Search Results

ArtUs is a general purpose diagnostic ultrasound imaging system intended for use by qualified and appropriately trained healthcare professionals to conduct ultrasound scan process or fluid flow analysis of the human body.

It is intended to be used for applications in Fetal, Abdominal, Pediatric, Small Organ (breast, thyroid, testicles), Musculo-Skeletal Conventional and Superficial, Cardiac (adult and pediatric), Adult Cephalic, and Peripheral Vascular.

Modes of operation include B, M, Pulse Wave Doppler (CFM), Power Doppler (CFM), Power Doppler (PDI), Directional Power Doppler (DPDI), Combined modes (B+B, B+M, 4B, B+PWD (Duplex), B+CFM/PDI/DPDI+PWD (Triplex)), Tissue Harmonic Imaging (THI) and Inverted Tissue Harmonic Imaging (ITHI).

The clinical environments where the system can be used include physician offices, clinics, hospitals, and clinical point-of-care for diagnosis of patients.

ArtUs system is intended for the multipurpose ultrasound examinations, based on electronic linear and convex scanning.

ArtUs system is a combination of proprietary hardware and software that has been designed for real-time imaging and is intended to be a basic diagnostic tool. Its basic function is to acquire ultrasound echo data and to display the image in ultrasound B-Mode or combined modes. The system is designed for imaging with transducer ranges of 2 to 15 MHz.

The devices referenced in this submission represent a transportable, software-controlled, diagnostic ultrasound system with accessories. This submission does not include technology or control feature changes nor deviations from indications for use different from those demonstrated in previously cleared devices operating in ultrasound B-Mode, M-Mode or combined modes, inclusive of the predicate devices so claimed.

The ArtUs only contains the hardware and firmware, everything else (e.g. ultrasound software, database) is located on a standard PC that is connected to the ArtUs via USB 3.0. Minimum requirements are given for the PC.

The Echo Wave II software was especially designed for the TELEMED devices. Software able to reside in a Windows-based PC.

The device variant is:

• ArtUs EXT-1H ultrasound system utilizing as hardware an ultrasound engine contained in a small standalone enclosure for connection to a host PC via a USB port with external power supply;
  The ArtUs can be used together with the appropriate transducers for the entire ultrasound diagnostic (2MHz to 15MHz probes).

This document is a 510(k) Pre-market Notification for the ArtUs ultrasound system. It claims substantial equivalence to predicate devices and focuses on technical specifications, safety, and regulatory compliance.

Crucially, this document does not contain information about studies proving the device meets specific acceptance criteria related to its diagnostic performance. It focuses on engineering acceptance criteria (e.g., meeting safety standards, biocompatibility, acoustic output, software functionality) and demonstrating substantial equivalence to previously cleared devices rather than novel diagnostic efficacy.

Therefore, I cannot fulfill all parts of your request as the provided text does not contain the required information for diagnostic performance studies.

Here's what can be extracted and what cannot:

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

Since this is a submission for substantial equivalence based on safety and technical performance rather than diagnostic accuracy, the acceptance criteria are generally related to compliance with standards and equivalence to predicate devices. No diagnostic performance metrics (e.g., sensitivity, specificity) are provided.

For points 2 through 9, the document explicitly states: "No additional clinical testing is required, as the indications for use are not a novel indication as shown by the predicate devices." This means there was no diagnostic performance study with a test set of patients to establish accuracy metrics such as sensitivity, specificity, or reader performance.

Therefore, the following points cannot be addressed from the provided text:

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
* Not applicable, no diagnostic performance test set described.

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)
* Not applicable, no ground truth for a diagnostic test set described.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
* Not applicable, no diagnostic test set described.

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 document describes an ultrasound device, not an AI-powered diagnostic algorithm for clinical interpretation. It does not mention AI assistance for human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
* Not applicable. This is not an AI algorithm submission seeking standalone diagnostic performance clearance.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
* Not applicable for diagnostic performance. Ground truth for safety and technical performance would be based on standard engineering and biocompatibility testing procedures.

8. The sample size for the training set
* Not applicable. This document is not for an AI algorithm that would typically have a training set.

9. How the ground truth for the training set was established
* Not applicable. This document is not for an AI algorithm.

Ask a specific question about this device

The Artus™ cervical plate system is intended for anterior fixation of the cervical spine (C2 to T1). The system is to be used to provide stabilization of the anterior cervical spine as an adjunct to fusion for the treatment of degenerative disc disease (defined as neck pain of discogenic origin with the degeneration of the disc confirmed by history and radiographic studies), spondylolisthesis, trauma (i.e., fractures or dislocations), tumors, spinal stenosis, deformity (i.e., kyphosis, lordosis or scoliosis), pseudarthrosis or failed previous fusion.

Artus™ is a cervical plate system that provides one- through four-level standard plate designs as well as one- and two-level midline plates. The plates are designed with a blocking mechanism to restrict screw backout. The plating system offers a variety of screw options including self-drilling, self-tapping and self-drilling/self-tapping, all available in either fixed or variable designs and in standard and rescue diameters. The implants are available in a variety of lengths to accommodate the individual anatomic and clinical circumstances of each patient.

The provided document is a 510(k) summary for the Artus™ cervical plate system. This is a medical device for spinal fixation and not an AI/ML powered device. Therefore, the questions related to AI/ML device acceptance criteria, study details, ground truth, expert involvement, and training/test sets are not applicable.

The document primarily focuses on demonstrating substantial equivalence to a predicate device through mechanical testing.

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

The document states that mechanical testing of the worst-case Artus™ construct was performed according to ASTM F1717, which includes dynamic compression bending. The acceptance criteria for such tests are generally defined by the FDA and industry standards to ensure the device can withstand physiological loads without failure. While the specific numerical acceptance criteria are not explicitly stated in this summary, the crucial statement is:

"The test results demonstrate that Artus™ device mechanical performance is substantially equivalent to the predicate devices."

This implies that the Artus™ device met or exceeded the performance of the predicate device (uNion™ Cervical Plate System) under the specified ASTM F1717 test, which serves as the de facto acceptance criterion for performance equivalence in this context.

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

This question is not applicable as the device is a physical implant, not an AI/ML software. The "test set" here refers to physical components for mechanical testing, not data.

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 question is not applicable as this is a physical medical device. "Ground truth" in this context would refer to the established engineering standards and performance of the predicate device. Mechanical engineers and quality control experts would be involved in designing and conducting the tests, but not in establishing an "AI ground truth."

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

This question is not applicable for a physical medical device.

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 question is not applicable as the device is a physical implant, not an AI/ML powered device.

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

This question is not applicable as the device is a physical implant, not an AI/ML powered device.

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

For a physical medical device like the Artus™ cervical plate system, the "ground truth" for performance is established through:

• Established engineering standards: Specifically, ASTM F1717 for spinal implant devices. These standards define the methods and expected performance characteristics for simulating physiological loads.
• Performance of the legally marketed predicate device: The Artus™ system's performance is compared to the uNion™ Cervical Plate System (K150666). The predicate's successful history and FDA clearance serve as the benchmark for "ground truth" for substantial equivalence.

8. The sample size for the training set

This question is not applicable as the device is a physical implant and does not involve AI/ML training data.

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

This question is not applicable as the device is a physical implant and does not involve AI/ML training data.

Ask a specific question about this device

The artus HSV-1/2 QS-RGQ MDx Kit is an in vitro real-time PCR DNA amplification assay performed on the QIAsymphony RGQ MDx system for the direct qualitative detection and differentiation of herpes simplex virus (HSV-1 and HSV-2) DNA in genital or oral vesicular lesions from male and female patients suspected of HSV infection.

The assay is intended for use as an aid in diagnosis of HSV infection in symptomatic patients.

Warning: The artus HSV-1/2 QS-RGQ MDx Kit is not FDA-cleared for use with cerebrospinal fluid (CSF) or for prenatal screening.

The artus HSV-1/2 QS-RGQ MDx Kit is an in vitro PCR assay for the qualitative detection and differentiation of nucleic acids encoding the Glycoprotein D and UL30 genes isolated from HSV-1 and HSV-2 DNA present in genital or oral lesions from male and female patients. Samples are extracted and prepared for PCR using the QIAsymphony SP/AS instrument with the QIAsymphony DSP Virus/Pathogen Mini Kit. Amplification and detection are carried out using the artus HSV-1/2 QS-RGQ MDx Kit with the Rotor-Gene O MDx (RGO MDx) and Rotor-Gene AssayManager software. The presence of a HSV-1 or HSV-2 target sequence is indicated by the fluorescent signal generated through the use of fluorescently labeled oligonucleotide probes. The probes do not generate a signal unless they are specifically bound to the amplified product. The amplification cycle at which fluorescent signal is detected by the RGQ MDx is inversely proportional to the HSV-1 and/or HSV-2 target concentration present in the original specimen. A plasmid construct containing DNA unrelated to HSV-1 and HSV-2 is introduced into each specimen during sample preparation to serve as an internal control. Run as a separate control, the positive control serves to demonstrate that the HSV-1/2 PCR reagents are functional. In addition, the positive control functions as a process control, to demonstrate that sample preparation has proceeded correctly during the run.

The provided documentation describes the performance characteristics and clinical study results for the artus® HSV-1/2 QS-RGQ MDx Kit, an in vitro real-time PCR assay for the detection and differentiation of HSV-1 and HSV-2 DNA.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally qualitative for this type of diagnostic device, revolving around achieving sufficient sensitivity and specificity compared to a predicate device or established methods. The reported device performance is detailed in the tables under "Performance Characteristics - Clinical Studies."

Ask a specific question about this device

The artus C. difficile QS-RGQ MDx Kit is an in vitro polymerase chain reaction (PCR) assay for use on the QIAsymphony RGQ MDx system for the qualitative detection of toxigenic Clostridium difficile toxin A and toxin B genes in human liquid or soft stool specimens from patients suspected of having Clostridium difficile associated disease. The test is intended to be used directly on patient samples.

The artus C. difficile QS-RGQ MDx Kit is intended to be used to aid in diagnosis of Clostridium difficile infection.

The artus C. difficile QS-RGQ MDx Kit assay uses PCR to generate an amplified product from the tcdA and tedB/tedBv genes of toxigenic C. difficile DNA in clinical specimens. Samples are extracted and prepared using the Q1Asymphony SP instrument with the QIAsymphony DSP Virus/Pathogen Mini Kit, followed by assay setup on the OIAsymphony AS. Amplification and detection are carried out using the artus C. difficile OS-RGQ MDx Kit with the Rotor-Gene Q MDx (RGQ MDx) and Rotor-Gene AssayManager software. The presence of a toxigenic C. difficile target sequence is indicated by the fluorescent signal generated through the use of fluorescently labeled oligonucleotide probes. The probes do not generate a signal unless they are specifically bound to the amplified product. The amplification cycle at which fluorescent signal is detected by the RGQ MDx is inversely proportional to the toxigenic C. difficile DNA target concentration present in the original specimen. A bacterial species unrelated to toxigenic C. difficile is introduced into each specimen during sample preparation to serve as an internal control. The internal control bacteria are lysed simultaneously with toxigenic C. difficile in the specimen. and amplified in the same reaction as the C. difficile targets using PCR, and serve to demonstrate that the entire assay process has proceeded correctly for each specimen.

Here's a summary of the acceptance criteria and study details for the QIAGEN artus® C. difficile QS-RGQ MDx Kit, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined acceptance criteria (e.g., "Sensitivity must be >X%", "Specificity must be >Y%"). Instead, it reports the device's performance against a comparative method (enriched toxigenic culture and direct toxigenic culture) for the purpose of demonstrating substantial equivalence to a predicate device.

However, based on the provided clinical performance tables, we can present the reported performance:

2. Sample Size and Data Provenance for the Test Set

• Sample Size (for clinical evaluation):
  • Initially, 759 liquid or soft stool specimens were collected.
  • 10 specimens were withdrawn due to missing results.
  • 16 specimens reported an invalid result with the artus kit (8 became valid upon retesting as negative, 8 remained invalid).
  • The final dataset for performance analysis included 741 specimens (for comparison against enriched culture).
  • For comparison against direct culture, 699 specimens were available.
• Data Provenance: The specimens were collected from 5 geographically diverse locations within the United States in 2013. The study was prospective as it involved collecting specimens from patients suspected of having Clostridium difficile-associated disease for concurrent testing.

3. Number of Experts and Qualifications for Ground Truth

The document does not mention the use of "experts" in the sense of clinicians or radiologists establishing ground truth. The "ground truth" for the clinical study was established by laboratory methods: enriched toxigenic culture and direct toxigenic culture. For discordant results, alternative PCR followed by bi-directional sequencing was used to resolve discrepancies. The qualifications of the personnel performing these laboratory tests are not specified, but it can be inferred they were trained laboratory technicians.

4. Adjudication Method for the Test Set

For discordant results in the clinical comparison studies:

• Discordant Analysis: An "alternative PCR followed by bi-directional sequencing" was used.
• Enriched Culture Comparison:
  • For 17 specimens that were artus Positive/Enriched Culture Negative, 12 were found positive by alternative PCR, agreeing with artus.
  • For 12 specimens that were artus Negative/Enriched Culture Positive, 10 were found negative by alternative PCR, agreeing with artus. One specimen was unavailable for testing.
• Direct Culture Comparison:
  • For 19 specimens that were artus Positive/Direct Culture Negative, 14 were found positive by alternative PCR, agreeing with artus. Two specimens were unavailable for testing.
  • The 1 specimen that was artus Negative/Direct Culture Positive was unavailable for testing.

This method resembles a third-party arbitration/adjudication (2+1 or similar logic) where an additional, more definitive test (alternative PCR + sequencing) was used to resolve disagreements between the index test (artus kit) and the primary comparator (culture).

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. This device is an in vitro diagnostic (IVD) assay that provides a quantitative or qualitative result, not an image-based diagnostic read by human observers. Therefore, the concept of "human readers improve with AI vs without AI assistance" is not applicable here.

6. Standalone Performance

Yes, the studies reported demonstrate the standalone performance of the algorithm (the artus C. difficile QS-RGQ MDx Kit). The clinical performance tables compare the kit's results directly against culture methods, without human interpretation for the artus kit's output.

7. Type of Ground Truth Used

The primary ground truth for the clinical studies was laboratory culture results, specifically:

• Enriched Toxigenic Culture
• Direct Toxigenic Culture
• For discordant cases, a more definitive molecular method, alternative PCR followed by bi-directional sequencing, was used as a confirmatory "reference standard" to resolve discrepancies.

8. Sample Size for the Training Set

The document does not specify the sample size used for any training set. This information is typically proprietary to the manufacturer's algorithm development process and is not always disclosed in 510(k) summaries for IVD devices. The studies described are performance validation studies, not algorithm training studies.

9. How Ground Truth for the Training Set Was Established

As the sample size for a training set is not provided, the method for establishing its ground truth is also not described.

Ask a specific question about this device

The artus® Infl A/B RG RT-PCR Kit is a multiplex real time PCR in vitro diagnostic test for the qualitative detection and identification of Influenza A and Influenza B virus RNA in nasopharyngeal swab specimens using the Rotor-Gene® Q MDx instrument. The test is intended for use as an aid in the differential diagnosis of Influenza A and Influenza B viral infections in patients symptomatic for respiratory tract infection in conjunction with clinical and epidemiological risk factors. It is not intended to detect Influenza C virus.

Negative results do not preclude respiratory 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 2009/2010 and 2010/2011 flu seasons when Influenza A (H3N2) and Influenza A/2009 (H1N1) were the predominant Influenza A viruses in circulation. When other Influenza A viruses emerge, 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 departments for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.

The artus Infl A/B RG RT-PCR Kit contains reagents and instructions for the detection and differentiation of Influenza A and Influenza B viral RNA in nasopharyngeal swabs of symptomatic patients.

The assay utilizes the EZ1 Advanced XL instrument with the EZ1 Advanced XL DSP Virus Card v. 1.0. and the EZ1 DSP Virus Kit (QIAGEN) for viral nucleic acid extraction. The Rotor-Gene Q MDx instrument with the artus Influenza Assay Software Package (QIAGEN) is used for amplification and detection.

Pathogen detection by the reverse transcription polymerase chain reaction (RT-PCR) is based on the reverse transcription of the RNA into complementary DNA (cDNA) and subsequent amplification of specific regions of the pathogen genome. In real-time PCR the amplified product is detected via fluorescent dyes. These are linked to oligonucleotides that bind specifically to the amplified product. Monitoring the fluorescence intensities during the PCR run (i.e., in real time) allows the detection of the accumulating product without having to re-open the reaction tubes after the PCR run.

The Influenza A/B Master contains primers, probes, enzymes, and other reaction components (except Mg solution) needed for the specific amplification of a 141 bp region of the Influenza A virus genome and a 95 bp region of the influenza virus B genome, and for the direct detection of the specific amplicons in two fluorescence channels of the Rotor-Gene O MDx instrument. The primers are complementary to highly conserved regions of the Matrix gene locus within the influenza B virus genome. The probes are dual-labeled with a reporter dye attached to the 5'-end and a quencher dye attached to the 3'-end. Detection is performed on the Rotor-Gene O MDx instrument at wavelengths listed in Table 5.1.

In addition, the Master contains a second heterologous primer/probe set to detect the Influenza A/B Internal Control (IC). The IC result identifies possible failure of RNA extraction or the presence of PCR inhibition. The Internal Control is detected in a third fluorescence channel.

An Influenza A Control and an Influenza B Control comprised of in vitro transcripts representing the amplified regions of the Influenza A virus genome and the Influenza B virus genome, respectively, are provided. PCR grade water is provided as a negative (notemplate) control.

The procedure consists of four consecutive steps:

1. Sample collection: Collect nasopharyngeal swab specimens from symptomatic patients using a polyester, nylon, or rayon swab and place it into virus transport medium.
2. Nucleic acid extraction: Add the Influenza IC to the carrier RNA before starting the extraction procedure. Extract viral RNA using the EZ1 DSP Virus Kit in combination with the EZ1 Advanced XL instrument.
3. Real-time RT-PCR: Add the extracted RNA and positive and negative control material to Influenza A/B Master mix. Perform real-time RT-PCR using the Rotor-Gene O MDx instrument.
4. Result interpretation: The Influenza Assay Package evaluates the results of the positive and negative controls to determine if the run is valid. If the run is valid, the internal control and target-specific results of each specimen are evaluated.

Here's an analysis of the acceptance criteria and supporting studies for the artus® Infl A/B RG RT-PCR Kit, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined acceptance criteria (e.g., "Sensitivity must be >90%"). Instead, it presents the "performance characteristics" observed in the clinical evaluations. The interpretation below assumes that achieving these reported performance levels was sufficient for acceptance.

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

• Prospective Clinical Evaluation:
  • Sample Size: 254 nasopharyngeal (NP) swab specimens.
  • Data Provenance: Prospective, collected at 3 clinical laboratories in the United States during the 2010-11 respiratory virus season.
• Retrospective Clinical Evaluation 1:
  • Sample Size: 212 specimens.
  • Data Provenance: Retrospective, collected from the 2009 and 2010 respiratory virus season. Country of origin not explicitly stated but implied to be US clinical laboratories where initial testing occurred.
• Prospectively Collected and Archived Clinical Evaluation (Retrospective Clinical 2):
  • Sample Size: 462 well-characterized, de-identified, residual specimens.
  • Data Provenance: Retrospective (archived), collected from August 2009 to May 2011 respiratory virus season. Country of origin not explicitly stated but implied to be US clinical settings.

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 the ground truth in the clinical studies.

• Prospective Clinical Evaluation: The reference method was "standard viral culture (shell vial) followed by direct fluorescent antibody (DFA) screening and identification." This typically involves trained laboratory personnel (e.g., microbiologists, lab technologists) rather than a panel of clinical experts for interpretation. Bidirectional sequencing was used to confirm some discrepant results.
• Retrospective Clinical Evaluation 1 & 2: The ground truth was established using "an FDA cleared molecular test" or "FDA cleared molecular tests for routine patient management." This implies reliance on the validated results from these predicate devices, not on a panel of human experts re-interpreting raw data.

4. Adjudication Method for the Test Set

The document does not describe a formal adjudication method (e.g., 2+1, 3+1) involving multiple experts for the test set.

• In the prospective study, discrepant results (artus positive, culture negative) were investigated using "bidirectional sequencing." This is a molecular confirmation, not an expert panel adjudication.
• In the retrospective studies, the "FDA cleared molecular tests" were used as the reference, suggesting agreement with those established results was the primary measure, not a separate adjudication process.

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. This device is a molecular diagnostic test (RT-PCR kit), not an imaging or AI-assisted diagnostic tool that would typically involve human "readers" or assess improvement with AI assistance. The performance is entirely based on the kit's analytical and clinical accuracy.

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

Yes, the performance reported for the artus® Infl A/B RG RT-PCR Kit is inherently standalone (algorithm only, without human-in-the-loop performance in the sense of interpretative assistance). The device outputs a qualitative positive/negative result for Influenza A and B. While human operators are involved in sample preparation and running the assay, the "results interpretation" step involves the "Influenza Assay Package evaluating the results of the positive and negative controls to determine if the run is valid" and then evaluating the "internal control and target-specific results of each specimen." This is an automated interpretation by the device's software package based on pre-defined thresholds.

7. The Type of Ground Truth Used

• Prospective Clinical Evaluation: The primary ground truth was standard viral culture (shell vial) followed by direct fluorescent antibody (DFA) screening and identification. For discrepant results, bidirectional sequencing was used as a confirmatory method.
• Retrospective Clinical Evaluation 1 & 2: An FDA cleared molecular test was used as the ground truth (reference method).

8. The Sample Size for the Training Set

The document does not specify a "training set" or its sample size. For molecular diagnostic kits like this, the "development" or "training" phase usually refers to the analytical studies (e.g., determining optimal primer/probe concentrations, establishing LoD, testing specificity and reactivity) and initial method validation, rather than a distinct 'training set' for an algorithm in the way it's used for AI/machine learning. The provided data focuses on the performance of the finalized device.

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

Since no specific "training set" is identified for the device in the context of an algorithm, the concept of establishing ground truth for it is not applicable here. The ground truth for the performance evaluation (test sets) was established as described in section 7. The analytical parameters of the assay (e.g., target genes, detection channels, controls) are designed and experimentally validated, not "trained" on a dataset with external ground truth in the AI sense.

Ask a specific question about this device