Search Results

NxTAG® Respiratory Pathogen Panel is a qualitative test intended for use on the Luminex® MAGPIX® Instrument for the simultaneous detection and identification of nucleic acids from multiple respiratory viruses and bacteria extracted from nasopharyngeal swabs collected from individuals with clinical signs and symptoms of a respiratory tract infection. The organism types and subtypes detected by the test are Influenza A H1, Influenza A H3, Influenza B, Respiratory Syncytial Virus A, Respiratory Syncytial Virus B, Coronavirus OC43, Coronavirus NL63, Coronavirus HKU1, Human Metapneumovirus, Rhinovirus, Adenovirus, Parainfluenza virus 1, Parainfluenza virus 2, Parainfluenza virus 3, Parainfluenza virus 4, Human Bocavirus, Chlamydophila pneumoniae, and Mycoplasma pneumoniae.

The test is indicated as an aid in the detection of viral and bacterial agents causing respiratory tract infections in symptomatic adult and pediatic patients, who are either hospitalized, admitted to emergency departments or who are outpatients with suspected respiratory tract infection.

The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Negative results in the setting of a respiratory illness may be due to infection with pathogens not detected by this test or lower respiratory tract infection that is not detected by a nasopharyngeal swab specimen. Positive results do not rule out co-infection with other pathogens. The agent detected may not be the cause of disease. The use of additional laboratory testing (e.g. bacterial and viral culture, immunofluorescence, and radiography) and clinical presentation must be taken into consideration in order to obtain the final diagnosis of respiratory tract infection.

Performance characteristics for influenza A were established using specimens obtained during the 2013/2014 and 2014/2015 influenza seasons 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 influenza A virus is suspected based on current clinical and epidemiological screening criteria recommended by public health authorties, specimens should be collected with appropriate infections for novel virulent Influenza viruses and sent to state or local health departments for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.

NxTAG® Respiratory Pathogen Panel is a qualitative test intended for use on the Luminex® MAGPIX® Instrument for the simultaneous detection and identification of nucleic acids from multiple respiratory viruses and bacteria extracted from nasopharyngeal swabs collected from individuals with clinical signs and symptoms of a respiratory tract infection. The organism types and subtypes detected by the test are Influenza A H1, Influenza A H3, Influenza B, Respiratory Syncytial Virus A, Respiratory Syncytial Virus B, Coronavirus OC43, Coronavirus NL63, Coronavirus HKU1, Human Metapneumovirus, Rhinovirus, Adenovirus, Parainfluenza virus 1, Parainfluenza virus 2, Parainfluenza virus 3, Parainfluenza virus 4, Human Bocavirus, Chlamydophila pneumoniae, and Mycoplasma pneumoniae.

The information provided does not contain details about specific acceptance criteria or a study proving the device meets those criteria. The document is an FDA clearance letter for the NxTAG Respiratory Pathogen Panel, indicating that the device has been substantially equivalenced to a predicate device for its stated indications for use.

While the "Indications for Use" section (Page 3) describes the intended use of the device and some general performance characteristics for influenza A, it does not present a table of acceptance criteria or detailed study results. It mentions that performance characteristics for influenza A were established using specimens from specific influenza seasons, but it doesn't quantify those characteristics or define specific thresholds for acceptance.

Therefore, I cannot fulfill your request for the detailed table, sample sizes, expert information, adjudication methods, MRMC study details, standalone performance, ground truth types, or training set information based on the provided text. This document is a regulatory clearance, not a performance study report.

Ask a specific question about this device

The ID NOW™ Influenza A & B 2 assay performed on the ID NOW™ Instrument is a rapid molecular in vitro diagnostic test utilizing an isothermal nucleic acid amplification technology for the qualitative detection and discrimination of influenza A and B viral RNA in direct nasal or nasopharyngeal swabs and nasal or nasopharyngeal swabs eluted in viral transport media from patients with signs and symptoms of respiratory infection. It is intended for use as an aid in the differential diagnosis of influenza A and B viral infections in humans in conjunction with clinical and epidemiological risk factors. The assay is not intended to detect the presence of influenza C virus.

Negative results do not preclude influenza virus infection and should not be used as the sole basis for diagnosis, treatment or other patient management decisions.

Performance characteristics for influenza A were established during the 2016-2017 influenza season when influenza A/H3 and A/H1N1 pandemic 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.

ID NOW Influenza A & B 2 is a rapid, instrument-based isothermal test for the qualitative detection and differentiation of influenza A and influenza B from nasal swab or nasopharyngeal swabs tested directly or after elution in viral transport media collected from patients presenting with signs and symptoms of respiratory infection.

All ID NOW™ assays utilize isothermal nucleic acid amplification technology and are comprised of:

• Sample Receiver single use, disposable containing the elution buffer .
• Test Base single use, disposable comprising two sealed reaction tubes, each . containing a lyophilized pellet
• Transfer Cartridge single use, disposable for transfer of the eluted sample to the Test . Base, and
• ID NOW™ Instrument repeat use reader .

The reaction tubes in the ID NOW Influenza A & B 2 Test Base contain the reagents required for amplification of the target nucleic acid and an internal control. ID NOW Influenza A & B 2 utilizes a pair of templates (similar to primers) for the specific amplification of RNA from influenza A and B and a fluorescently labeled molecular beacon designed to specifically identify the amplified RNA targets.

ID NOW Influenza A & B 2 is performed within the confinement of the Test Base, and no other part of the ID NOW Instrument has contact with the sample during the amplification process. This reduces the risk of instrument contamination and sample carry-over between measurements.

To perform the assay, the Sample Receiver and Test Base are inserted into the ID NOW™ Instrument and the elution buffer is automatically heated by the instrument. The sample is added to the Sample Receiver and transferred via the Transfer Cartridge to the Test Base, resuspending the lyophilized pellets contained within the Test Base and target amplification. Heating, mixing and detection by fluorescence is provided by the instrument. with results automatically reported.

Results are displayed by the ID NOW Instrument and are also stored in an on-board archive and are assigned to a sample ID that has been entered into the ID NOW Instrument by the operator. and the date/time the test was performed. Data can be retrieved and downloaded by the operator at any time after testing. An external Universal Printer can be attached via USB to the ID NOW Instrument to print test results.

The provided text describes a 510(k) submission for the ID NOW™ Influenza A & B 2 assay, specifically focusing on a software modification to mitigate potential false positive Influenza B test results during sequential workflow testing. The submission is a "Special 510(k)," indicating that the changes are minor and do not significantly alter the device's fundamental technology or safety/effectiveness.

The document emphasizes the equivalence to a legally marketed predicate device (ID NOW Influenza A & B 2, K220801). Therefore, the study presented here is primarily a comparative study to demonstrate that the modified device performs equivalently to the predicate, rather than establishing de novo performance characteristics against a clinical ground truth for a novel device.

Here's an analysis of the provided information, framed by your request for acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this Special 510(k) are implicitly tied to demonstrating non-inferiority or equivalence of the modified device's performance to the predicate device, particularly concerning the reduction of false positives for Influenza B. The document states:

• "A modification of the ID NOW Influenza A & B 2 algorithm was made, as a preventive measure, to mitigate the potential occurrence of false positive Influenza B test results during sequential workflow testing."
• "ID NOW Influenza A & B 2 incorporating the software modification was compared to the legally marketed predicate device, the 510(k) cleared ID NOW Influenza A & B 2."

While the document states the purpose and the comparison, it does not explicitly list quantitative acceptance criteria (e.g., a specific percentage reduction in false positives, or a non-inferiority margin for sensitivity/specificity) or the reported device performance in a table format as you requested. The provided text is a summary letter and general description, not a detailed study report. For a device like this, the performance data (sensitivity, specificity, positive predictive value, negative predictive value) for both the modified and predicate devices would typically be presented in the detailed 510(k) submission, but this information is not included in the provided excerpt.

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

The provided text does not explicitly state the sample size used for the test set. It mentions the study compares the modified device to the predicate, implying a test set was used for this comparison.

Regarding data provenance: The document does not specify the country of origin of the data or whether the data was retrospective or prospective. These details would be crucial for a full understanding of the study's design.

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

For a molecular diagnostic test like ID NOW Influenza A & B 2, the "ground truth" is typically established by a highly sensitive and specific reference method, such as RT-PCR (Reverse Transcription Polymerase Chain Reaction), which is considered the gold standard for viral detection. The document does not mention the use of human experts (e.g., radiologists) to establish ground truth because this is a laboratory diagnostic assay, not an imaging device. Therefore, no information is provided on expert qualifications or the number of experts.

4. Adjudication Method for the Test Set

Since the ground truth for molecular diagnostics is typically established by a reference laboratory method (e.g., RT-PCR), an "adjudication method" involving human readers (like 2+1 or 3+1 for imaging studies) is not applicable in this context and is therefore not mentioned.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not applicable and therefore not done. MRMC studies are typically used for evaluating diagnostic imaging systems where human interpretation plays a critical role, and the impact of AI assistance on human reader performance is being assessed. The ID NOW Influenza A & B 2 is an automated molecular diagnostic test; human "readers" do not interpret results in the same way as in imaging.

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

Yes, the very nature of this device (an automated molecular diagnostic test) means that the performance is standalone (algorithm only without human-in-the-loop performance). The ID NOW Instrument performs the test, processes the sample, and reports results automatically. The software modification described directly impacts this automated process. The comparison to the predicate device would inherently evaluate the standalone performance of the modified algorithm against the predicate algorithm.

7. The Type of Ground Truth Used

As mentioned in point 3, the ground truth for molecular diagnostic tests like this is almost universally established by a highly sensitive and specific reference laboratory method, typically RT-PCR. While the document does not explicitly state "RT-PCR was used as ground truth," this is the industry standard for validating such devices. "Expert consensus," "pathology," or "outcomes data" are generally not the primary ground truth methods for direct viral detection assays.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This is a software modification to an existing, cleared device, implying the original device would have undergone substantial training and validation. For a Special 510(k) focusing on a specific bug fix (false positives in sequential workflow), the emphasis is on a targeted verification and validation of the change, rather than retraining a comprehensive model. If a machine learning model were involved, reporting training set size would be crucial, but the description here suggests a more rule-based or algorithmic adjustment.

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

Since no information on a specific "training set" for the software modification is provided, there is also no information on how the ground truth for such a training set (if it existed) was established.

Ask a specific question about this device

The Panther Fusion® AdV/hMPV/RV assay is a multiplex real-time PCR (RT-PCR) in vitro diagnostic test for the rapid and qualitative detection and differentiation of Adenovirus (AdV), human Metapneumovirus (hMPV), and Rhinovirus (RV). Nucleic acids are isolated and purified from nasopharyngeal (NP) swab specimens obtained from individuals exhibiting signs and symptoms of a respiratory tract infection.

This assay is intended to aid in the differential diagnosis of Adenovirus, human Metapneumovirus, and Rhinovirus infections in humans. Negative results do not preclude Adenovirus, human Metapneumovirus, and Rhinovirus infections and should not be used as the sole basis for treatment or other management decisions. This assay is designed for use on the Panther Fusion system.

The Panther Fusion AdV/hMPV/RV assay is a multiplex real-time PCR (RT-PCR) in vitro diagnostic test for the rapid and qualitative detection and differentiation of Adenovirus (AdV) human Metapneumovirus (RV). Nucleic acids are isolated and purified from nasopharyngeal (NP) swab specimens obtained from individuals exhibiting signs and symptoms of a respiratory tract infection.

Prior to processing and testing on the Panther Fusion system, specimen Lysis Tube containing specimen transport media (STM) that lyses the cells, releases target nucleic acid and protects them from degradation during storage. The Internal Control-S (IC-S) is added to each test specimen and controls via the working Panther Fusion Capture Reagent-S (wFCR-S). The lC-S in the reagent monitors specimen processing, and detection. Capture oligonucleotides hybridize to nucleic acid in the test specimen. Hybridized nucleic acid is then specimen in a magnetic field. Wash steps remove extraneous components from the reaction tube. The elution step elutes acid. During the nucleic acid capture and elution step, total nucleic acid is isolated from specimens.

During the elution transfer step, eluted nucleic acid is transferred to a Panther Fusion tube already containing oil and reconstituted masternix. For RV, hMPV, and internal control targets, amplification occurs via RT-PCR. A reverse transcriptase step qenerates DNA copies of the target sequence. For AdV, target amplification occurs via PCR. For all targets, specific forward and reverse primers and probes amplify targets while simultaneously detecting and discriminating multiplex PCR. The Panther Fusion system compares the fluorescence signal to a predece a qualitative result for the presence or absence of the analyte. The assay analytes (Adenovirus, human Metapheumovirus, and Internal Control) through specific gene targets (Hexon, Nucleocapsid, 5' UTR, and n/a, respectively) are detected in different channels of the Panther Fusion system (HEX, ROX, FAM, and RED677, respectively).

The provided text describes a 510(k) premarket notification for the "Panther Fusion AdV/hMPV/RV Assay," an in vitro diagnostic test. The notification details the device, its intended use, and a comparison to a predicate device. Crucially, it highlights that the subject device incorporates "software algorithm changes" to improve hMPV specificity, specifically to decrease false positives, without significantly altering clinical results or assay claims.

However, the document states: "All analytical and clinical data used to support the predicate device intended use and performance was re-analyzed with the updated software. All pre-determined acceptance criteria from the original protocols were met." It does not provide the specific acceptance criteria or the detailed results of this re-analysis, nor does it describe a new study conducted to prove the device meets acceptance criteria. It only affirms that the previous data, when re-analyzed with the new software, continued to meet the original acceptance criteria.

Because the document only states that original acceptance criteria were met by re-analysis of existing data, and does not outline specific acceptance criteria or an independently designed study for the new software, I can only infer information from what is provided.

Here's an attempt to answer your questions based on the limited information that can be extracted or reasonably inferred from the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table of acceptance criteria or reported device performance for the new software. It only states: "All pre-determined acceptance criteria from the original protocols were met." Without the original protocols, the exact acceptance criteria and the specific performance metrics (e.g., sensitivity, specificity, accuracy) are not available in this document. The focus of the changes is on improving hMPV specificity, implying that this was a key performance area.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document states: "All analytical and clinical data used to support the predicate device intended use and performance was re-analyzed with the updated software." This indicates that the same test set (both analytical and clinical data) used for the predicate device was re-used for the updated software. The sample size and data provenance are therefore not detailed in this document, as it refers to pre-existing data. It doesn't specify if the original data was retrospective or prospective, nor its country of origin.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the document. The study described is a re-analysis of previously established analytical and clinical data for an in-vitro diagnostic test. Establishing "ground truth" for clinical samples in an IVD context typically involves clinical diagnosis or other validated laboratory methods, rather than expert radiology reads as might be the case for imaging AI.

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

This information is not provided in the document. As an IVD device, the "adjudication method" in the context of clinical studies for diagnostic accuracy would typically refer to how the true status of a specimen (positive/negative for a pathogen) was determined.

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

No, an MRMC comparative effectiveness study was not done or described. This device is an in-vitro diagnostic test (a laboratory assay), not an AI imaging analysis tool that assists human readers. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply here.

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

The device is an in-vitro diagnostic test that operates on a "Panther Fusion system." The "software algorithm changes" affect how the assay results are processed and interpreted by the system itself. This is essentially a "standalone" or "algorithm only" performance, as the algorithm's output directly determines the qualitative detection and differentiation of the viruses. Human intervention likely involves sample preparation and loading, and subsequent interpretation of the system's output. The re-analysis was of the system's performance with the new software.

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

The document relates to an In Vitro Diagnostic (IVD) test for nucleic acid detection. For such assays, "ground truth" for the test set would typically be established by:

• Reference laboratory methods: Such as highly sensitive and specific PCR methods, sequencing, or culture that are considered gold standard.
• Clinical diagnosis: Based on a physician's assessment, symptoms, and other diagnostic tests.
• Composite reference standard: A combination of clinical and laboratory findings.

The exact type of ground truth used for the original predicate device data (which was re-analyzed) is not specified in this document.

8. The sample size for the training set

The document states that "All analytical and clinical data used to support the predicate device intended use and performance was re-analyzed with the updated software." This implies that the software updates likely occurred after the initial assay development. It's not explicitly stated that a new training set was used for the "software algorithm changes." The changes are presumably based on internal development and validation, potentially informed by performance issues (like the hMPV false positives). Details about any specific training set for the software algorithm are not provided.

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

As there is no specific mention of a separate training set for the new algorithm within this document, the method for establishing its ground truth is also not provided. If the algorithm was developed iteratively based on observed performance issues (e.g., false positives), the "ground truth" for its development would be based on the established true status of the samples that generated those observed issues, similar to how the ground truth is established for the test set (reference methods or clinical diagnosis).

Ask a specific question about this device

The cobas® Influenza A/B & RSV Nucleic acid test for use on the cobas® Liat® System (cobas® Influenza A/B & RSV) is an automated multiplex real-time RT-PCR assay for the rapid in vitro qualitative detection and discrimination of Influenza A virus, Influenza B virus and respiratory syncytial virus (RSV) RNA in nasopharyngeal swab specimens from patients with signs and symptoms of respiratory infection in conjunction with clinical and epidemiological risk factors. The test is intended for use as an aid in the differential diagnosis of Influenza A, Influenza B, and RSV in humans and is not intended to detect Influenza C.

Negative results do not preclude Influenza virus or RSV infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease.

Performance characteristics for Influenza A were established during the 2013-2014 and the 2014-2015 influenza seasons when Influenza A/H3 and A/H1N1 pandemic 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 BSL3+ facility is available to receive and culture specimens.

The cobas® Liat® Influenza A/B & RSV Nucleic Acid Test for use on the cobas® Liat® System (cobas® Influenza A/B & RSV) is an automated in vitro diagnostic test for the qualitative detection of Influenza A, Influenza B, and RSV RNA in nasopharyngeal swab (NPS) specimens. The sample-to-result time is ~20 minutes.

The assay is performed on the Analyzer which automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using realtime RT-PCR assays. The assay targets a well-conserved region of the matrix gene of Influenza A (Inf A target), the non-structure protein gene of Influenza B (Inf B target), and the matrix gene of RSV (RSV target). An Internal Process Control (IPC) is also included. The IPC is present to control for adequate processing of the target virus through all steps of the assay process and to monitor the presence of inhibitors in the RT-PCR reactions.

The System consists of an instrument and preloaded software for running tests and viewing the results. The system requires the use of a single-use disposable cobas® Influenza A/B & RSV assay tube that holds the nucleic acid purification and RT-PCR reagents, and hosts the sample preparation and RT-PCR processes.

The detection module monitors the reaction in real-time, while an on-board computer analyzes the collected data and outputs an interpreted result. The latter is displayed in the assay report on the integrated LCD touch screen of the cobas® Liat® Analyzer and in an electronic file. The report can be printed directly through a USB or network-connected printer. The results can also be exported to an external server, middleware or data management system, or to a Laboratory Information System (LIS).

The provided text describes a 510(k) premarket notification for a medical device: "cobas Influenza A/B & RSV nucleic acid test for use on the cobas Liat System." This document is focused on demonstrating the substantial equivalence of a modified device to a previously cleared predicate device, specifically regarding a change in the negative control buffer and positive control diluent. It does not contain detailed information about initial acceptance criteria, a comprehensive study proving the device met those criteria, sample sizes for test sets, data provenance, expert adjudication, MRMC studies, standalone performance, or training set details that would be typical for a de novo device clearance or a more extensive clinical validation study.

Therefore, many of the requested details cannot be extracted from this document. The document primarily states that the performance claims were not impacted by the change, implying that the performance previously demonstrated for the predicate device still holds true.

Here's what can be extracted and what cannot:

1. Table of acceptance criteria and reported device performance:

The document doesn't explicitly lay out "acceptance criteria" for a new device but rather compares the performance aspects of the submitted device (with the changed control materials) to the predicate device. It asserts that performance claims were not impacted. The relevant performance aspects of the predicate device (which the current device is deemed equivalent to) are listed, essentially serving as the implied performance to be met.

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

• The document states: "Performance of the cobas® Influenza A/B & RSV assay when used with NEG BUF as a negative control and positive control diluent was assessed."
• Sample size and data provenance are NOT explicitly stated. This document focuses on demonstrating that a change to control materials did not impact performance, rather than providing the full details of a new clinical study. The original predicate device's performance characteristics for Influenza A were established during the 2013-2014 and 2014-2015 influenza seasons, implying retrospective data from those periods for the predicate. However, details of the assessment of the impact of the control material change (which is the focus of this 510(k)) are not provided.

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

• NOT explicitly stated. This type of detail is typically found in clinical study reports for initial device approvals, not usually in a 510(k) for a minor modification like a control reagent change. The ground truth for real-time PCR assays like this is usually established by highly sensitive and specific laboratory methods (e.g., cell culture, sequencing, or a gold-standard PCR).

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

• NOT applicable/explicitly stated. This refers to human reader adjudication for image-based AI devices. This document describes an in vitro diagnostic (IVD) PCR assay, which ideally has a definitive laboratory-based ground truth rather than subjective human interpretation needing adjudication.

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 PCR assay, not an AI-assisted diagnostic imaging device that involves human readers.

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

• Partially Applicable. The cobas Liat System is an automated assay that processes samples and outputs results. The "performance" described (Limit of Detection, Reactivity, etc.) inherently represents its standalone (algorithm/instrument only) performance. There is no human interpretation component that would require a human-in-the-loop study.

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

• For molecular diagnostic tests like this, the ground truth is typically established by:
  • Clinically confirmed cases: Samples from patients with confirmed infections by other validated methods (e.g., viral culture, sequencing, or a highly sensitive and specific reference PCR method).
  • Characterized challenge panels: Samples with known concentrations of the target analytes and related organisms.
• The document implies that the ground truth for the predicate's performance was based on the presence/absence of viral RNA and likely confirmed by other laboratory methods. It references "established during the 2013-2014 and the 2014-2015 Influenza seasons," which suggests clinical samples with confirmed infection statuses.

8. The sample size for the training set:

• NOT applicable/explicitly stated. This is not an AI/machine learning device that typically has a "training set" in the common sense. It's a PCR assay with defined reagents and a fixed algorithm. The development would involve analytical verification and validation, but not machine learning "training."

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

• NOT applicable. See point 8.

Ask a specific question about this device

The cobas® Influenza A/B & RSV Nucleic acid test for use on the cobas® Liat® System (cobas® Influenza A/B & RSV) is an automated multiplex real-time RT-PCR assay for the rapid in vitro qualitative detection and discrimination of Influenza A virus, Influenza B virus and respiratory syncytial virus (RSV) RNA in nasopharyngeal swab specimens from patients with signs and symptoms of respiratory infection with clinical and epidemiological risk factors. The test is intended for use as an aid in the differential diagnosis of Influenza B, and RSV in humans and is not intended to detect Influenza C.

Negative results do not preclude Influenza virus or RSV infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule-out bacterial infection with other viruses. The agent detected may not be the definite cause of disease.

Performance characteristics for Influenza A were established during the 2013-2014 and the 2014-2015 Influenza seasons when Influenza A/H3 and A/H/N1 pandemic 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.

The cobas® Influenza A/B & RSV Nucleic Acid Test for use on the cobas® Liat® System (cobas® Influenza A/B & RSV) is an automated in vitro diagnostic test for the qualitative detection of Influenza A, Influenza B, and RSV RNA in nasopharyngeal swab (NPS) specimens. The sample-to-result time is ~20 minutes.

The assay is performed on the cobas® Liat® Analyzer which automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using real-time RT-PCR assays. The assay targets a well-conserved region of the matrix gene of Influenza A (Inf A target), the non-structure protein gene of Influenza B (Inf B target), and the matrix gene of RSV (RSV target). An Internal Process Control (IPC) is also included. The IPC is present to control for adequate processing of the target virus through all steps of the assay process and to monitor the presence of inhibitors in the RT-PCR reactions.

The cobas® Liat® System consists of an instrument and preloaded software for running tests and viewing the results. The system requires the use of a single-use disposable cobas® Influenza A/B & RSV assay tube that holds the nucleic acid purification and RT-PCR reagents, and hosts the sample preparation and RT-PCR processes.

The detection module monitors the reaction in real-time, while an on-board computer analyzes the collected data and outputs an interpreted result. The latter is displayed in the assay report on the integrated LCD touch screen of the cobas® Liat® Analyzer and in an electronic file. The report can be printed directly through a USB or network-connected printer. The results can also be exported to an external server, middleware or data management system, or to a Laboratory Information System (LIS).

Here's a breakdown of the acceptance criteria and study information for the cobas® Influenza A/B & RSV Nucleic acid test, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on demonstrating that the modified device (cobas® Influenza A/B & RSV Assay Script v1.16) has equivalent performance to the predicate device (cobas® Influenza A/B & RSV Assay Script v1.15). Therefore, the acceptance criteria are largely implicitly tied to matching or maintaining the performance characteristics of the predicate device.

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

• Sample Size: The test set included "multiple sample types" for each configuration of the assay script (v1.15 and v1.16). Specifically, these included negative controls, positive controls, negative specimens, and positive specimens containing co-formulated Influenza A, Influenza B, and RSV target material at a concentration of 3X the Limit of Detection (LoD). For the 3X LoD samples, mean Ct values were assessed.
• Data Provenance: The document does not explicitly state the country of origin. It indicates the study was conducted internally by Roche Molecular Diagnostics (RMD), Pleasanton, CA. It is a retrospective study in the sense that it compares a modified version of the software (v1.16) against a previously cleared version (v1.15) using defined sample types, rather than collecting new clinical samples from patients.

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

Not applicable. This study is an analytical performance assessment comparing a software version against a previous version, not a clinical study involving diagnosis by experts. The "ground truth" for the test set specimens (e.g., negative controls, positive controls, 3X LoD samples) would have been established by the manufacturer's internal quality control and characterization processes.

4. Adjudication Method for the Test Set

Not applicable, as this was an analytical comparison study of software versions, not a clinical trial requiring adjudication of diagnostic outcomes.

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

No. This was not a multi-reader, multi-case comparative effectiveness study. It was a technical comparison of an updated software algorithm (Assay Script v1.16) against a previous version (v1.15) for an existing in vitro diagnostic device. Therefore, there's no mention of human readers or improved performance with AI assistance.

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

Yes, this study is inherently a standalone performance assessment of the updated algorithm. The cobas® Liat® System is an automated system that outputs an interpreted result directly (qualitative detection of viral RNA). The study assessed the impact of the algorithm change on these automated results.

7. The Type of Ground Truth Used

The ground truth for the test set samples used in this study was based on:

• Defined characteristics of controls: Negative controls and positive controls have known compositions.
• Spiked samples: Positive specimens containing co-formulated target material at a known concentration (3X LoD) were used, allowing for a quantitative ground truth for viral load.

8. The Sample Size for the Training Set

The document does not provide information about a training set. The changes implemented were to an "Algorithm parameter" and "Correction of defects (bug fixes)" in the assay script. This suggests the changes were based on identifying and addressing specific performance characteristics or issues with the original algorithm, rather than a re-training of a machine learning model.

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

Not applicable, as a discrete "training set" in the context of machine learning model development is not mentioned or implied by the description of the software changes. The algorithm modifications were likely based on internal engineering analysis and optimization to address specific performance aspects (like tolerating early Cts) or bug fixes within the existing RT-PCR assay interpretation.

Ask a specific question about this device

The DiaSorin Molecular Simplexa™ Flu A/B & RSV Direct Gen II assay is intended for use on the LIAISON® MDX instrument for the in vitro qualitative detection and differentiation of influenza B virus, and respiratory syncytial virus (RSV) RNA in nasopharyngeal swabs (NPS) from human patients with signs and symptoms of respiratory tract infection in conjunction with clinical and epidemiological risk factors. This test is intended for use as an aid in the differential diagnosis of influenza A. influenza B. and RSV viral infections in humans.

Negative results do not preclude influenza virus or RSV infection and should not be used as the sole basis for treatment or other patient management decisions.

Performance characteristics for influenza A were established with clinical specimens collected during the 2010/2011 influenza season when 2009 H1N1 influenza and H3N2 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 the 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.

The DiaSorin Molecular Simplexa™ Flu A/B & RSV Positive Control Pack is intended to be used as a control with the Simplexa™ Flu A/B & RSV Direct kit and the Simplexa™ Flu A/B & RSV Direct Gen II kit for use on the LIAISON® MDX instrument. This control is not intended for use with other assays or systems.

Not Found

The provided document is a 510(k) clearance letter from the FDA for the DiaSorin Molecular Simplexa™ Flu A/B & RSV Direct Gen II assay. It primarily focuses on the device's regulatory clearance and indications for use, not on the detailed study results and acceptance criteria for performance evaluation.

Therefore, I cannot extract the detailed information requested in your prompt regarding acceptance criteria and performance study specifics from this document. The document states that the device is "substantially equivalent" to a legally marketed predicate device, implying that its performance was assessed, but the actual data and criteria are not included here.

To provide the answers you're looking for, I would need a different type of document, such as a summary of safety and effectiveness data (SSED) or the actual clinical study report that was submitted to the FDA for review.

Ask a specific question about this device

The cobas® Influenza A/B Nucleic acid test for use on the cobas® Liat® System (cobas® Influenza A/B) is an automated multiplex real-time RT-PCR assay for the rapid in vitro qualitative detection and discrimination of Influenza A virus and Influenza B virus RNA in nasopharyngeal swab specimens from patients with signs and symptoms of respiratory infection in conjunction with clinical and epidemiological risk factors. The test is intended for use as an aid in the differential diagnosis of Influenza A and Influenza B in humans and is not intended to detect Influenza C.

Negative results do not preclude Influenza virus infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease.

Performance characteristics for Influenza A were established when Influenza A/H1 and A/H3 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 BSL3+ facility is available to receive and culture specimens.

The cobas® Influenza A/B & RSV Nucleic acid test for use on the cobas® Liat® System (cobas® Influenza A/B & RSV) is an automated multiplex real-time RT-PCR assay for the rapid in vitro qualitative detection and discrimination of Influenza A virus. Influenza B virus and respiratory syncytial virus (RSV) RNA in nasopharyngeal swab specimens from patients with signs and symptoms of respiratory infection in conjunction with clinical and epidemiological risk factors. The test is intended for use as an aid in the differential diagnosis of Influenza A. Influenza B. and RSV in humans and is not intended to detect Influenza C. Negative results do not preclude Influenza virus or RSV infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule-out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease. Performance characteristics for Influenza A were established during the 2013-2014 and the 2014-2015 Influenza seasons when Influenza A/H3 and A/H1N1 pandemic 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 BSL3+ facility is available to receive and culture specimens.

The cobas® Strep A nucleic acid test for use on the cobas® Liat® System (cobas® Strep A) is a qualitative in vitro diagnostic test for the detection of Streptococcus pyogenes (Group A ß-hemolytic Streptococcus, Strep A) in throat swab specimens from patients with signs and symptoms of pharyngitis.

The cobas® Strep A assay utilizes nucleic acid purification and polymerase chain reaction (PCR) technology to detect Streptococcus pyogenes by targeting a segment of the Streptococcus pyogenes genome.

The cobas® Strep A Nucleic acid test for use on the cobas® Liat® System is intended for professional use in a clinical laboratory setting or point-of care (POC) location.

The cobas® Influenza A/B Nucleic Acid Test for use on the cobas® Liat® System is a rapid, automated in vitro diagnostic test for qualitative detection and differentiation of Influenza type A and type B viral RNA. The assay is performed on the cobas® Liat® System. The system automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using real-time RT-PCR assays. The cobas® Liat® Analyzer consists of an instrument and preloaded software for running tests and viewing the results. The cobas® Liat® System consists of the analyzer and a single-use disposable cobas® Influenza A/B assay tube that holds the sample purification and RT-PCR reagents and hosts the sample preparation and RT-PCR processes. Other than adding the sample to the cobas® Influenza A/B assay tube, no reagent preparation or additional steps are required. Because each cobas® Influenza A/B assay tube is self-contained, cross-contamination between samples is minimized. Turnaround time for a test is 20 minutes.

The cobas® Liat® Influenza A/B & RSV Nucleic Acid Test for use on the cobas® Liat® System is an automated in vitro diagnostic test for the qualitative detection of Influenza B, and RSV RNA in nasopharyngeal swab (NPS) specimens. The sample-to-result time is ~20 minutes.

The assay is performed on the Analyzer which automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using realtime PCR assays. The assay targets a well-conserved region of the matrix gene of Influenza A (Inf A target), the non-structure protein gene of Influenza B (Inf B target), and the matrix gene of RSV (RSV target). An Internal Process Control (IPC) is also included. The IPC is present to control for adequate processing of the target virus through all steps of the assay process and to monitor the presence of inhibitors in the RT-PCR reactions.

The System consists of an instrument and preloaded software for running tests and viewing the results. The system requires the use of a single-use disposable cobas® Influenza A/B & RSV assay tube that holds the nucleic acid purification and RT-PCR reagents, and hosts the sample preparation and RT-PCR processes.

The cobas® Strep Nucleic Acid Test for use on the cobas® Liat® System is a rapid, automated in vitro diagnostic test for the qualitative detection of Streptococcus pyogenes (Group A B -hemolytic Streptococcus, Strep A) DNA in throat swab specimens in Amies media.

The assay utilizes silica magnetic bead-based nucleic acid extraction, and TagMan probe-based real-time PCR amplification and detection. The assay targets a well-conserved region of the spy1258 gene of Strep A. An Internal Process Control (IPC) is also included. The IC is present to control for adequate processing of the target bacteria and to monitor the presence of inhibitors in the sample preparation and PCR.

The cobas® Liat® System automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples. Other than adding the sample to the cobas® Strep A assay tube, no reagent preparation or additional steps are required.

The system consists of an instrument with integrated software for running tests and analyzing the results. The system requires the use of a single-use disposable cobas® Strep A assay tube that holds all the sample purification and PCR reagents and hosts the sample preparation and PCR processes.

The provided text describes three distinct devices:

1. cobas® Influenza A/B Nucleic acid test for use on the cobas® Liat® System
2. cobas® Influenza A/B & RSV Nucleic acid test for use on the cobas® Liat® System
3. cobas® Strep A Nucleic acid test for use on the cobas® Liat® System

The submission K200065 is a 510(k) premarket notification for an update to the core software (Software 3.3) for these existing devices, rather than a new device or a new clinical study to establish primary performance. The key point is that the assay performance of each device was evaluated to ensure that the software changes did not impact the overall assay performance or claims when compared to the previously cleared software versions. Therefore, the provided document explicitly states that "analytical or clinical performance has not changed."

This means that the acceptance criteria and performance data for these devices were established in their original 510(k) submissions (K191729 for cobas Influenza A/B, K153544 for cobas Influenza A/B & RSV, and K141338 for cobas Strep A). The current submission (K200065) refers to these predicate devices for their performance characteristics.

Given this, I will extract the relevant performance data from the descriptions of the predicate devices as provided in the "Comparison of the... Assay with cobas® Liat® Analyzer Software 3.3 to the Predicate Device" tables for each assay.

1. cobas® Influenza A/B Nucleic acid test for use on the cobas® Liat® System

1. Table of Acceptance Criteria and Reported Device Performance

None of the provided sections for the cobas® Influenza A/B test (pages 5-13) specify explicit acceptance criteria or numerical performance metrics for Influenza A/B, beyond stating its intended use for qualitative detection and discrimination. The comparison table (pages 9-10) focuses on technological characteristics and states "Same" for most items, including a clinical laboratory improvement amendments (CLIA) waiver (CW150003). The conclusion explicitly states that "Performance of the cobas® Influenza A/B assay with cobas® Liat® Analyzer Software 3.3 was evaluated. The result of this evaluation determined that the overall cobas® Influenza A/B assay performance and claims were not impacted by changes implemented in cobas® Liat® Analyzer Software 3.3, when compared to the current commercially available core software version." This implies that the performance as established in K191729 is maintained. However, the specific metrics from K191729 are not detailed in this document.

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

Not provided in this document as it refers to prior clearance (K191729). The current submission is for a software update, and performance was "evaluated" to ensure no impact.

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

Not applicable/provided for this software update.

4. Adjudication method for the test set

Not applicable/provided for this software update.

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 nucleic acid test, not an imaging AI diagnostic.

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

This is an automated in vitro diagnostic test, which inherently operates in a standalone manner. The results are output on a screen.

7. The type of ground truth used

Not detailed as this submission is for a software update. The original K191729 likely used a reference method (e.g., culture or another FDA-cleared molecular assay) as the ground truth.

8. The sample size for the training set

Not applicable/provided as this is a software update for an existing assay.

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

Not applicable/provided.

2. cobas® Influenza A/B & RSV Nucleic acid test for use on the cobas® Liat® System

1. Table of Acceptance Criteria and Reported Device Performance

The provided text (pages 14-22) does not specify explicit numerical acceptance criteria for sensitivity or specificity for Flu A, Flu B, or RSV. However, it lists several performance characteristics from the predicate device (K153544) that were confirmed to be unchanged by the software update.

Study Proving Device Meets Acceptance Criteria:
The document states: "Performance of the cobas® Influenza A/B & RSV assay with cobas® Liat® Analyzer Software 3.3 was evaluated. The result of this evaluation determined that the overall cobas® Influenza A/B & RSV assay performance and claims were not impacted by changes implemented in cobas® Liat® Analyzer Software 3.3, when compared to the current commercially available core software version." (page 21). This evaluation confirms that the modified device (with Software 3.3) maintains the performance characteristics established by the predicate device (K153544). Specific details of this evaluation (e.g., sample size, specific tests) are not provided in this summary.

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

The document does not detail the sample size or provenance for the evaluation performed for this software update (K200065). These details would have been part of the original K153544 submission. For the current submission, a "performance evaluation" was conducted to ensure no impact from the software changes.

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

Not applicable/provided for this software update.

4. Adjudication method for the test set

Not applicable/provided for this software update.

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 nucleic acid test.

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

Yes, this is an automated in vitro diagnostic test, operating in a standalone manner with results displayed directly to the user.

7. The type of ground truth used

Not detailed in this document. For the original K153544, it would have been a reference method such as viral culture or another FDA-cleared molecular assay.

8. The sample size for the training set

Not applicable/provided.

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

Not applicable/provided.

3. cobas® Strep A Nucleic acid test for use on the cobas® Liat® System

1. Table of Acceptance Criteria and Reported Device Performance

The provided text (pages 23-30) does not specify explicit numerical acceptance criteria for sensitivity or specificity for Strep A. However, it lists several performance characteristics from the predicate device (K141338) that were confirmed to be unchanged by the software update.

Study Proving Device Meets Acceptance Criteria:
The document states: "Performance of the cobas® Strep A assay with cobas® Liat® Analyzer Software 3.3 was evaluated. The result of this evaluation determined that the overall cobas® Strep A assay performance and claims were not impacted by changes implemented in cobas® Liat® Analyzer Software 3.3, when compared to the current commercially available core software version." (page 29). This evaluation confirms that the modified device (with Software 3.3) maintains the performance characteristics established by the predicate device (K141338). Specific details of this evaluation (e.g., sample size, specific tests) are not provided in this summary.

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

The document does not detail the sample size or provenance for the evaluation performed for this software update (K200065). These details would have been part of the original K141338 submission. For the current submission, a "performance evaluation" was conducted to ensure no impact from the software changes.

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

Not applicable/provided for this software update.

4. Adjudication method for the test set

Not applicable/provided for this software update.

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 nucleic acid test.

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

Yes, this is an automated in vitro diagnostic test, operating in a standalone manner with results displayed directly to the user.

7. The type of ground truth used

Not detailed in this document. For the original K141338, it would have been a reference method such as bacterial culture or another FDA-cleared molecular assay.

8. The sample size for the training set

Not applicable/provided.

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

Not applicable/provided.

Ask a specific question about this device

The BioCode Respiratory Pathogen Panel (RPP) is a qualitative multiplexed nucleic acid-based in vitro diagnostic test intended for use with BioCode MDx 3000 Instrument. The BioCode of the simultaneous detection and identification of nucleic acids from multiple viruses and bacteria extracted from nasopharyngeal swab (NPS) samples obtained from individuals with signs and/or symptoms of respiratory tract infection. The following pathogens and subtypes are identified using the BioCode RPP:

• Adenovirus
• · Coronavirus (229E, OC43, HKU1, and NL63)
• Human Metapneumovirus A/B
• · Influenza A, including subtypes H1, H1 2009 Pandemic, and H3
• Influenza B
• Parainfluenza Virus 1
• Parainfluenza Virus 2
• · Parainfluenza Virus 3
• · Parainfluenza Virus 4
• · Respiratory Syncytial Virus A/B
• Rhinovirus/Enterovirus
• · Bordetella pertussis
• Chlamydia pneumoniae
• Mycoplasma pneumoniae

The detection and identification of specific viral and bacterial nucleic acids from individuals exhibiting signs and/or symptoms of a respiratory infection aids in the diagnosis of respiratory infection if used in conjunction with other clinical and epidemiological information. The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions.

Negative results in the setting of a respiratory illness may be due to infection with pathogens that are not detected by this test, or lower respiratory tract infection that may not be detected by a nasopharyngeal swab specimen. Positive results do not rule out co-infection with other organisms: the agent(s) detected by the BioCode RPP may not be the definite cause of disease. Additional laboratory testing (e.g. bacterial and viral culture, immunofluorescence, and radiography) may be necessary when evaluating a patient with possible respiratory tract infection.

Due to the genetic similarity between Human Rhinovirus, the BioCode RPP cannot differentiate them. A positive BioCode RPP Rhinovirus/Enterovirus result should be followed up using an alternate method (e.g., cell culture or sequence analysis) if differentiation is required. The BioCode RPP detects Human Rhinovirus with reduced sensitivity. If a more accurate Rhinovirus result is required, it is recommended that specimens found to be negative for Human Rhinovirus/Enterovirus after examination using BioCode RPP be confirmed by an alternate method (e.g. FDA cleared molecular tests).

Performance characteristics for Influenza A were established when Influenza A H1 2009 Pandemic and A H3 were the predominant Influenza A viruses in circulation. Performance of detecting Influenza A may vary if other Influenza A strains are circulating or a novel Influenza A virus emerges.

The BioCode® Respiratory Pathogen Panel is a respiratory pathogen multiplex nucleic acid test designed for use with the BioCode® MDx-3000 system. The BioCode® MDx-3000 is an automated system that integrates PCR amplification, target capture, signal generation and optical detection for multiple viral and bacterial pathogens from a single nasopharyngeal swab specimen collected in transport media. Specimens are processed and nucleic acids extracted with the NucliSens easyMAG or Roche MagNA Pure 96 automated systems. Once the PCR plate is set up and sealed, all other operations are automated on MDx-3000. The BioCode® RPP simultaneously tests for 17 pathogens and/or subtypes (see table below) from nasopharyngeal swab specimens collected in UTM or VTM. Results from the BioCode RPP test are available within about 5 hours, including off-board nucleic acids extraction.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text.

Based on the provided text, the device is an in vitro diagnostic test (BioCode Respiratory Pathogen Panel - RPP). The primary evidence for meeting acceptance criteria comes from clinical performance studies and analytical performance studies. The document does not explicitly state pre-defined acceptance criteria values (e.g., "Positive Agreement must be > X%"), but rather presents the results achieved and implicitly confirms they meet regulatory expectations for substantial equivalence.

Acceptance Criteria and Reported Device Performance

Since explicit numerical acceptance criteria were not stated, I'll present the reported performance, which implicitly met the necessary thresholds for FDA clearance. The document focuses on Positive Percent Agreement (PA) and Negative Percent Agreement (NA) compared to an FDA-cleared molecular multiplexed respiratory pathogen panel (the "comparator test").

Table of Acceptance Criteria (Implicit) and Reported Device Performance (Clinical Study - Total Specimens)

Study Details:

1. Sample Size and Data Provenance:

   • Clinical Test Set (Prospective Study):
     • Sample Size: 2649 residual nasopharyngeal swab (NPS) specimens in VTM or UTM.
     • Data Provenance: Prospectively collected from patients suspected of respiratory tract infections at five geographically diverse clinical sites in the U.S. (August 2017 to May 2019). Specimens were either tested freshly (stored 2-8°C for no more than 7 days) or stored frozen and thawed later.
   • Clinical Test Set (Archived Specimens - Retrospective Study):
     • Sample Size: 165 clinical specimens (archived NPS in VTM or UTM).
     • Data Provenance: Retrospective, preselected archives from source laboratories, chosen because they had previously tested positive for low-prevalence pathogens or were negative. These specimens were then randomized and blinded.
   • Contrived Specimens (Analytical Performance):
     • Chlamydia pneumoniae & Influenza A H1: 50 unique negative natural NPS in VTM or UTM specimens were spiked to create 100 positive samples (2X LOD or greater) and interspersed with negative samples. A total of 110 samples were tested.
     • Reproducibility Study: 6 contrived positive samples and 1 negative sample, each extracted in triplicate, each assayed in singlet. This translates to 90 samples per concentration level per extraction type (easyMAG, MagNA Pure 96) across multiple sites/runs, total 90 (3x LoD) + 90 (1.5x LoD) + 450 (no analyte) = 630 for each virus/bacteria category listed (e.g., Adenovirus, Coronavirus, Human Metapneumovirus).
     • Limit of Detection (LoD): 20 replicates for each target at or near the presumptive LoD.
     • Analytical Reactivity/Inclusivity: Triplicate extractions for each strain/serotype.
     • Analytical Specificity/Cross Reactivity: Triplicate extractions for each off-panel and on-panel organism.
     • Interfering Substances/Microbes: Triplicate extractions for each sample/substance combination.
     • Competitive Inhibition: Triplicate extractions for each pooled sample.
     • Specimen Stability: Triplicate extractions for each time point and storage condition.
     • Matrix Equivalency: Quadruplicate extractions for each pool/matrix combination.

2. Number of Experts and Qualifications for Ground Truth:

   • The document states that the BioCode RPP test results were compared against those from an "FDA-cleared molecular multiplexed respiratory pathogen panel" (Standard of Care/Comparator Test). This FDA-cleared comparator test serves as the primary "ground truth" for the clinical studies.
   • For discrepant results in the clinical studies, further investigation was conducted by "performing independent molecular tests, including analytically validated PCR followed by bi-directional sequencing assays and alternate NAATs." This implies the use of specialized laboratory personnel with expertise in molecular diagnostics, but the exact number or specific qualifications (e.g., "radiologist with 10 years of experience") are not specified as this is a molecular diagnostic device, not an imaging device typically read by radiologists. The ground truth for presence/absence of pathogens is established by these comparator and confirmatory molecular tests.

3. Adjudication Method for the Test Set:

   • For the clinical studies (prospective and archived), the method for addressing discrepancies between the BioCode RPP and the comparator test was to perform "independent molecular tests, including analytically validated PCR followed by bi-directional sequencing assays and alternate NAATs." This serves as an adjudication method, where an orthogonal, high-accuracy method is used to determine the true positivity or negativity of discrepant samples. The specific "2+1" or "3+1" concensus type is not explicitly mentioned, but the retesting with confirmatory methods acts as a form of adjudication.

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

   • No, an MRMC study was not done. This type of study (comparative effectiveness with human readers) is typical for AI-powered imaging devices where human interpretation is a key component. The BioCode RPP is an in vitro diagnostic (IVD) molecular test where the output is directly from the instrument analysis, not reliant on human interpretation of complex images. The study focuses on comparing the device's accuracy against a legally marketed predicate device/standard of care, not on improving human reader performance.

5. Standalone Performance (Algorithm Only):

   • Yes, the primary performance evaluation is standalone. The device ("BioCode RPP") is a qualitative multiplexed nucleic acid-based in vitro diagnostic test for use with the "BioCode MDx-3000 Instrument." The instrument integrates PCR, target capture, signal generation, and optical detection. The results are generated by the system (the "algorithm" in this context refers to the instrument's processing logic and interpretation algorithm), and the performance metrics (PA, NA) are reported for this system. There is no human interpretation component in the direct testing process that could be "assisted" by the algorithm.

6. Type of Ground Truth Used:

   • The ground truth for the clinical test sets (prospective and archived) was established by an FDA-cleared molecular multiplexed respiratory pathogen panel (Standard of Care).
   • For discrepant results, expert molecular laboratory retesting using analytically validated PCR followed by bi-directional sequencing assays and alternate NAATs served as the confirmatory ground truth. This is a form of expert consensus/confirmatory testing using highly accurate molecular methods.
   • For the analytical studies (e.g., LoD, inclusivity, specificity, inhibition), the ground truth was based on known concentrations of purified organisms/nucleic acids or genetically characterized strains (e.g., ATCC strains, Zeptometrix controls). This is a form of analytical ground truth where the content is precisely controlled and known.

7. Sample Size for the Training Set:

   • The document does not specify a separate "training set" sample size. For IVD devices, especially those based on molecular assays, a distinct "training set" as understood in machine learning (where an algorithm learns from labeled data) is not typically described in the same way. The device's underlying "algorithm" is the biochemical and optical detection system itself, and its performance characteristics are established through extensive analytical and clinical validation, not by training on a large dataset of patient samples in the AI sense. The design and validation are based on principles of molecular biology and traditional assay development.

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

   • As there isn't a "training set" in the machine learning sense, this question isn't directly applicable for this type of IVD device. The development of the assay (e.g., primer and probe design) would rely on known genetic sequences of the target pathogens. The validation data (clinical and analytical studies) demonstrate that the final, developed assay meets its intended performance, rather than being used to train a model in an iterative machine learning manner.

Ask a specific question about this device

NxTAG® Respiratory Pathogen Panel is a qualitative test intended for use on the Luminex® MAGPIX® Instrument for the simultaneous detection and identification of nucleic acids from multiple respiratory viruses and bacteria extracted from nasopharyngeal swabs collected from individuals with clinical signs and symptoms of a respiratory tract infection. The organism types and subtypes detected by the test are Influenza A H1, Influenza A H3, Influenza B, Respiratory Syncytial Virus A, Respiratory Syncytial Virus B, Coronavirus OC43, Coronavirus NL63, Coronavirus HKU1, Human Metapneumovirus, Rhinovirus/Enterovirus, Parainfluenza virus 1, Parainfluenza virus 2, Parainfluenza virus 3, Parainfluenza virus 4, Human Bocavirus, Chlamydophila pneumoniae, and Mycoplasma pneumoniae.

The test is indicated as an aid in the detection and identification of viral and bacterial agents causing respiratory tract infections in symptomatic adult and pediatic patients, who are either hospitalized, admitted to emergency departments or who are outpatients with suspected respiratory tract infection.

The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Negative results in the setting of a respiratory illness may be due to infection with pathogens not detected by this test or lower respiratory tract infection that is not detected by a nasopharyngeal swab specimen. Positive results do not rule out co-infection with other pathogens. The agent detected may not be the cause of disease. The use of additional laboratory testing (e.g. bacterial and viral culture, immunofluorescence, and radiography) and clinical presentation must be taken into consideration in order to obtain the final diagnosis of respiratory tract infection.

Performance characteristics for influenza A were established using specimens obtained during the 2013/2014 and 2014/2015 influenza seasons 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 authorties, specimens should be collected with appropriate infection control precautions for novel virulent Influenza viruses and sent to state or local health departments for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.

Not Found

The provided document is an FDA 510(k) clearance letter for the NxTAG Respiratory Pathogen Panel, a diagnostic device. It does not contain information about acceptance criteria or a study that proves the device meets those criteria in the way described in your prompt (e.g., performance against ground truth established by experts, MRMC studies, or standalone algorithm performance). This document is primarily an administrative letter confirming substantial equivalence to a predicate device and outlining regulatory information.

The information you are requesting typically comes from detailed study reports submitted as part of the 510(k) application, which are not included in this clearance letter. The letter briefly mentions "Performance characteristics for influenza A were established using specimens obtained during the 2013/2014 and 2014/2015 influenza seasons," but it does not provide the specific performance metrics, study design, or ground truth details.

Therefore, I cannot fulfill your request using only the information provided in the given document. The document confirms the device's clearance and its intended use, but it does not delve into the specifics of the validation study's acceptance criteria, sample sizes, expert qualifications, or ground truth establishment.

Ask a specific question about this device

The cobas® Influenza A/B Nucleic acid test for use on the cobas® Liat® System (cobas® Influenza A/B) is an automated multiplex real-time RT-PCR assay for the rapid in vitro qualitative detection and discrimination of Influenza A virus and Influenza B virus RNA in nasopharyngeal swab specimens from patients with signs and symptoms of respiratory infection in conjunction with clinical and evidemiological risk factors. The test is intended for use as an aid in the differential diagnosis of Influenza A and Influenza B in humans and is not intended to detect Influenza C.

Negative results do not preclude Influenza virus infection and should not be used as the sole basis for treatment or other patient management decisions. Conversely, positive results do not rule out bacterial infection or co-infection with other viruses. The agent detected may not be the definite cause of disease.

Performance characteristics for Influenza A were established when Influenza A/H1 and A/H3 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 BSL3+ facility is available to receive and culture specimens.

The cobas® Influenza A/B assay is a rapid, automated in vitro diagnostic test for qualitative detection and differentiation of Influenza type A and type B viral RNA. The assay is performed on the cobas® Liat® System. The system automates and integrates sample purification, nucleic acid amplification, and detection of the target sequence in biological samples using real-time RT-PCR assays. The cobas® Liat® Analyzer consists of an instrument and preloaded software for running tests and viewing the results. The cobas® Liat® System consists of the analyzer and a single-use disposable cobas® Influenza A/B assay tube that holds the sample purification and RT-PCR reagents and hosts the sample preparation and RT-PCR processes. Other than adding the sample to the cobas® Influenza A/B assay tube, no reagent preparation or additional steps are required. Because each cobas® Influenza A/B assay tube is self-contained, cross-contamination between samples is minimized. Turnaround time for a test is 20 minutes.

The cobas® Influenza A/B assay includes reagents for the detection and differentiation of Influenza A and B viral RNA in nasopharyngeal swab (NPS) specimens in universal transport media (UTM) from patients suspected of having Influenza. The assay targets a well-conserved region of the matrix gene of Influenza A viral RNA (Inf A target) and non-structural protein (NS) gene of Influenza B (Inf B target). An Internal Process Control (IPC) is also included. The IPC is present to control for adequate processing of the target viruses through all steps of the assay process and to monitor the presence of inhibitors in the RT-PCR reactions.

The cobas® Influenza A/B assay tube uses a flexible tube as a sample processing vessel. It contains all requisite PCR reagents pre-packed in assay tube segments separated by breakable seals. When a cobas® Influenza A/B assay tube containing a raw biological sample is inserted into the cobas Liat® Analyzer. multiple sample processing actuators in the cobas® Liat Analyzer compress the cobas® Influenza A/B assay tube to selectively release the reagents, moving the sample from one segment to the next, and controlling reaction conditions. An embedded microprocessor controls and coordinates these actions to perform all required assay processes, including sample preparation, nucleic acid extraction, target concentration enrichment, inhibitor removal, nucleic acid elution, and real-time PCR. All assay steps are performed within the closed and self-contained cobas® Influenza A/B assay tube, minimizing cross-contamination between samples.

The detection module monitors the reaction in real-time, while an on-board computer analyzes the collected data and outputs an interpreted result. The latter is displayed in the assay report on the integrated LCD touch screen of the cobas® Liat® Analyzer and in an electronic file. The report can be printed directly through a USB or network-connected printer. The results can also be exported to an external server, middleware or data management system, or to a Laboratory Information System (LIS).

The provided document does not contain information related to an AI/ML-based device; instead, it describes a nucleic acid amplification test (NAT) for the detection of Influenza A/B. Therefore, many of the requested details, such as MRMC studies, training set specifics, and expert adjudication, which are pertinent to AI/ML device evaluations, are not applicable to this submission.

However, I can extract the relevant information regarding the device's performance evaluation and acceptance criteria for this specific type of diagnostic test.

Acceptance Criteria and Reported Device Performance

The document describes the cobas® Influenza A/B Nucleic acid test for use on the cobas® Liat® System. This is a real-time RT-PCR assay for the qualitative detection and differentiation of Influenza A and B viral RNA. The evaluation focuses on demonstrating that the performance of the updated software version (FABA v1.35) is equivalent to the previously cleared version (FABA v1.31) and does not negatively impact the assay's existing performance claims.

Since this is a diagnostic test and not an AI/ML device, the performance is primarily evaluated in terms of its analytical and clinical performance as a diagnostic test, rather than typical AI metrics like AUC, sensitivity, or specificity for an AI model. The document states that the overall cobas® Influenza A/B assay performance and claims were not impacted by changes implemented in FABA v1.35.

Table of Acceptance Criteria (Implied) and Reported Device Performance:

"Equivalent performance of the modified device and the current commercial device has been demonstrated, and analytical or clinical performance has not changed." |
| Regulatory Equivalence | Substantial equivalence to the predicate device (K111387 and CW150003). | The modified device is substantially equivalent to the predicate device, as originally cleared through K111386 and CLIA waived through CW150003. |

Important Note: The document focuses on demonstrating that the software update (FABA v1.35) does not degrade the already established performance of the cobas® Influenza A/B assay. It does not re-establish the primary performance characteristics (e.g., clinical sensitivity, specificity) from scratch, but rather ensures the new software maintains the established performance. Therefore, detailed performance metrics (like percentages for sensitivity/specificity) for the entire assay are not reiterated in this summary specifically for the software update, as they were presumably part of the original clearance.

Study Details for the Software Update (FABA v1.35)

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

   • The document states that the performance was evaluated using "data from submissions (K111386, CW150003), internal studies, release testing, and the field."
   • Specific sample sizes for these evaluations are not provided in this summary.
   • Data provenance (e.g., country of origin, retrospective/prospective) is not specified for these combined data sources, beyond "internal studies, release testing, and the field." The reference to previous FDA clearances (K111386, CW150003) implies that some data would have been derived from clinical samples used in those original studies, which are typically prospective for diagnostic assay clearances.

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

   • This is a diagnostic assay, and ground truth for such tests is typically established through a combination of reference methods (e.g., viral culture, another cleared PCR assay, or a composite reference standard) rather than human expert consensus on images.
   • Therefore, the concept of "experts" in the context of radiologists or similar interpreters for AI/ML models is not applicable here. The ground truth for influenza detection would be based on the established gold standard for virological diagnosis.

3. Adjudication Method for the Test Set:

   • Not applicable in the context of an AI/ML model's output being adjudicated by human experts. For a diagnostic assay, discrepant results between the investigational device and the reference method would typically undergo further investigation (e.g., retesting, re-extraction), but not "adjudication" by multiple human readers of an output.

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

   • No. This is a diagnostic RT-PCR assay, not an AI/ML system that assists human readers in interpreting medical images or data. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant or performed for this type of device.

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

   • In a sense, yes, the "algorithm" (the RT-PCR chemistry and instrument's software interpretation) is standalone in that it provides a direct qualitative result (Influenza A detected, Influenza B detected, Negative, Invalid) without requiring human interpretation of raw signals beyond basic quality control. The human "in the loop" is the laboratory technologist performing the test and reviewing the automated result, but not interpreting nuanced images or complex data as in AI applications. The performance evaluation therefore focuses on the accuracy and reliability of these automated results.

6. The Type of Ground Truth Used:

   • The document does not explicitly state the ground truth methodology for the software update evaluation, but for the initial assay clearances (K111386, CW150003) mentioned, the ground truth for an influenza diagnostic test would typically be established by:
     • Composite Reference Standard (CRS): Often involves multiple methods, such as viral culture, another FDA-cleared molecular assay, and/or clinical presentation.
     • Clinical Diagnosis: Corroborated by symptoms and potentially other lab findings.
     • Reference Laboratory PCR: Testing using highly sensitive and specific laboratory-developed or research-use only PCR tests considered to be expert-level.
   • The critical aspect of this submission is demonstrating that the changes in the software (FABA v1.35) do not alter the established performance characteristics, meaning the ground truth from prior studies remained valid against the updated software's performance.

7. The Sample Size for the Training Set:

   • Not applicable in the context of an AI/ML training set. This is a rule-based diagnostic algorithm for PCR analysis, not a machine learning model that requires explicit training data in the same way. The software changes refer to updates in logic and bug fixes, developed based on internal R&D processes and prior performance data, not a "training set" for model parameters.

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

   • Not applicable as there is no "training set" in the AI/ML sense for this type of device. The logic and cut-offs for the RT-PCR assay are based on established molecular biology principles and analytical validation, refined and verified through various studies to define detection thresholds and interpretation rules.

Ask a specific question about this device