FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The Verigene® Respiratory Virus Nucleic Acid Test on the Verigene SP System (RVNATsg) is a qualitative multiplex in vitro diagnostic test for the detection and identification of Influenza A Virus, Influenza B Virus, and Respiratory Syncytial Virus (RSV) nucleic acids purified from nasopharyngeal swab specimens obtained from patients symptomatic for viral upper respiratory infection. The test is intended to be used on the Verigene® SP System as an aid in the differential diagnosis of Influenza A, Influenza B, and RSV infections. The test is not intended to detect Influenza C virus.

Negative results do not preclude influenza virus or RSV infection and should not be used as the sole basis for treatment or other management decisions. It is recommended that negative test results be confirmed by culture.

Performance characteristics for Influenza A Virus were established when Influenza A/H3 and A/H1 were the predominant Influenza A viruses in circulation. When other Influenza A viruses are emerging, performance characteristics may vary.

If infection with a novel Influenza A virus is suspected based on current clinical and epidemiological screening criteria recommended by public health authorities, specimens should be collected with appropriate infection control precautions for novel virulent Influenza viruses and sent to state or local health department for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.

Device Description

The entire RVNATSP is performed on the Verigene® SP System, which is a bench-top molecular diagnostics workstation that consists of two instruments, the Verigene SP Processor and the Verigene Reader. The Verigene SP Processor performs the assay steps on each sample by using a robotic pipettor to transfer and mix reagents within and between separate testing modules designed for nucleic acid extraction, target amplification, and the Verigene Hybridization test. The Verigene hybridization test module is the same as in the previous Verigene System with added modules for nucleic acid extraction and RT-PCR target amplification. Key functions of the Verigene SP Processor include:

Reading of the barcode identification label on inserted Test Consumables to maintain positive identification of patient samples throughout processing.
Facilitation of nucleic acid extraction, multiplex RT-PCR target amplification, and the Verigene Hybridization Test.
Real-time communication of test processing status to the Reader.

The Verigene Reader is the same instrument as in the FDA-cleared VRNAT. It is a free-standing instrument with a touch screen control panel and a wand-based barcode scanner. It utilizes a graphical user interface to guide the user through the process of ordering tests and reporting results. There are no serviceable parts and no user calibration is required. Interaction with the touch screen is minimized through barcode use. This instrument also serves as the reader of the Test Cartridges using advanced optics. The key functions of the Verigene Reader include:

Entry and tracking of specimen identification numbers via manual keyboard input or via barcode-reader wand.
Test selection for each specimen.
Automated transfer of specimen processing instructions on Test Cartridge-specific basis to linked Processor unit(s). A single Reader unit can control up to 32 Processor units.
Automated imaging and analysis of Test Cartridges.
Results display.
Results report generation.

RVNATSP consumables within each single-use disposable test kit include: (i) Tip Holder Assembly; (ii) Extraction Tray; (iii) Amplification Tray; and (iv) RV Test Cartridge. The kit components are inserted into the corresponding module of the Verigene SP Processor prior to each test, and the sample is added to the Extraction Tray. Patient information is entered into the Reader to initiate the test procedure.

Tip Holder Assembly – The robotic pipettor picks up pipettes from the Tip Holder Assembly. The pipettes are used for mixing and transferring reagents within the test procedure.
Extraction Tray – Nucleic acids are extracted from the sample by using magnetic bead-based methods within the Extraction Tray. Each Tray contains reagents for a single extraction procedure. A robotic pipette transfers reagents to designated wells within the Extraction Tray to affect the steps of lysis, capture of nucleic acids onto the magnetic beads, washing, and eluting the isolated nucleic acids from the magnetic beads.
Amplification Tray – The isolated nucleic acids are amplified by using multiplex RT-PCR within the Amplification Tray. Each Tray contains reagents for a single multiplex RT-PCR procedure. A robotic pipette transfers the reagents to a specific well within the Amplification Tray. A set thermal profile is then initiated to perform all of the amplification related steps including UDG-based decontamination, reverse transcription, and multiplex PCR in a single tube. Upon completion, an aliquot of the amplified sample is mixed with hybridization buffer containing the virus specific mediator probes. The sample is then transferred to the Test Cartridge.
RV Test Cartridge for Verigene Hybridization Test - The virus-specific amplicons are detected and identified within a Test Cartridge by using specific nucleic acid probes in conjunction with gold nanoparticle probe-based detection technology. Each Test Cartridge is a self-contained, laboratory consumable that consists of two parts. The upper housing of each cartridge is called the "reagent pack" and contains reservoirs filled with the detection reagents. When in place with the 'substrate holder', the reagent pack creates an air-tight hybridization chamber surrounding the region of the substrate containing a target-specific capture array. As each step of the test is completed, old reagents are moved out of the hybridization chamber and new reagents are added from the reagent pack via microfluidic channels and pumps. Once the test is complete, the Test Cartridge is removed from the Verigene SP Processor unit and the reagent pack is snapped off and discarded. The remaining slide is now ready for imaging and analysis in the Verigene Reader.
End-point detection on the Verigene Reader: The test slide is inserted into the Verigene Reader wherein it is illuminated along its side. The gold-silver aggregates at the test sites scatter the light, which is in turn captured by a photosensor. The relative intensity arising from each arrayed test site is tabulated. Net signals, defined as the absolute signal intensities with background signals subfracted, are compared with thresholds determined by negative controls within the slide in order to arrive at a decision regarding the presence or absence of target. These results are linked to the test and patient information entered at the beginning of each test session to provide a comprehensive results file.

AI/ML Overview

The provided document describes the Verigene® Respiratory Virus Nucleic Acid Test on the Verigene® SP System (RVNATSP), a qualitative multiplex in vitro diagnostic test for the detection and identification of Influenza A Virus, Influenza B Virus, and Respiratory Syncytial Virus (RSV) nucleic acids. The study aims to demonstrate substantial equivalence to a previously cleared predicate device, the Verigene® Respiratory Virus Nucleic Acid Test (VRNAT, K083088).

1. Table of Acceptance Criteria and Reported Device Performance:

The primary acceptance criteria for the RVNATSP were established by demonstrating equivalence to the predicate VRNAT device (K083088) in terms of analytical sensitivity (Limit of Detection), lack of carryover/crossover contamination, precision/reproducibility, and method comparison (percent agreement). Based on the provided information, the acceptance criteria are implicitly that the performance of the RVNATSP should be comparable or identical to that of the cleared VRNAT.

Acceptance Criteria Category	Specific Metric	Acceptance Threshold (Implicit)	RVNATSP Performance (Reported)
Analytical Sensitivity	Limit of Detection (LOD) for Influenza B, RSV A, RSV B, and Influenza A.	Identical to the LOD of the cleared VRNAT (K083088).	Identical to the LOD observed with the same strains on the cleared VRNAT (K083088) for Influenza B (50 TCID50/mL), RSV A (10 TCID50/mL), RSV B (2 TCID50/mL), and Influenza A (2 TCID50/mL).
Contamination	Evidence of carryover and/or crossover contamination.	No evidence of cross-contamination.	No evidence of cross-contamination from any test steps (sample extraction, multiplex RT-PCR, Verigene Hybridization Test).
Precision/Reproducibility	Agreement of 'Observed Results' to 'Expected Results' across High Negative, Low Positive, and Moderate Positive samples for Influenza A, Influenza B, RSV A, and RSV B. Combined % Agreement and 95% Confidence Interval.	Clinically and statistically equivalent to the cleared VRNAT.	Clinically and statistically equivalent to the cleared VRNAT. For all panel members, the RVNATSP showed high agreement (e.g., 100% for most moderate positive and high negative samples, 98.7% for low positives, 99% for RSV A High Negative) with comparable 95% CIs to the VRNAT.
Method Comparison	Positive Percent Agreement (PPA) and Negative Percent Agreement (NPA) between RVNATSP and cleared VRNAT for all viruses combined.	Collective lower bound 95% CI for PPA and NPA greater than 90%. Clinically and statistically equivalent.	PPA: 97.9% (95% CI: 94.8% - 99.0%) (all sites combined). NPA: 100.0% (95% CI: 99.0% - 100.0%) (all sites combined). All reported discordant samples were low-positive Influenza A, which were positive on repeat testing.

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

Analytical Sensitivity (LOD) Study: For each virus strain, 20 replicates were tested at the LOD concentration after an initial quadruplicate testing of serially diluted stocks. This was done for Influenza B, RSV A, RSV B, and Influenza A. The samples were prepared from strains with established titers serially diluted into Universal Transport Media (Copan). The country of origin of the data is not explicitly stated but implies internal laboratory studies. The data is prospective for the purpose of this study.
Carryover and Crossover Contamination Studies: High positive samples of Influenza A, Influenza B, and RSV B were alternated with high negative samples. The exact number of samples or alternations is not specified but the "collective data" demonstrated no cross-contamination. This appears to be a prospective internal study.
Precision/Reproducibility Studies: Eight unique sample panels (viral strains at high negative, low positive, and moderate positive concentrations) were tested.
- Site 1 (Precision Study): The sample set was tested over 12 non-consecutive days with two operators performing the test in duplicate (total of 48 tests per panel member for Influenza A, Influenza B, RSV A, RSV B).
- Sites 2 and 3 (Reproducibility Study): The sample set was tested in triplicate daily by 2 operators on each of five non-consecutive days (total of 15 tests per panel member per site for Influenza A, Influenza B, RSV A, RSV B).
- The total number of individual results used for precision/reproducibility comparison across all sites for each panel member was 78 (48 from Site 1 + 15 from Site 2 + 15 from Site 3). This was a prospective, multi-site study. Data provenance is not specified beyond "three sites."
Method Comparison Studies: A total of 62 unique samples (from culture positive and negative nasopharyngeal swab samples) were prepared, representing Influenza A (15 positive, 47 negative), Influenza B (16 positive, 46 negative), and RSV A/B (34 positive, 28 negative). These were diluted to yield viral load levels close to low positive. Each sample provided a decision for all three viruses, resulting in 186 decisions per test.
- The sample set was tested at one internal site (Site 1) using the cleared VRNAT.
- The same sample set was tested at all three sites (Site 1, Site 2, and Site 3) using the RVNATSP.
- "Total of 62x4 = 248 unique tests" (implying 62 samples tested once on VRNAT at Site 1, and once on RVNATSP at each of the 3 sites). The comparison data in Tables 7-9 use the VRNAT (Old System) results (presumably from Site 1) as the reference for each RVNATSP site's results. The combined data in Table 10 then aggregates results from all three RVNATSP sites against the VRNAT reference.
- Data provenance is not explicitly stated, but "culture positive nasopharyngeal swab samples" suggests patient samples. This was a prospective, multi-site study.

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

This device is a molecular diagnostic test. The "ground truth" for the test set is established by the known concentration of viral strains (for analytical sensitivity/LOD and precision/reproducibility) or by the results from the predicate device (cleared VRNAT) for the method comparison study. There are no human "experts" required to establish a ground truth in the way a radiologist would for an imaging study. The reference method for comparison is a previously cleared, similar molecular diagnostic test.

4. Adjudication Method for the Test Set:

Not applicable in the context of this molecular diagnostic device comparison. The "ground truth" for method comparison is the result obtained from the predicate device (cleared VRNAT). For discordant results in the method comparison study (e.g., in Site 2 and Site 3 performance for Influenza A), "Repeat tests were positive and gave the expected result," suggesting internal re-testing or confirmation processes were employed for discrepancies, but not necessarily a formal adjudication by a panel of human experts.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

Not applicable. This is a molecular diagnostic device, not an imaging device requiring human readers or AI assistance in interpretation. The output is a qualitative "Detected" or "Not Detected" result for specific viral nucleic acids.

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

The device (RVNATSP) operates as a standalone system once the sample is loaded. The "algorithm" in this context refers to the molecular diagnostic assay steps and the instrument's internal decision algorithm for generating "Detected" or "Not Detected" results. The performance studies described (analytical sensitivity, contamination, precision, method comparison) inherently evaluate the standalone performance of the RVNATSP system without human intervention in the result interpretation after the run is initiated. The comparison against the predicate device also assesses standalone performance.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.):

For Analytical Sensitivity (LOD) and Precision/Reproducibility: The ground truth was based on known concentrations of specific viral strains (e.g., TCID50/mL values) that were serially diluted into a sample matrix.
For Method Comparison: The ground truth was established by the results obtained from the FDA-cleared predicate device (VRNAT, K083088). This is a "device-to-device" comparison where the cleared device serves as the reference standard.

8. The Sample Size for the Training Set:

This document describes a 510(k) submission for a molecular diagnostic device, not a machine learning or AI-based system that typically uses a "training set." The RVNATSP is built upon established molecular biology principles and reagents. Therefore, the concept of a "training set" for an algorithm, as described in AI development, is not directly applicable to this device. The development of such assays involves extensive R&D and analytical optimization, which could be considered an iterative "training" process for the assay design itself, but not a distinct dataset for algorithm training in the computational sense.

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

As noted above, the concept of a "training set" with established ground truth as understood in AI/ML development does not directly apply to this molecular diagnostic device. The assay design and optimization would rely on established molecular biology techniques, purified viral samples, and potentially a range of clinical samples, but these are part of the assay development and validation rather than a formally defined "training set" for an algorithm.

Summary

Regulation Number and Section

§ 866.3980 Respiratory viral panel multiplex nucleic acid assay.

(a)
Identification. A respiratory viral panel multiplex nucleic acid assay is a qualitative in vitro diagnostic device intended to simultaneously detect and identify multiple viral nucleic acids extracted from human respiratory specimens or viral culture. The detection and identification of a specific viral nucleic acid from individuals exhibiting signs and symptoms of respiratory infection aids in the diagnosis of respiratory viral infection when used in conjunction with other clinical and laboratory findings. The device is intended for detection and identification of a combination of the following viruses:(1) Influenza A and Influenza B;
(2) Influenza A subtype H1 and Influenza A subtype H3;
(3) Respiratory Syncytial Virus subtype A and Respiratory Syncytial Virus subtype B;
(4) Parainfluenza 1, Parainfluenza 2, and Parainfluenza 3 virus;
(5) Human Metapneumovirus;
(6) Rhinovirus; and
(7) Adenovirus.
(b)
Classification. Class II (special controls). The special controls are:(1) FDA's guidance document entitled “Class II Special Controls Guidance Document: Respiratory Viral Panel Multiplex Nucleic Acid Assay;”
(2) For a device that detects and identifies Human Metapneumovirus, FDA's guidance document entitled “Class II Special Controls Guidance Document: Testing for Human Metapneumovirus (hMPV) Using Nucleic Acid Assays;” and
(3) For a device that detects and differentiates Influenza A subtype H1 and subtype H3, FDA's guidance document entitled “Class II Special Controls Guidance Document: Testing for Detection and Differentiation of Influenza A Virus Subtypes Using Multiplex Nucleic Acid Assays.” See § 866.1(e) for the availability of these guidance documents.