Search Results

The BD CTGCTV2 assay incorporates automated DNA extraction and real-time polymerase chain reaction (PCR) for the direct, qualitative detection of DNA from:

• Chlamydia trachomatis (CT)
• Neisseria gonorrhoeae (GC)
• Trichomonas vaginalis (TV)

The assay may be used for detection of CT, GC and/or TV DNA in patient- or clinician-collected vaginal swab specimens (in a clinical setting) and male and female urine specimens. The assay may also be used for the detection of CT and GC DNA in endocervical swab and Liquid-Based Cytology (LBC) specimens in ThinPrep® PreservCyt® Solution using an aliquot that is removed prior to processing for the ThinPrep® Pap test. The assay may also be used for the detection of CT and GC DNA in clinician-collected rectal and oropharyngeal swab specimens.

The assay is indicated for use with asymptomatic and symptomatic individuals to aid in the diagnosis of chlamydial, gonococcal, and/or trichomoniasis urogenital disease and chlamydial and gonococcal extragenital infection.

The BD CTGCTV2 assay is available for use with the BD MAX™ System (urogenital specimens) or the BD COR™ System (urogenital and extragenital specimens), as described above.

The BD CTGCTV2 assay, performed on the BD COR™ System (hereafter referred to as BD CTGCTV2), is designed for use with the applicable BD Molecular specimen collection and transport devices for male and female urine, rectal swabs, oropharyngeal swabs, vaginal swabs, endocervical swabs, and LBC specimens (PreservCyt®). Specimens are collected and transported to the testing laboratory using their respective transport devices under conditions of time and temperature that have been determined to maintain the integrity of the target nucleic acids.

The BD COR™ MX Instrument, when combined with the BD COR™ PX Instrument, is to be used for automated sample preparation, extraction, and purification of nucleic acids from multiple specimen types, as well as the automated amplification and detection of target nucleic acid sequences by fluorescence-based real-time PCR for simultaneous and differential detection of Chlamydia trachomatis, Neisseria gonorrhoeae, and Trichomonas vaginalis.

The BD CTGCTV2 assay extraction reagents are dried in 96-well microtiter plates that contain binding magnetic affinity beads and Sample Processing Control (SPC). Each tube is capable of binding and eluting sample nucleic acids. The SPC monitors the integrity of the reagents and the process steps involved in DNA extraction, amplification and detection, as well as for the presence of potential assay inhibitors.

The BD CTGCTV2 assay liquid reagent plate includes Wash, Elution and Neutralization buffers. The beads (described above), together with the bound nucleic acids, are washed and the nucleic acids are eluted by a combination of heat and pH. When performed on BD COR™ System, there is an additional buffer to rehydrate the dried extraction mix. Eluted DNA is neutralized and transferred to the Amplification reagent (described below) to rehydrate the PCR reagents. After reconstitution, the BD COR™ System dispenses a fixed volume of PCR-ready solution containing extracted nucleic acids into the BD PCR Cartridge. Microvalves in the BD PCR Cartridge are sealed by the system prior to initiating PCR in order to contain the amplification mixture and thus prevent evaporation and contamination.

The BD CTGCTV2 assay is comprised of two targets for Chlamydia trachomatis (detected on the same optical channel), two targets for Neisseria gonorrhoeae (detected on two different optical channels) and one target for Trichomonas vaginalis (detected on one optical channel). Only one Chlamydia trachomatis target is required to be positive in order to report a positive result. Both Neisseria gonorrhoeae targets are required to be positive in order to report a positive result.

The amplified DNA targets are detected using hydrolysis (TaqMan®) probes, labeled at one end with a fluorescent reporter dye (fluorophore), and at the other end, with a quencher moiety. Probes labeled with different fluorophores are used to detect the target analytes in different optical channels of the BD COR™ System. When the probes are in their native state, the fluorescence of the fluorophore is quenched due to its proximity to the quencher. However, in the presence of target DNA, the probes hybridize to their complementary sequences and are hydrolyzed by the 5'-3' exonuclease activity of the DNA polymerase as it synthesizes the nascent strand along the DNA template. As a result, the fluorophores are separated from the quencher molecules and fluorescence is emitted. The BD COR™ System monitors these signals at each cycle of the PCR and interprets the data at the end of the reaction to provide qualitative test results for each analyte (i.e., positive or negative).

The provided FDA 510(k) clearance letter and summary for the BD CTGCTV2 assay detail its performance in detecting Chlamydia trachomatis (CT) and Neisseria gonorrhoeae (GC) in extragenital specimens (rectal and oropharyngeal swabs).

Here's an analysis based on your request:

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the BD CTGCTV2 assay are implicitly demonstrated through its clinical performance results, where the assay's sensitivity (Positive Percent Agreement - PPA) and specificity (Negative Percent Agreement - NPA) for extragenital specimens are compared against a Composite Comparator Algorithm (CCA). The FDA's clearance indicates that these performance metrics met the necessary standards for substantial equivalence.

Table of Acceptance Criteria and Reported Device Performance:

While explicit numerical acceptance criteria (e.g., "PPA must be >= X%") are not directly stated in the provided text, the reported performance measures are the ones that met the FDA's requirements for clearance.

Ask a specific question about this device

CentroVena Central Venous Catheter (CVC)

Acute central venous catheters are indicated to provide short term access (

Vena Central Venous Catheters are power-injectable, constructed of medical grade polyurethane and designed for insertion into the central venous system. The central venous catheters are radiopaque and have a soft tip that is more pliable than the catheter body. Each catheter is provided in a sterile package with other applicable insertion kit accessories.

The CentroVena One Insertion System integrates the essential components for placing central venous catheters. It combines an introducer needle with a passive needle tip safety mechanism, syringe, guidewire, and self-dilating catheter into one unit. The device is preassembled and also has an integrated drape clip permanently attached to the guidewire designed to keep the system organized in the sterile field and prevent guidewire embolism.

The provided document is a 510(k) clearance letter for a medical device: CentroVena Central Venous Catheter (CVC) with the CentroVena One Insertion System.

Important Note: The document is primarily a regulatory approval and comparison to a predicate device. It lists numerous "acceptance criteria" through reference standards and tests, but it does not provide the specific numerical results or performance metrics that demonstrate the device quantitatively meets these criteria. It also doesn't detail specific study designs for these tests beyond listing the reference standards.

Therefore, the following information will be extracted where explicitly stated or inferable from the document. Many aspects of a detailed study design (like sample sizes for performance tests, expert qualifications, adjudication methods, or specific effect sizes for human performance improvement with AI) are not typically included in a 510(k) summary for a physical medical device like a catheter and related insertion system as they are more relevant to AI/software as a medical device studies.

Description of Acceptance Criteria and the Study that Proves the Device Meets the Acceptance Criteria

The CentroVena Central Venous Catheter (CVC) with the CentroVena One Insertion System underwent various performance and safety tests to demonstrate substantial equivalence to its predicate device, the BD Acute Central Line (K190855). The acceptance criteria for the device are primarily derived from compliance with recognized industry consensus standards and FDA guidance documents. The studies involved functional performance testing, biocompatibility testing, and evaluation of the insertion system.

1. Table of Acceptance Criteria (as indicated by reference standards) and Reported Device Performance

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

The document does not explicitly state the specific sample sizes for each of the numerous tests conducted. The testing described is typical for physical medical devices and usually involves a statistically relevant number of units/components for each specific test to ensure robust results.

The data provenance is not explicitly stated beyond the fact that these are tests conducted by Becton Dickinson Inc. (BD) to support their 510(k) submission. These would generally be pre-market, prospective tests conducted in a controlled laboratory environment. The country of origin of the data is not mentioned but would presumably be where BD's testing facilities are located.

3. Number of Experts and Qualifications for Ground Truth

This information is not applicable and not provided in the document. The device is a physical catheter and insertion system, not an AI/software device that requires expert labeled ground truth for image interpretation or diagnosis. The "ground truth" for these tests would be the established scientific and engineering principles outlined in the reference standards themselves.

4. Adjudication Method

This information is not applicable. Adjudication methods (like 2+1, 3+1 consensus) are typically used in studies where human readers are interpreting images or data and their decisions need to be reconciled to establish a ground truth, often for AI performance evaluation. This is not relevant for the type of bench and performance testing documented here.

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

No MRMC study was done or is mentioned. This type of study is specifically designed for evaluating the performance of diagnostic devices, especially those involving human interpretation (e.g., radiology AI aids), and comparing human performance with and without AI assistance. This device is a physical medical instrument, not a diagnostic AI.

6. Standalone (Algorithm Only) Performance

Not applicable. This device is a physical medical instrument, not an algorithm or software requiring standalone performance testing.

7. Type of Ground Truth Used

The "ground truth" for the various performance tests is established by:

• Established Industry Consensus Standards: Such as ISO 10993, ISO 10555, ASTM F640, etc. These standards outline methodologies and acceptable performance limits for specific characteristics of medical devices.
• FDA Guidance Documents: Which also provide testing recommendations and performance expectations for device types.
• Engineering Specifications and Design Requirements: The device must meet its own design specifications, which are based on the intended use and safety considerations, often derived from the above standards.

8. Sample Size for the Training Set

Not applicable. This device is a physical medical instrument, not an AI/machine learning model that requires a training set. The tests performed are for verification and validation of the manufactured device.

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

Not applicable. As there is no training set for this type of device, no ground truth needs to be established for it.

Ask a specific question about this device

The BDC Dental Unit is intended to supply power to and serve as a base for dental devices and accessories. This device includes a dental chair and is intended for use in the dental clinic environment and is designed for use by trained dental professionals, dentists and/or dental assistants.

The BDC dental unit is intended to supply air, water, vacuum and electrical power to allow the dental practitioner an intuitive control center for all common and normal patient treatment procedures performed in the dental operatory. The BDC dental unit consists of a patient chair, dentist element (tray table), assistant element (3-way syringe, high volume evacuator and saliva ejector), side cabinet support center, foot control, cuspidor and a dental operating light, which for patient to sit during the dental diagnosis, treatment and/or operation.

The provided text appears to be an FDA 510(k) clearance letter and summary for a dental unit. It describes a medical device (BDC Dental Unit) that is essentially a dental chair with integrated controls for air, water, vacuum, and electrical power for dental devices. The device's primary function is to serve as a base and power supply for other dental instruments used by trained dental professionals.

Based on the provided document, there is NO information about an AI/ML component or study involving acceptance criteria related to AI/ML device performance. The document focuses on establishing substantial equivalence to a predicate device (A-dec 500) through non-clinical testing of mechanical, electrical, software (non-AI), and biocompatibility aspects.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance for an AI/ML component.
2. Sample size and data provenance for an AI/ML test set.
3. Number and qualifications of experts for AI/ML ground truth.
4. Adjudication method for an AI/ML test set.
5. Multi Reader Multi Case (MRMC) comparative effectiveness study for AI assistance.
6. Standalone (algorithm only without human-in-the-loop performance) study for an AI/ML component.
7. Type of ground truth for an AI/ML component.
8. Sample size for the training set (for AI/ML).
9. How ground truth for the training set was established (for AI/ML).

The document explicitly states: "Clinical data is not needed to characterize performance and establish substantial equivalence. The non-clinical test data characterize all performance aspects of the device based on well-established scientific and engineering principles. Clinical testing has not been conducted on this product." This further reinforces that there was no study like the one you are asking for, especially not one involving human readers or AI performance metrics.

The "Software Verification and Validation Testing" section mentions: "The software for this device was considered as a 'BASIC' level of concern, since a failure or latent flaw in the software would not directly result in serious injury or death to the patient or operator." This implies standard software validation, not necessarily AI/ML model validation.

In summary, the provided text does not contain the information required to answer your prompt regarding acceptance criteria and studies for an AI/ML medical device. The device described is a conventional dental unit, and its clearance is based on substantial equivalence to a predicate device through standard non-clinical performance and safety testing.

Ask a specific question about this device

The Denali™ Filter is indicated for use in the prevention of recurrent pulmonary embolism via placement in the vena cava in the following situations:

-Pulmonary thromboembolism when anticoagulants are contraindicated

-Failure of anticoagulant therapy for thromboembolic disease

-Emergency treatment following massive pulmonary embolism where anticipated benefits of conventional therapy are reduced

-Chronic, recurrent pulmonary embolism where anticoagulant therapy has failed or is contraindicated.

The Denali™ Filter may be removed according to the instructions supplied under the Section labeled: Optional Procedure for Filter Removal.

The Denali™ Vena Cava Filter is a venous interruption device designed to prevent pulmonary embolism. The Denali™ Filter can be delivered via the femoral and jugular/subclavian approaches. A separate delivery system is available for each approach. The Denali™ Filter is designed to act as a permanent filter. When clinically indicated, the Denali™ Filter may be percutaneously removed after implantation according to the instructions provided under the "Optional Procedure for Filter Removal" section in the Instructions for Use.

The Denali™ Filter consists of twelve shape-memory laser-cut nickel-titanium appendages. These twelve appendages form two levels of filtration with the legs providing the lower level of filtration and the arms providing the upper level of filtration. The Denali™ Filter is intended to be used in the inferior vena cava (IVC) with a diameter less than or equal to 28mm.

The Denali™ Vena Cava Filter System consists of an introducer sheath, an 8 French dilator, and a preloaded Denali™ Filter in a storage tube with a pusher. The 8 French dilator accepts a 0.035" guidewire and allows for an 800 psi maximum pressure contrast power injection. Radiopaque marker bands on the end of the dilator aid in measuring the maximum indicated IVC diameter. They are spaced at a distance of 28mm (outer-to-outer). The 55cm, 8.4 French I.D. introducer sheath contains a radiopaque marker and hemostasis valve with a side port. The pusher advances the filter through the introducer sheath to the predeployment mark and is then used to fix the filter in place while the filter is unsheathed.

This document, K240257, pertains to a 510(k) premarket notification for the "Denali™ Vena Cava Filter System – Femoral and Jugular/Subclavian Delivery Kit." It explicitly states that no changes have been made to the subject Denali™ Filter or Delivery System and that no performance testing was performed. The purpose of the submission is solely to update the Instructions for Use (IFU) for inclusion of the PRESERVE study summary data.

Therefore, there is no information in this document regarding new acceptance criteria for the device or a study performed to prove the device meets new acceptance criteria. The approval is based on the substantial equivalence to a predicate device (K160866) and the clinical testing previously provided to the FDA under an Investigational Device Exemption.

As the request asks to describe the acceptance criteria and the study that proves the device meets the criteria, and this document states no new testing was performed, I cannot provide the requested information from this document.

Summary of available information:

• No new acceptance criteria or device performance reported in this document. The submission focuses on updating the Instructions for Use with summary data from the PRESERVE study, which was previously conducted for the predicate device.
• No new studies were conducted for this submission. The document explicitly states: "Therefore, no performance testing was performed." and "The clinical testing was previously provided to FDA under the Investigational Device Exemption."

All other questions regarding sample size, data provenance, number of experts, adjudication method, MRMC study, standalone study, type of ground truth, and training set details are not applicable or cannot be answered from the provided text, as no new studies or performance evaluations were conducted for this 510(k) submission.

Ask a specific question about this device

The BD Veritor™ System for Rapid Detection of Flu A+B CLIA-Waived Kit is a rapid chromatographic immunoassay for the direct and qualitative detection of influenza A and B viral nucleoprotein antigens from nasal and nasopharyngeal swabs of symptomatic patients. The BD Veritor™ System for Rapid Detection of Flu A+B CLIA-Waived Kit (also referred to as the BD Veritor System and BD Veritor System Flu A+B) is a differentiated test, such that influenza A viral antigens can be distinguished from influenza B viral antigens from a single processed sample using a single device. The test is to be used as an aid in the diagnosis of influenza A and B viral infections. A negative test is presumptive, and it is recommended that these results be confirmed by viral culture or an FDA-cleared influenza A and B molecular assay. Negative test results do not preclude influenza viral infection and should not be used as the sole basis for treatment or other patient management decisions. The test is not intended to detect influenza C antigens.

Performance characteristics for influenza A and B were established during January through March of 2011 when influenza viruses A/2009 H1N1, A/H3N2, B/Victoria lineage, and B/Yamagata lineage were the predominant influenza viruses in circulation according to the Morbidity and Mortality Weekly Report from the CDC entitled "Update: Influenza Activity-United States, 2010-2011 Season, and Composition of the 2011-2012 Influenza Vaccine." Performance characteristics may vary against other emerging influenza viruses.

If infection with a novel influenza 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. Virus culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.

The BD Veritor™ System for Rapid Detection of Flu A+B CLIA Waived Kit is a rapid chromatographic immunoassay for the direct and qualitative detection of influenza A and B viral antigens from nasopharyngeal and nasal swabs of symptomatic patients. The test is to be used as an aid in the diagnosis of influenza A and B viral infections. It is a differentiated test, such that influenza A viral antigens can be distinguished from influenza B viral antigens from a single processed sample using a single test device. Negative test results do not preclude influenza viral infection and should not be used as the sole basis for treatment or other management decisions. All negative test results should be confirmed by another methodology, such as a nucleic acid-based method.

BD Veritor™ System Flu A+B test devices are interpreted by a BD Veritor™ Plus Analyzer. When using the BD Veritor™ Plus Analyzer, workflow steps depend on the selected operational mode and the Analyzer configuration settings. In Analyze Now mode, the instrument evaluates assay devices after manual timing of their development. In Walk Away mode, devices are inserted immediately after application of the specimen, and timing of assay development and analysis is automated.

The BD Veritor™ System Flu A+B CLIA-Waived Kit is an immuno-chromatographic assay for detection of influenza A and B viral antigens in samples processed from respiratory specimens. The viral antigens detected by the BD Flu A+B test are nucleoprotein, not hemagglutinin (HA) or neuraminidase (NA) proteins. Flu viruses are prone to minor point mutations (i.e., antigenic drift) in either one or both of the surface proteins (i.e., HA or NA). The BD Flu A+B test is not affected by antigenic drift or shift because it detects the highly conserved nucleoprotein of the influenza viruses. To perform the test, the patient specimen swab is treated in a supplied reaction tube prefilled with a lysing agent that serves to expose the target viral antigens, and then expressed through a filter tip into the sample well on a BD Veritor"10 Flu A+B test device. Any influenza A or influenza B viral antigens present in the specimen bind to anti-influenza antibodies conjugated to colloidal gold micro-particles on the BD Veritor™ Flu A+B test strip. The antigen-conjugate complex then migrates across the test strip to the capture zone and reacts with either Anti-Flu A or Anti-Flu B antibodies that are immobilized on the two test lines on the membrane.

The BD Flu A+B test device shown in Figure 1 is designed with five spatially distinct zones including positive and negative control line positions, separate test line positions for the target analytes, and a background zone. The test lines for the target analytes are labeled on the test device as 'A' for flu A position, and 'B' for flu B position. The onboard positive control ensures the sample has flowed correctly and is indicated on the test device as 'C'. Two of the five distinct zones on the test device are not labeled. These two zones are an onboard negative control line and an assay background zone. The active negative control feature in each test identifies and compensates for specimen-related, nonspecific signal generation. The remaining zone is used to measure the assay background.

The BD Veritor™ Plus Analyzer is a digital immunoassay instrument that uses a reflectance-based measurement method and applies assay specific algorithms to determine the presence or absence of the target analyte. The Analyzer supports the use of different assays by reading an assay-specific barcode on the test device. Depending on the configuration chosen by the operator, the instrument communicates status and results to the operator via a liquid crystal display (LCD) on the instrument, a connected printer, or through a secure connection to the facility's information system.

In the case of the Flu A + B test, the BD Veritor™ Plus Analyzer subtracts nonspecific signal at the negative control line from the signal present at both the Flu A and Flu B test lines. If the resultant line signal is above a pre-selected assay cutoff, the specimen scores as positive. If the resultant line signal is below the cutoff, the specimen scores as negative. Use of the active negative control feature allows the BD Veritor™ Plus Analyzer to correctly interpret test results that cannot be scored visually because the human eye is unable to accurately perform the subtraction of the nonspecific signal. The measurement of the assay background zone is an important factor during test interpretation as the reflectance is compared to that of the control and test zones. A background area that is white to light pink indicates the device has performed correctly.

The provided text describes a 510(k) premarket notification for modifications to the BD Veritor™ System for Rapid Detection of Flu A+B CLIA-Waived Kit. The current submission (K232434) focuses on changes to the BD Veritor™ Plus Analyzer, not the assay itself. Therefore, the details about acceptance criteria and clinical performance studies relate to the predicate device (K223016) and the assay's original clearance (K180438), as the modifications in K232434 do not impact the assay's analytical or clinical performance.

Here's a breakdown based on the provided input:

1. Table of Acceptance Criteria and Reported Device Performance

The current submission (K232434) is for modifications to the analyzer, not a new or modified assay. Therefore, it does not present new acceptance criteria or device performance data for the assay's diagnostic accuracy. Instead, it relies on the previously established performance of the predicate device (K223016) which itself relies on the performance established in K180438. The acceptance criteria for the current submission are related to the safety and electromagnetic compatibility of the modified analyzer.

Performance Characteristics for Influenza A and B (as established for K180438 / K223016 and referenced here):

The document mentions that performance characteristics for influenza A and B were established during January through March of 2011. While specific sensitivity and specificity values are not provided in this document excerpt, the "Indications for Use" and "Intended Use" sections clearly state that the device is for "direct and qualitative detection of influenza A and B viral nucleoprotein antigens."

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

The provided text does not include the specific sample size for the test set used to establish the clinical performance of the Flu A+B assay, nor does it explicitly state the data provenance (e.g., retrospective or prospective studies) in detail, beyond mentioning:

• "Performance characteristics for influenza A and B were established during January through March of 2011"
• This period corresponded to when "influenza viruses A/2009 H1N1, A/H3N2, B/Victoria lineage, and B/Yamagata lineage were the predominant influenza viruses in circulation" in the United States, according to CDC reports. This implies real-world, clinical data from symptomatic patients in the US during that influenza season was used.

Since the current submission is for analyzer modifications and explicitly states, "Clinical Performance: Clinical performance testing was not required because the changes made to the Analyzer do not have an impact on the assay-specific clinical performance," this information would be found in the original submission (K180438) that cleared the assay.

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

This information is not provided in the given text. It would be part of the detailed clinical study report from the original assay clearance (K180438).

4. Adjudication Method for the Test Set

This information is not provided in the given text. It would be part of the detailed clinical study report from the original assay clearance (K180438).

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

This is not applicable to the BD Veritor System. This device is a rapid chromatographic immunoassay read by a digital analyzer (BD Veritor™ Plus Analyzer), not an AI system designed to assist human readers in interpreting complex images or data. The analyzer automatically interprets the test results based on its algorithms and provides a positive, negative, or invalid result, rather than providing input to a human reader for their interpretation.

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

Yes, in essence, the BD Veritor™ Plus Analyzer operates as a standalone algorithm without human-in-the-loop performance for result interpretation. The text states:

• "The Analyzer is a digital immunoassay instrument that uses a reflectance-based measurement method and applies assay specific algorithms to determine the presence or absence of the target analyte."
• "The BD Veritor™ Plus Analyzer subtracts nonspecific signal at the negative control line from the signal present at both the Flu A and Flu B test lines. If the resultant line signal is above a pre-selected assay cutoff, the specimen scores as positive. If the resultant line signal is below the cutoff, the specimen scores as negative."
• "Use of the active negative control feature allows the BD Veritor™ Plus Analyzer to correctly interpret test results that cannot be scored visually because the human eye is unable to accurately perform the subtraction of the nonspecific signal."

This clearly describes an automated interpretation process by the device's algorithms.

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

The document states, "A negative test is presumptive, and it is recommended that these results be confirmed by viral culture or an FDA-cleared influenza A and B molecular assay." This implies that viral culture or an FDA-cleared influenza A and B molecular assay served as the reference standard (ground truth) for establishing performance characteristics during the original clinical studies.

8. The Sample Size for the Training Set

This information is not provided in the given text, and it's less relevant for an immunoassay where "training data" for a machine learning model might not be explicitly defined in the same way as for complex AI algorithms. For immunoassays, the "training" involves optimizing the assay reagents and conditions, and setting cutoff values, which are then validated with clinical samples.

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

This information is not provided in the given text. As mentioned above, the concept of a "training set ground truth" might not apply directly in the traditional sense for this type of immunoassay. Instead, the ground truth for establishing performance (and implicitly for setting cutoffs) would be established using the reference methods mentioned in point 7.

Ask a specific question about this device

BD Respiratory Viral Panel for BD MAX™ System is an automated multiplexed real-time reverse transcriptase polymerase chain reaction (RT- PCR) test intended for the simultaneous, qualitative detection and differentiation of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), influenza A, influenza B, and/or respiratory syncytial virus (RSV) nucleic acid in nasopharyngeal swab (NPS) and anterior nasal swab (ANS) specimens from individuals with signs and symptoms of respiratory tract infection. Clinical signs and symptoms of respiratory tract infection due to SARS-COV-2, influenza, and RSV can be similar.

BD Respiratory Viral Panel for BD MAX™ System is intended for use as an aid in the differential diagnosis of SARS-CoV-2, influenza A, influenza B, and/or RSV infection if used in conjunction with other clinical and epidemiological information, and laboratory findings. SARS-CoV- 2, influenza A, influenza B, and RSV viral nucleic acid are generally detectable in NPS and ANS specimens during the acute phase of infection.

Positive results do not rule out co-infection with other organisms. The agent(s) detected by the BD Respiratory Viral Panel for BD MAX™ System may not be the definitive cause of disease.

Negative results do not preclude SARS-CoV-2, influenza B, and/or RSV infection.

The results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions.

BD Respiratory Viral Panel-SCV2 for BD MAX™ System:

BD Respiratory Viral Panel-SCV2 for BD MAX™ System is an automated multiplexed real-time reverse transcriptase polymerase chain reaction (RT-PCR) test intended for the simultaneous, qualitative detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) viral nucleic acid in nasopharyngeal swab (NPS) and anterior nasal swab (ANS) specimens from individuals with signs and symptoms of respiratory tract infection. SARS-CoV-2 viral RNA is generally detectable in NPS and ANS specimens during the acute phase of infection.

The BD Respiratory Viral Panel-SCV2 for BD MAX™ System is intended for use as an aid in the diagnosis of SARS-CoV-2 infection if used in conjunction with other clinical and epidemiological information, and laboratory findings.

Positive results do not rule out co-infection with other organisms. The agent detected by the BD Respiratory Viral Panel-SCV2 for BD MAX™ System may not be the definitive cause of disease.

Negative results do not preclude SARS-CoV-2 infection.

The results of this test should not be used as the sole basis for diagnosis, treatment management decisions.

The BD Respiratory Viral Panel (BD RVP) and BD Respiratory Viral Panel-SCV2 (BD RVP-SCV2) along with the BD MAXTM System are comprised of an instrument with associated hardware and accessories, disposable microfluidic cartridges, master mixes, unitized reagent strips, and extraction reagents. The instrument automates sample preparation including target lysis, Total Nucleic Acid (TNA) extraction and concentration, reagent rehydration, target nucleic acid amplification and detection using real-time PCR. The assay includes a Sample Processing Control (SPC) that is present in the Extraction Tube. The SPC monitors RNA extraction steps, thermal cycling steps, reagent integrity and the presence of inhibitory substances. The BD MAX™ System software automatically interprets test results. For the BD Respiratory Viral Panel for BD MAX™ System and BD Respiratory Viral Panel-SCV2 for BD MAX™ System, a test result may be called as POS, NEG or UNR (Unresolved) based on the amplification status of the targets and of the Sample Processing Control. IND (Indeterminate) or INC (Incomplete) results are due to BD MAX™ System failure.

The provided text describes the analytical and clinical performance evaluation of two molecular diagnostic devices: the BD Respiratory Viral Panel (BD RVP) for BD MAX System and the BD Respiratory Viral Panel-SCV2 (BD RVP-SCV2) for BD MAX System. Both are real-time RT-PCR tests for detecting respiratory viruses in nasopharyngeal and anterior nasal swab specimens.

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

Important Note: The provided text is a summary of a 510(k) premarket notification. As such, it reports performance data but does not explicitly state "acceptance criteria" in the format of a pre-defined table with specific percentage goals for PPA and NPA. Instead, the reported performance itself serves as the demonstration that the device is "substantially equivalent" to predicate devices, implying that the observed performance would be considered acceptable by the FDA for the given intended use. For this response, I will interpret "acceptance criteria" as the performance metrics and results deemed sufficient for clearance.

1. Table of Acceptance Criteria (Interpreted) and Reported Device Performance

Given that this is a 510(k) submission, the "acceptance criteria" are not explicitly listed with numeric targets in the document. Instead, the reported performance is presented to demonstrate substantial equivalence to legally marketed predicate devices. The implicit acceptance criteria are the high percentages of Positive Percent Agreement (PPA) and Negative Percent Agreement (NPA) achieved by the device when compared to a composite reference method (ground truth).

The primary performance data comes from clinical evaluation studies for both the BD RVP and BD RVP-SCV2.

BD Respiratory Viral Panel (BD RVP) for BD MAX System - Clinical Performance Summary

BD Respiratory Viral Panel-SCV2 (BD RVP-SCV2) for BD MAX System - Clinical Performance Summary

For BD RVP-SCV2 clinical performance, the text refers to the same clinical study results as BD RVP, but only for SARS-CoV-2.

• SARS-CoV-2 (NP Swab): PPA 34.6% (541/1562), NPA not explicitly listed but implied from overall subject data. This seems to be a positivity rate, not an agreement rate. The clinical performance summary tables (Table 28 and 29) for SARS-CoV-2 are the relevant ones.
  • NP (Overall): PPA 98.9%, NPA 97.7%
  • ANS (Overall): PPA 98.4%, NPA 97.7%
    (These are the same as reported for the full BD RVP, which makes sense as SCV2 is a subset).

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

BD Respiratory Viral Panel (BD RVP) for BD MAX System:

• Prospective Clinical Evaluation:

  • Sample Size:
    • 2,005 subjects enrolled.
    • Test Set: 1,562 nasopharyngeal swabs (NPS) and 1,566 anterior nasal swabs (ANS).
    • For performance calculations, slightly fewer compliant specimens were used:
      • NPS: 1,545 for SARS-CoV-2, 1,562 for Flu A, Flu B, and RSV.
      • ANS: 1,561 for SARS-CoV-2, 1,564 for Flu A, Flu B, and RSV.
  • Data Provenance:
    • Country of Origin: United States (six geographically distinct U.S. study sites) and Europe (two geographically distinct sites).
    • Retrospective or Prospective: Primarily Prospective. Specimens were collected between January and August 2022.
      • January to early April 2022: Prospective archived/frozen (Category II).
      • Mid-April to August 2022: Prospective fresh (Category I).

• Retrospective Clinical Evaluation:

  • Sample Size:
    • NPS: 240 frozen retrospective nasopharyngeal swabs.
    • Nasal Swabs: 187 frozen retrospective nasal swabs.
  • Data Provenance:
    • Country of Origin: Not explicitly stated within the retrospective section, but implied to be part of the broader US/Europe context from the prospective study.
    • Retrospective or Prospective: Retrospective. Specimens collected between December 2019 and January 2022 (for NPS) and February 2021 and February 2023 (for nasal swabs) from external sources. These were "archived, frozen specimens".

BD Respiratory Viral Panel-SCV2 for BD MAX System:

• The text states: "In the BD Respiratory Viral Panel-SCV2 for BD MAX™ System clinical study, reportable results from specimens compliant at the specimen and PCR levels were obtained from 8 geographically diverse sites. Nasopharyngeal and nasal specimens totaled 1.566 respectively." This refers to the same clinical study data as the broader BD RVP, specifically focusing on SARS-CoV-2 results from that dataset.

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

The document does not specify the number of experts or their qualifications for establishing ground truth.

Instead, the ground truth for the clinical evaluation (test set) was established by comparison to highly sensitive molecular assays (NAATs).

• For SARS-CoV-2: A composite method of "two out of three highly sensitive molecular assays (NAATS) that are FDA authorized under EUA for SARS-CoV-2."
• For influenza B and RSV: "an FDA-cleared high sensitivity RT-PCR assay."

This indicates an analytical or "reference method" based ground truth rather than a human expert consensus.

4. Adjudication Method for the Test Set

The adjudication method relies on a "two out of three" rule for SARS-CoV-2 and a single FDA-cleared RT-PCR assay for influenza B and RSV.

• SARS-CoV-2: "Any specimen that tested positive by two EUA assays was considered positive for SARS-CoV-2, whereas any specimen that tested negative by two EUA assays was considered negative."
• Influenza B and RSV: Comparison to a single "FDA-cleared high sensitivity RT-PCR assay."

No explicit 2+1 or 3+1 human expert adjudication method is mentioned, as the ground truth derivation is assay-based.

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

No, an MRMC comparative effectiveness study was not done. This device is a diagnostic assay (RT-PCR test), not an AI-assisted imaging product. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply. The performance is assessed on the device's ability to accurately detect specific viral nucleic acids.

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

While the term "algorithm" is used to describe the software interpreting PCR data, the entire device (BD MAX System with the viral panel) is an automated system. The performance data presented (PPA, NPA) is the standalone performance of the device without human interpretation of the raw PCR signals for diagnosis. The BD MAX™ System software "automatically interprets test results" (page 7). Therefore, the clinical performance described is the standalone performance.

7. The Type of Ground Truth Used

The ground truth used was reference method comparison / composite molecular assay results:

• SARS-CoV-2: Composite reference method using results from "two out of three highly sensitive molecular assays (NAATs) that are FDA authorized under EUA for SARS-CoV-2." (Page 42)
• Influenza A, Influenza B, and RSV: An "FDA-cleared high sensitivity RT-PCR assay." (Page 42)

This is a form of "analytical ground truth" established by other validated diagnostic tests, rather than pathology, expert consensus on images, or long-term clinical outcomes.

8. The Sample Size for the Training Set

The document does not explicitly state a separate "training set" sample size for the assay's development in the context of a statistical machine learning model.

However, it mentions: "As the product undergoes product development, the data is supplemented, and the algorithm is adjusted ('trained') using viral cultures spiked into clinical background matrices at levels surrounding the limit of detection and expected clinical range." (Page 30, and repeated on Page 40 for SCV2). This refers to internal development and optimization using contrived samples, not a distinct, pre-defined "training set" of patient data for a typical AI/ML model for regulatory submission.

Performance data for the submission is based on the "test set" (clinical evaluation studies described in section 2) and analytical studies.

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

As noted above, there isn't a "training set" ground truth in the sense of independently verified patient data used to directly train a submitted AI model. Instead, the "algorithm" (how the BD MAX software interprets PCR signals to call positive/negative) was "adjusted ('trained')" using:

• Viral cultures spiked into clinical background matrices at various concentrations (e.g., around the Limit of Detection and expected clinical range).
• These are contrived samples with a known (positive or negative) status and precise viral concentrations.

The ground truth for these internal development/training stages would be the known concentration of spiked viral material.

Ask a specific question about this device

The BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application is an in-vitro diagnostic software program that requires the BD Kiestra™ Laboratory Automation Solution in order to operate.

The BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application is applied to digital images of BD BBL™ CHROMagar™ MRSA II culture plates inoculated with anterior nares samples.

Algorithms are applied to digital images to provide a qualitative assessment of colony growth and colorimetric detection of target colonies for the detection of nasal colonization by MRSA and to serve as an aid in the prevention and control of MRSA infection. Applied algorithms provide the following results:

• "No growth", which will be manually released individually or as a batch (with other no growth samples) by . a trained microbiologist upon review of the digital plate images.
• . "Growth - other" (growth without mauve color), which digital plate images will be manually reviewed by a trained microbiologist.
• "Growth MRSA Mauve" (growth with mauve color), which digital plate images will be manually reviewed ● by a trained microbiologist.

The assay is not intended to guide, diagnose, or monitor treatment for MRSA infections. It is not intended to provide results of susceptibility to oxacillin/methicillin.

The BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application is indicated for use in the clinical laboratory.

The BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application will be optional for the BD Kiestra™ Laboratory Automation Solution and will support laboratory technologists in batching no growth on the BD BBL™ CHROMagar™ MRSA II, growth with no key colony color detected for MRSA ("Growth – other"), and growth with key colony color detected for MRSA ("Growth MRSA Mauve"). These classifications will be characterized as "no growth" and "growth with mauve color" from BD BBLTM CHROMagar™ MRSA II media, from anterior nares samples.

The technologist has the ability to create work lists in BD Synapsys™ informatics solution based on the classifications (growth, no growth or growth with mauve color). These work lists will be used for followup work and batching of results, at the sample level.

The BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application will apply Image Algorithms to the digital images to determine if the plate contains "growth" or "no growth". At the individual plate level when the Image Algorithms detects colony growth and potential mauve color the classification will be "growth with mauve color".

When the BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application is not capable of automatically generating the outputs (visual attributes: growth with or without mauve color/no growth), the laboratory technologist will be required to read the digital image of the plate on the computer screen and decide on follow-up action as is the current standard laboratory practice.

Here's a summary of the acceptance criteria and the study details for the BD Kiestra™ Methicillin-resistant Staphylococcus aureus (MRSA) Application, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated as distinct numerical targets in the provided document. However, the studies demonstrate performance metrics related to agreement with manual interpretation and reproducibility.

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

• Digital Quality Image Study:
  • Sample Size: 521 plate images (across 3 microbiologists, so 174, 172, and 175 plates respectively for each microbiologist's manual review).
  • Data Provenance: Internal digital image quality study, using simulated surveillance samples (MRSA, non-MRSA, saline controls). Implies data was generated specifically for this study. The location or country of origin is not explicitly stated, but it's an "internal" study. The nature (simulated surveillance samples) suggests it was a prospective generation of samples for the study.
• Digital Image Reproducibility Study:
  • Sample Size: 518 plate images (3 images excluded due to invalid results from at least one microbiologist).
  • Data Provenance: Same as the Digital Quality Image Study, as it re-analyzed the results from that study. "Internal" study, likely newly generated for this purpose.
• Reproducibility Study (Seeded Samples):
  • Sample Size: Variable, ranging from 55 to 1056 individual observations per dilution/organism combination across two sites. Total observations are in the thousands (e.g., 2089 for saline controls).
  • Data Provenance: Internal reproducibility study using seeded samples (bacterial strains grown in saline). Conducted at two internal sites (BD Sparks, MD location). This is also prospective generation of data.
• Clinical Performance Studies:
  • Sample Size: Approximately 1,800 clinical anterior nares specimens.
  • Data Provenance: Clinical anterior nares specimens. Collected at "three clinical sites." The text does not specify the country of origin, but "clinical sites" generally refer to real-world healthcare settings. This is a prospective collection of real patient samples.

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

• Digital Quality Image Study & Digital Image Reproducibility Study:
  • Number of Experts: 3.
  • Qualifications: "Three trained clinical microbiologists." Specific years of experience or board certifications are not provided.
• Reproducibility Study (Seeded Samples):
  • The ground truth for seeded samples is inherently defined by the known organisms and dilutions used to create the samples. The study then assesses the automated system's agreement with this known "ground truth" for growth and color. Human experts here are likely involved in verifying the initial seeding and later in the interpretation of the results, but the definition of "mauve" or "non-mauve" for specific strains is pre-defined.
• Clinical Performance Studies:
  • Number of Experts: Not explicitly stated as a fixed number, but the images were "manually read by trained microbiologists at those sites." This implies multiple microbiologists across the three clinical sites.
  • Qualifications: "Trained microbiologists." Specific years of experience or board certifications are not provided.

4. Adjudication method for the test set

• Digital Image Reproducibility Study: The "final digital image result" was "determined by 2/3 majority microbiologist result." This indicates a form of consensus-based adjudication, specifically a majority vote among the three microbiologists.
• Other studies (Digital Quality Image, Reproducibility with Seeded Samples, Clinical Performance): The primary comparison for these studies appears to be between the device's output and individual manual reads by microbiologists or known characteristics of seeded samples. Explicit adjudication methods for generating a single "ground truth" reference for these specific studies are not detailed, though for the clinical study, the manual read at each site serves as the reference.

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

• A MRMC comparative effectiveness study, where human readers' performance with and without AI assistance is quantitatively measured and compared, is not explicitly described in the provided text.
• The studies focus on the agreement of the device with manual reads (Digital Quality Image, Clinical Performance) and the reproducibility of human reads of digital images (Digital Image Reproducibility). While these demonstrate the device's capability to produce similar results to human reads, they don't directly quantify the improvement of human readers due to AI assistance. The device's stated purpose is to "aid in the prevention and control of MRSA infection" and to support laboratory technologists in "batching" and "streamline and optimize the reading workflow," suggesting an assistive role. However, the magnitude of this assistance in terms of effect size on human reader performance is not presented.

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

• Yes, a standalone performance analysis was conducted. The tables in the "Analytical Performance" and "Clinical Performance Studies" sections (e.g., Table 1, Table 6, and the final clinical performance table on page 17) directly compare the BD Kiestra™ MRSA App's output to the manual plate reads or ground truth. The "Percent Agreement" values (e.g., "No Growth Percent Agreement 75.6% (773/1023)") represent the algorithm's performance against those references.
• It's important to note that even when the app provides results, the indications for use state that "No growth", "Growth - other", and "Growth MRSA Mauve" classifications "will be manually reviewed by a trained microbiologist." This means that while the algorithm provides a classification, a human-in-the-loop is always part of the final release process. However, the data presented directly assesses the algorithm's standalone accuracy in classifying the images.

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

• Expert Consensus: Used in the "Digital Image Reproducibility Study," where a 2/3 majority microbiologist result formed the ground truth for comparing individual microbiologist reproducibility.
• Manual Expert Reading: For the "Digital Quality Image Study" and the "Clinical Performance Studies," the ground truth was established by the manual interpretation of the plates (or digital images of plates) by trained microbiologists. This acts as the "gold standard" for comparison.
• Known Sample Characteristics: For the "Reproducibility Study (Seeded Samples)," the ground truth was defined by the known bacterial strains, dilutions, and expected growth/color characteristics of the seeded samples.

8. The sample size for the training set

• The document does not provide information on the sample size used for the training set. It focuses solely on the performance of the already-trained and developed algorithm.

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

• The document does not describe how the ground truth for the training set was established. Information regarding the training data, annotation process, or expert involvement in labeling training data is not included in the provided text.

Ask a specific question about this device

The BD Veritor System for Rapid Detection of Flu A+B CLIA waived assay is a rapid chromatographic immunoassay for the direct and qualitative detection of influenza A and B viral nucleoprotein antigens from nasal and nasopharyngeal swabs of symptomatic patients. The BD Veritor System for Rapid Detection of Flu A+B (also referred to as the BD Veritor System and BD Veritor System Flu A+B) is a differentiated test, such that influenza A viral antigens can be distinguished from influenza B viral antigens from a single processed sample using a single device. The test is to be used as an aid in the diagnosis of influenza A and B viral infections. A negative test is presumptive and it is recommended that these results be confirmed by viral culture or an FDA-cleared influenza A and B molecular assay. Negative test results do not preclude influenza viral infection and should not be used as the sole basis for treatment or other patient management decisions. The test is not intended to detect influenza C antigens.

The BD Veritor™ System for Rapid Detection of Flu A+B is a rapid chromatographic immunoassay for the direct and qualitative detection of influenza A and B viral antigens from nasopharyngeal and nasal swabs of symptomatic patients. The test is to be used as an aid in the diagnosis of influenza A and B viral infections. It is a differentiated test, such that influenza A viral antigens can be distinguished from influenza B viral antigens from a single processed sample using a single test device. Negative test results do not preclude influenza viral infection and should not be used as the sole basis for treatment or other management decisions. All negative test results should be confirmed by another methodology, such as a nucleic acid-based method.

BD Veritor™ System Flu A+B test devices are interpreted by a BD Veritor™ Plus Analyzer. When using the BD Veritor™ Plus Analyzer, workflow steps depend on the selected operational mode and the Analyzer configuration settings. In Analyze Now mode, the instrument evaluates assay devices after manual timing of their development. In Walk Away mode, devices are inserted immediately after application of the specimen, and timing of assay development and analysis is automated. Depending on the configuration chosen by the operator, the instrument communicates status and results to the operator via a liquid crystal display (LCD) on the instrument, a connected printer, or through a secure connection to the facility's information system.

This document (K223016) is a 510(k) Premarket Notification for a modified version of the BD Veritor System for Rapid Detection of Flu A+B CLIA-Waived Kit. The core assay (the rapid immunoassay for Influenza A and B detection) remains unchanged from previous clearances (K180438 and earlier). The modifications focus on the accompanying instrument, the BD Veritor™ Plus Analyzer.

Therefore, the document explicitly states "There have been no changes to the analytical performance of the BD Veritor™ System for Rapid Detection of Flu A+B CLIA-Waived Kit since the assay was last cleared in K180438. The modifications to the Analyzer do not have an impact on the assay-specific analytical performance. " and "There have been no changes to the clinical performance of the BD Veritor™ System for Rapid Detection of Flu A+B CLIA-Waived Kit since the assay was last cleared in K180438. The modifications to the Analyzer do not have an impact on the assay-specific clinical performance."

This means that no new performance studies (analytical or clinical) were conducted for the assay itself as part of this specific 510(k) submission. The acceptance criteria and performance data for the assay would refer to the studies presented in the previous 510(k)s, most recently K180438.

The testing performed for this K223016 submission focuses solely on the modifications made to the BD Veritor™ Plus Analyzer:

1. Overvoltage Protection Circuitry: Testing confirms that the added circuitry does not affect the function of the trigger board (recognition of a cartridge and USB connection).
2. Extended Lifetime: Verification that the Analyzer performs up to 10,000 cycles (tests) within current specifications (increased from 3,500 tests).
3. InfoWiFi Module Functionality: Verification of the general functionalities of the new InfoWiFi module, which provides wireless communication capabilities.

Since the provided document does not contain the details of the analytical and clinical performance studies for the assay, and instead refers to previous submissions, I cannot extract the specific acceptance criteria and detailed study data for the assay itself from this text.

Assuming the request is for the acceptance criteria and study proving the changes to the analyzer meet the criteria, the following applies:

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

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

• Sample Size: Not explicitly stated in the document for any of the new tests. The document refers to "testing was performed."
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). This would typically be non-clinical, in-house verification testing by the manufacturer.

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

• Not applicable as this is a device modification verification, not a clinical study requiring expert ground truth for diagnostic accuracy. The "truth" here is engineering functionality.

4. Adjudication method for the test set:

• Not applicable. This is not a study requiring adjudication of diagnostic results.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No. This type of study is for evaluating human reader performance with or without AI assistance. The modifications here are to the hardware of an automated test reader, not an AI diagnostic algorithm.

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

• The BD Veritor System itself operates as a standalone diagnostic device interpreted by the analyzer. However, the algorithm for interpreting the test results (analyzing line intensity) was established in previous submissions (K180438) and is stated as "Same" and "Original" in the comparison table, meaning it was not changed or re-evaluated in this submission. The testing done for this 510(k) relates to the hardware modifications of the analyzer, not a new or modified interpretation algorithm.

7. The type of ground truth used:

• For the hardware modifications, the "ground truth" is defined by engineering specifications and expected functionality. For example, for "overvoltage protection," the ground truth is "does the circuit protect against overvoltage without impairing core function?" For "lifetime," the ground truth is "does the device successfully complete 10,000 tests?" For "InfoWiFi," the ground truth is "does it perform the specified wireless functionalities?"

8. The sample size for the training set:

• Not applicable. This is hardware verification, not a machine learning model.

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

• Not applicable.

Ask a specific question about this device

BD Surgiphor™ Antimicrobial Irrigation System is intended to mechanically loosen and remove debris, and foreign materials, including microorganisms, from wounds.

The subject BD Surgiphor™ Antimicrobial Irrigation System is a terminally sterilized 450 mL aqueous solution for irrigation and debridement of wounds. The device includes one bottle of Surgiphor™ solution (0.5% Povidone Iodine) which is used to loosen and remove wound debris. The mechanical action of fluid moving across the wound provides the mechanism of action and aids in the loosening and removal of debris, and foreign materials, including microorganisms, from wounds. The povidone iodine in the Surgiphor™ solution serves as a preservative to ensure that no unwanted microbial growth occurs in the solution after the bottle is open.

The provided text describes a 510(k) premarket notification for a medical device called the "BD Surgiphor™ Antimicrobial Irrigation System." This submission is based on demonstrating substantial equivalence to a previously cleared predicate device (K213616).

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

Acceptance Criteria and Device Performance:

The core of this 510(k) submission is to demonstrate that a modified device is substantially equivalent to a predicate device, not to establish new performance criteria for a novel device. Therefore, the "acceptance criteria" here are primarily tied to demonstrating that the changes made do not negatively impact the safety or effectiveness of the device compared to the predicate.

The main change in the subject device (K221504) from its predicate (K213616) is the removal of the SurgiRinse™ solution bottle. The device still includes one bottle of Surgiphor™ solution. The manufacturer asserts that the fundamental "mechanism of action" (mechanical loosening and removal of debris and foreign materials, including microorganisms, from wounds through fluid pressure) remains unchanged. The povidone iodine in the Surgiphor™ solution continues to act as a preservative.

Given this context, the acceptance criteria are implicitly met by demonstrating that the modified device performs comparably to the predicate device, specifically by showing that removing the rinse bottle does not introduce new safety or efficacy concerns.

1. Table of Acceptance Criteria and Reported Device Performance:

Since this is a 510(k) for a modified device, the "acceptance criteria" are not reported as specific performance metrics like sensitivity, specificity, or accuracy (as one might see for an AI/ML device). Instead, the acceptance criteria are met by demonstrating that the changes do not degrade performance or safety.

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

The document does not describe a "test set" in the context of an AI/ML algorithm or a clinical trial with human subjects. This 510(k) relies on design verification and validation testing and standards compliance to demonstrate substantial equivalence to a predicate device, given a minor change (removal of one component from a kit).

Therefore, there is no mention of data provenance (country of origin, retrospective/prospective) because the studies are primarily engineering and quality control tests (sterilization, packaging, shelf-life) rather than clinical performance studies on patient data.

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

This information is not applicable to this 510(k) submission. Ground truth establishment by experts (e.g., radiologists) is typically relevant for diagnostic AI/ML devices where a clinical reference standard is needed. This device is a physical irrigation system, and its "ground truth" for substantial equivalence is derived from a combination of:

• The established performance and safety of its predicate device.
• Laboratory testing (sterilization, packaging) against recognized standards.
• Engineering assessment that a structural change (removing a bottle) does not alter intended use or introduce new risks.

4. Adjudication Method for the Test Set:

This information is not applicable for the same reasons as #3. Clinical adjudication methods are not relevant for the type of testing described.

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

This information is not applicable. An MRMC study is relevant for evaluating the performance of diagnostic aids, particularly AI/ML algorithms, in how they affect human reader performance. This device is an irrigation system, not a diagnostic tool, and the submission is focused on physical and chemical equivalence and safety, not on human interpretation of outputs.

6. Standalone (Algorithm Only) Performance:

This information is not applicable. This submission is for a physical medical device, not an algorithm.

7. Type of Ground Truth Used:

The "ground truth" in this context is established through:

• Engineering specifications and design verification: Ensuring the physical and chemical properties of the device (solution composition, packaging, sterility) remain consistent with safe and effective operation as defined by standards.
• Predicate device's established safety and effectiveness: The fundamental "truth" is that the predicate device was already deemed safe and effective for its intended use, and the current submission argues that the modified device maintains this "truth" despite the change.

8. Sample Size for the Training Set:

This information is not applicable. There is no "training set" as this device does not involve an AI/ML component.

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

This information is not applicable. Since there is no training set, there is no ground truth established for it.

In summary:

The provided FDA letter and 510(k) summary pertain to a physical medical device (an irrigation system) undergoing a minor modification. The "acceptance criteria" and "study" described are primarily related to engineering validation, quality control testing (e.g., sterility, shelf-life), and a comparison to a legally marketed predicate device to demonstrate substantial equivalence. It does not involve the types of studies (e.g., clinical trials, AI/ML performance evaluations) that would typically require the detailed information on test sets, expert readers, or ground truth methodologies for diagnostic or AI-powered devices. The crucial point of this submission is the statement: "The changes do not impact the safety or effectiveness of the subject device [compared to the predicate device]."

Ask a specific question about this device

The BD MAX Vaginal Panel performed on the BD MAX System is an automated qualitative in vitro diagnostic test for the direct detection of DNA targets from bacteria associated with bacterial vaginosis (qualitative results reported based on detection and quantitation of targeted organism markers), Candida species associated with vulvovaginal candidiasis, and Trichomonas vaginalis from vaginal swabs in patients who are symptomatic for vaginitis/vaginosis. The test utilizes real-time polymerase chain reaction (PCR) for the amplification of specific DNA targets and utilizes fluorogenic target-specific hybridization probes to detect and differentiate DNA from:

• · Bacterial vaginosis markers (Individual markers not reported)
  Lactobacillus spp. (L. crispatus and L. jensenii) Gardnerella vaginalis Atopobium vaginae Bacterial Vaginosis Associated Bacteria-2 (BVAB-2) Megasphaera-1
• Candida spp. (C. albicans, C. tropicalis, C. parapsilosis, C. dubliniensis)
• Candida glabrata
• Candida krusei
• Trichomonas vaginalis
  The BD MAX Vaginal Panel is intended to aid in the diagnosis of vaginal infections in women with a clinical presentation consistent with bacterial vaginosis, vulvovaginal candidiasis, and trichomoniasis.

The BD MAX System and the BD MAX Vaginal Panel are comprised of an instrument with associated hardware and accessories, disposable microfluidic cartridges, master mixes, unitized reagent strips, and extraction reagents. The instrument automates sample preparation including target lysis, DNA extraction and concentration, reagent rehydration, target nucleic acid amplification and detection using real-time PCR. The assay includes a Sample Processing Control (SPC) that is present in the Extraction Tube. The SPC monitors DNA extraction steps, thermal cycling steps, reagent integrity and the presence of inhibitory substances. The BD MAX System software automatically interprets test results. For the BD MAX Vaginal Panel, a test result may be called as POS, NEG or UNR (Unresolved) based on the amplification status of the targets and of the Sample Processing Control. IND (Indeterminate) or INC (Incomplete) results are due to BD MAX System failure.

This document describes the 510(k) premarket notification for the BD MAX Vaginal Panel for use with the BD MAX System. The purpose of this submission is to demonstrate the substantial equivalence of the modified device, particularly the BD Molecular Swab Collection Kit, to its predicate device, the BD MAX Vaginal Panel (DEN160001 and K191957) which used the BD MAX UVE Specimen Collection Kit.

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text focuses on demonstrating the substantial equivalence of the collection kit for an already cleared device, rather than establishing initial performance for a novel diagnostic device. Therefore, explicit acceptance criteria in terms of sensitivity, specificity, PPV, and NPV for the BD MAX Vaginal Panel itself are not directly stated in this section, as those would have been established during the original clearances (DEN160001 and K191957).

However, the performance is evaluated in comparison to the predicate's collection kit. The reported performance for the comparison study between the cleared collection device (BD MAX UVE Specimen Collection Kit) and the new collection device (BD Molecular Swab Collection Kit) demonstrated the following:

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

• Sample Size for Comparison Study: The document states that a "comparison study of performance between the cleared collection device and the new collection device tested with the BD MAX Vaginal Panel on the BD MAX System with clinical specimens" was conducted. However, the exact number of clinical specimens used in this comparison study is not explicitly provided in the text.
• Data Provenance: The data used for the comparison study are from "clinical specimens." The country of origin is not specified, and it is stated as a retrospective or prospective study.

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

The document does not describe the establishment of a ground truth by experts for the comparison study of the collection kits. For molecular diagnostic assays like the BD MAX Vaginal Panel, the "ground truth" for the original device's performance validation is often established using methods such as:

• Culture: For culturable organisms like Candida species or Trichomonas vaginalis.
• Microscopy (e.g., Amsel's criteria, Nugent scoring): For bacterial vaginosis.
• Reference molecular methods: For organisms difficult to culture or quantify.

Since the focus here is on the collection kit equivalence, the ground truth would inherently refer to the original diagnostic results obtained using the predicate device's collection kit, which are then compared to the results from the new collection kit. The text does not mention any independent expert panel establishing ground truth specifically for these comparison studies.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (such as 2+1, 3+1, or none) for the test set used in the comparison study. The comparison is between the performance of two collection kits with the same diagnostic panel, suggesting a direct comparison of results rather than an adjudication process involving multiple human readers to establish a reconciled truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the Effect Size

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study is typically used for imaging or interpretation tasks where human readers play a significant role. The BD MAX Vaginal Panel is an automated in vitro diagnostic test, and its results are interpreted by the BD MAX System software, not human readers in a diagnostic capacity that would warrant an MRMC study.

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

Yes, the BD MAX Vaginal Panel operates as a standalone (algorithm-only) device. The device description explicitly states: "The BD MAX System software automatically interprets test results." There is no human-in-the-loop performance described for the interpretation of the test results themselves. The studies confirm the analytical and clinical performance of the automated system with the new collection kit.

7. The Type of Ground Truth Used

For the comparison study, the "ground truth" for evaluating the new collection kit's performance would implicitly be the results obtained when the same clinical specimens were tested using the predicate device's collection kit (BD MAX UVE Specimen Collection Kit) with the BD MAX Vaginal Panel. This is because the study aims to show the collections kits are equivalent and the performance of the BD MAX Vaginal Panel is already established with the predicate kit.

The initial ground truth for the diagnostic panel itself (BD MAX Vaginal Panel, cleared as DEN160001 and K191957) would have been established through a combination of:

• Clinical diagnosis and criteria: For example, Amsel's criteria or Nugent score for bacterial vaginosis, or clinical signs and symptoms for vaginitis.
• Culture: For culturable pathogens.
• Reference molecular methods: For specific DNA targets.

8. The Sample Size for the Training Set

The document does not provide information regarding a "training set" or its sample size. This is typical for an IVD device submission that is demonstrating substantial equivalence of a component (collection kit) for an already cleared diagnostic system. The algorithms for the BD MAX System and the Vaginal Panel would have been developed and "trained" (in a broad sense of model development) prior to the original 510(k) clearances (DEN160001 and K191957). This document does not detail the development phase of the assay.

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

As no training set is discussed in this document, the method for establishing its ground truth is also not described. As mentioned above, the development and establishment of ground truth for the original assay would have occurred during its prior 510(k) clearances.

Ask a specific question about this device