explicit quantitative criteria, a table like the one requested cannot be fully populated. However, if we infer "equivalence" as the acceptance criterion, the reported performance is that this equivalence was supported by the comparison studies.

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

The document mentions "a data set including results obtained within a comparison study between new and predicate device, results obtained for clinically defined sera, and results obtained for samples from apparently healthy subjects (normal population)."

• Test Set Sample Size: The document does not specify the exact sample sizes used for the comparison study, clinically defined sera, or healthy subjects.
• Data Provenance: The document does not specify the country of origin for the data. It also does not explicitly state if the data was retrospective or prospective. Given the nature of a 510(k) submission for an in vitro diagnostic, it is highly probable that the "clinically defined sera" and "samples from apparently healthy subjects" would be retrospective collections, but this is not explicitly stated.

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

The document describes the devices as "intended for the in vitro semi-quantitative measurement of IgG antibodies... to aid in the clinical diagnosis... in conjunction with other laboratory and clinical findings." The "clinically defined sera" implies that the cases likely had their diagnosis confirmed by clinical experts.

• Number of Experts: The document does not specify the number of experts used to establish the ground truth for the clinically defined sera.
• Qualifications of Experts: The document does not specify the qualifications of these experts. However, for "clinically defined" cases, it would typically involve physicians specializing in the relevant diseases (e.g., rheumatologists, nephrologists) who use a combination of clinical symptoms, imaging, and other laboratory tests for diagnosis.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for establishing the ground truth for the test set.

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

• Was an MRMC study done? No, the devices are immunoassays, which are laboratory tests that produce a quantitative or semi-quantitative result. They are not image-based AI tools interpreted by human readers, so an MRMC comparative effectiveness study involving human readers is not applicable to this type of device.

6. Standalone (Algorithm Only) Performance

• Was a standalone study done? Yes, the described "comparison study between new and predicate device," "results obtained for clinically defined sera," and "results obtained for samples from apparently healthy subjects" represent the standalone performance of the immunoassay system. The device itself (the immunoassay) produces the semi-quantitative measurement of antibodies. There is no human-in-the-loop component for interpreting the direct output of these specific diagnostic tests, although a clinician then uses these results in conjunction with other findings for diagnosis.

7. Type of Ground Truth Used

The ground truth for the clinical cases appears to be "clinically defined diagnoses." The document specifically mentions "clinically defined sera," implying that patients were diagnosed with GPA, MPA, or Goodpasture syndrome based on established clinical criteria, which would likely include a combination of clinical symptoms, other laboratory tests, and potentially biopsy results (e.g., pathology for kidney biopsies in Goodpasture syndrome). For the "healthy subjects," the ground truth is the absence of these diseases.

8. Sample Size for the Training Set

The document does not provide information on a specific "training set" sample size. For an immunoassay, the "training" analogous to machine learning often involves assay development, optimization, and establishment of referent ranges and cut-offs. The sample sets described ("comparison study," "clinically defined sera," "healthy subjects") are typically used for validation or verification of performance, not explicitly for "training" in the AI sense.

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

As no explicit "training set" is described in the context of machine learning, the establishment of its ground truth is not applicable. For the performance studies, as mentioned in point 7, the ground truth was based on clinically defined diagnoses.

Ask a specific question about this device

The QUANTA Flash PR3 is a chemiluminescent immunoassay (CIA) for the semiquantitative detection of IgG anti-proteinase 3 (PR3) autoantibodies in human serum on the BIO-FLASH® instrument. QUANTA Flash PR3 is an aid in the diagnosis of granulomatosis with polyangiitis (GPA) in conjunction with clinical findings and other laboratory tests.

The QUANTA Flash PR3 Calibrators are intended for use with the QUANTA Flash PR3 chemiluminescent immunoassay (CIA) on the BIO-FLASH® instrument. Each calibrator establishes a point of reference for the working curve that is used in the measurement of IgG anti-proteinase 3 (PR3) autoantibodies in human serum.

The QUANTA Flash PR3 Controls are intended for quality control purposes of the QUANTA Flash PR3 chemiluminescent immunoassay (CIA) kit run on a BIO-FLASH® instrument that is used in the measurement of IgG anti-proteinase 3 (PR3) autoantibodies in human serum.

The QUANTA Flash MPO is a chemiluminescent immunoassay (CIA) for the semiquantitative detection of IgG anti-myeloperoxidase (MPO) autoantibodies in human serum on the BIO-FLASH® instrument. QUANTA Flash MPO is an aid in the diagnosis of microscopic polyangiitis (MPA) in conjunction with clinical findings and other laboratory tests.

The QUANTA Flash MPO Calibrators are intended for use with the QUANTA Flash MPO chemiluminescent immunoassay (CIA) on the BIO-FLASH® instrument. Each calibrator establishes a point of reference for the working curve that is used in the measurement of IgG anti-myeloperoxidase (MPO) autoantibodies in human serum.

The QUANTA Flash MPO Controls are intended for quality control purposes of the QUANTA Flash MPO chemiluminescent immunoassay (CIA) kit run on a BIO-FLASH® instrument that is used in the measurement of IgG anti-myeloperoxidase (MPO) autoantibodies in human serum.

The QUANTA Flash GBM is a chemiluminescent immunoassay (CIA) for the semiquantitative detection of IgG anti-glomerular basement membrane (GBM) autoantibodies in human serum on the BIO-FLASH® instrument. QUANTA Flash GBM is an aid in the diagnosis of Goodpasture's Syndrome in conjunction with clinical findings and other laboratory tests.

The QUANTA Flash GBM Calibrators are intended for use with the QUANTA Flash GBM chemiluminescent immunoassay (CIA) on the BIO-FLASH® instrument. Each calibrator establishes a point of reference for the working curve that is used in the measurement of IgG anti-glomerular basement membrane (GBM) autoantibodies in human serum.

The QUANTA Flash GBM Controls are intended for quality control purposes of the QUANTA Flash GBM chemiluminescent immunoassay (CIA) kit run on a BIO-FLASH® instrument that is used in the measurement of IgG anti-glomerular basement membrane (GBM) autoantibodies in human serum.

Not Found

This document is an FDA 510(k) clearance letter for the QUANTA Flash® suite of autoantibody detection assays. It primarily outlines the indications for use for each reagent, calibrator, and control, and states that the devices are substantially equivalent to legally marketed predicate devices.

The document does not contain the acceptance criteria or study details regarding the performance of the device. This type of information is typically found in the 510(k) submission summary or other supporting documentation, which is not provided in your input. The FDA clearance letter summarizes the regulatory decision, not the technical performance data that led to it.

Therefore, requested information cannot be extracted from the provided text.

Ask a specific question about this device

The FIDIS™ VASCULITIS* kit is a semi-quantitative homogeneous fluorescent-based microparticle immunoassay using flow cytometry. The test system is used to simultaneously detect the presence of anti-neutrophil cytoplasmic antibodies (ANCA) directed against Myeloperoxidase (MPO), Serine Proteinase 3 (PR3) and antibodies directed against glomerular basement membrane (GBM) in human serum samples.

The results of the FIDIS™ VASCULITIS* test are to be used in conjunction with the clinical findings and the other laboratory tests to aid in the diagnosis of various primary systemic small blood vessel vasculitides and glomerular basement membrane disease.

Clinical utility:
The detection of ANCA is associated with primary systemic small blood vessel vasculitides: Wegener's granulomatosis, Churg Strauss syndromes, microscopic periarteritis and idiopathic crescentic glomerulonephritis; and the detection of anti-GBM antibodies is associated with Goodpasture's syndrome.

FIDIS™ VASCULITIS* kit uses serum only, and is to be run on the FIDIS™ Instrument and MLX-BOOSTER Software.

FIDIS™ VASCULITIS* kit may be used with the CARIS™ system (diluting and dispensing device).

This kit is for In vitro diagnostic use.

• Detection of the serologic markers for primary systemic small blood vessel vasculitides (ANCA) and for Goodpasture syndrome (GBM).

FIDIS™ VASCULITIS* kit is a multiplex flow immunoassay, which allows simultaneous identification and detection of several antibodies.

FIDIS™ VASCULITIS* is based on the use of distinct uniform size color-coded microsphere sets and a benchtop flow cytometer interfaced to digital signal processing hardware and software. A red diode laser beam in the flow cytometer recognizes each set of microspheres on the basis of its unique fluorescence intensity (red and infrared) thus identifying which parameter is being tested. At the same time, a green laser beam illuminates the external second molecule fluorescence to quantify the reaction related to the specific antigen.

Three different fluorescently "colored" sets of microspheres are coated with antigens associated with various primary systemic small blood vessel vasculitides and glomerular basement membrane disease (MPO, PR3 and GBM). An additional microsphere (Internal Bead standard) set is coated with anti-IgG to ensure that false negative results due to operational error are detected.

The four different sets of microspheres are mixed together. The mixture is lyophilized and constitutes the final microspheres reagent.

The test is performed using a 96 wells microplate with a filtering membrane at the bottom of the wells.

In the first step, the sample is distributed in each well containing the reconstituted microspheres mixture, allowing any anti-MPO, anti-PR3 or anti-GBM antibodies present to bind to the immobilized antigens on the microspheres, as well as free IgG to bind to the anti-IgG microsphere.

After incubation, a wash step using a filtration process removes the unbound antibodies.

A phycoerythrin anti-human IgG conjugate is then added that binds to the previously bound antibodies.

A final wash step stops the reaction and eliminates the unbound conjugate.

The reaction is then measured directly by the flow cytometer, which distinguishes each set of microspheres by its fluorescence color while simultaneously measuring the average fluorescence emitted by the conjugate.

A calibration system allows the determination of the titer (AU/mL) of each sample by interpolation for each antigenic specificity.

Here's a breakdown of the acceptance criteria and the study details for the FIDIS™ VASCULITIS Assay kit, based on the provided document:

Acceptance Criteria and Device Performance:

The acceptance criteria for the FIDIS™ VASCULITIS Assay kit are derived from demonstrating substantial equivalence to a predicate device (K070458 FIDIS™ VASCULITIS system) and demonstrating comparable performance between manual and automated assay preparation. The performance metrics are Positive Percent Agreement (PPA), Negative Percent Agreement (NPA), and Overall Agreement (OA) for three specificities: MPO, PR3, and GBM. Precision (within-run and between-run %CV) was also assessed.

Table of Acceptance Criteria and Reported Device Performance:

Study Proving Acceptance Criteria:

The document describes two primary studies to demonstrate that the device meets acceptance criteria:

1. Comparison study with predicate - Using Manual Pipetting: This study aimed to show substantial equivalence of the modified FIDIS™ VASCULITIS kit to the legally marketed predicate device (K070458).
2. Comparison studies (manual versus automated assay preparation steps) with CARIS™: This study aimed to demonstrate that the use of the CARIS™ system for automated sample preparation provided comparable results to manual preparation with the modified FIDIS™ VASCULITIS kit.

Detailed Study Information:

1. Sample sized used for the test set and the data provenance:

• Comparison with predicate Study:
  • Test set sample size: 280 samples.
  • Data provenance: Not explicitly stated, but given that both the original and modified device are from "Biomedical Diagnostics S.A." in France, it is highly likely the data is from French or European sources. The study is retrospective as it compares the modified device against previously characterized samples with the predicate test.
• CARIS™ Comparison Study:
  • Test set sample size: 106 samples.
  • Data provenance: Not explicitly stated, but also likely from French or European sources. The study seems to be prospective or concurrent comparison of two methods on the same set of samples.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

The document does not mention the use of experts or their qualifications for establishing ground truth. The "ground truth" for these studies is not clinical diagnosis by experts, but rather the results obtained from the predicate device (K070458 FIDIS™ VASCULITIS system) for the first study, and the modified FIDIS™ VASCULITIS with manual assay preparation for the second study. These methods are considered the reference for comparison.

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

Not applicable. There was no explicit adjudication described as the "ground truth" was established by the reference assays (predicate device or modified device with manual preparation). The document mentions how equivocal results were handled for calculation purposes (included with negative or positive results), but this is not an adjudication method for ground truth.

4. 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:

Not applicable. This device is an in vitro diagnostic (IVD) assay kit, not an AI-assisted diagnostic tool that involves human readers. The performance is based on agreement between two assay methods.

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

The device itself (FIDIS™ VASCULITIS Assay kit) is essentially a standalone algorithm/test in the context of generating a quantitative result (AU/mL). The "standalone" performance is assessed by its agreement with the predicate device and the manual method. There is no human-in-the-loop directly interpreting raw data beyond what is typical for laboratory technicians running an assay and interpreting its results. The comparison studies effectively represent "standalone" performance against a defined reference.

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

The "ground truth" in these studies is the results of a reference in-vitro diagnostic method.

• For the predicate comparison study, the ground truth was the results obtained from the predicate device (K070458 FIDIS™ VASCULITIS).
• For the CARIS™ comparison study, the ground truth was the results obtained from the modified FIDIS™ VASCULITIS with manual assay preparation.

7. The sample size for the training set:

Not applicable. This is an IVD assay kit, not an AI/machine learning model that typically requires a distinct training set. The performance is established through analytical validation studies (precision, method comparison).

8. How the ground truth for the training set was established:

Not applicable, as there is no training set in the AI/ML sense.

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device