The VERSANT HCV RNA Qualitative Assay is an in vitro nucleic acid amplification assay for the detection of hepatitis C virus (HCV) RNA in human plasma (EDTA, sodium heparin, sodium citrate, and ACD) or serum. The VERSANT HCV RNA Qualitative Assay is indicated for use with fresh or frozen specimens from the following populations: individuals with antibody evidence of HCV infection with evidence of liver disease, and individuals suspected to be actively infected with HCV with antibody evidence, and individuals at risk for HCV infection with antibodies to HCV. Detection of HCV RNA is evidence of active HCV infection. Detection of HCV RNA does not discriminate between an acute and chronic state of infection or indicate the presence of liver disease. A negative result does not exclude active HCV replication. It is not known if performance is affected by the state of HCV infection (acute or chronic) or by the presence or absence of liver disease. Performance has not been demonstrated for monitoring HCV infected patients. WARNING: This assay has not been FDA-approved for the screening of blood or plasma donors.
Device Story
The VERSANT HCV RNA Qualitative Assay is a target amplification-based nucleic acid probe test for detecting HCV RNA in human plasma or serum. It utilizes Transcription-Mediated Amplification (TMA) to amplify conserved regions within the 5' untranslated region of the HCV genome. The process involves three steps in a single tube: sample preparation, target amplification, and amplicon detection. It uses MMLV reverse transcriptase and T7 RNA polymerase to generate multiple RNA copies from the viral template. An internal nucleic acid control is added to each specimen to monitor assay performance. The device is used in clinical laboratory settings by trained personnel. Results are provided to healthcare providers to confirm active HCV infection in patients with prior antibody evidence or risk factors. By identifying active viral replication, the assay assists in clinical diagnosis, though it does not distinguish between acute and chronic states or monitor treatment efficacy.
Clinical Evidence
Multi-center study of 1,511 subjects (hepatology clinics, drug abuse clinics, transfusion centers, AIDS clinics). Compared VERSANT HCV RNA Qualitative Assay against anti-HCV serology and an FDA-cleared PCR test. Overall positive agreement with PCR was 99.7% (95% CI: 99.1-99.9%) and negative agreement was 97.9% (95% CI: 96.3-98.9%). Performance was consistent across genotypes 1-6. Analytical sensitivity (LOD) determined to be 5.3 IU/mL (95% probability).
Technological Characteristics
Target amplification-based nucleic acid probe test using Transcription-Mediated Amplification (TMA). Employs MMLV reverse transcriptase and T7 RNA polymerase. Reagents include Target Capture Reagent, Master Kit, Auto Detect Reagent Kit, and Control Kit. Requires specific storage temperatures (frozen, refrigerated, or room temperature). Standalone diagnostic assay performed in a laboratory setting.
Indications for Use
Indicated for individuals with antibody evidence of HCV infection with liver disease, individuals suspected of active HCV infection with antibody evidence, and individuals at risk for HCV infection with antibodies to HCV. Not for blood/plasma donor screening.
Regulatory Classification
Identification
A nucleic acid-based hepatitis C virus (HCV) ribonucleic acid (RNA) test is identified as an in vitro diagnostic device intended for prescription use as an aid in the diagnosis of HCV infection in specified populations, and/or as an aid in the management of HCV-infected patients including guiding the selection of genotype-specific treatment in individuals with chronic HCV infection. The test is intended for use with human serum or plasma. The test is not intended for use as a donor screening test for the presence of HCV antibodies in blood, blood products, or tissue donors.
Special Controls
*Classification.* Class II (special controls). The special controls for this device are:(1) For all nucleic acid-based HCV RNA tests, the labeling required under § 809.10(b) of this chapter must include:
(i) A prominent statement that the test is not intended for use as a donor screening test for the presence of HCV RNA from human cells, tissues, and cellular and tissue-based products.
(ii) A detailed explanation of the principles of operation and procedures for performing the assay.
(iii) A detailed explanation of the interpretation of results.
(iv) Limitations, which must be updated to reflect current clinical practice and disease presentation and management. These limitations must include, but are not limited to, statements that indicate:
(A) The specimen types for which the device has been cleared and that use of this test kit with specimen types other than those specifically cleared for this device may result in inaccurate test results.
(B) When applicable, that assay performance characteristics have not been established in populations of immunocompromised or immunosuppressed patients or, other populations where test performance may be affected.
(C) Test results are to be interpreted by qualified licensed healthcare professionals in conjunction with the individual's clinical presentation, history, and other laboratory results.
(2) For all nucleic acid-based HCV RNA tests, the design verification and validation must include:
(i) Detailed device description, including the device components, ancillary reagents required but not provided, and an explanation of the device methodology. Additional information appropriate to the technology must be included such as design of primers and probes, rationale for the selected gene targets, specifications for amplicon size, and degree of nucleic acid sequence conservation.
(ii) For devices with assay calibrators, the design and nature of all primary, secondary, and subsequent quantitation standards used for calibration as well as their traceability to a standardized reference material that FDA has determined is appropriate (
*e.g.,* a recognized consensus standard). In addition, analytical testing must be performed following the release of a new lot of the standard material that was used for device clearance or approval, or when there is a transition to a new calibration standard.(iii) Documentation and characterization (
*e.g.,* determination of the identity, supplier, purity, and stability) of all critical reagents (including nucleic acid sequences for primers and probes) and protocols for maintaining product integrity.(iv) Detailed documentation of analytical performance studies conducted as appropriate to the technology, specimen types tested, and intended use of the device, including, but not limited to, limit of detection (LoD), upper and lower limits of quantitation (ULoQ and LLoQ, respectively), linearity, precision, endogenous and exogenous interferences, cross reactivity, carryover, matrix equivalency, and sample and reagent stability. Samples selected for use in analytical studies or used to prepare samples for use in analytical studies must be from subjects with clinically relevant circulating genotypes in the United States. Cross-reactivity studies must include samples from HCV RNA negative subjects with other causes of liver disease, including autoimmune hepatitis, alcoholic liver disease, chronic hepatitis B virus, primary biliary cirrhosis, and nonalcoholic steatohepatitis, when applicable. The effect of each claimed nucleic-acid isolation and purification procedure on detection must be evaluated.
(v) Risk analysis and management strategies, such as Failure Modes Effects Analysis and/or Hazard Analysis and Critical Control Points summaries and their impact on test performance.
(vi) Final release criteria to be used for manufactured test lots with appropriate evidence that lots released at the extremes of the specifications will meet the claimed analytical and clinical performance characteristics as well as the stability claims.
(vii) Multisite reproducibility study that includes the testing of three independent production lots.
(viii) All stability protocols, including acceptance criteria.
(ix) Final release test results for each lot used in clinical studies.
(x) Analytical sensitivity and specificity of the test must be the same or better than that of other cleared or approved tests.
(xi) Lot-to-lot precision studies, as appropriate.
(3) For devices intended for the qualitative detection of HCV RNA, in addition to the special controls listed in paragraphs (b)(1) and (2) of this section, the design verification and validation must include detailed documentation of performance from a multisite clinical study. Performance must be analyzed relative to an FDA cleared or approved qualitative HCV RNA test, or a comparator that FDA has determined is appropriate. This study must be conducted using appropriate patient samples, with appropriate numbers of HCV positive and negative samples in applicable risk categories. Additional genotypes must be validated using appropriate numbers and types of samples. The samples may be a combination of fresh and repository samples, sourced from within and outside the United States, as appropriate. The study designs, including number of samples tested, must be sufficient to meet the following criteria:
(i) Clinical sensitivity of the test must have a lower bound of the 95 percent confidence interval of greater than or equal to 95 percent.
(ii) Clinical specificity of the test must have a lower bound of the 95 percent confidence interval of greater than or equal to 96 percent.
(4) For devices intended for the quantitative detection of HCV RNA, the following special controls, in addition to those listed in paragraphs (b)(1) and (2) of this section, apply:
(i) Labeling required under § 809.10(b) of this chapter must include a prominent statement that the test is not intended as a diagnostic test to confirm the presence of active HCV infection, when applicable.
(ii) Design verification and validation must include the following:
(A) Detailed documentation of the following analytical performance studies conducted as appropriate to the technology, specimen types tested, and intended use of the device, including but not limited to: LoD, ULoQ and LLoQ. LoD, LLoQ, and linearity studies must demonstrate acceptable device performance with all HCV genotypes detected by the device.
(B) Detailed documentation of clinical performance testing from either:
(
*1* ) A multisite clinical study with an appropriate number of clinical samples from chronically HCV infected patients in which the results are compared to an FDA-cleared or approved quantitative HCV RNA test, or a comparator that FDA has determined is appropriate. This study must include a sufficient number of HCV positive samples containing an analyte concentration near the LLoQ to describe performance at this level. Clinical samples must cover the full range of the device output and must be consistent with the distribution of these genotypes in the U.S. population. Clinical samples may be supplemented with diluted clinical samples for those viral load concentrations that are not sufficiently covered by natural clinical specimens, or(
*2* ) A clinical study with prospectively collected samples demonstrating clinical validity of the device.(C) Detailed documentation of a qualitative analysis near the lower end of the measuring range demonstrating acceptable performance when used as an aid in diagnosis.
(5) For devices intended for HCV RNA genotyping, in addition to the special controls listed in paragraphs (b)(1) and (2) of this section, design verification and validation must include the following:
(i) Detailed documentation of an analytical performance study demonstrating the LoD for all HCV genotypes detected by the device.
(ii) Detailed documentation, including results, of a multisite clinical study that assesses genotyping accuracy (
*i.e.,* the proportion of interpretable results that match with the reference method result) and the genotyping rate (*i.e.,* the proportion of results that were interpretable).(6) For any nucleic acid-based HCV RNA test intended for Point of Care (PoC) use, the following special controls, in addition to those listed in paragraphs (b)(1) and (2) of this section, apply:
(i) Clinical studies must be conducted at PoC sites.
(ii) Additional labeling must include a brief summary of the instructions for use that are appropriate for use in a PoC environment.
Reference Devices
AMPLICOR HCV Test, v2.0
VERSANT HCV RNA 3.0 Assay (bDNA)
VERSANT HCV Genotype Assay (LiPA)
Submission Summary (Full Text)
{0}
# SUMMARY OF SAFETY AND EFFECTIVENESS
## I. GENERAL INFORMATION
Device Generic Name: In vitro nucleic acid amplification assay for the detection of hepatitis C virus (HCV) RNA in human plasma or serum.
Device Trade Name: VERSANT™ HCV RNA Qualitative Assay
Applicant’s Name and Address: Gen-Probe Incorporated
10210 Genetic Center Drive
San Diego, CA 92121
Premarket Approval Application (PMA) Number: P020011
Date of Panel Recommendation: None
Date of Notice of Approval to Applicant: November 7, 2002
## II. INDICATIONS FOR USE
The VERSANT HCV RNA Qualitative Assay is an *in vitro* nucleic acid amplification assay for the detection of hepatitis C virus (HCV) RNA in human plasma (EDTA, sodium heparin, sodium citrate, and ACD) or serum. The VERSANT HCV RNA Qualitative Assay is indicated for use with fresh or frozen specimens from the following populations: individuals with antibody evidence of HCV infection with evidence of liver disease, and individuals suspected to be actively infected with HCV with antibody evidence, and individuals at risk for HCV infection with antibodies to HCV. Detection of HCV RNA is evidence of active HCV infection.
Detection of HCV RNA does not discriminate between an acute and chronic state of infection or indicate the presence of liver disease. A negative result does not exclude active HCV replication. It is not known if performance is affected by the state of HCV infection (acute or chronic) or by the presence or absence of liver disease. Performance has not been demonstrated for monitoring HCV infected patients.
**WARNING**: This assay has not been FDA-approved for the screening of blood or plasma donors.
{1}
# III. DEVICE DESCRIPTION
The VERSANT HCV RNA Qualitative Assay is a target amplification-based nucleic acid probe test that detects HCV RNA in human plasma and serum. The VERSANT HCV RNA Qualitative Assay utilizes Transcription-Mediated Amplification (TMA) to amplify conserved regions within the 5' untranslated region (5'-UTR) of the HCV genome. TMA utilizes Moloney Murine Leukemia Virus (MMLV) reverse transcriptase (RT) and T7 RNA polymerase to generate multiple RNA copies from the viral nucleic acid template. Assay performance is monitored by means of an internal nucleic acid control that is added to each specimen with the Target Capture Reagent.
The VERSANT HCV RNA Qualitative Assay has three main steps, all of which are performed within a single tube: sample preparation, target amplification, and amplicon detection.
The VERSANT HCV RNA Qualitative Assay consists of the following kits:
- The HCV RNA Qualitative Assay Master Kit
- The Auto Detect Reagent Kit
- The HCV RNA Qualitative Assay Control Kit
Each kit contains labeled reagents assembled according to storage temperature requirements (frozen [-15° to -35°C]; refrigerated [2° to 8°C] and controlled room temperature [15° to 30°C]).
# IV. CONTRAINDICATIONS, WARNINGS, AND PRECAUTIONS
There are no known contraindications for the VERSANT HCV RNA Qualitative Assay.
Refer to the Package Insert for a listing of warnings and precautions.
# V. ALTERNATE PRACTICES AND PROCEDURES
Currently, the diagnosis of HCV infection is largely established using serologic screening with EIA for anti-viral antibodies followed by supplemental testing with RIBA. The technology for detection of anti-HCV has progressed to third generation EIA and RIBA assays. Detection of HCV antibody is primarily limited due to the elapsed time from acute infection to seroconversion, which may take from three to six months. Furthermore, in patients who are immunosuppressed or immunocompromised, such as by infection with human immunodeficiency virus (HIV) or chronic renal failure (i.e., dialysis patients), evidence of anti-HCV seroconversion may never occur. Additionally, anti-HCV serology tests cannot distinguish between active and inactive viral replication.
Recently, nucleic acid amplification tests (NAATs) have been developed, which can detect HCV RNA in serum or plasma within one to two weeks after exposure to the virus and weeks before the onset of ALT elevations or the appearance of anti-HCV.
9
{2}
3
10
# VI. MARKETING HISTORY
The VERSANT HCV RNA Qualitative Assay received approval outside the U.S. to be marketed in France, Japan, and Canada.
The VERSANT HCV RNA Qualitative Assay has not been withdrawn from marketing for any reason related to the safety or effectiveness of the product.
# VII. POTENTIAL ADVERSE EFFECTS OF THE DEVICE ON HEALTH
The only adverse effect of the Versant HCV RNA, as with all *in vitro* diagnostic assays, is the possibility of misdiagnosis due to an erroneous test result, which is likely due to a false positive or a false negative test result.
In the case of a false positive result, patients may be subjected to unnecessary medical interventions or faced with undesirable social implications. A false negative result may delay needed intervention to mediate pain and suffering and improve health or allow for the continued transmission of an infectious disease.
A false positive VERSANT HCV RNA Qualitative Assay test result may initiate certain medical interventions associated with the diagnosis and treatment of HCV infection. A presumptive misdiagnosis of HCV infection may occur if the false positive result is coincident with an ALT value that was elevated due to other reasons. As a result, the patient would be subject to undue psychological stress and a liver biopsy with its potential for side effects. False positive results may be caused by the presence of cross-reacting species in the specimen, procedural errors, carryover contamination, specimen misidentification, or transcription errors.
A false negative VERSANT HCV RNA Qualitative Assay test result may delay needed diagnostic procedures to identify those at risk or suspected of having HCV infection. Due to the parenteral means of disease transmission, failure to identify infected individuals may increase the likelihood of new cases of HCV infection. False negative results may be caused by specimen inhibition, interfering substances, procedural deviations, use of the test by unqualified personnel, or transcription errors.
# VIII. SUMMARY OF NONCLINICAL STUDIES
Nonclinical studies were conducted to establish the analytical performance and potential limitations of the VERSANT HCV RNA Qualitative Assay. The effects of non-HCV factors on assay performance (non-specificity studies) were also included in the studies. These nonclinical laboratory studies were performed by the Research and Development Department (R&D) at Gen-Probe Incorporated and by the Nucleic Acid Assay Development Laboratory at Bayer Diagnostics, Bayer Corporation.
The performance characteristics determined through the conduct of the nonclinical testing are summarized in the package insert for the VERSANT HCV RNA Qualitative Assay. Brief summaries of the results from the nonclinical studies are also provided in the following sections.
{3}
# Specificity
The specificity of the VERSANT HCV RNA Qualitative Assay was determined using 1,000 serum and 1,504 EDTA plasma specimens from anti-HCV negative volunteer blood donors. The specimens were negative for antibodies to HCV using FDA approved methods. Of the total samples tested, 2,495/2,504 was nonreactive in the VERSANT HCV RNA Qualitative Assay, yielding a specificity of 99.6%.
# Analytical Sensitivity
1. Limit of Detection (WHO International Standard)
The Limit of Detection (LOD) for the VERSANT HCV RNA Qualitative Assay was determined by testing serial dilutions of the WHO International Standard for HCV genotype 1 RNA (NIBSC code 96/790). The tables in the package insert present the percent detection of each panel member. Each panel member was tested in replicates ranging from 60 to 240.
Serial dilutions of the WHO International Standard for HCV genotype 1 RNA were detected ≥95% of the time as low as 7.5 IU/mL. Linear regression analysis determined 5.3 IU/mL (95% probability) as the limit of detection for the VERSANT HCV RNA Qualitative Assay.
2. Detection of HCV Genotypes Using RNA Transcripts
Transcripts of HCV genotypes 1, 2a, 2b, 3a, 4a, 5a, and 6a made from the 5'-untranslated region of the HCV genome were tested using the VERSANT HCV RNA Qualitative Assay. All transcripts were quantitated using phosphate analysis and confirmed using hyperchromicity and OD₂₆₀. The copies/mL were converted to IU/mL using an in-house conversion factor: 5.2 copies/mL = 1 IU/mL.
Dilutions of each transcript were tested at 9.6 IU/mL (50 copies/mL) for genotypes 1, 2a, 3a, 4a, 5a, and 6a. Genotype 2b was diluted to 14.4 IU/mL (75 copies/mL). Each transcript was tested in replicates ranging from 360 to 720. The results are presented in the package insert.
With the exception of genotype 2b, all genotype transcripts were detected ≥95% of the time at 9.6 IU/mL (50 copies/mL). Genotype 2b was detected ≥95% of the time at 14.4 IU/mL (75 copies/mL).
3. Detection of HCV Genotypes Using Clinical Specimens
Clinical specimens representing HCV genotypes 1 to 6 at different concentrations were used to determine the percent detection of the VERSANT HCV RNA Qualitative Assay. The specimens were quantitated using the VERSANT HCV RNA 3.0 Assay (bDNA). The genotypes of the specimens were provided by the specimen vendor and confirmed using the VERSANT HCV Genotype Assay (LiPA) and sequencing. The results are presented in the package insert. The overall percent detected across all HCV genotypes tested was ≥95% at 9.6 IU/mL (50 copies/mL).
4
{4}
In a supplemental study, 61 clinical specimens representing genotypes 1 to 6 were tested at 1,00, 300 and 100 c/mL; no testing was performed at 50 c/mL. With the exception of specimens representing HCV genotype 2, all specimens were detected at all levels. All clinical specimens containing HCV genotypes 1 to 6 showed reactivity in the VERSANT HCV RNA Assay. These included 8 specimens in the transcript testing, 6 in the clinical specimen testing, and 61 in the supplemental testing.
## Analytical Specificity
### 1. Cross Contamination Frequency
The potential cross-contamination frequency was determined by testing replicates of a high titer HCV genotype 1 positive specimen and replicates of an HCV negative specimen. HCV positive samples (1 × 10⁶ copies/mL) were alternated with HCV negative samples using a "checkerboard" pattern. Forty-five (45) replicates each of HCV negative and HCV positive samples were tested in each of five runs, for a total of 225 replicates of the HCV positive samples and 225 replicates of the HCV negative samples. No false results were obtained; two negative samples were invalid. Combined results across all runs yielded a cross-contamination frequency of 0% (0/223).
### 2. Microorganisms and Viruses
The potential cross-reaction and interference of other microorganisms and viruses was evaluated by adding selected microorganisms and viruses to HCV negative specimens and specimens spiked with HCV genotype 1 at 9.6 IU/mL (50 copies/mL); skin flora microorganisms that may contaminate a blood sample or microorganisms and viruses that can co-infect individuals with HCV infection were tested.
The microorganisms and viruses were pooled and tested at final concentrations of 5 × 10⁴ CFU/mL or 5 × 10⁴ copies/mL, respectively. Pool 1 contained E. coli, P. aeruginosa, K. pneumoniae, H. influenzae, and cytomegalovirus (CMV) (Towne). Pool 2 contained E. cloacae, P. fluorescens, S. aureus, S. marcescens, and S. pneumoniae. Pool 3 contained S. epidermidis, Streptococcus group B, C. albicans, hepatitis B virus (HBV), and HIV-1 B. Pool 4 contained HIV-1 A, HIV-1 C, and HIV-1 D. Pool 5 contained HIV-1 E, HIV-1 F, HIV-1 O and P. acnes. Hepatitis G virus (HGV) also was tested both in the presence and absence of spiked HCV 1a at 9.6 IU/mL (50 copies/mL) using five HGV-positive specimens. HGV titers were not known due to the lack of an HGV quantitative assay. For all microorganisms and viruses tested, no cross-reactions or interference were observed in the VERSANT HCV RNA Qualitative Assay.
## Potentially Interfering Substances
12
{5}
6
13
# 1. Endogenous Substances
Potentially interfering endogenous substances were tested by adding these substances to HCV negative specimens and specimens spiked with HCV genotype 1 at 9.6 IU/mL (50 copies/mL). The concentrations of potentially interfering endogenous substances were tested according to NCCLS Document EP7-P.
The following endogenous substances were tested: 500 mg/dL hemoglobin, 60 mg/dL bilirubin (conjugated), 60 mg/dL bilirubin (unconjugated), 3,000 mg/dL triglycerides, and 8 g/dL protein. None of the endogenous substances tested interfered with the sensitivity and specificity of the VERSANT HCV RNA Qualitative Assay.
# 2. Therapeutic Drugs
The potential interference of commonly prescribed drugs to treat HCV or other viral diseases was tested by adding these substances to HCV negative specimens and specimens spiked with HCV genotype 1 at 9.6 IU/mL (50 copies/mL). The drugs were pooled and tested at final concentrations five times the reported peak serum or plasma concentrations in the therapeutic range. Pool 1 contained Intron A, Ribavirin, and Azathioprine. Pool 2 contained Cyclosporine, Aldactone, and Prednisone. Pool 3 contained Roferon A, Tacrolimus, and Amantadine HCl. Pool 4 contained Fluoxetine HCl, Peginterferon Alfa-2b, and Azidothymidine. Pool 5 contained Ganciclovir and Dideoxycytidine, and Pool 6 contained Didanosine and Didehydrodeoxythymidine. None of the drugs tested interfered with the sensitivity and specificity of the VERSANT HCV RNA Qualitative Assay.
# 3. Other Potentially Interfering Substances
The effect of other potentially interfering substances was determined by testing HCV negative specimens and specimens spiked with HCV genotype 1 at 9.6 IU/mL (50 copies/mL). The disease categories tested were: myeloma IgG (n=12) positive specimens, anti-nuclear antibody positive specimens (n=10), anti-doublestranded DNA positive specimens (n=6), rheumatoid factor positive specimens (n=19), and specimens from subjects with systemic lupus erythematosus (n=10).
With the exception of a subset of the myeloma specimens, none of the tested samples from subjects with HCV-like disease states interfered with the performance of the VERSANT HCV RNA Qualitative Assay. Refer to the Limitations section of the package insert for information on myeloma specimens.
# 4. Specimen Collection (Commonly Used Anticoagulants)
HCV-negative specimens and specimens spiked with HCV genotype 1 at 9.6 IU/mL (50 copies/mL) were collected in serum separator tubes (SST PLUS, plastic), K₂ EDTA (PLUS, plastic), K₂ EDTA (PPT), sodium citrate (glass, 4%), ACD-solution A (glass) and sodium heparin (PLUS, plastic 60 USP units) tubes. None of the anticoagulants tested affected the sensitivity and specificity of the VERSANT HCV RNA Qualitative Assay.
{6}
# IX. SUMMARY OF CLINICAL STUDIES
Performance characteristics for the VERSANT HCV RNA Qualitative Assay were established in a multi-center study at four geographically diverse clinical sites. In the study, serum or plasma specimens from 1,511 subjects enrolled in hepatology clinics, intravenous drug abuse clinics, transfusion centers and AIDS clinics were evaluated. The study population included 938 (62.1%) subjects with a medical history of liver disease or positive anti-HCV serology and 741 (49.0%) subjects diagnosed with chronic HCV hepatitis. A history of one or more risk factors was reported by 1,175 (77.8%) subjects. Symptoms associated with HCV infection were reported by 741 (49.0%) subjects and 112 (7.4%) subjects were infected with HIV or another hepatitis virus. No patients were on anti-viral therapy at the time of enrollment into the study.
Of the 1,511 total subjects, 544 (36.0%) were female and 967 (64.0%) were male. Subject age ranged from 17 years to 89 years with a mean of 47 years. Ethnicity representation included: White, Non-Hispanic, 689 (45.6%); Black, Non-Hispanic, 588 (38.9%); White, Hispanic, 149 (9.9%); Asian/Pacific Islander, 23 (1.5%); Black, Hispanic, 19 (1.3%); Native American, Alaskan, 8 (0.5%); and unknown or other, 35 (2.3%).
# CLINICAL STUDY RESULTS
A total of 5,542 EIA, RIBA, PCR and VERSANT HCV RNA Qualitative Assay results were used in the clinical data analysis. Performance characteristics were based on calculations of Positive and Negative Percent Agreement and 95% Confidence Intervals of VERSANT HCV RNA Qualitative Assay results compared to anti-HCV serology results and to PCR results in three different populations: subjects with or without anti-HCV, subjects with anti-HCV with or without biochemical (i.e., elevated ALT) or histological evidence of liver disease, and subjects at risk for HCV with or without anti-HCV. Liver histopathology was characterized by cirrhosis, fibrosis, hepatocellular carcinoma, or other histopathological diagnosis. Subjects were classified as "at risk for HCV" if they were exposed to needle-stick accidents or another occupational exposure, blood or blood product transfusion, past or current injection-drug use or use of shared drug tools, multiple sex partners, sex with an HCV-positive partner, men having sex with men, dialysis, or a history of a sexually transmitted disease (STD).
For assay comparisons made within each population, performance of the VERSANT HCV RNA Qualitative Assay was similar across the four study sites and for each specimen type. Summary data are provided in Tables IX-1 and IX-.2 for each population and overall. Serum and plasma data are shown combined.
# Comparison with Anti-HCV Serology
Performance of the VERSANT HCV RNA Qualitative Assay compared to anti-HCV serology was similar for each population and overall as shown in Table IX-1. Of the 1,511 VERSANT HCV RNA Qualitative Assay and anti-HCV results available in subjects with or without evidence of HCV, ten (10) anti-HCV serology results were indeterminate. Of the remaining 1,501 VERSANT HCV RNA Qualitative Assay and conclusive anti-HCV results available in this population, 93.6% were in agreement between the two assays. The VERSANT HCV RNA Qualitative Assay detected HCV RNA in 930 of 1,014 (91.7% Positive Agreement) anti-HCV
14
{7}
serology positive specimens, but not in 475 of 486 (97.7% Negative Agreement) anti-HCV serology negative specimens. Sixteen (16) results were RIBA indeterminate or negative, however, five (5) of the 16 were PCR positive. Therefore, these five (5) subjects were infected. The VERSANT HCV RNA Qualitative Assay agreed with all 5 of these results (100%).
Of the 522 specimens collected from subjects with anti-HCV and biochemical or histological evidence of liver disease, the VERSANT HCV RNA Qualitative Assay detected HCV RNA in 486 (93.1%) specimens. HCV RNA was detected in: (a) 368 (98.7%) of 373 specimens from subjects with elevated ALT and liver histopathology, (b) 92 (74.8%) of 123 specimens from subjects with normal ALT and liver histopathology, and (c) 26 (100%) of 26 specimens from subjects with elevated ALT and no liver histopathology. Of the 129 specimens collected from subjects without anti-HCV with evidence liver disease, the VERSANT HCV RNA Qualitative Assay did not detect HCV RNA in 127 (98.4%) specimens. Six (6) results were RIBA indeterminate or negative; however, three (3) of the six (6) were PCR positive. Therefore, these three (3) subjects were infected. The VERSANT HCV RNA Qualitative Assay agreed with all three (3) of these results (100%).
Of the 1,175 subjects at risk for HCV, the VERSANT HCV RNA Qualitative Assay detected HCV RNA in 765 of 831 (92.1%) anti-HCV serology positive specimens, but not in 328 of 336 (97.6%) anti-HCV serology negative specimens. Nine (9) results were RIBA indeterminate or negative; however, PCR was positive for four (4) of the nine (9) subjects, indicating that they were infected. The VERSANT HCV RNA Qualitative Assay agreed with all four (4) of these results (100%).
Table IX-1. Agreement of the VERSANT HCV RNA Qualitative Assay and Anti-HCV Serology for Each Study Population
| | N | VERSANT+ Serology+ | VERSANT+ Serology- | VERSANT- Serology+ | VERSANT- Serology- | % Negative Agreement | 95% C.I. | % Positive Agreement | 95% C.I. |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Total | 1511 | 935 | 11 | 84 | 481 | 97.8 | 96.0-98.9 | 91.8 | 89.9-93.4 |
| Anti-HCV Serology | 1511 | 935 | 11 | 84 | 481 | 97.8 | 96.0-98.9 | 91.8 | 89.9-93.4 |
| EIA R / RIBA Pos | 1014 | 930 | 0 | 84 | 0 | N/A | N/A | 91.7 | 89.8-93.3 |
| EIA R / RIBA Neg | 6 | 1^{1} | 0 | 0 | 5 | 100 | 47.8- 100 | 100 | 2.5- 100 |
| EIA R / RIBA Ind | 10 | 4^{1} | 0 | 0 | 6^{2} | 100 | 54.1- 100 | 100 | 39.8- 100 |
| EIA NR^{2} | 481 | 0 | 11 | 0 | 470 | 97.7 | 95.9-98.9 | N/A | N/A |
Anti-HCV Serology, ALT, Liver Histological Findings
| Total | 658 | 490 | 2 | 37 | 129 | 98.5 | 94.6-99.8 | 93.0 | 90.5-95.0 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Elevated ALT and Liver Histopathology | 425 | 371 | 0 | 5 | 49 | 100 | 92.7- 100 | 98.7 | 96.9-99.6 |
| EIA R / RIBA Pos | 373 | 368 | 0 | 5 | 0 | N/A | N/A | 98.7 | 96.9-99.6 |
| EIA R / RIBA Neg | 3 | 1^{1} | 0 | 0 | 2 | 100 | 15.8- 100 | 100 | 2.5- 100 |
| EIA R / RIBA Ind | 3 | 2^{1} | 0 | 0 | 1^{3} | 100 | 2.5- 100 | 100 | 15.8- 100 |
| EIA NR^{2} | 46 | 0 | 0 | 0 | 46 | 100 | 92.3-100 | N/A | N/A |
{8}
| Normal ALT and Liver Histopathology | 205 | 92 | 2 | 31 | 80 | 97.6 | 91.5-99.7 | 74.8 | 66.2-82.2 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| EIA R / RIBA Pos | 123 | 92 | 0 | 31 | 0 | N/A | N/A | 74.8 | 66.2-82.2 |
| EIA R / RIBA Neg | 1 | 0 | 0 | 0 | 1 | 100 | 2.5-100 | N/A | N/A |
| EIA R / RIBA Ind | 1 | 0 | 0 | 0 | 1³ | 100 | 2.5- 100 | N/A | N/A |
| EIA NR² | 80 | 0 | 2 | 0 | 78 | 97.5 | 91.3-99.7 | N/A | N/A |
| Elevated ALT and No Liver Histopathology | 26 | 26 | 0 | 0 | 0 | N/A | N/A | 100 | 86.8-100 |
| EIA R / RIBA Pos | 26 | 26 | 0 | 0 | 0 | N/A | N/A | 100 | 86.8-100 |
| EIA R / RIBA Neg | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA R / RIBA Ind | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA NR² | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| Normal ALT and No Liver Histopathology | 2 | 1 | 0 | 1 | 0 | N/A | N/A | 50.0 | 1.3-98.7 |
| EIA R / RIBA Pos | 2 | 1 | 0 | 1 | 0 | N/A | N/A | 50.0 | 1.3-98.7 |
| EIA R / RIBA Neg | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA R / RIBA Ind | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA NR² | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
At Risk
| Total | 1175 | 769 | 8 | 66 | 332 | 97.6 | 95.4-99.0 | 92.1 | 90.1-93.8 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| EIA R / RIBA Pos | 831 | 765 | 0 | 66 | 0 | N/A | N/A | 92.1 | 90.0-93.8 |
| EIA R / RIBA Neg | 2 | 1¹ | 0 | 0 | 1 | 100 | 2.5- 100 | 100 | 2.5- 100 |
| EIA R / RIBA Ind | 7 | 3¹ | 0 | 0 | 4³ | 100 | 39.8- 100 | 100 | 29.2- 100 |
| EIA NR² | 335 | 0 | 8 | 0 | 327 | 97.6 | 95.3-99.0 | N/A | N/A |
VERS = VERSANT Ser = Serology R = Reactive NR = Nonreactive Pos = Positive
Neg = Negative Agree = Agreement N/A = Insufficient data for meaningful result
Ind = Indeterminate
¹Subject was designated infected per CDC guidelines if RIBA was indeterminate or negative, and PCR was positive.
²Patients who had anti-HCV EIA non-reactive results were studied for approximating the specificity of the AMPLICOR HCV Test, v2.0, but these data do not imply performance for testing of anti-HCV EIA non-infected individuals.
³Subject was designated as having uncertain infection per CDC guidelines if RIBA was indeterminant and PCR was negative.
## Comparison with PCR
As shown in Table XI-2, performance of the VERSANT HCV RNA Qualitative Assay compared to an FDA-cleared PCR test was similar for each population and overall. Of the
9
{9}
1,013 anti-HCV serology positive specimens, HCV RNA was detected in 921 specimens by both assays (99.7% positive Agreement) and not in 83 specimens (91.2% Negative Agreement). The VERSANT HCV RNA Qualitative Assay was in 100% agreement with PCR for specimens with indeterminate or negative RIBA results. The VERSANT HCV RNA Qualitative Assay and the PCR test detected HCV RNA in 4 of 10 specimens with indeterminate RIBA results and in 1 of 6 specimens with RIBA negative results. Of the 471 anti-HCV serology negative specimens, both assays detected HCV RNA in 6 EIA nonreactive specimens, but not in 459 EIA nonreactive specimens.
Of the 522 VERSANT HCV RNA Qualitative Assay and PCR test results for subjects with anti-HCV and biochemical or histological evidence of liver disease, 520 (99.6%) were in agreement between the two assays: (a) 373 (100%) of 373 specimens from subjects with elevated ALT and liver histopathology, (b) 121 (98.4%) of 123 specimens from subjects with normal ALT and liver histopathology, and (c) 26 (100%) of 26 specimens from subjects with elevated ALT and no liver histopathology. Both assays were in 100% agreement for specimens with indeterminate or negative RIBA results. The HCV TMA Assay and the PCR test detected HCV RNA in 2 of 4 specimens with indeterminate RIBA results and in 1 of 4 specimens with RIBA negative results. Of the 126 specimens collected from subjects without anti-HCV, 125 (99.2%) were in agreement. Both assays detected HCV RNA in 1 EIA nonreactive specimen, but not in 124 EIA nonreactive specimens.
Of the 830 VERSANT HCV RNA Qualitative Assay and PCR test results for subjects at risk for HCV infection with anti-HCV, 824 (99.3%) were in agreement between the two assays. Both assays detected HCV RNA in 759 specimens, but not in 65 specimens. Furthermore, both assays were in 100% agreement for specimens with indeterminate or negative RIBA results. The VERSANT HCV RNA Qualitative Assay and the PCR test detected HCV RNA in 3 of 7 specimens with indeterminate RIBA results and in 1 of 2 specimens with RIBA negative results. Of the 325 specimens collected from subjects at risk for HCV infection without anti-HCV, 321 (98.8%) were in agreement. Of the 325 anti-HCV serology negative specimens from subjects at risk for HCV infection, both assays detected HCV RNA in 5 EIA nonreactive specimens, but not in 316 EIA nonreactive specimens.
Table XI-2. Agreement of the VERSANT HCV RNA Qualitative Assay and PCR for Each Study Population
| | N | VERSANT+ PCR+ | VERSANT+ PCR- | VERSANT- PCR+ | VERSANT- PCR- | % Negative Agreement | 95% C.I. | % Positive Agreement | 95% C.I. |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Total | 1500^{1} | 932 | 12 | 3 | 553 | 97.9 | 96.3-98.9 | 99.7 | 99.1-99.9 |
| Anti-HCV Serology | 1500 | 932 | 12 | 3 | 553 | 97.9 | 96.3-98.9 | 99.7 | 99.1-99.9 |
| EIA R / RIBA Pos | 1013 | 921 | 8 | 1 | 83 | 91.2 | 83.4-96.1 | 99.9 | 99.4-100 |
| EIA R / RIBA Neg | 6 | 1 | 0 | 0 | 5 | 100 | 47.8-100 | 100 | 2.5-100 |
| EIA R / RIBA Ind | 10 | 4 | 0 | 0 | 6 | 100 | 54.1-100 | 100 | 39.8-100 |
| EIA NR^{2} | 471 | 6 | 4 | 2 | 459 | 99.1 | 97.8-99.8 | 75.0 | 34.9-96.8 |
{10}
Anti-HCV Serology, ALT, Liver Histological Findings
| Total | 658 | 489 | 3 | 0 | 166 | 98.2 | 94.9-99.6 | 100 | 99.2-100 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Elevated ALT and Liver Histopathology | 425 | 371 | 0 | 0 | 54 | 100 | 93.4-100 | 100 | 99.0-100 |
| EIA R / RIBA Pos | 373 | 368 | 0 | 0 | 5 | 100 | 47.8-100 | 100 | 99.0-100 |
| EIA R / RIBA Neg | 3 | 1 | 0 | 0 | 2 | 100 | 15.8-100 | 100 | 2.5-100 |
| EIA R / RIBA Ind | 3 | 2 | 0 | 0 | 1 | 100 | 2.5-100 | 100 | 15.8-100 |
| EIA NR² | 46 | 0 | 0 | 0 | 46 | 100 | 92.3-100 | N/A | N/A |
| Normal ALT and Liver Histopathology | 205 | 91 | 3 | 0 | 111 | 97.4 | 92.5-99.5 | 100 | 96.0-100 |
| EIA R / RIBA Pos | 123 | 90 | 2 | 0 | 31 | 93.9 | 79.8-99.3 | 100 | 96.0-100 |
| EIA R / RIBA Neg | 1 | 0 | 0 | 0 | 1 | 100 | 2.5-100 | N/A | N/A |
| EIA R / RIBA Ind | 1 | 0 | 0 | 0 | 1 | 100 | 2.5-100 | N/A | N/A |
| EIA NR² | 80 | 1 | 1 | 0 | 78 | 98.7 | 93.1-100 | 100 | 2.5-100 |
| Elevated ALT and No Liver Histopathology | 26 | 26 | 0 | 0 | 0 | N/A | N/A | 100 | 86.8-100 |
| EIA R / RIBA Pos | 26 | 26 | 0 | 0 | 0 | N/A | N/A | 100 | 86.8-100 |
| EIA R / RIBA Neg | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA R / RIBA Ind | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA NR² | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| Normal ALT and No Liver Histopathology | 2 | 1 | 0 | 0 | 1 | 100 | 2.5-100 | 100 | 2.5-100 |
| EIA R / RIBA Pos | 2 | 1 | 0 | 0 | 1 | 100 | 2.5-100 | 100 | 2.5-100 |
| EIA R / RIBA Neg | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA R / RIBA Ind | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
| EIA NR² | 0 | 0 | 0 | 0 | 0 | N/A | N/A | N/A | N/A |
At Risk
| Total | 1164 | 768 | 7 | 3 | 386 | 98.2 | 96.4-99.3 | 99.6 | 98.9-99.9 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| EIA R / RIBA Pos | 830 | 759 | 5 | 1 | 65 | 92.9 | 84.1-97.6 | 99.9 | 99.3-100 |
| EIA R / RIBA Neg | 2 | 1 | 0 | 0 | 1 | 100 | 2.5-100 | 100 | 2.5-100 |
| EIA R / RIBA Ind | 7 | 3 | 0 | 0 | 4 | 100 | 39.8-100 | 100 | 29.2-100 |
| EIA NR² | 325 | 5 | 2 | 2 | 316 | 99.4 | 97.7-99.9 | 71.4 | 29.0-96.3 |
VERS = VERSANT R = Reactive NR = Nonreactive Pos = Positive Neg = Negative
Agree = Agreement N/A = Insufficient data for meaningful result Ind = Indeterminate
N/A = Insufficient data for meaningful result
11
{11}
# Clinical Specimen Storage Study
Specimen storage conditions were evaluated for their effects on assay performance. Specimens from each of 72 subjects were separated into two aliquots. One aliquot was stored at $2^{\circ}$ to $8^{\circ}\mathrm{C}$ and tested within 48 hours. The other aliquot was stored frozen at $-20^{\circ}\mathrm{C}$ or below for up to 44 days. Data indicated no difference in the detection of HCV RNA in specimens stored in the two conditions.
# Signal Analysis
A summary of the VERSANT HCV RNA Qualitative Assay signal analysis for the assay calibrators and controls and the internal control in plasma and serum specimens is shown in the table below:
| Calibrator | N | Mean RLU (x 1000) | SD (x 1000) | % CV | Min RLU (x 1000) | Max RLU (x 1000) |
| --- | --- | --- | --- | --- | --- | --- |
| Positive | 111 | 1,265 | 102 | 8.0 | 795 | 1493 |
| Negative | 110 | 5.6 | 3.0 | 53.2 | 0 | 13.1 |
| Control | N | Mean S/CO | SD | % CV | Min S/CO | Max S/CO |
| --- | --- | --- | --- | --- | --- | --- |
| Positive | 54 | 22.5 | 2.1 | 9.5 | 11.2 | 27.3 |
| Negative | 54 | 0.07 | 0.04 | 55.1 | 0.01 | 0.2 |
| Internal Control | N | Mean IC S/CO | SD | %CV | Min S/CO | Max S/CO |
| --- | --- | --- | --- | --- | --- | --- |
| Serum | 355 | 2.1 | 0.1 | 6.1 | 1.0 | 3.0 |
| Plasma | 210 | 2.1 | 0.09 | 4.3 | 1.7 | 2.2 |
# REPRODUCIBILITY
Reproducibility testing was performed at three laboratories (A, B, C) to obtain measures of repeatability and reproducibility during the clinical trial; two of the sites were outside laboratories and one was in-house. Testing was also conducted in-house during the preclinical phase (D). In the clinical testing, the three sites were provided with six identical panels of eight samples containing 0 to 9,615 IU/mL (0 to 50,000 copies/mL) genotype 1 or 0 to 577 IU/mL (0 to 3,000 copies/mL) genotype 2b in serum or plasma. In the preclinical phase testing, six member serum or plasma panels for genotype 1 at 0 to 14.4 IU/mL (0 to 75 copies/mL) and genotype 2b at 0 to 69.2 IU/mL (0 to 360 copies/mL) were tested. At sites A, B, and C, each of two operators performed two days of testing with each of three kit lots for a total of six days of testing. At Site D, three operators tested the genotype 1 panel with each of three kit lots on six separate days. Similarly, Site D tested the genotype 2b panel with each of three kit lots on each of five separate days. Reproducibility testing at or near the assay's limit of detection was not done with genotypes other than genotype 1. The data is presented in the package insert.
19
{12}
# X. CONCLUSIONS DRAWN FROM STUDIES
## Risk/Benefit Analysis
As a nucleic acid and amplification assay, the VERSANT HCV RNA Qualitative Assay detects the presence of HCV RNA in human plasma or serum. Detection of viral nucleic acid is indicative of viral replication and therefore, active HCV infection. The primary benefit of using this test is the detection of active HCV infection in individuals with antibody evidence of HCV infection with evidence of liver disease, and individuals suspected to be actively infected with HCV with antibody evidence, and individuals at risk for HCV infection with antibodies to HCV.
The potential risks seen for *in vitro* diagnostic assays are not unusual in the laboratory setting, and appropriate warnings and risks are contained in the labeling for these devices. Standard good laboratory practices are recommended to minimize the risks to the end user. The benefits to patients tested with the VERSANT HCV RNA Qualitative Assay exceed the known or potential risks or adverse events for patients or laboratory personnel.
## Safety
The VERSANT HCV RNA Qualitative Assay is a diagnostic test that utilizes blood specimens and, as such, requires the withdrawal of blood from individuals being tested. The safety hazards to individuals being tested are no greater than those involved in other diagnostic tests for which blood is drawn.
# XI. PANEL RECOMMENDATIONS
Pursuant to Section 515(c)(2) of the act as amended by the Safe Medical Devices Act of 1990, this PMA was not the subject of an FDA Microbiology Devices Advisory Panel meeting because the information in the PMA substantially duplicated information previously reviewed by the Panel.
# XII. CDRH DECISION
The applicant’s manufacturing facility inspected on was found to be in compliance with the Quality Systems Regulation (21 CFR 820).
FDA issued an approval order on November 7, 2002.
# XIII. APPROVAL SPECIFICATIONS
Directions for use: See Labeling
Hazards to Health from Use of the Device: See Indications, Contraindications, Warning, precautions and Adverse Events in the labeling.
Postapproval Requirements and Restrictions: See approval order.
13
20
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.
