Search Results

Bladder EpiCheck Kit is intended for the qualitative detection of DNA methylation patterns of 15 loci in human DNA that are associated with transitional cell carcinoma of the bladder. The test is performed on voided urine samples and run on the ABI® 7500 Fast Dx Real-Time PCR system.

Bladder EpiCheck Kit is indicated for use as a non-invasive method to monitor for tumor recurrence in conjunction with cystoscopy in patients previously diagnosed with Non-Muscle Invasive Bladder Cancer.

The Bladder EpiCheck Test is a real-time PCR-based in vitro diagnostic assay intended for the qualitative detection of DNA methylation patterns associated with transitional cell carcinoma of the bladder to monitor for tumor recurrence (in conjunction with cystoscopy) in patients previously diagnosed with non-muscle invasive bladder cancer (NMIBC).

The assay consists of a panel of 15 novel DNA methylation (covalent addition of methyl (CH3) groups to the C5 position of the pyrimidine ring of cytosines, typically in a CpG dinucleotide) biomarkers that were found to distinguish between patients with bladder cancer and patients without bladder cancer. The Bladder EpiCheck Test differentiates between methylated and non-methylated DNA, creating a unique platform for methylation profiling of urine specimens towards the detection of bladder cancer recurrence in patients previously diagnosed with the disease. The test is comprised of reagents for end-to-end (sample-to-answer) processing of urine samples (reagents for DNA extraction, DNA digestion, PCR amplification, and analysis software), and is performed using the Applied Biosystems® 7500 Fast Dx Real-Time PCR system.

A voided urine specimen is centrifuged, and the cells (both normal and cancerous if present) are separated from the urine supernatant. DNA is then extracted from the cell pellet using the Bladder EpiCheck Extraction kit (P/N NX899090-01C). The extracted DNA is digested using a methylation-sensitive restriction enzyme mix. which cleaves DNA at specific recognition sequences if they are unmethylated. Methylated DNA is protected from enzymatic digestion and therefore remains intact.

Here's a breakdown of the acceptance criteria and study details for the Bladder EpiCheck Kit, based on the provided FDA 510(k) summary:

Device: Bladder EpiCheck Kit
Intended Use: Qualitative detection of DNA methylation patterns of 15 loci in human DNA associated with transitional cell carcinoma of the bladder, used as a non-invasive method to monitor for tumor recurrence in conjunction with cystoscopy in patients previously diagnosed with Non-Muscle Invasive Bladder Cancer.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined acceptance criteria in a dedicated table format. However, performance metrics are reported. Based on the "Method Comparison" section (9.2 Clinical), the de facto acceptance criteria appear to be tied to non-inferiority against the predicate device (UroVysion Bladder Cancer Kit) and sufficient performance against a Gold Standard.

2. Sample Size and Data Provenance for Test Set (Clinical Performance Study)

• Sample Size:
  • Against Gold Standard: 583 subjects (total voided urine specimens collected from 583 subjects). Valid Bladder EpiCheck and GS results were obtained from 449 subjects.
  • Against Predicate Device (Matched Cases): Valid Bladder EpiCheck, UroVysion, and GS results were obtained from 352 samples.
  • Specificity in Urology Patients without Bladder Cancer: 147 subjects.
  • Clinical Specificity - Cross Reactivity with Other Cancers: 147 urine samples.
• Data Provenance:
  • Country of Origin: U.S. and Canada (from 11 academic and urology specialty medical centers).
  • Retrospective or Prospective: The main clinical study (Method Comparison) was a multi-center, prospective, IRB-approved longitudinal study. The specificity study in urology patients without bladder cancer was also multi-center, prospective. The cross-reactivity study utilized banked remnant de-identified urine samples, which would generally be considered retrospective.

3. Number of Experts and their Qualifications for Establishing Ground Truth for the Test Set

The document does not specify the number of experts or their qualifications for establishing the ground truth. It states that positive cases were confirmed by "cystoscopy and pathology." This implies that the ground truth was established by clinical diagnoses and pathological examination of tissue, presumably performed by trained urologists and pathologists, which are standard practices. No "experts" are explicitly described as reviewing cases for the purpose of establishing a "ground truth" consensus for the study, beyond the routine clinical workflow.

4. Adjudication Method for the Test Set

The adjudication method is implicitly described for the Gold Standard (GS) definition:

• "a subject was considered 'positive' if the interpretation for either cytology or the combined cystoscopy/pathology results were positive"
• "and a subject was considered 'negative' if both cytology and the combined cystoscopy/pathology results were negative."

This indicates a hierarchical or "any positive result makes it positive" adjudication for the ground truth definition. There is no explicit mention of an adjudication panel (e.g., 2+1, 3+1) for cases of disagreement between cytology and pathology results, or for disagreements among multiple readers of the ground truth modalities.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted. This device is a molecular diagnostic test (in-vitro diagnostic) and not an imaging AI device that assists human readers. Therefore, the concept of human readers improving with AI vs. without AI assistance does not apply in this context. The comparison was between the Bladder EpiCheck test result and clinical ground truth (cytology/pathology), and between Bladder EpiCheck test results and the predicate device's test results.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance Study

Yes, the device's performance, as reported in the "Method Comparison" section, is a standalone (algorithm only without human-in-the-loop) performance. The Bladder EpiCheck Kit provides a qualitative result (positive/negative) based on its algorithm (EpiScore), and this result is compared directly to the established Gold Standard.

7. Type of Ground Truth Used

The primary ground truth used for the clinical performance study consisted of:

• Combined Cystoscopy/Pathology data: This is the gold standard for definitive diagnosis of bladder cancer recurrence.
• Clinical Cytology: Urine cytology was also part of the Gold Standard definition.

Therefore, the ground truth is a combination of pathology (histopathological examination of biopsy/resection specimens) and outcomes data (clinical diagnosis via cystoscopy, supplemented by cytology).

8. Sample Size for the Training Set

The document refers to "Clinical Cutoff (Training and Feasibility Data)" in section 9.1.

• Total for software algorithm development: 178 samples.
• First set (for cut-off definition): 109 samples (40 control, 69 UCC positive).
• Second set (for cut-off validation): 67 samples (51 control, 16 UCC positive).

It's important to note that this "training" refers to the development and validation of the EpiScore algorithm's cutoff, not necessarily a machine learning training set in the AI sense.

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

For the "training" set (used for algorithm development and cutoff definition, section 9.1), the ground truth was established by:

• "urine samples collected from control patients with a history of bladder cancer and bladder cancer positive patients confirmed by cystoscopy and pathology."
• "Urothelial Cell Carcinoma (UCC) positive patients confirmed by pathology."

Similar to the test set, the ground truth for algorithm development was based on definitive clinical diagnosis and pathological confirmation.

Ask a specific question about this device

The UroVysion Bladder Cancer Recurrence Kit (UroVysion Kit) is designed to detect aneuploidy for chromosomes 3, 7, 17, and loss of the 9p21 locus via fluorescence in situ hybridization (FISH) in urine specimens from subjects with transitional cell carcinoma of the bladder. Results from the UroVysion Kit are intended for use as a noninvasive method for monitoring for tumor recurrence in conjunction with cystoscopy in patients previously diagnosed with bladder cancer.

The UroVysion Kit is based upon fluorescence in situ hybridization (FISH) DNA probe technology. The UroVysion probes are fluorescently labeled nucleic acid probes for use in in situ hybridization assays on urine specimens fixed on slides. The UroVysion Kit consists of a 4-color, four-probe mixture of DNA probe sequences homologous to specific regions on chromosomes 3, 7, 9, and 17. The UroVysion probe mixture consists of Chromosome Enumeration Probe (CEP®) 3 SpectrumRed™, CEP 7 SpectrumGreen™, CEP 17 SpectrumAqua™ and Locus Specific Identifier (LSI®) 9p21 SpectrumGold™.

Here's an analysis of the acceptance criteria and the study that proves the UroVysion Bladder Cancer Recurrence Kit meets those criteria, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state quantitative acceptance criteria in a dedicated section. However, based on the "Substantial Equivalence vs. BTAstat Test" section, the key performance metric for substantial equivalence appears to be that the 95% Confidence Intervals (CIs) for UroVysion's agreement percentages (positive, negative, and overall) are greater than the BTAstat test's scores minus 15%.

For other aspects, the "acceptance criteria" are implied by the reported performance deemed satisfactory for marketing authorization.

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

• Specificity Study (Non-cancer patients):
  • Sample Size: 315 patient visits initially, resulting in 309 usable office visits and ultimately 275 unique patients yielding informative results. The data points used for specificity calculation totaled 357 (some patients had multiple conditions).
  • Data Provenance: Multi-center, prospective study. Patients were "healthy volunteers and urology patients without prior history or clinical evidence of bladder cancer." (implicitly from the US, given FDA submission context).
• Performance vs. Standard of Care (Bladder cancer recurrence monitoring):
  • Sample Size: 309 patient visits initially, resulting in 251 usable office visits and 176 unique patients with informative FISH results.
  • Data Provenance: Multi-center, prospective, longitudinal study. Patients had a "history of bladder cancer." (implicitly from the US, given FDA submission context).
• Reproducibility: 4 specimens from bladder carcinoma cell lines.
• Interference/Preservative: Three voided urine pools from normal healthy volunteers, spiked with various substances.

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

The document does not explicitly state the number of experts used to establish the ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience").

• For the Performance vs. Standard of Care study, the comparative reference was "cystoscopy followed by histology." Histology is typically interpreted by pathologists. The document mentions "central pathologist" in the longitudinal study details (Page 18), but doesn't specify how many or their experience level.

4. Adjudication Method for the Test Set

The document does not explicitly detail an adjudication method (e.g., 2+1, 3+1) for the ground truth establishment.

• For the "Performance vs. Standard of Care" study:
  • "The comparative reference used for all percent agreement calculations was cystoscopy with histology confirmation for positive or suspicious cystoscopies."
  • "If a patient had a positive cystoscopy but histology was absent (e.g., the lesion was fulgurated), then the specimen was considered positive for bladder cancer."
  • "If a test had a suspicious cystoscopy but histology was absent, then the case was omitted from analysis."
    This indicates a defined hierarchy and decision rule for establishing the ground truth (cystoscopy + histology).

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

A MRMC study was not explicitly done comparing human readers with and without AI assistance, because the device is a Fluorescence in situ hybridization (FISH) DNA probe technology, not an AI-assisted diagnostic tool.

However, the study did compare the UroVysion Kit's performance to two other human-interpreted methods:

• BTAstat test (lateral flow assay, antigen-specific antibodies, qualitative interpretation)
• Cytology (visual interpretation of cells)

The study demonstrated the superiority of the UroVysion Kit over BTAstat and cytology, particularly in agreement of positive results across various tumor stages and grades. For example:

• Overall Agreement of (+) Results:
  • UroVysion: 71.0%
  • BTAstat: 50.0%
  • Cytology: 26.2%
• For patients treated with BCG:
  • UroVysion: 92.3%
  • BTAstat: 69.2%
  • Cytology: 30.8%

The basis for substantial equivalence was to demonstrate that the UroVysion Kit's 95% CIs for agreement were greater than the BTAstat test's score minus 15%, which it met across positive, negative, and overall agreement categories. This showcases a significant effectiveness improvement compared to a legally marketed predicate directly by the device itself, rather than human readers improving with AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The UroVysion Kit is a FISH assay that involves human visual interpretation by an analyst to recognize fluorescent signals. Therefore, its performance is inherently human-in-the-loop, and a standalone (algorithm only) performance study, in the context of AI, is not applicable. The detection relies on DNA probes and fluorescence, with an analyst visually counting signals, rather than an automated algorithm making the final call.

7. Type of Ground Truth Used

• Specificity Study: Ground truth was "healthy volunteers and urology patients without prior history or clinical evidence of bladder cancer."
• Performance vs. Standard of Care Study: Ground truth for bladder cancer recurrence was established by cystoscopy followed by histology confirmation. If cystoscopy was positive but histology was absent (e.g., lesion fulgurated), it was considered positive. Suspicious cystoscopies without histology were omitted. This can be categorized as a form of clinical outcome/pathology-confirmed diagnosis.
• Reproducibility and Analytical Specificity: Used cultured human bladder carcinoma cell lines (positive target) and normal lymphoblast cell lines (negative target), and metaphase spreads for structural analysis.

8. Sample Size for the Training Set

The document describes premarket clinical studies and does not refer to a "training set" in the context of machine learning. The studies are for device validation.

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

As there is no mention of a "training set" for an AI algorithm, this question is not applicable to the provided document. The studies describe validation of a diagnostic kit based on established biological principles (FISH technology).

Ask a specific question about this device

The NMP22 BladderChek Test is indicated for professional and prescription home use as an aid in monitoring bladder cancer patients, in conjunction with standard diagnostic procedures.

The NMP22 BladderChek Test for nuclear matrix protein NMP22 is an immunochromatographic assay utilizing monoclonal antibodies in a lateral flow strip encased in plastic. Two different antibodies are used, one as a capture and one as a reporter antibody. Unprocessed patient urine is added to the sample well of the cartridge and allowed to react with the colloidal gold conjugated reporter antibody. If the antigen is present in urine, it will interact with the reporter conjugate to form an immune complex. The reaction mixture flows through the membrane, which contains zones of immobilized antibodies. In the Test (T) zone, antigen-conjugate complexes are trapped by the capture antibody, forming a visible line if the concentration of antigen in urine is elevated. The procedural Control (C) zone contains an immobilized goat anti-mouse IgG-specific antibody that will capture the conjugated antibody independently of the presence or absence of the antigen, thereby always producing a visible line in the Control window. This procedural control assures the operator that each device is working properly.

Here's a summary of the acceptance criteria and study details for the NMP22 BladderChek™ Kit, based on the provided text:

1. Acceptance Criteria and Reported Device Performance

Although explicit "acceptance criteria" (numerical thresholds that must be met for approval) are not directly stated in the summary, the overall performance goals are implied by successful demonstration of substantial equivalence to the predicate device and satisfactory clinical performance. The table below presents the clinical performance metrics reported for the NMP22 BladderChek™ Test and, for comparison, the predicate device.

Summary of the Study Proving Acceptance Criteria:

The device's performance was evaluated through non-clinical and clinical studies to demonstrate substantial equivalence to the predicate device, BTA Stat.

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

• Clinical Test Set:

  • Sample Size: 668 patients.
  • Data Provenance: Prospective clinical trial conducted at 23 sites. The country of origin is not explicitly stated but implied to be the US given the submission to the FDA.

• Non-Clinical Test Set (Reproducibility by Laboratory Technicians):

  • Sample Size: 150 individual reads per panel level (3 readers x 10 devices per panel x 5 days) for 4 NMP22 levels (0, 5, 15, 25 U/mL). Total 600 reads per lot. Experiment conducted on three separate lots, so 1800 total unique device reads.
  • Data Provenance: Not specified, but likely internal lab studies.

• Non-Clinical Test Set (Reproducibility by Lay Users Compared to Professional Readers):

  • Sample Size: 5 lay readers (10 results per level) and 2 professional readers (10 results per level) for a three-level precision panel (2, 10, 15 U/mL). In total, 50 lay user results and 20 professional reader results.
  • Data Provenance: Not specified, but likely internal lab studies.

• Non-Clinical Test Set (Performance of Lay Users Compared to Professionals – Field Studies):

  • Sample Size: 137 volunteers (aged 50+), across 3 sites.
  • Data Provenance: Field studies at three unspecified locations.

• Non-Clinical Test Set (Concordance of NMP22 BladderChek and NMP22 Test Kit (microplate)):

  • Sample Size: 217 voided urine samples.
  • Data Provenance: Urology clinics.

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

• Clinical Test Set:

  • Number of Experts: Not explicitly stated, but the ground truth for bladder cancer status was determined by physicians conducting cystoscopies and subsequent pathological examination of resected lesions. These are highly qualified medical professionals (e.g., urologists and pathologists).
  • Qualifications: "Physicians conducting the cystoscopies" and "pathologically determined to be malignant."

• Non-Clinical Test Set (Reproducibility):

  • Laboratory Technicians: 3 laboratory technicians. Qualifications not specified, but implied to be trained in laboratory procedures.
  • Professional Readers (Lay User Reproducibility): 2 professional readers. Qualifications not specified.

4. Adjudication Method for the Test Set:

• Clinical Test Set: The primary ground truth was established by cystoscopy findings, confirmed by pathology for resected lesions. Physicians were blinded to the device results, suggesting an independent assessment of ground truth. There is no mention of a specific adjudication method (like 2+1 or 3+1) among multiple experts for establishing the cancer status itself, rather it relies on standard medical diagnostic procedures.

• Non-Clinical Test Set (Reproducibility):

  • For the lab technician reproducibility, the ground truth was based on the known NMP22 concentration of the prepared specimen panels (0, 5, 15, 25 U/mL).
  • For lay user vs. professional reproducibility, the ground truth was based on the known NMP22 concentration of the prepared samples (2, 10, 15 U/mL). Concordance was measured between readers rather than against an external adjudicator.

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

• No specific MRMC comparative effectiveness study was mentioned comparing human readers with and without AI assistance (as the device is a diagnostic kit, not an AI).
• However, the study did involve a comparison of lay users vs. professional readers using the device, which is a form of multi-reader evaluation. There was 100% concordance between lay and professional readers on precision panels and high concordance (95.6% - 96.4%) in field studies for real urine samples, indicating that the device design allows for consistent interpretation across different user types.

6. Standalone Performance:

• Yes, a standalone performance study was done. The entire clinical study assessed the performance of the NMP22 BladderChek™ Test alone (algorithm/device only, without human-in-the-loop assistance influencing the result) against the cystoscopy/pathology ground truth. The reported sensitivity, specificity, PPV, and NPV are all measures of this standalone performance.

7. Type of Ground Truth Used:

• Clinical Test Set: The ground truth was based on cystoscopy findings, with confirmation by pathology for malignant lesions. "Patients were considered negative if no tumor was seen endoscopically, or, if a lesion was seen, was pathologically determined to be nonmalignant. Patients were considered positive for bladder cancer if a tumor was seen during cystoscopy, and, if removed was pathologically determined to be malignant." This is a combination of observational medical findings and definitive pathological diagnosis.

• Non-Clinical Test Set (Reproducibility): The ground truth was based on known concentrations of NMP22 in prepared urine specimens.

8. Sample Size for the Training Set:

• Not explicitly stated. The submission describes validation studies but does not detail a separate training set size for the development of the device itself (e.g., for antibody selection or cut-off determination). This is typical for a diagnostic kit where the "training" (e.g., cut-off determination) often happens during product development and optimization, rather than a distinct "training set" in the context of an AI algorithm.

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

• Not explicitly detailed as a distinct training set is not explicitly mentioned. For the development and optimization of such a diagnostic device (e.g., determining the NMP22 threshold for a positive result like 10 U/mL mentioned in the microplate comparison), ground truth would typically be established similarly to the clinical test set: using urine samples from known bladder cancer patients and healthy controls, confirmed by established diagnostic methods like cystoscopy and pathology. The 10 U/mL cutoff for the NMP22 microplate test is stated, implying that this was an established threshold for a positive result.

Ask a specific question about this device

The UroVysion Bladder Cancer Recurrence Kit (UroVysion Kit) is designed to detect aneuploidy for chromosomes 3, 7, 17, and loss of the 9p21 locus via fluorescence in situ hybridization (FISH) in urine specimens from subjects with transitional cell carcinoma of the bladder. Results from the UroVysion Kit are intended for use as a noninvasive method for monitoring for turnor recurrence in conjunction with cystoscopy in patients previously diagnosed with bladder cancer.

The UroVysion Kit is based upon fluorescence in situ hybridization (FISH) DNA probe technology. The UroVysion probes are fluorescently labeled nucleic acid probes for use in in situ hybridization assays on urine specimens fixed on slides. . The UroVysion Kit consists of a 4-color, four-probe mixture of DNA probe sequences homologous to specific regions on chromosomes 3, 7, 9, and 17. The UroVysion probe mixture consists of Chromosome Enumeration Probe (CEP®) 3 SpectrumRed™, CEP 7 SpectrumGreen™, CEP 17 SpectrumAqua™, and Locus Specific Identifier (LSI®) 9p21 SpectrumGold TM .

The UroVysion Bladder Cancer Recurrence Kit is intended for use as a noninvasive method for monitoring for tumor recurrence in conjunction with cystoscopy in patients previously diagnosed with bladder cancer. The study demonstrated that the device is substantially equivalent to the predicate device, the Bard® (Bion) BTAstat™ Test, and meets the acceptance criteria for specificity and performance compared to the standard of care (cystoscopy/histology).

Acceptance Criteria and Reported Device Performance

Study Information

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

   • Specificity Study: 309 usable office visits (resulting in 357 data points due to patients having multiple conditions) from healthy volunteers and urology patients without a prior history or clinical evidence of bladder cancer. This was a multi-center, prospective study. The country of origin is not explicitly stated but implies US clinical sites due to FDA submission.
   • Performance vs. Standard of Care Study: 251 usable office visits (representing 176 unique patients) from patients with a history of bladder cancer. This was a multi-center, prospective, longitudinal study conducted at 21 investigation sites. The country of origin is not explicitly stated but implies US clinical sites.
   • Reproducibility (Cell Lines): 80 specimens prepared from human bladder carcinoma cell lines.
   • Interference Study: Three voided urine pools from normal healthy volunteers, spiked with 29 different substances.
   • HYBrite/VP 2000 Validation: Three human urine pools from normal donors.

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

   • The document implies that the "standard of care" (cystoscopy with histology confirmation) was the ground truth. While no specific number of experts is given for the histological analysis, it is implicitly performed by qualified pathologists, which is standard practice for histology confirmation. No specific qualifications (e.g., 10 years of experience) are provided for these pathologists.

3. Adjudication method for the test set:

   • For the "Performance vs. Standard of Care" study, the comparative reference for all percent agreement calculations was cystoscopy with histology confirmation for positive or suspicious cystoscopies.
   • If a patient had a positive cystoscopy but histology was absent (e.g., lesion fulgurated), the specimen was considered positive for bladder cancer.
   • If a test had a suspicious cystoscopy but histology was absent, the case was omitted from analysis.
   • This indicates a hierarchical adjudication or ground truth definition rather than a consensus among multiple readers of the test device's results.

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:

   • No MRMC comparative effectiveness study involving human readers and AI assistance was conducted. The device is a diagnostic kit (FISH probes), and its interpretation relies on visual recognition by an analyst. The studies compare the UroVysion kit's performance against the standard of care (cystoscopy/histology) and the predicate device (BTAstat), and there is no mention of AI.

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

   • The UroVysion Kit requires visual analysis by an analyst to recognize fluorescent signals on chromosomes. Therefore, this is not a standalone algorithm-only device. The "analyst visually recognizes chromosomes" (page 1) indicating human-in-the-loop performance.

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

   • Pathology/Outcomes Data: The primary ground truth for the "Performance vs. Standard of Care" study was cystoscopy with histology confirmation. For cases where biopsy was not performed but cystoscopy was positive, it was still considered positive. The longitudinal study also used recurrence confirmed by cystoscopy/histology as an outcome.

7. The sample size for the training set:

   • The document does not explicitly describe a "training set" in the context of machine learning. The studies described are for validation/testing of the UroVysion Kit itself. The device is a FISH-based diagnostic kit, not an AI/ML algorithm that undergoes a distinct training phase with a labeled dataset. Its "training" would align more with its development and optimization, rather than a quantifiable dataset used for algorithm training.

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

   • As there is no explicit "training set" for an AI/ML algorithm described, this question is not directly applicable. The performance of the UroVysion Kit itself (hybridization efficiency, specificity, etc.) was established through laboratory tests and clinical studies, where outcomes like histology served as the reference standard.

Ask a specific question about this device

Ask a specific question about this device

The BTA stat test is indicated for use as an aid in the management of bladder cancer patients in conjunction with cystoscopy. This 510(k) is to expand the same indication to prescription home use of the product. The original 510(k) was K964151.

The BTA stat test for bladder tumor associated antigen is an immunochromatographic assay utilizing monoclonal antibodies to specifically detect the presence of bladder tumor associated antigen in urine. Patient urine is added to the sample well and allowed to react with a colloidal gold-conjugated antibody. If the antigen is present in the sample, an antigen conjugate complex is formed and a line in the patient (P) test zone appears.

Here's a breakdown of the acceptance criteria and study information for the BTA stat Test, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Study 1 (Comparison of Lay-persons vs. Laboratorians): Not explicitly stated, but implies multiple sites and "professional lay-persons."
• Study 2 (Home User Performance): Not explicitly stated, but refers to "persons with a previous diagnosis of bladder cancer" and "bladder cancer patients."
• Data Provenance: Not explicitly stated, but the submission is for the BTA Stat Test which is manufactured by Bion Diagnostic Sciences, Inc. in Redmond, WA. The studies were likely conducted in the US. The studies are prospective in nature, as they evaluate user performance.

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

The concept of "ground truth" as it relates to expert consensus on clinical findings (like interpreting medical images) is not directly applicable here. This device detects a "bladder tumor associated antigen" in urine. The studies are evaluating the user's ability to perform and interpret the test correctly, rather than the test's diagnostic accuracy against a clinical ground truth.

For Study 1, "laboratorians" would be considered the expert standard for performing the test. Their qualifications are not explicitly stated, but it's implied they are trained laboratory professionals.

For Study 2, the ground truth relates to the correct performance and interpretation of the immunoassay by the home user.

4. Adjudication Method for the Test Set

Not applicable in the traditional sense. The studies focused on whether users could correctly perform and read the test, implying a comparison against an objective result (e.g., presence or absence of a line on the test strip) or against results obtained by trained laboratorians. There's no mention of a
multi-expert adjudication process for the test results themselves.

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 BTA stat Test is an immunoassay, not an AI-powered diagnostic device requiring human interpretation in the context of images. The studies evaluate user performance with the device itself, not human performance with or without AI assistance.

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

This is not applicable. The BTA stat Test is an immunoassay designed to be used by humans (either laboratorians or home users), who then interpret the visible result (a line on the test strip). There is no "algorithm only" component.

7. The Type of Ground Truth Used

As mentioned in point 3, the "ground truth" in these studies is the correct performance and interpretation of the BTA stat immunoassay.

• For Study 1, the ground truth for test performance was likely established by the "accuracy and repeatability" achieved by trained laboratorians.
• For Study 2, the ground truth for test performance and interpretation was established by comparing home user results to what the test should objectively show, likely based on known samples or comparison to laboratorian results from Study 1. The study also assessed comprehension of the "Instructions for Home Use," where correct comprehension would be the ground truth.

8. The Sample Size for the Training Set

The provided text does not mention a "training set" in the context of machine learning. The studies described are performance studies for the device and user's ability to operate it.

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

Not applicable, as there is no mention of a training set for machine learning.

Ask a specific question about this device

The Bard BTA TRAK Test is an in vitro diagnostic assay indicated for the quantitative detection of bladder tumor associated antigen in human urine. This test is intended for use as an aid in management of bladder cancer patients in conjuction with cystoscopy.

The BTA TRAK test for bladder tumor associated antigen is an enzyme immunoassay utilizing monoclonal antibodies to specifically detect the presence of bladder tumor associated antigen in urine.

Here's a breakdown of the acceptance criteria and the study details for the Bard BTA TRAK™ Test, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The 510(k) summary does not explicitly state pre-defined "acceptance criteria" in terms of specific performance thresholds that the device had to meet to be considered effective. Instead, it presents the device's sensitivity results (performance data) and claims substantial equivalence to predicate devices. The implicit acceptance criteria are that the device demonstrates comparable or acceptable sensitivity for detecting bladder cancer, stratified by stage and grade, and acceptable specificity across various disease states.

Here's the reported performance:

BTA TRAK Test Sensitivity by Stage and Grade

Specificity Results of the Bard BTA TRAK test by Disease State (Mean - U/mL)

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

• Sensitivity Test Set:
  • Sample Size: 220 patients with biopsy-proven bladder tumors.
  • Data Provenance: Samples were "collected from diverse geographic locations" and stored frozen until tested. It does not explicitly state if it was retrospective or prospective, but the description of biopsy-proven cases and prior collection suggests a retrospective or a pre-collected cohort analysis.
• Specificity Test Set:
  • Sample Size:
    • Healthy Subjects: 212
    • Non-Genitourinary Benign Diseases: 52
    • Various Genitourinary Diseases: 26 (BPH), 32 (Benign Renal), 94 (Misc. GU), 30 (UTI/Cystitis), 24 (STD), 40 (Other)
    • Genitourinary Trauma: 54
    • Various Genitourinary Cancers (excluding active bladder cancer): 45 (Prostate), 7 (Renal), 25 (Other)
    • No Evidence of Disease (history of bladder cancer): 107
  • Data Provenance: Not explicitly stated, but similar to the sensitivity set, the nature of disease states suggests collected samples rather than a real-time prospective study for this broad specificity analysis.

3. Number of Experts and Qualifications for Ground Truth

The summary states that the sensitivity results were determined using "biopsy proven bladder tumors." This implies that the ground truth for bladder cancer presence and its stage/grade was established through histopathological examination by medical professionals (pathologists). The number of pathologists or their specific qualifications (e.g., years of experience) are not provided.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for establishing the ground truth. The sole mention of "biopsy proven" suggests that a single, definitive pathological diagnosis was considered sufficient for ground truth.

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

No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned. This study focuses on the standalone performance of the BTA TRAK test as an aid in management, rather than evaluating its impact on human reader performance with or without AI assistance.

6. Standalone Performance

Yes, a standalone (algorithm only) performance study was performed. The data presented in the tables (Sensitivity and Specificity) represent the direct output and performance of the BTA TRAK test itself, without human intervention in interpreting the test result as part of a diagnostic pathway. The intended use as an "aid in management... in conjunction with cystoscopy" highlights its role as a standalone diagnostic tool whose results are then considered by clinicians.

7. Type of Ground Truth Used

The primary ground truth for the presence and characteristics of bladder cancer was pathology (specifically, "biopsy proven bladder tumors" and "biopsy" for those with no evidence of disease if applicable). For other conditions mentioned in the specificity section (e.g., BPH, UTI, other cancers), the ground truth would likely be based on standard clinical diagnosis, imaging, and/or other laboratory tests.

8. Sample Size for the Training Set

The document does not provide any information about a training set or its sample size. This type of regulatory submission (510(k)) for an in vitro diagnostic device often focuses on verification and validation data from a pre-defined test set, rather than detailing the development (training) phase of the assay. For an immunoassay, the "training" would involve assay development and optimization rather than machine learning model training.

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

Since no training set details are provided, the method for establishing its ground truth is also not mentioned.

Ask a specific question about this device

AuraTek FDP is a rapid one-step gold dye particle lateral flow immunoassay indicated for the in vitro qualitative measurement of fibringen and fibrinogen degradation products (FDP) in human urine, to be used with standard cystoscopic examination to aid in the management of patients with a history of bladder cancer.

AuraTek FDP is a one-step gold dye particle immunoassay on a porous carrier. Mobile purple-red dye particles labeled with anti-FDP and fibrinogen antibody and immobile capture anti-FDP and fibringgen antibodies are coated as discrete zones on the porous carrier. In addition a test control zone with antimurine IgG (Reaction Control 2) is coated on the carrier. A sample placed on the device is absorbed by the porous carrier. The rehydrated colored sol particles move through the porous carrier to the capture anti-FDP and then to the anti-murine IgG. If the sample contains FDP and/or fibrinogen, the antibodylabeled sol particles will bind in a sandwich-type reaction to the capture anti-FDP and fibrinogen antibody producing a purple-red dot in the test result window. With a negative sample, the white test result window remains unchanged at the time of reading. AuraTek FDP has the unique feature that the test run validity is double-checked with the appearance and disappearance of color in the Reaction Control 1 window and development of a purple-red dot in the Reaction Control 2 window.

Here's a breakdown of the acceptance criteria and the study details for the AuraTek FDP device, based on the provided document:

Acceptance Criteria and Device Performance

The acceptance criteria are not explicitly stated as distinct thresholds in the document. Instead, the device's performance is presented in comparison to existing methods (cytology and hemoglobin dipstick) and against general clinical expectations for accuracy in bladder cancer monitoring. The key performance metrics are Sensitivity and Specificity.

Here's a table summarizing the reported device performance and implicitly, the targets it aims to meet or exceed:

Study Details

2. Sample Size and Data Provenance

• Test Set Sample Size:
  • Clinical Sensitivity Study: 192 patients with a history of bladder cancer undergoing cystoscopic examination.
    • 79 patients with confirmed bladder tumors (positive cystoscopy with confirmatory biopsy).
    • 113 patients with negative cystoscopy results (used for specificity analysis).
  • Specificity Study (Healthy Subjects): 73 healthy subjects.
  • Specificity Study (Non-Bladder Cancer Urological Disease): 232 subjects with various non-bladder cancer urological diseases.
• Data Provenance: The study was a "multi-center study" involving "a general urology practice." While specific countries are not mentioned, the context of a 510(k) submission to the FDA suggests the data would be primarily from the United States. The study is prospective as it involved patients "undergoing cystoscopic examination," implying data collection at the time of follow-up.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Not explicitly stated.
• Qualifications of Experts: The ground truth for bladder cancer confirmation was established by positive cystoscopy results with confirmatory biopsy. This implies a pathologist would be involved in interpreting the biopsy and a urologist in performing the cystoscopy. Specific years of experience are not mentioned, but these are standard clinical practices performed by qualified medical professionals.

4. Adjudication Method

• The document implies that the ground truth for cancer diagnosis was established by confirmatory biopsy following cystoscopy. This is a definitive diagnostic method, not typically requiring additional adjudication among experts in the same way imaging interpretations might. The mention of "positive cystoscopy results with confirmatory biopsy" suggests a definitive, pathological diagnosis. Therefore, a specific adjudication method (like 2+1 or 3+1) among multiple readers of the same data type isn't detailed, as the biopsy serves as the ultimate diagnostic confirmation.

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

• No, a MRMC comparative effectiveness study was not done in the context of human readers improving with AI vs. without AI assistance.
• The study compares the performance of the AuraTek FDP device to standard clinical methods (cytology and hemoglobin dipstick) directly, not as an AI-assisted tool for human readers. It's a standalone device performance study.

6. Standalone Performance Study

• Yes, a standalone (algorithm only without human-in-the-loop performance) study was done. The entire "Summary of Studies" section (1.7) details the performance of the AuraTek FDP device in isolation, evaluating its sensitivity, specificity, reproducibility, high dose hook effect, and interference from various substances. The reported sensitivity and specificity values are for the device itself.

7. Type of Ground Truth Used

• The primary ground truth for the presence of bladder cancer in the clinical sensitivity study was Pathology (confirmatory biopsy following positive cystoscopy).
• For the specificity analyses, ground truth was derived from "healthy subjects," "cystoscopy negative patients with a history of bladder cancer," and patients diagnosed with "non-bladder cancer urological disease" (presumably confirmed by standard clinical diagnostic procedures relevant to their conditions).

8. Sample Size for the Training Set

• Not applicable / Not explicitly stated. This device is a rapid immunoassay (lateral flow immunoassay), not an AI/machine learning device that typically requires a large 'training set' in the conventional sense. The "training" of such a device involves optimization of its chemical and physical components (e.g., antibody concentrations, membrane properties) during its development, rather than a data-driven algorithmic training process. The document describes analytical validation and clinical performance studies, not an AI model's training phase.

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

• Not applicable. As explained in point 8, this is not an AI/machine learning device. Therefore, there isn't a "training set" with ground truth in the context of an algorithm learning from data. The device's performance is driven by its biological and chemical design (monoclonal antibodies, gold dye particles, etc.).

Ask a specific question about this device

The BTA stat test is an in vitro diagnostic immunoassay indicated for the qualitative detection of bladder turnor associated antigen in urine of persons diagnosed with bladder cancer. This test is indicated for use as an aid in the management of bladder cancer patients in conjunction with cystoscopy.

The BTA stat test is a qualitative test indicated for use as an aid in the management of bladder cancer patients in conjunction with cystoscopy.

The BTA stat test for bladder tumor associated antigen is an immunochromatographic assay utilizing monoclonal antibodies to specifically detect the presence of bladder tumor associated antigen in urine. Patient urine is added to the sample well and allowed to react with a colloidal gold-conjugated antibody. If the antigen is present in the sample, an antigen conjugate complex is formed and a line in the patient (P) test zone appears.

Here's a breakdown of the acceptance criteria and study information for the Bard BTA stat™ Test, based on the provided 510(k) summary:

Acceptance Criteria and Device Performance

The 510(k) summary for the Bard BTA stat™ Test does not explicitly state pre-defined acceptance criteria (e.g., "device must achieve X sensitivity and Y specificity"). Instead, it presents the device's performance metrics and implicitly asks the FDA to accept these results as substantially equivalent to the predicate device. The performance is primarily evaluated through clinical sensitivity and clinical specificity.

Study Details

Here's the breakdown of the study components:

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

   • Clinical Sensitivity:
     • Initial cohort: 220 patients with histologically confirmed bladder cancer.
     • Subset for comparison with Bard BTA test: 181 patients from the sensitivity cohort.
     • Subset for comparison with Voided Urine Cytology (VUC): 131 patients (with histologically confirmed bladder cancer).
     • Data Provenance: Samples were "collected from 5 different may and the no have you intelles. United States." (This phrasing is a bit ambiguous, but suggests multiple sites within the US, prospectively collected for the study). Samples were stored frozen (-80°C) until tested.
   • Clinical Specificity:
     • No history of bladder cancer cohort: 555 individuals.
     • History of bladder cancer - No Evidence of Disease cohort: 107 patients. This cohort's no evidence of disease was confirmed by cystoscopy and/or biopsy.
     • Data Provenance: Samples were "collected from 5 different may and the no have you intelles. United States." (as above). Stored frozen (-80°C).

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

   • The primary ground truth for clinical sensitivity was histological confirmation of bladder cancer. This implies that pathology reports from pathologists were used. The number of pathologists involved is not specified, but it's standard practice in clinical studies for a pathologist to confirm diagnosis.
   • For the "History of Bladder Cancer - No Evidence of Disease" specificity cohort, ground truth was established by cystoscopy and/or biopsy. The experts performing these procedures (e.g., urologists) and interpreting the results (e.g., pathologists for biopsies) are not explicitly quantified or qualified in this summary.

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

   • The summary does not explicitly mention an adjudication method for the final diagnosis (ground truth). The reliance on "histological confirmation" and "cystoscopy and/or biopsy" suggests that these established diagnostic methods served as the definitive ground truth, implying standard clinical practice for diagnosis rather than a specific multi-reader adjudication process for the test device interpretation. The device itself is a qualitative assay with a direct positive/negative result.

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:

   • No, an MRMC comparative effectiveness study involving human readers and AI assistance was not mentioned. This device is an in-vitro diagnostic (IVD) assay designed for direct interpretation (presence/absence of a line), not an AI-powered image analysis tool requiring human reader interpretation in comparison.

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

   • Yes, this entire study is a standalone performance evaluation of the Bard BTA stat™ Test as an algorithm/device only without a human-in-the-loop component for interpretation. The device provides a direct qualitative result (positive or negative based on line appearance).

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

   • Pathology: "Histological confirmation" was the primary ground truth for bladder cancer diagnosis (clinical sensitivity).
   • Clinical Outcomes/Procedures: "Cystoscopy and/or biopsy" confirmed "no evidence of disease" for defining part of the specificity cohort.

7. The sample size for the training set:

   • The document describes performance studies, which are equivalent to test set evaluations. It does not specify a separate training set for the development of the Bard BTA stat Test itself. This is typical for IVD devices where the analytic and clinical performance are assessed once the device's formulation and design are finalized. The device operates based on a fixed immunological reaction rather than a machine learning algorithm that requires a separate training phase.

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

   • As there's no mention of a separate "training set" for the device's development in the context of machine learning, this question isn't directly applicable. The device's "training" or development involved optimizing the immunochromatographic assay components, which would have been done using known positive and negative samples, but these are not described as a "training set" in the sense of a machine learning model.

Ask a specific question about this device