Search Results

The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Analyzer, is a qualitative and semiquantitative flocculation test for the detection of nontreponemal antibodies in human serum and plasma to aid in the diagnosis of syphilis. All reactive RPR test samples should be further tested with a treponemal test to determine serological evidence of syphilis infection. The test is intended to be used for in vitro diagnostic testing.

The ASI Evolution is an integrated digital particle analyzer designed to objectively interpret certain slide agglutination tests manufactured by Arlington Scientific. Inc. (ASI). The ASI Evolution fully automates the sample and reagent handling steps of the test procedure. Qualitative and semiquantitative tests are performed by laboratory professionals who use the ASI Evolution to provide standardized test interpretation using criteria that define reactive and nonreactive agglutination reactions.
The ASI Evolution employs a camera that uses light reflectance to create a highly sensitive and high-resolution image of the agglutination immunoassay. This image is then analyzed by the proprietary software algorithm to interpret the agglutination pattern.

The ASI Evolution further provides tools that enable the creation, storage, retrieval and transmittal of the test results.

The ASI Automated RPR Test for Syphilis reagents include the following:

CARBON ANTIGEN - 0.003% cardiolipin, 0.020-0.022% lecithin, 0.09% cholesterol, charcoal (activated) as visual enhancer, phosphate buffer, 0.1% sodium azide as preservative and stabilizers.

CONTROLS (REACTIVE, WEAK REACTIVE, NONREACTIVE) - Human serum or defibrinated plasma (liquid), with 0.1% sodium azide as preservative.

Reagents have two-year expiration dating from date of manufacture. The specific expiration date is located on the label on the vial.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

This submission is for a new algorithm for an existing device, the ASI Evolution Automated Syphilis Analyzer, used with the ASI Automated RPR Test for Syphilis. The study aims to demonstrate substantial equivalence of the new algorithm to the original algorithm. Therefore, the acceptance criteria and study design are geared towards showing comparable performance rather than de novo validation against a clinical gold standard.

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the goal of demonstrating substantial equivalence to the original algorithm. This means the new algorithm's performance (positive agreement and negative agreement) should be comparable to or better than the original algorithm's. While explicit numerical thresholds for acceptance are not stated for agreement, the 95% Confidence Intervals are provided, which typically are evaluated against a pre-defined acceptance range (e.g., lower bound of 90% for positive agreement). The reproducibility section demonstrates 100% agreement, which is a strong indicator of meeting a high standard for reproducibility.

Table of Acceptance Criteria (Implicit) and Reported Device Performance (Calculated from provided data)

Details of the Study Proving Device Meets Acceptance Criteria

1. Sample Sizes Used for the Test Set and Data Provenance:

• Retrospective Study Comparing Algorithms:
  • Serum Samples: 872 individual retrospective samples.
  • Plasma Samples: 890 individual retrospective samples.
  • Pregnant Women Testing: 280 samples (30 reactive, 250 nonreactive).
  • Total Samples for Algorithm Comparison: 872 (serum) + 890 (plasma) + 280 (pregnant women) = 2042 samples.
• Reproducibility Study:
  • 7 samples (2 nonreactive, 2 reactive 1:2, 1 reactive 1:4, 1 reactive 1:8, 1 reactive 1:16).
  • Each sample tested in duplicate within the panel, for 5 non-consecutive days, producing 60 data points per sample (60/60 reported). Total 7 samples x 60 data points = 420 data points.
• End-point Titer Testing:
  • 9 samples (2 nonreactive, 7 reactive with varying titers).
  • Each sample tested in 8 replicates on 10 different days, resulting in 80 data points for each sample. Total 9 samples x 80 data points = 720 data points.
• Data Provenance: Retrospective samples, with identifiers removed, collected from different Departments of Public Health Labs and Blood Banks. No specific country of origin is mentioned, but "U.S. Food & Drug Administration" implies U.S. data.

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

• For Algorithm Equivalence Study: The "ground truth" for the algorithm comparison study was the results interpreted by the original ASI Evolution algorithm (K173376 and K182391). This device was already cleared by the FDA, implying its outputs were considered reliable. No human experts were explicitly stated to establish ground truth for this direct comparison between two algorithms. However, for discordant results:
  • The 6 discordant serum results (new algorithm nonreactive, original algorithm reactive) were investigated and tested with a treponemal test and found to be reactive. This implies confirmation by an independent, more specific test, which is a common form of "ground truth" for syphilis diagnosis.
  • The 6 discordant plasma results (1 new reactive/original nonreactive, 5 new nonreactive/original reactive) were investigated. The new reactive/original nonreactive sample was tested with a treponemal test and found to be nonreactive. The 5 new nonreactive/original reactive samples were attributed to bubbles or artifacts in the test well. This also points to investigation and confirmation using a more definitive test or root cause analysis, serving as a form of expert adjudication or outcome-based truth.
• For Reproducibility and End-point Titer Testing: The "Expected Result" for these tests was established either by the manual interpretation method prior to testing (for end-point titer samples) or by the known characteristics of the control samples used. This implies laboratory or subject matter expert consensus or established reference values.

3. Adjudication Method for the Test Set:

• For the algorithm comparison (serum and plasma), discordant results between the new and original algorithms were investigated using a treponemal test (for biological confirmation) or attributed to technical issues (e.g., bubbles/artifacts). This serves as an adjudication method based on a more definitive test or root cause analysis.
• For the pregnant women testing, the comparison was made against the "ASI RPR Card Test for Syphilis on the ASiManager-AT Result," which acts as the reference.
• No explicit "2+1" or "3+1" human expert adjudication method was described as the primary ground truth establishment for the algorithm comparison, as the goal was algorithm-to-algorithm equivalence rather than algorithm-to-human.

4. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No, an MRMC comparative effectiveness study was not performed as the primary validation for this submission. The study focused on demonstrating substantial equivalence between two automated algorithms (new vs. original ASI Evolution algorithm), not on comparing human readers with and without AI assistance.
• Effect size of human readers improving with AI vs. without AI assistance: Not applicable to this study design.

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

• Yes, the core of the submission is a standalone performance study comparing the new algorithm's interpretation capabilities against the existing, cleared original algorithm on the same instrument. The "Performance Data" section explicitly states, "A comparison of the digital interpretation of the results from the ASI Evolution using the original interpretation algorithm... to establish substantial equivalence to the interpretation made by the ASI Evolution using the new interpretation algorithm was conducted."

6. The Type of Ground Truth Used:

• Algorithm vs. Algorithm (Predicate Device as Reference): The primary "ground truth" for the main algorithm comparison study was the output of the predicate device's algorithm (original ASI Evolution algorithm).
• Confirmatory Treponemal Test: For discrepant results in the algorithm comparison studies, a treponemal test was used as a more definitive clinical ground truth to resolve ambiguities.
• Manual Interpretation Methods / Known Reactivity: For reproducibility and end-point titer testing, the "expected result" was based on prior manual interpretation methods or known characteristics of control samples.
• No pathology or direct outcomes data was cited as the primary ground truth for the device clearance.

7. The Sample Size for the Training Set:

• Not specified in the provided document. The document describes a study comparing the new algorithm's performance against the old one (test set). It does not provide details about if or how the new algorithm itself was "trained" using specific data. Given the context of medical device clearance, it's presumed that the algorithm development (training, if any) would have occurred prior to this validation study.

8. How the Ground Truth for the Training Set was Established:

• Not specified in the provided document. As the training set details are not provided, neither is the method for establishing its ground truth.

Ask a specific question about this device

The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Syphilis Analyzer, is a qualitative and semi-quantitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis. All reactive RPR test samples should be further tested with a treponemal test. The ASI Automated RPR Test for Syphilis is for professional use only. The test is intended to be used for in vitro diagnostic testing and blood donor screening.

The ASI Evolution is intended to be used as a fully automated analyzer to objectively interpret the results of the ASI Automated RPR Test for Syphilis. The ASI Evolution is designed to provide standardized test interpretation and to provide for storage, retrieval, and transmittal of the test results. It is intended to be acquired, possessed and used only by health care professionals. The ASI Evolution analyzer, in conjunction with the ASI Automated RPR Test for Syphilis is intended to be used for in vitro diagnostic testing and blood donor screening.

The Automated RPR Test for Syphilis performed on the ASI Evolution is an automated nontreponemal flocculation test for the detection of reqain antibodies in human serum and plasma.

The ASI Evolution is an integrated digital particle analyzer designed to objectively interpret certain slide agglutination tests manufactured by Arlington Scientific, Inc. (ASI). The ASI Evolution fully automates the sample and reagent handling steps of the test procedure. Qualitative and semiquantitative tests are performed by laboratory professionals who use the ASI Evolution to provide standardized test interpretation using criteria that define reactive and nonreactive agglutination reactions.

The ASI Evolution employs a camera that uses light reflectance to create a highly sensitive and high-resolution image of the agglutination immunoassay. This image is then analyzed by the proprietary software algorithm to interpret the agglutination pattern.

The ASI Evolution further provides tools that enable the creation, storage, retrieval and transmittal of the test results.

The ASI Automated RPR Test for Syphilis reagents include the following:

CARBON ANTIGEN - 0.003% cardiolipin, 0.020-0.022% lecithin, 0.09% cholesterol, charcoal (activated) as visual enhancer, phosphate buffer, 0.1% sodium azide as preservative and stabilizers.

CONTROLS (REACTIVE, WEAK REACTIVE, NONREACTIVE) - Human serum or defibrinated plasma (liguid), with 0.1% sodium azide as preservative.

Reagents have two-year expiration dating from date of manufacture. The specific expiration date is located on the label on the vial.

The provided text describes the acceptance criteria and the study that proves the device meets those criteria for the ASI Automated RPR Test for Syphilis on the ASI Evolution, specifically focusing on the semi-quantitative claim for endpoint titer determination.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Description: A randomized and blinded panel of 10 human serum samples with known reagin antibody endpoint titers.
• Sample Size: Each of the 10 samples was tested a minimum of 80 times, for a total of 800 tests (10 samples * 80 tests/sample).
  • 2 of the 10 samples were non-reactive (total 160 non-reactive tests).
  • 8 of the 10 samples were reactive (total 640 reactive tests).
• Data Provenance: The tests were performed in-house on at least five different days by one operator using a single ASI Evolution instrument. The origin of the human serum samples themselves (e.g., country of origin) is not explicitly stated, but they are described as having "known reagin antibody endpoint titers." The study can be considered prospective as it involved testing pre-selected samples with the device to determine its performance against established ground truth.

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

• The ground truth for the 10 human serum samples (known reagin antibody endpoint titers) was "determined by the ASI RPR Card Test for Syphilis on the ASiManager-AT."
• The document does not explicitly state the number or qualifications of experts used to establish the ground truth via the ASI RPR Card Test on the ASiManager-AT. It implies that this was an established method of determining titers, rather than an expert consensus process for this specific study.

4. Adjudication Method for the Test Set

• None specified. The study setup describes the device's output being compared directly against the "known reagin antibody endpoint titers" established by the ASiManager-AT, implying a direct comparison rather than an adjudication process between human readers or the device.

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

• No. The provided text describes an analytical study evaluating the semi-quantitative performance (endpoint titer validation) of the automated system. It does not include an MRMC study comparing human reader performance with and without AI assistance for this specific indication.
• The document mentions "Clinical performance of the ASI Automated RPR Test for Syphilis on the ASI Evolution was evaluated under K173376," but focuses on overall qualitative detection rather than human reader AI assistance.

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

• Yes. The described study is a standalone performance evaluation of the ASI Evolution device itself, as it automates the interpretation of the RPR test. The device's proprietary software algorithm analyzes the image and interprets the agglutination pattern to report results (Reactive, Nonreactive, endpoint titers).

7. Type of Ground Truth Used

• The ground truth used was "known reagin antibody endpoint titers," which were "determined by the ASI RPR Card Test for Syphilis on the ASiManager-AT." This can be classified as a reference standard method (another established diagnostic test) rather than direct pathology or outcomes data from patients.

8. Sample Size for the Training Set

• The sample size for the training set is not specified in the provided text. The document describes pre-market validation for the analytical performance and refers to previous clinical performance evaluations (K173376) for qualitative detection. It does not provide details on the data used to train the proprietary software algorithm itself.

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

• As the training set size is not specified, how its ground truth was established is also not detailed in this document. It is implicitly understood that for an automated system, the training data would also require established ground truth to enable the algorithm to learn to interpret agglutination patterns, but the specifics are not provided here.

Ask a specific question about this device

The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Syphilis Analyzer, is a qualitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis. All reactive RPR test samples should be further tested with a treponemal test. The ASI Automated RPR Test for Syphilis for use on the ASI Evolution produces only a reactive or non-reactive result and does not report RPR titers for reactive samples. The ASI Automated RPR Test for Syphilis is for professional use only. The test is intended to be used for in vitro diagnostic testing. The ASI Evolution is intended to be used as a fully automated analyzer to objectively interpret the results of the ASI automated RPR test for syphilis. The ASI Evolution is designed to provide standardized test interpretation and to provide for storage, retrieval, and transmittal of the test results. It is intended to be acquired, possessed and used only by health care professionals. The ASI Evolution analyzer, in conjunction with the ASI Automated RPR Test is intended to be used for in vitro diagnostic testing. The ASI Automated RPR Test for Syphilis for use on the ASI Evolution produces only a reactive or non-reactive result and does not report RPR titers for reactive samples.

The ASI Evolution is an integrated digital particle analyzer designed to objectively interpret certain slide agglutination tests manufactured by Arlington Scientific, Inc. (ASI). The ASI Evolution fully automates the sample and reagent handling steps of the test procedure. Qualitative tests are performed by laboratory professionals who use the ASI Evolution to provide standardized test interpretation using criteria that define reactive and nonreactive aqqlutination reactions. The ASI Evolution employs a camera that uses light reflectance to create a highly sensitive and high-resolution image of the agglutination immunoassay. This image is then analyzed by the proprietary software algorithm to interpret the agglutination pattern. The ASI Evolution further provides tools that enable the creation, storage, retrieval and transmittal of the test results. The ASI Automated RPR Test for Syphilis reagents include the following: CARBON ANTIGEN - 0.003% cardiolipin, 0.020-0.022% lecithin, 0.09% cholesterol, charcoal (activated) as visual enhancer, phosphate buffer, 0.1% sodium azide as preservative and stabilizers. CONTROLS (REACTIVE, WEAK REACTIVE, NONREACTIVE) - Human serum or defibrinated plasma (liquid), with 0.1% sodium azide as preservative. Reagents have two-year expiration dating from date of manufacture. The specific expiration date is located on the label on the vial.

This document describes the regulatory approval for the ASI Automated RPR Test for Syphilis ASI Evolution. The product is a qualitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma for syphilis screening. It is designed to be used with the ASI Evolution Automated Syphilis Analyzer, which objectively interprets test results as reactive or non-reactive.

Here is a summary of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the ASI Automated RPR Test for Syphilis ASI Evolution are based on demonstrating substantial equivalence to its predicate device, the ASI RPR Card Test for Syphilis on the ASiManager-AT. The key performance metrics are positive and negative agreement rates.

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

• Prospective Samples: 1,068 individual samples. Collected at two different Departments of Public Health Labs. Data provenance is prospective.
• Retrospective Serum Samples (Agreement Study): 10 individual samples. Collected from various reference labs and serum and plasma vendors from across the United States. Data provenance is retrospective.
• Retrospective Plasma Samples (Agreement Study): 1,003 individual samples. Collected from various reference labs and serum and plasma vendors from across the United States. Data provenance is retrospective.
• ASI Evolution Characterized Specimen Testing (Clinical Diagnosis): Total of 1,068 + 1,013 = 2,081 samples (Total samples from prospective and retrospective studies)
  • Prospective Random Samples:
    • Site a: 567 Serum samples (country not specified, likely US based on other descriptions)
    • Site b: 501 Serum samples (country not specified, likely US based on other descriptions)
  • Retrospective Samples:
    • Site c: 17 Known infected samples (serum & plasma, from across the United States)
    • Site c: 996 Known uninfected samples (serum & plasma, from across the United States)
    • Total Retrospective samples: 1013
• Performance with Samples from Pregnant Women: 250 non-reactive and 30 reactive samples from pregnant women. Serum samples. Country not specified, likely US.
• Precision Testing: 10 samples (3 nonreactive, 7 reactive at various titers), each tested 192 times (total 1920 tests).
• Reproducibility Testing (7 samples): 7 samples (2 nonreactive, 5 reactive at various titers), tested at 3 sites, each sample tested 180 times across various conditions (total 1260 tests).
• Reproducibility Testing (448 samples): 448 retrospective serum samples (48 nonreactive, 400 reactive), tested at 3 sites (total 1344 tests). Samples collected from various reference labs and serum and plasma vendors from across the United States.
• Cross Reactivity/Interfering Substances: 368 samples across various categories (e.g., ANA (+), HIV (+), pregnant women, etc.).
• Carry-Over: 48 aliquots per run (24 reactive, 24 nonreactive). Run over 5 days.
• On-board Stability Testing: 4 samples (1 nonreactive, 3 reactive at various titers), each run in triplicate morning and afternoon for 5 days by 2 operators (total 120 tests).
• Frozen vs. Refrigerated Testing: Total of 55 samples (20 non-reactive, 35 reactive at various titers) tested as both frozen and refrigerated.

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

The document does not explicitly state the "number of experts" or their "qualifications" for establishing the ground truth for the test set in the comparative studies.

• For the comparative studies against the ASiManager-AT, the predicate device's results (interpreted by "trained laboratory professionals") served as the reference. These professionals are implicitly qualified by their training to interpret RPR tests.
• For the "ASI Evolution Characterized Specimen Testing," the "Expected results are based on known clinical diagnosis." This implies that clinical experts (e.g., physicians, specialists) established the diagnosis, which then served as a proxy for ground truth.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method like 2+1 or 3+1. For the comparative studies, the results of the ASiManager-AT, interpreted by trained laboratory professionals, were considered the comparator. In cases of discrepancies or challenges, no specific adjudication process is detailed for these studies. For the Characterized Specimen Testing, the "known clinical diagnosis" itself serves as the ground truth, implying no further adjudication on the test results against the diagnosis.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, a traditional MRMC comparative effectiveness study, where multiple human readers interpret cases with and without AI assistance to measure improvement in human performance, was not performed. The study focused on the standalone performance of the ASI Evolution device compared to the predicate device (ASiManager-AT) and known clinical diagnoses. When human operators were involved (e.g., for ASiManager-AT interpretation), they were trained professionals, but the study did not measure their improvement with AI assistance.

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

Yes, the studies primarily assessed the standalone performance of the ASI Evolution. The device is described as a "fully automated analyzer to objectively interpret the results" of the RPR test. The comparison against the ASiManager-AT (which involves human interpretation of results) and known clinical diagnoses evaluates the ASI Evolution's direct output.

7. The Type of Ground Truth Used

The ground truth used varied:

• Comparative Studies: The results obtained from the predicate device, the ASI RPR Card Test for Syphilis on the ASiManager-AT, interpreted by trained laboratory professionals, served as the comparator/reference.
• Characterized Specimen Testing: "Known clinical diagnosis" was used as the ground truth. This implies diagnoses established by medical professionals through various clinical and laboratory indicators.
• Precision, Reproducibility, Cross-Reactivity, Carry-Over, On-board Stability, Frozen vs. Refrigerated Testing: Expected results for controls and characterized samples (e.g., "RPR nonreactive," "RPR reactive 1:1 titered samples") were used as the ground truth. These expected results are typically established during the characterization and manufacturing of the control materials themselves.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size used for the training set of the ASI Evolution's algorithm. It mentions that the "same proprietary interpretive algorithm used in the predicate device (ASiManager-AT) is used in the ASI Evolution." This suggests that the algorithm was developed and potentially trained using data prior to this submission, possibly with data collected for the ASiManager-AT validation. However, details of that training are not provided here.

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

As the document does not specify a training set for the ASI Evolution's algorithm, it also does not detail how the ground truth for such a set was established. Given the claim that the algorithm is the "same proprietary interpretive algorithm" as in the predicate device, it is likely that the ground truth for any initial algorithm development would have been established through expert human interpretation of RPR flocculation patterns over a large set of samples, potentially correlated with confirmatory treponemal tests or clinical diagnoses.

Ask a specific question about this device

The Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System is a non-treponemal flocculation test that can qualitatively determine the presence of reagin antibodies in human serum. It may be used to aid in the diagnosis of syphilis when used in conjunction with supplemental treponemal laboratory tests and other clinical information. This test may also be used to detect non-treponemal antibodies in samples serially diluted to establish titer information. This test is not intended for screening blood or tissue donors.

The Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System in a non-treponemal test for the qualitative determination of reagin antibodies in human serum to aid in the diagnosis of syphilis. This test is also used to detect non-treponemal antibodies in samples serially diluted to establish titer information. The system consists of the Gold Standard Diagnostics RPR test reagents and the Gold Standard Diagnostics AIX1000 Agglutination Analyzer. The AIX1000 Analyzer delivers serum from collection tubes into test wells. After antigen suspension is added, the test wells are then incubated while being shaken. An onboard camera creates a high resolution image. The image is then analyzed by the proprietary software algorithm to produce a result.

Here's an analysis of the acceptance criteria and the studies that prove the device meets these criteria, based on the provided text:

Device Name: Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System
K Number: K150358

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" in a bulleted or numbered list with predefined thresholds for all studies. However, performance expectations are implied by the nature of the tests conducted and the reported agreement percentages. I will interpret the reported performance metrics as demonstrating the device meets an implied acceptance for its intended use, particularly through comparison to a predicate device.

• Low RPR Reactivity (1:4): 100% agreement (93.6% - 100% C.I.)
• Moderately Reactive (1:16): 100% agreement (93.6% - 100% C.I.)
• Reactive (1:64): 97.8% agreement (88.2% - 99.9% C.I.)
• Highly Reactive (1:128): 100% agreement (93.6% - 100% C.I.)
• Reactive control: 100% agreement (54.9% - 100% C.I.)
• Non-reactive control: 100% agreement (54.9% - 100% C.I.) |
  | Reproducibility | High agreement (e.g., >90%) within ± 1 titer across operators, instruments, days, and runs. | - Non-Reactive Serum: 100% (Between-Runs, Between-Days, Between-Operators, Between-Instruments)
• Low RPR Reactivity (1:4): 100% (all categories)
• Moderately Reactive (1:16): 100% (all categories)
• Reactive (1:64): 100% (Between-Runs, Between-Operators, Between-Instruments), 97.8% (Between-Days)
• Highly Reactive (1:128): 100% (Between-Runs, Between-Days, Between-Instruments), 98.1% (Between-Operators)
• Reactive control: 100% (90.5% - 100% C.I.)
• Non-reactive control: 100% (90.5% - 100% C.I.) |
  | Carry-over | No evidence of carry-over (no false positives in negative samples due to highly reactive samples). | All 480 replicates of the negative samples were reported as non-reactive when highly reactive samples were alternated with non-reactive samples. |
  | Clinical Agreement (Prospective Samples vs. Predicate) | High Positive Percent Agreement (PPA) and Negative Percent Agreement (NPA) with predicate. | PPA: 95.5% (C.I. 77.2% - 99.9%)
  NPA: 99.9% (C.I. 99.3% - 100%) |
  | Clinical Agreement (Retrospective Samples vs. Predicate) | High PPA and NPA with predicate. | PPA: 97.2% (C.I. 95.5% - 98.4%)
  NPA: 99.1% (C.I. 98.5% - 99.5%) |
  | Special Populations (Pregnant Women vs. Predicate) | High PPA and NPA with predicate. | PPA: 100% (C.I. 90.5% - 100%)
  NPA: 100% (C.I. 98.8% - 100%) |
  | Special Populations (HIV Positive Individuals vs. Predicate) | High PPA and NPA with predicate. | PPA: 100% (C.I. 90.5% - 100%)
  NPA: 100% (C.I. 98.8% - 100%) |
  | Healthy Individuals | Low and expected reactivity in a healthy, no-risk population. | All 100 samples from apparently healthy individuals (not at risk, no syphilis test ordered) were non-reactive. |
  | Clinical Stages Correlation | High agreement with clinically diagnosed syphilis cases across various stages. | Primary Treated (13/13 reactive), Primary Untreated (12/12 reactive), Secondary Treated (25/25 reactive), Secondary Untreated (25/25 reactive), Latent Treated (25/25 reactive), Latent Untreated (25/25 reactive). All showed 100% agreement with corresponding 95% C.I. ranges of 77.9%-100% to 88.7%-100%. |

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

The document describes several test sets:

• Cross Reactivity: Panels of 10-16 individual patient samples per condition (totaling 17 conditions for viral, bacterial, and autoimmune).
• Interfering Substances: 5 samples (1 non-reactive, 4 reactive) per interfering substance.
• Precision: 5 samples (Non-reactive, Low RPR (1:4), Moderately Reactive (1:16), Reactive (1:64), Highly Reactive (1:128)). Each tested in 9 replicates.
• Reproducibility: The same 5 sample panels as precision, tested across 6 operators, 3 instruments, 2 runs over 5 days.
• Carry-over: 1 reactive (1:64), 1 highly reactive (1:128), and 2 non-reactive samples. Highly reactive samples alternated with non-reactive samples 96 times per run over 5 runs.
• Clinical Studies - Prospectively Collected Samples:
  • Sample Size: 765 serum samples.
  • Data Provenance: Collected prospectively from patient samples with a physician's order for syphilis testing. Collected at two geographically distinct reference laboratories (Southeastern and Western United States).
• Clinical Studies - Retrospectively Collected Samples:
  • Sample Size: 2,246 samples.
  • Data Provenance: Collected retrospectively from patients referred for syphilis testing. Obtained from sample brokers who collect from multiple sites across the United States. Collection dates: January 2005 - July 2014.
• Clinical Studies - Pregnant Women (Retrospective):
  • Sample Size: 250 non-reactive, 30 reactive (spiked) samples. Total 280.
  • Data Provenance: Retrospectively collected from pregnant women at one site (Southeastern United States). Collection dates: July 2012 - August 2013.
• Clinical Studies - HIV Positive Individuals (Retrospective):
  • Sample Size: 250 non-reactive, 30 reactive samples. Total 280.
  • Data Provenance: Retrospectively collected from HIV positive individuals at four sites (one Southeastern, one Mid-Western States). Collection dates: February 2012 - June 2015.
• Apparently Healthy Individuals (Prospective):
  • Sample Size: 100 serum samples.
  • Data Provenance: Prospectively collected from healthy individuals not at risk for syphilis and for whom a syphilis test had not been ordered (submitted for routine chemistry testing).
• Correlation with Clinically Diagnosed Syphilis Sera - Various Stages (Purchased Panel):
  • Sample Size: Primary Treated (13), Primary Untreated (12), Secondary Treated (25), Secondary Untreated (25), Latent Treated (25), Latent Untreated (25).
  • Data Provenance: Purchased from serum brokers, characterized by clinical diagnosis.

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

The document does not mention the use of human experts to establish ground truth for the test sets in the context of adjudication or interpretation of the RPR results. Instead, it relies on:

• Reference laboratory results (for prospective samples).
• Predicate device results (for comparison in clinical studies).
• FDA-cleared treponemal (TP) assays (for further investigation of discrepant non-treponemal results).
• Clinical diagnosis (for the purchased syphilis stage panel).
• Serum broker confirmation of disease markers (for cross-reactivity samples).

Therefore, there is no direct information on the number or qualifications of experts involved in establishing ground truth through manual interpretation of RPR images or similar tasks for the "AIX1000" aspect. The 'AI' component is described as proprietary software interpreting images (standalone).

4. Adjudication Method for the Test Set

Adjudication methods (like 2+1, 3+1) are typically used when multiple human readers interpret the same image/case and disagreements need to be resolved. This device is an automated test system for a flocculation assay where the "AIX1000 Agglutination Analyzer" uses a proprietary software algorithm to produce a result.

For the discrepancies in the clinical studies where the GSD AIX1000 RPR Test System disagreed with the comparator device:

• Prospective Samples: The two discrepant samples were tested on a "third FDA cleared RPR assay."
• Retrospective Samples: The 31 discrepant samples were tested on a "third FDA cleared RPR assay."

This suggests a form of tie-breaking or external reference testing for discrepant results, rather than a human expert adjudication of visual interpretations by the device itself.

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

No, an MRMC comparative effectiveness study was not conducted. The device is an automated test system that interprets RPR assay results without direct human intervention in the interpretation process described. The comparisons were between the automated device and a predicate automated device or clinical outcomes, not between human readers with and without AI assistance.

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

Yes, the studies reported represent standalone performance of the Gold Standard Diagnostics AIX1000 RPR Automated Test System. The device's proprietary software algorithm directly produces the results from images captured by its onboard camera. The clinical studies (prospective, retrospective, special populations) directly compare the device's output to a predicate device's output or clinical diagnosis, without human modification or override of the AIX1000's initial determination. The interpretation of the flocculation assay itself is automated.

7. The Type of Ground Truth Used

The ground truth or reference methods varied depending on the study:

• Clinical Studies (Prospective and Retrospective): The primary ground truth for comparison was the legally marketed predicate device (Arlington Scientific Inc. (ASI) RPR Card Test for syphilis on the ASiManager-AT Analyzer). For discrepant samples, a third FDA cleared RPR assay was used as a tie-breaker. Further investigation for NT+ samples used an FDA cleared treponemal (TP) assay.
• Correlation with Clinically Diagnosed Syphilis Sera: Clinical Diagnosis (Primary, Secondary, Latent stages as characterized by documented symptoms, dark field microscopy, and reactive treponemal/non-treponemal tests).
• Cross-Reactivity Study: Confirmation of disease markers by serum brokers.
• Special Populations (Pregnant Women, HIV Positive): Predicate device results, and also confirmed pregnancy status via HCG test and HIV positive status.
• Apparently Healthy Individuals: Lack of risk factors and no physician's order for syphilis testing defined this as "healthy."

8. The Sample Size for the Training Set

The document does not provide information on the sample size used for the training set for the proprietary software algorithm. This information is typically proprietary to the manufacturer and not usually detailed in 510(k) summaries unless specifically requested or deemed critical for substantial equivalence. The focus of the 510(k) is often on comparing the new device's performance to a predicate, rather than the internal development of its algorithm.

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

Similar to the training set size, the document does not provide information on how the ground truth for the training set was established. Since the device uses a "proprietary software algorithm" to analyze images for flocculation, it can be inferred that this algorithm was developed and trained using a collection of RPR test results with established reactivity and titer values. However, the specifics of this ground truth (e.g., expert consensus on visual flocculation, correlation with other assays) are not detailed in this submission.

Ask a specific question about this device

Ask a specific question about this device

Synthetic Venereal Disease Research Laboratory (VDRL) antigen is intended for use in the qualitative and quantitative VDRL slide tests for the detection of IgM and IgG nontreponemal antibodies in the serum or cerebrospinal fluid of persons with syphilis.

Synthetic VDRL Antigen

I am sorry, but the provided text is a letter from the FDA to Dr. Victoria Pope regarding the 510(k) clearance of the "Synthetic VDRL Antigen" device. It confirms the device's substantial equivalence to legally marketed predicate devices and outlines general regulatory obligations.

The document does not contain any information about acceptance criteria, device performance studies, sample sizes, ground truth establishment, or expert qualifications. Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based on the provided text.

Ask a specific question about this device

Avanti's VDRL antigen and Buffered Saline are intended for use in the Venereal Disease Research Laboratory (VDRL) slide test for syphilis. The VDRL slide test is a non-treponemal, micro-flocculation test, that provides both qualitative and semi-quantitative results. The test is for the detection of IgM and IgG anticardiolipin antibodies in serum specimens.

The Venereal Disease Research Laboratory slide test is a test for the detection of syphilis. The test employs an antigen containing cardiolipin, phosphatidylcholine (lecithin), and cholesterol dissolved in ethanol. The antigen is suspended in a buffered saline solution, which flocculates when combined with serum containing IgM and IgG anti-cardiolipin antibodies. The IgM and IgG antibodies are produced in response to infection by Treponema pallidum the causitive agent of syphilis. The flocculation forms a three-dimensional lattice structure that can be seen at low magnification (10x oculars and 10x objective) with a light microscope.

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

Device: Avanti Polar Lipids VDRL Antigen Slide Test Kit
Intended Use: For use in the Venereal Disease Research Laboratory (VDRL) slide test for syphilis, a non-treponemal, micro-flocculation test that provides both qualitative and semi-quantitative results to detect IgM and IgG anticardiolipin antibodies in serum.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Specificity and Sensitivity (Performance Data): 100 documented cases of syphilis.
• Sample Size for Reproducibility Data: Not explicitly stated, but “specimens from a blind, coded panel” were used. The number of specimens in this panel is not provided.
• Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective. It only mentions "documented cases of syphilis," implying these were existing patient samples with established diagnoses.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The ground truth is referred to as "documented cases of syphilis," which implies a clinical diagnosis, but the method or personnel establishing this documentation are not detailed. For reproducibility, "different clinicians" were involved, but their qualifications are not given.

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 of the "documented cases of syphilis." The ground truth appears to be based on pre-existing diagnostic records. For reproducibility, results from different clinicians were compared, but no formal adjudication process between them is outlined beyond comparing an end point within two doubling dilutions of the "true end point."

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

No, an MRMC comparative effectiveness study was not done. The study focuses on the performance of the Avanti Polar Lipids VDRL Antigen Slide Test Kit itself, not on how human readers' performance might improve with or without AI assistance. This device is an antigen for a manual slide test, not an AI-assisted diagnostic tool.

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

Yes, a standalone performance assessment was conducted. The sensitivity and specificity reported are those of the "Avanti Polar Lipids, Inc. VDRL Antigen Slide Test Kit" itself, meaning the kit's ability to react correctly with samples. While a human is involved in observing the flocculation under a microscope, the performance metrics are attributed to the device's ability to yield the correct reaction, forming the basis for a diagnosis. It's a test kit, not an algorithm, so algorithm-specific standalone performance isn't applicable in the modern AI sense. However, the data presented pertains to the device's inherent performance.

7. The Type of Ground Truth Used

The ground truth used for sensitivity and specificity was based on "documented cases of syphilis." This broadly refers to clinical diagnosis or confirmed cases (likely by other established methods for syphilis diagnosis). For reproducibility, a "true end point" was mentioned, which would presumably be a previously established titer for the control specimens in the blind panel.

8. The Sample Size for the Training Set

The document does not mention a training set or any machine learning/AI components. This device is a traditional in vitro diagnostic (IVD) test kit, not an AI/ML-based device.

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

As no training set is mentioned (since it's not an AI/ML device), this information is not applicable.

Ask a specific question about this device

Ask a specific question about this device

Not Found

Not Found

This K955136 submission is for the RPR Card Test Kit, a device for detecting Treponema pallidum infection. The provided documents describe the performance characteristics of two RPR antigens (Ag#1 and Ag#2) compared to existing RPR antigens.

While the documents indicate that the RPR Card Test Kit is "effective when tested under the conditions for its intended use" and includes "relative sensitivity and specificity data," they do not explicitly state quantitative acceptance criteria or provide a table of performance against such criteria. The focus is on comparing the REMEL manufactured antigens to existing and CDC-approved antigens.

Here's an attempt to extract and infer the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

As explicit, quantitative acceptance criteria are not provided, we can infer that the general acceptance criterion was "satisfactory performance" as judged by the CDC and consistency with comparator tests and clinical history.

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

The exact sample sizes for the test sets are not explicitly stated in terms of total number of specimens. The text mentions "many of the reactive samples" were titered or had clinical history documented. For Ag#2, a subset of "U. of Texas discrepant samples along with 12 known reactive samples and 12 known nonreactive samples" were sent blinded to Michigan.

• Data Provenance: The studies were conducted at the University of Texas and the Michigan Department of Public Health within the United States. The data appears to be retrospective, using clinical samples, based on the mention of "patient genders," "stage of infection with Treponema pallidum and history of treatment."

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

The ground truth appears to be established through a combination of:

• Comparator tests: BD RPR antigen, MHA-TP, Difco USR antigen. These are established laboratory tests.
• Clinical history: "Stage of infection with Treponema pallidum and history of treatment."

The individuals involved in the evaluation were:

• Dr. Beth Hartwell at the University of Texas.
• Mr. Harlan Stiefel at the Michigan Department of Public Health.
• The CDC (for initial evaluation and "satisfactory" determination).

Their specific qualifications (e.g., number of years of experience in serology or infectious disease diagnostics) are not detailed, beyond their institutional affiliations. It is implied that they are experts in their respective fields capable of conducting and evaluating these tests.

4. Adjudication Method

The adjudication method is not explicitly stated as a formal process like "2+1" or "3+1." The evaluation involves comparative testing against established methods (BD RPR, Difco USR, MHA-TP) and consistency with clinical records. Discrepancies were noted and, in the case of Ag#2, a subset of discrepant samples along with known samples were sent "blinded" to the Michigan site for re-evaluation and verification, indicating a form of external review. However, a structured adjudication protocol for the entire test set is not described.

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

There is no indication of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done to assess human reader improvement with or without AI assistance. This device is a diagnostic kit, not an AI-assisted interpretation tool for human readers.

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

This request is not applicable to the RPR Card Test Kit. This is a manual diagnostic test kit, not an algorithm or AI system. Its performance inherently involves human interpretation of results (e.g., flocculation). The study assesses the performance of the antigen/reagent, not a standalone algorithm.

7. Type of Ground Truth Used

The ground truth used is a combination of:

• Expert Consensus/Established Comparator Tests: Performance against "Satisfactory" ratings by the CDC, BD RPR antigen, Difco USR antigen, and MHA-TP (Microhemagglutination Assay for Treponema pallidum). MHA-TP is a treponemal-specific test, often used for confirmation of RPR results.
• Outcomes/Clinical Data: "Stage of infection with Treponema pallidum and history of treatment." This clinical information serves as a crucial part of establishing the true status of the patient (e.g., reactive RPR should align with active infection or treated infection history).

8. Sample Size for the Training Set

No explicit training set is mentioned. For diagnostic kits like this, the "training" equivalent would typically involve formulation and initial in-house testing to optimize the antigen and kit components. The provided text describes the evaluation of already formulated antigens (Ag#1 and Ag#2) that were deemed "Satisfactory" by the CDC prior to the reported comparison studies.

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

Since no explicit training set is mentioned in the context of algorithm development, this question is not directly applicable. However, the "ground truth" for the initial development and "satisfactory" determination by the CDC would likely involve:

• Known positive and negative samples (well-characterized clinical specimens).
• Comparison to standard reference preparations or established, validated RPR tests.
• Correlation with other serological tests for syphilis (e.g., FTA-ABS, MHA-TP) and clinical diagnosis.

The "satisfactory" rating from the CDC for both antigens before their use in the reported studies implies that a ground truth was established for the antigens themselves, but the details of that establishment are not provided within these documents.

Ask a specific question about this device

Visuwell® Reagin II is an enzyme-linked immunosorbent assay for the in vitro qualitative detection of non-treponemal (reagin) antibodies as a screening test in syphilis serology. It is not intended for use in screening blood or plasma donors.

Visuwell® Reagin II is an enzyme-linked immunosorbent assay for the in vitro qualitative detection of non-treponemal (reagin) antibodies in syphills serology. In this device, serum is incubated with a mixture of cardiolipin, lecithin, cholesterol dried to a polystyrene solid phase. Antilipid antibodies react with the lipoidal antigen to form an immune complex. The presence of non-treponemal complexed antibodies is detected with a monoclonal anti-human lgG-peroxidase conjugate. The presence of bound conjugate is detected by the addition of enzyme substrate and subsequent development of colour. The reaction is stopped by the addition of acid and colour intensity is determined spectrophotometrically at 450 nm. Test results are interpreted relative to a floating cutoff based on the negative control. Positive and negative controls are used for establishing test validity.

Acceptance Criteria and Device Performance Study for Visuwell® Reagin II

1. Table of Acceptance Criteria and Reported Device Performance

Note on "Substantially equivalent": The report explicitly states that Visuwell® Reagin II was "substantially equivalent" in performance to the reference tests despite some numerical differences. For example, for sensitivity in treated syphilis, Visuwell® Reagin II showed lower reactivity (75.4% vs 90.2%), but this was interpreted as potentially beneficial for therapy monitoring, and the device was still deemed substantially equivalent for its primary intended use of detecting non-treponemal antibody in untreated syphilis.

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

• Specificity Comparison: 10,738 specimens from random, low-risk, and high-risk populations.
• Sensitivity Comparison:
  • 306 patients with untreated syphilis
  • 74 patients with unknown treatment status
  • 325 patients with treated syphilis
• Predictive Values:
  • Predictive value of positive calculated for the Sexually Transmitted Disease (STD) population.
  • Predictive value of negative calculated with data from "all sites."
• Cross-Reactivity: 151 specimens from individuals with various bacterial, viral, and auto-immune disorders, including syphilis biological false-positives, pregnancy, and drug abuse.
• Overall Agreement: 11,443 total sera (presumably the aggregate of relevant specificity and sensitivity samples).

Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective. It refers to "various populations" and "all sites," suggesting a multicenter study, but lacks specific details on geographical location or study design.

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

The document does not provide information on the number of experts used or their qualifications for establishing ground truth. The comparison is made against "legally marketed reference non-treponemal tests" (VDRL, RPR, RST), implying that the results from these established tests were considered the ground truth.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1). The nature of the study involves comparing the Visuwell® Reagin II results directly to the results obtained from established reference non-treponemal tests. The interpretation of these reference tests (VDRL, RPR, RST) is described as "subjective... according to the presence or absence of flocculation," which implies expert interpretation of the reference test results themselves, but no explicit adjudication process for disagreements is mentioned.

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

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was mentioned. The study focused on the performance of the Visuwell® Reagin II device compared to existing non-treponemal tests, not on human reader performance with or without AI assistance.

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

Yes, this was a standalone performance study. Visuwell® Reagin II is an "enzyme-linked immunosorbent assay," and its results are "objectively spectrophotometrically interpreted." This indicates an automated or semi-automated process where the device's output (color intensity) is directly converted into a result relative to a floating cutoff, without human-in-the-loop interpretation being the primary focus of the comparison with reference methods.

7. Type of Ground Truth Used

The ground truth was established by comparison to existing, legally marketed reference non-treponemal tests (Venereal Disease Research Laboratory (VDRL) Slide Test, Rapid Plasma Reagin (RPR) Card Test, Reagin Screen Test (RST)). These tests are implied to be the standard of care for detecting non-treponemal antibodies in syphilis serology. Clinical diagnosis of syphilis (e.g., "patients with untreated syphilis") was also used to categorize some samples for sensitivity calculations.

8. Sample Size for the Training Set

The document does not provide specific details about a dedicated "training set" or its size for the Visuwell® Reagin II device development. The information presented pertains to a performance study evaluating the final device's performance against reference methods.

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

As no specific training set is described in the provided text, there is no information on how its ground truth was established. The focus of this submission is on the validation of the device, comparing its performance to established methods in various clinical populations.

Ask a specific question about this device