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

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

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

The Randox Ammonia Ethanol Control Levels 1, 2 & 3 are intended for in vitro diagnostic use in the quality control of Ammonia and Alcohol Assays to monitor precision and to detect systematic analytical deviations on clinical chemistry systems. This device is for prescription use only.

The Randox Ammonia Ethanol Controls are liquid and supplied at levels 1, 2 and level 3. The base matrix used for the manufacture of Randox Ammonia Ethanol Controls Levels 1, 2 & 3 is saturated benzoic acid with added chemicals. Each level of control is supplied in liquid form in 6 x 2ml vials and is ready for use. Only the required amount of product should be removed from the vial. After use, any residual product should not be returned to the original vial.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance Study

1. Table of Acceptance Criteria and Reported Device Performance

Device Type: Randox Ammonia Ethanol Control Levels 1, 2 & 3 (Multi-analyte Controls, Assayed)

Study Focus: Open Vial Stability and Real-Time Shelf-Life Stability

• Level 1: 0.7%
• Level 2: -0.9%
• Level 3: -2.0%
  Ethanol (RX Daytona):
• Level 1: 4.7%
• Level 2: 1.2%
• Level 3: 1.3% | Not explicitly given for individual analytes at specific time points, but states "Current Real Time studies support an 18 month shelf life." |
  | Real Time Shelf-Life (Percentage Deviation to routine temp. controls) | ≤ 5% | N/A (Applies to comparison against routine temp. controls, not open vial test) | "Current Real Time studies support an 18 month shelf life." |
  | Value Assignment Precision (CV) | ≤ 10% for Control Level 1
  ≤ 7.5% for Control Levels 2 and 3 | Not explicitly stated in the results section, only the criteria. | N/A |
  | Value Assignment Recovery Error (Master Lot) | ≤ 7.5% for all control levels | Not explicitly stated in the results section, only the criteria. | N/A |

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

• Sample Size: The text does not explicitly state the number of vials or how many test runs were conducted for the open vial stability study. It mentions testing "a set of Randox Ammonia Ethanol Control levels 1, 2 & 3." For real-time testing, it mentions "the controls were then tested." The exact number of replicates or distinct samples per time point is not provided.
• Data Provenance: The study was conducted by Randox Laboratories Limited, located in Crumlin, County Antrim, BT29 4QY, United Kingdom. The data is prospective as it involves testing materials over time under specific conditions to assess stability.

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

This information is not applicable to this device and study. The "device" is a quality control material, not a diagnostic tool that provides a result that requires human interpretation or expert ground truth. The "ground truth" in this context is the measured concentration of Ammonia and Ethanol by the specified analytical instruments (ADVIA 1650 for Ammonia and RX Daytona for Ethanol) and comparison to a fresh control or a defined target value.

4. Adjudication Method for the Test Set

This information is not applicable as the study does not involve subjective human interpretation that would require adjudication. The results are quantitative measurements from analytical instruments.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study is relevant for diagnostic imaging or interpretation tasks where reader performance is a key metric. This submission is for a quality control material where the performance is assessed through analytical precision and stability.

6. If a Standalone Study (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a standalone study was done. The device itself is a control material, and its performance (stability, value assignment) is evaluated independently using established laboratory methods and instruments (ADVIA 1650 and RX Daytona). There is no "human-in-the-loop" interaction for the functioning or assessment of the control material itself in these studies.

7. The Type of Ground Truth Used

The ground truth used for this study is based on:

• Analytical Measurement: The measured concentrations of ammonia and ethanol obtained from established and calibrated clinical chemistry systems (ADVIA 1650 for Ammonia, RX Daytona for Ethanol).
• Comparison to Fresh Material: For open vial stability, the "fresh result" serves as the reference point (ground truth) for calculating percentage difference.
• Comparison to Routine Temperature Controls: For real-time testing, the "control material stored unopened at the routine storage temperature of +2 to +8°C" serves as the reference.
• Master Lot Concept: For value assignment, a "master lot" is used as a reference to assign values to new lots.

Essentially, the ground truth is derived from objective analytical measurements and comparisons to reference materials/conditions rather than expert consensus, pathology, or outcomes data.

8. The Sample Size for the Training Set

Not applicable/Not provided. The concept of a "training set" is generally associated with machine learning or artificial intelligence models. This submission is for a quality control material, which does not involve such a training process.

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

Not applicable. As the device is a quality control material and not an AI/ML diagnostic model, there is no "training set" or "ground truth for the training set" in the context typically described for such technologies.

Ask a specific question about this device

Liquichek Ethanol/Ammonia Control is intended for use as an assayed quality control serum to monitor the precision of laboratory testing procedures for the analytes listed in the package insert.

Liquichek Ethanol/Ammonia Control is prepared from bovine serum albumin with chemicals, stabilizers and preservatives added. This control is provided in liquid form for convenience.

The provided document is a 510(k) Premarket Notification for a Liquichek Ethanol/Ammonia Control, which is a quality control material used to monitor the precision of laboratory testing procedures. This is not a medical device that utilizes AI or machine learning, nor is it designed for diagnostic imaging or similar applications where the requested information (like MRMC studies, human reader improvement, or expert ground truth establishment) would be relevant.

Therefore, many of the requested categories about acceptance criteria and study design are not applicable to this type of product. The document describes a traditional medical device (a control solution) that undergoes stability testing, not a device that involves complex algorithms or human interpretation of outputs.

Here's a breakdown of the applicable information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical "acceptance criteria" in the format typically seen for diagnostic devices (e.g., sensitivity, specificity thresholds). Instead, it describes "stability studies" performed to determine shelf-life and open-vial stability. The "reported device performance" is the claim of stability for these periods.

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

The document does not specify a "test set" in the context of an algorithm or diagnostic evaluation. The stability studies likely involved multiple aliquots or batches of the control material over the specified periods.

• Sample Size: Not explicitly stated, but implies "replicate analyses" and "a representative sampling of this lot of product."
• Data Provenance: The studies were performed by the manufacturer (Bio-Rad Laboratories) and/or independent laboratories. No country of origin for the data is specified, but the manufacturer is based in Irvine, California, USA. The studies are prospective in nature, as they are establishing future stability claims.

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

This concept is not applicable to a quality control material. Ground truth in this context would refer to the true concentration of ethanol and ammonia, which is established by precise laboratory methods and analytical chemistry, not by human expert interpretation. The "value assignment" section states that mean values and ±3SD ranges were "derived from replicate analyses" by the manufacturer and independent laboratories.

4. Adjudication Method for the Test Set

This is not applicable. The "test set" in this context refers to samples used for analytical stability studies, not for the evaluation of a diagnostic algorithm's output that would require adjudication.

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

This is not applicable. This type of study is designed for diagnostic devices that are interpreted by human readers, often with AI assistance. The Liquichek Ethanol/Ammonia Control is a quality control solution for laboratory instruments, not a device that human readers interact with in this manner.

6. Standalone Performance Study

This is not applicable in the sense of an algorithm operating independently. The "performance" of this device is its ability to maintain stable concentrations of ethanol and ammonia over time, which is assessed through laboratory testing of the control material itself (standalone in that sense, but not for an algorithm).

7. Type of Ground Truth Used

The ground truth for this device (the true values of Ethanol and Ammonia) is established through analytical testing and measurement using laboratory instruments specified in the value assignment section. It's based on precise chemical analysis, not expert consensus, pathology, or outcomes data.

8. Sample Size for the Training Set

This is not applicable. There is no "training set" as this device is not an AI/ML algorithm.

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

This is not applicable.

Ask a specific question about this device

The EasyRA EtOH reagent is intended for the quantitative measurement of Alcohol (EtOH) in human urine, using MEDICA's EasyRA Chemistry Analyzer in clinical laboratories. Alcohol measurements are used for the diagnosis and treatment of alcohol intoxication and poisoning.

The EasyCal Ethanol Calibrator is intended for in-vitro diagnostic use for the calibration of the ethyl alcohol assay on the EasyRA Chemistry Analyzer for the quantitative determination of ethyl alcohol in urine.

The EasyQC Ethanol quality control material is intended for in-vitro diagnostic use for the validation of the ethyl alcohol assay, which is used on the EasyRA Chemistry Analyzer for the quantitative determination of ethyl alcohol in urine.

Not Found

The provided text is a 510(k) premarket notification letter from the FDA to Medica Corporation regarding their Easy RA Ethyl Alcohol Reagent, Calibrator, and QC Material. It details the regulatory approval of the devices for "quantitative measurement of Alcohol (EtOH) in human urine" and states that "Alcohol measurements are used for the diagnosis and treatment of alcohol intoxication and poisoning."

However, this document does not contain information about specific acceptance criteria, study details, sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, or how ground truth was established for these devices. The letter primarily confirms that the device is substantially equivalent to legally marketed predicate devices and is subject to general controls provisions.

Therefore, I cannot fulfill your request for a description of the acceptance criteria and the study that proves the device meets them based on the provided text.

Ask a specific question about this device

Randox Ethanol Assay: The Randox Ethanol Assay is an in vitro diagnostic test for the quantitative analysis of Ethanol in human urine and serum on the forme analysers, which includes the JX day to na™ and the Amota™ analysers. The measurement of ethanol is used for the diagnosis and treatment of alcohol intoxication and poisoning. This is an in vitro diagnostic device intended for prescription use only.
Randox Ethanol Calibrator Set: The Randox Ethanol Calibrator Set is intended for the Randox Ethanol assay, which is used for the quantitative analysis of ethanol in human urine and serum on the December analysers which includes the X day to na™ and the 121mona™.
Randox Ethanol Control Set: The Randox Ethanol Control Set is intended for the quality control of the Randox Ethanol assay, which is used for the quantitative analysis of ethanol in human urine and serum on the forme analysers which includes the Aday to na™ and the Mimola™. This is an in vitro diagnostic device intended for prescription use only.

Not Found

The provided text is a 510(k) premarket notification for an in vitro diagnostic device (Randox Ethanol Assay and Calibrators/Controls). It does not contain information about acceptance criteria, device performance, or a study report with details like sample sizes, expert qualifications, or ground truth establishment. This type of document primarily confirms that the device is substantially equivalent to a legally marketed predicate device and outlines regulatory compliance.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and reported device performance.
• Sample sizes, data provenance, number of experts, adjudication methods, or ground truth types for a test set.
• Information on MRMC comparative effectiveness studies or standalone algorithm performance.
• Sample size for the training set or how ground truth was established for it.

Ask a specific question about this device

The Audit MicroCV Ammonia/Ethanol Linearity Set is assayed quality control material consisting of five levels protein (bovine) based serum. Each level contains Ammonia and Ethanol analytes. The five levels demonstrate a linear relationship to each other for Ammonia and Ethanol analytes. It is intended to simulate human patient serum samples and to detect systematic analytical deviations of laboratory testing procedures for Ammonia and Ethanol. This product may be used as unassayed quality control material for Ammonia and Ethanol analytes. The product is intended for use with quantitative assays on the indicated analyzer provided in the labeling. The Audit MicroCV Ammonia/Ethanol Linearity Set is "For In Vitro Diagnostic Use Only."

The Audit™ MicroCV™ Ammonia/Ethanol Linearity Set is a protein (bovine) based calibration verification material containing multiple levels used to confirm proper calibration, linear operating range, and reportable range of the measured analyte. Level A has concentration near the lower limit level and Level E has concentrations near the upper limit level of instruments. Levels B - D are related by linear dilution of Level A and Level E.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Audit™ MicroCV™ Ammonia/Ethanol Linearity Set:

1. Table of Acceptance Criteria and Reported Device Performance

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

The provided 510(k) summary does not explicitly detail the sample size or provenance (country of origin, retrospective/prospective) of the data used for the performance studies. It simply states, "Stability studies have been performed to determine stability and shelf life for the Audit™ MicroCV™ Ammonia/Ethanol Linearity Set. All supporting data is retained on file at Aalto Scientific, Ltd." and refers to "stability data generated" for the substantial equivalence conclusion.

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

Given that this is a linearity and stability test for an in vitro diagnostic quality control material, the concept of "experts establishing ground truth" in the common sense of clinical image review or diagnostic interpretation does not apply directly. The ground truth for this device would be established by:

• Analytical measurements: Precise laboratory equipment and reference methods would be used to determine the actual concentrations of Ammonia and Ethanol at each level.
• Time-point measurements: For stability studies, measurements would be taken at various time points to assess degradation or changes over time.

Therefore, no "experts" in the sense of clinicians or radiologists are involved in establishing ground truth for this type of device. The expertise lies in the analytical chemists and laboratory personnel conducting the tests according to validated protocols.

4. Adjudication Method for the Test Set

Again, the concept of an adjudication method (like 2+1, 3+1 for clinical consensus) does not apply to the analytical performance testing described for this device. The assessment of linearity and stability would involve:

• Statistical analysis: Determining if the measured concentrations across the five levels indeed show a linear relationship using statistical methods (e.g., linear regression, acceptable deviation from linearity).
• Comparison to predefined limits: For stability, measured concentrations at different time points would be compared to initial concentrations or predefined stability specifications.

No human adjudication panel is necessary for these types of objective quantitative measurements.

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

No, an MRMC comparative effectiveness study was not done for this device. This type of study is typically used for diagnostic devices that involve human interpretation (e.g., radiology AI tools to assess reader performance). The Audit™ MicroCV™ Ammonia/Ethanol Linearity Set is an in vitro diagnostic quality control material, not a device interpreted by human readers for diagnostic purposes.

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

No, the concept of a "standalone algorithm" is not applicable to this device. This device is a physical reagent set used to verify the performance of analytical chemistry systems (analyzers). It is not an algorithm, nor does it operate as a standalone diagnostic tool without human interaction (as it requires human setup and operation within a laboratory).

7. The Type of Ground Truth Used

The ground truth used for verifying the performance of this device would be:

• Analytical Reference Values: Established concentrations of Ammonia and Ethanol in the linearity set, ideally traceable to recognized reference materials or methods.
• Stability Specifications: Predetermined acceptable limits of variation from the initial reference values over time under specified storage conditions.

It relies on precise chemical measurements and validated laboratory procedures, not expert consensus, pathology, or direct outcomes data in the clinical sense.

8. The Sample Size for the Training Set

This device is not an AI/ML algorithm, so the concept of a "training set" does not apply. The manufacturer develops the product, then tests its analytical performance (linearity, stability).

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

As stated above, there is no training set for this type of in vitro diagnostic quality control material.

Ask a specific question about this device

Ammonia/Ethanol/CO2 Calibrator is for use in the calibration of quantitative Roche methods on Roche clinical chemistry analyzers as specified in the enclosed value sheet.

Ammonia/Ethanol/CO2 Control is for use in quality control by monitoring accuracy and precision for the quantitative methods as specified in the enclosed value sheet.

The Ammonia/Ethanol/CO2 Calibrator is a liquid ready-for-use calibrator based on a buffered aqueous solution. The concentration of the calibrator The Ammonia/Ethanol/CO2 Controls are liquid ready-for-use controls based on a buffered aqueous solution. The adjusted concentrations of the control components are in the normal range for the Normal control and the pathological range for the Abnormal control.

This document is a 510(k) summary for a medical device (Ammonia/Ethanol/CO2 Calibrator and Controls) and does not contain information typically found in a study proving a device meets acceptance criteria for an AI or software-based medical device.

The provided text describes a calibrator and controls for in vitro diagnostic devices, which are reagents used to ensure the accuracy and precision of laboratory tests on clinical chemistry analyzers. These are physical products, not software/AI, and therefore the concepts of "acceptance criteria," "device performance," "sample size for test/training sets," "ground truth," "MRMC studies," or "standalone performance" as typically applied to AI/software devices are not directly applicable in the same way.

The document focuses on establishing substantial equivalence to existing legally marketed predicate devices, which is the regulatory pathway for this type of product. Substantial equivalence means the new device is as safe and effective as a legally marketed device that is not subject to PMA (Premarket Approval).

Here's a breakdown of the information in relation to your request, highlighting what's missing due to the nature of the device:

1. Table of Acceptance Criteria and Reported Device Performance:

This type of table is not present in the document because this is not a performance study of an AI/software device. For a calibrator/control, "performance" relates to its ability to accurately and precisely calibrate and control the analytical process of a clinical chemistry analyzer. The document states:

• Intended Use of Calibrator: "for use in the calibration of quantitative Roche methods on Roche clinical chemistry analyzers as specified in the enclosed value sheet."
• Intended Use of Control: "for use in quality control by monitoring accuracy and precision for the quantitative methods as specified in the enclosed value sheet."

The "acceptance criteria" here would generally be related to the stability, homogeneity, and assigned values of the calibrator/control, and their ability to ensure the accuracy of the assay. These details are not within this summary. Substantial equivalence usually means that the new device performs similarly to the predicate in these aspects.

Regarding items 2-9, these are generally not applicable to this type of device and submission:

2. Sample size used for the test set and the data provenance: Not applicable. There's no "test set" in the context of an AI/software algorithm. The device itself is a physical calibrator/control.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI/software device is not relevant here. The ground truth for the calibrator/control would be the analytically determined true values of the analytes within the product, established through reference methods or highly accurate assays, not expert consensus on images or similar data.
4. Adjudication method for the test set: Not applicable.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not applicable. This type of study is for evaluating human performance with and without AI assistance for tasks like diagnosis or detection.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an algorithm.
7. The type of ground truth used: For a calibrator/control, the "ground truth" refers to the assigned values or the true concentrations of the analytes (Ammonia, Ethanol, CO2) within the calibrator and control materials. This is typically established through a rigorous analytical process using reference methods and highly accurate instrumentation, not expert consensus, pathology, or outcomes data in the way these terms are used for AI/software devices.
8. The sample size for the training set: Not applicable. No training set for an AI/software algorithm.
9. How the ground truth for the training set was established: Not applicable.

Summary of what's provided for this type of device and submission:

• Device Name: Ammonia/Ethanol/CO2 Calibrator and Controls
• Intended Use: Calibration and quality control for quantitative Roche methods on Roche clinical chemistry analyzers.
• Predicate Device:
  • Ammonia/Ethanol/CO2 Calibrator (K952282)
  • Ammonia/Ethanol/CO2 Controls (K951595)
• Regulatory Conclusion: Substantial Equivalence to the predicate devices. This means the FDA has determined the new device is as safe and effective as the existing marketed devices. The "study that proves the device meets the acceptance criteria" in this context is the evidence presented by the manufacturer to the FDA demonstrating this substantial equivalence, which would include data on the formulation, stability, and characterization of the calibrator and controls, demonstrating they perform comparably to the predicate. These detailed data points are not typically included in the 510(k) Summary, but rather in the full 510(k) submission.

Ask a specific question about this device

The Bayer ADVIA IMS Ethanol (ETOH) assay is an in vitro diagnostic device intended to quantitatively measure ethanol concentration in human serum or plasma (Lithium Heparin). Measurement of ethanol is used in the diagnosis of ethanol (alcohol) toxicity and overdose.

Not Found

The Bayer ADVIA® IMS™ Ethanol assay is an in vitro diagnostic device intended to quantitatively measure ethanol concentration in human serum or plasma (Lithium Heparin). This assay is used in the diagnosis of ethanol (alcohol) toxicity and overdose.

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device