Archived clinical serum samples from routine laboratory testing
Retrospective clinical samples were used to evaluate the performance of the Plexus EBV IgG assay by comparing results against predicate devices and a consensus-based algorithm.
Patients for whom EBV tests were ordered; retrospective samples were pre-selected based on EBV VCA IgM positive results from an FDA-cleared device.; Sample Size: 150; Number of Sites: 1
Percent agreement with consensus predicate results
Indications for Use
Focus Diagnostics' Plexus™ EBV IgG Multi-Analyte Diagnostics test kit is intended for qualitatively detecting the presence or absence of human IgG class antibodies to viral capsid antigen (VCA), early antigen-diffuse (EA-D), and nuclear antigen-1 (EBNA-1) of Epstein-Barr virus in human sera. The test is indicated as an aid in the diagnosis of EBV infection and EBV-associated infectious mononucleosis. The performance of this assay has not been established for use in the diagnosis of nasopharyngeal carcinoma and Burkitt's lymphoma, for testing of immunocompromised patients, for use by a point of care facility or for use with automated equipment. This assay has not been evaluated for donor screening.
Device Story
Multiplexed microparticle immunoassay using Luminex xMAP technology; detects IgG antibodies to EBV VCA, EA-D, and EBNA-1. Input: human serum samples. Process: patient sera incubated with antigen-conjugated polystyrene beads; bound antibodies detected via PE-conjugated anti-human IgG; fluorescence measured by Luminex xMAP system using orange/green lasers. Output: qualitative results for each analyte. Used in clinical laboratories; operated by trained personnel. Output aids clinicians in diagnosing EBV infection and infectious mononucleosis.
Clinical Evidence
Clinical performance evaluated using 723 prospective and 150 retrospective serum samples. Prospective samples compared against consensus predicates (for VCA) or commercial ELISA (for EBNA-1/EA-D). Positive percent agreement for VCA IgG in acute samples was 100% (95% CI: 93.7-100%). Reproducibility studies (inter-laboratory, intra-assay, inter-assay, and inter-lot) performed across three sites. Cross-reactivity tested against ANA, CMV, HSV, HHV-6, Measles, Mumps, Rubella, Toxoplasma, and VZV.
Technological Characteristics
Multiplexed microparticle immunoassay using polystyrene beads conjugated with recombinant EBV antigens (EA-D, EBNA-1) and affinity-purified VCA. Energy source: Luminex xMAP system (lasers). Connectivity: Standalone instrument. Software: Plexus Multi Analyte Diagnostic Software. Sterilization: Not applicable (reagents).
Indications for Use
Indicated for qualitative detection of human IgG antibodies to EBV VCA, EA-D, and EBNA-1 in human serum as an aid in diagnosing EBV infection and EBV-associated infectious mononucleosis. Not for use in immunocompromised patients, nasopharyngeal carcinoma, Burkitt's lymphoma, point-of-care, or donor screening.
Regulatory Classification
Identification
Epstein-Barr virus serological reagents are devices that consist of antigens and antisera used in serological tests to identify antibodies to Epstein-Barr virus in serum. The identification aids in the diagnosis of Epstein-Barr virus infections and provides epidemiological information on diseases caused by these viruses. Epstein-Barr viruses are thought to cause infectious mononucleosis and have been associated with Burkitt's lymphoma (a tumor of the jaw in African children and young adults) and postnasal carcinoma (cancer).
Predicate Devices
Diamedix EBV VCA IgG ELISA
Diamedix EBV EBNA-1 IgG ELISA
Diamedix EBV EA-D IgG ELISA
ATHENA MULTI-LYTE EBV IGG TEST SYSTEM
Focus EBV-VCA ANTIBODY (IGG) - IFA
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K073382
B. Purpose for Submission:
New device.
C. Measurand:
Epstein - Barr virus (EBV) specific IgG antibodies to the EBV nuclear antigen (EBV NA-1), viral capsid antigen (EBV VCA), and early antigen-diffuse (EBV EA-D)
D. Type of Test:
Multiplexed micro particle immunoassay based on Luminex xMAP technology
E. Applicant:
Focus Diagnostics, Inc.
F. Proprietary and Established Names:
Plexus™ EBV IgG Multi-Analyte Diagnostics (MP0500G)
G. Regulatory Information:
1. Regulation section:
21 CFR 866.3235 – Epstein Barr Virus Serological Reagents
2. Classification:
Class I, non exempt
3. Product code:
LSE
4. Panel:
Microbiology (83)
{1}
H. Intended Use:
1. Intended use(s):
Focus Diagnostics' Plexus™ EBV IgG Multi-Analyte Diagnostics test kit is intended for qualitatively detecting the presence or absence of human IgG class antibodies to viral capsid antigen (VCA), early antigen-diffuse (EA-D), and nuclear antigen-1 (EBNA-1) of Epstein-Barr virus in human sera. The test is indicated as an aid in the diagnosis of EBV infection and EBV-associated infectious mononucleosis.
The performance of this assay has not been established for use in the diagnosis of nasopharyngeal carcinoma and Burkitt's lymphoma, for testing of immunocompromised patients, for use by a point of care facility or for use with automated equipment. This assay has not been evaluated for donor screening.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
Instrument: The Luminex xMAP® System.
Software: Plexus™ Multi Analyte Diagnostic Software for Luminex xMAP instrument with Luminex IS 2.3 software (SW.MP0001)
I. Device Description:
The Focus Diagnostics Plexus™ EBV IgG Multi-Analyte Diagnostic uses an antigen bead suspension that contains three distinct EBV antigen bead types (viral capsid antigen (VCA), early antigen-D (EA-D) and nucleic antigen-1 (EBNA-1)) and one process control bead type that fluoresce at different wavelengths and/or intensities.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Predicate devices: Diamedix EBNA-1 IgG ELISA (K946353), Diamedix EA-D IgG ELISA (K884829), Diamedix VCA IgG (K884591).
Consensus comparator: For VCA IgG the performance was compared to a consensus based algorithm based on a 2 out of 3 rule,
{2}
consisting of the predicate device Diamedix VCA IgG ELISA (K884951) and 2 other devices; Athena Multi-Lyte EBV IgG Test System (K042118) and Focus EBV-VCA Antibody (IgG) IFA (K884591)
2. Predicate K number(s):
See J1 above
3. Comparison with predicate:
VCA IgG:
| Component | Similarities | | | |
| --- | --- | --- | --- | --- |
| | Device | K | K | K |
| Measurand | EBV VCA IgG | EBV VCA IgG | EBV VCA IgG | EBV VCA IgG |
| Matrix | Serum | Serum | Serum | Serum |
| Intended Use | Qualitative detection of EBV VCA IgG to aid in diagnosis of infectious mononucleosis | Qualitative detection of EBV VCA IgG to aid in diagnosis of infectious mononucleosis | Qualitative detection of EBV VCA IgG to aid in diagnosis of infectious mononucleosis | Qualitative detection of EBV VCA IgG to aid in diagnosis of infectious mononucleosis |
| | Differences | | | |
| Technology | Multiplexed flow immunoassay | Traditional ELISA | Multiplex bead immunoassay | Immunofluorescence Antibody (IFA) test |
| Antigen | EBV-VCA: VCA gp 125, affinity purified antigen | EBV-VCA: Recombinant 47 kDa fusion half of p18 | EBV VCA gp25 | purified protein |
EBNA-1 IgG:
| Component | Similarities | |
| --- | --- | --- |
| | Device | Predicate |
| Measurand | EBNA-1 IgG | EBNA-1 IgG |
| Matrices | Serum | Serum |
| Intended Use | Aid in diagnosis of infectious mononucleosis | Aid in diagnosis of infectious mononucleosis |
| | Differences | |
| | Device | Predicate |
| Technology | Multiplexed flow immunoassay | Traditional ELISA |
| Antigen | Recombinant EBNA-1, truncated, 35 kDa | 27 kDa purified native protein |
{3}
EA-D IgG:
| Component | Similarities | |
| --- | --- | --- |
| | Device | Predicate |
| Measurand | EBV EA-D IgG | EBV EA-D IgG |
| Matrices | Serum | Serum |
| Intended Use | Qualitative detection of EBV EA-D IgG to aid in diagnosis of infectious mononucleosis | Qualitative detection of EBV EA-D IgG to aid in diagnosis of infectious mononucleosis |
| | Differences | |
| | Device | Predicate |
| Technology | Multiplexed flow immunoassay | Traditional ELISA |
| Antigen | EBV-EA: Recombinant EA-D | EBV-EA: Recombinant EA-D 28 kDa |
K. Standard/Guidance Document referenced (if applicable):
Guidance for Industry and FDA Staff, Format for Traditional and Abbreviated 510(k), 08/12/2005, (http://www.fda.gov/cdrh/ode/guidance/1567.pdf)
Off-The-Shelf Software Use in Medical Devices, 09/9/1999, (http://www.fda.gov/cdrh/ode/guidance/585.pdf)
Cyber security for Networked Medical Devices Containing Off-The-Shelf (OTS) Software, 01/14/2005, (http://www.fda.gov/cdrh/comp/guidance/1553.pdf)
Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, 05/11/2005, (http://www.fda.gov/cdrh/ode/guidance/337.pdf)
General Principles of Software Validation, 01/11/2002, (http://www.fda.gov/cdrh/comp/guidance/938.pdf)
L. Test Principle:
The Focus Diagnostics Plexus™ EBV IgG Multi-Analyte Diagnostic is a three step procedure.
1. Patient sera are diluted and incubated with multiplexed bead suspension consisting of a mixture of distinguishable sets of polystyrene beads. Conjugated to the primary set of beads are the following EBV antigens; EA-D, EBNA- 1 and VCA. The bead mix also contains one background bead set designed to check for nonspecific reactivity in the patient sample. If EBV antibodies are present, then the
{4}
antibodies bind to the corresponding antigen beads. The beads are rinsed to remove non-reactive serum proteins.
2. Phycoerythrin (PE)-conjugated goat anti human IgG, (Conjugate) is added, and the conjugate binds to the bound EBV antibody. The beads are rinsed to remove non-reactive conjugate.
3. Fluorescence from each distinct EBV antigen bead type is measured and compared against a Cutoff calibrator. The fluorescence is read in a plate reader, similar to an ELISA reader. Beads are first read with an orange laser to identify the bead type (e.g., EB-D, VCA, EBNA-1, or background), and then read with a green laser to the measure amount of fluorescence from the PE contained in the conjugate.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
The inter/intra-assay reproducibility and the inter-laboratory reproducibility testing were performed at three laboratories. Each of the three laboratories tested twelve samples in triplicate on five different days. The results of the study are summarized in the table below:
| Plexus VCA IgG | | | | | | Plexus EBNA IgG | | | | | | Plexus EA IgG | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Intra-assay & Inter-assay %CV | | | Inter-Lab | | ID | Intra-assay & Inter-assay %CV | | | Inter-Lab | | ID | Intra-assay & Inter-assay %CV | | | Inter-Lab | |
| | Mean Index | Intra-assay | Inter-assay | Mean Index | % CV | | Mean Index | Intra-assay | Inter-assay | Mean Index | % CV | | Mean Index | Intra-assay | Inter-assay | Mean Index | % CV |
| 5 | 5.38 | 2.1% | 8.1% | 5.38 | 7.4% | 12 | 6.66 | 2.1% | 8.7% | 6.66 | 8.9% | 12 | 4.42 | 3.9% | 7.5% | 4.42 | 2.0% |
| 19 | 5.12 | 2.9% | 10.0% | 5.12 | 10.1% | 15 | 4.41 | 4.1% | 6.9% | 4.42 | 5.0% | 4 | 2.69 | 3.6% | 19.9% | 2.69 | 7.0% |
| 20 | 5.02 | 2.4% | 8.4% | 5.03 | 8.1% | 8 | 3.66 | 2.5% | 6.7% | 3.66 | 5.8% | 16 | 1.88 | 4.7% | 7.5% | 1.88 | 4.7% |
| 6 | 4.21 | 3.2% | 6.7% | 4.20 | 3.7% | 4 | 2.68 | 5.6% | 18.3% | 2.67 | 7.8% | 15 | 1.39 | 5.6% | 15.6% | 1.39 | 15.7% |
| 4 | 3.37 | 4.3% | 16.6% | 3.37 | 2.5% | 18 | 2.05 | 3.8% | 9.0% | 2.05 | 8.6% | 19 | 0.99 | 6.0% | 12.0% | 0.99 | 7.9% |
| 16 | 2.21 | 4.1% | 28.4% | 2.22 | 27.0% | 5 | 1.84 | 3.7% | 8.0% | 1.84 | 4.8% | 8 | 0.91 | 3.7% | 8.6% | 0.91 | 2.1% |
| 18 | 2.11 | 4.0% | 6.0% | 2.11 | 3.7% | 6 | 1.47 | 5.1% | 11.8% | 1.46 | 11.7% | 5 | 0.76 | 4.7% | 12.6% | 0.76 | 5.6% |
| 2 | 2.01 | 3.9% | 7.9% | 2.01 | 4.4% | 2 | 1.00 | 4.0% | 13.4% | 1.00 | 13.6% | 20 | 0.63 | 5.3% | 8.5% | 0.63 | 2.6% |
| 11 | 1.16 | 6.3% | 13.3% | 1.16 | 11.9% | 3 | 0.81 | 6.1% | 16.0% | 0.81 | 11.9% | 18 | 0.32 | 5.3% | 9.6% | 0.32 | 6.6% |
| 8 | 1.11 | 4.7% | 77.0% | 1.12 | 31.1% | 16 | 0.77 | 6.1% | 59.1% | 0.77 | 50.9% | 6 | 0.29 | 6.1% | 33.8% | 0.29 | 4.7% |
| 15 | 0.38 | 8.7% | 19.6% | 0.38 | 13.4% | 20 | 0.65 | 5.4% | 11.1% | 0.65 | 8.9% | 2 | 0.21 | 5.2% | 61.9% | 0.21 | 12.4% |
| 1 | 0.17 | 18.2% | 69.2% | 0.17 | 59.3% | 9 | 0.15 | 9.8% | 304.1% | 0.15 | 134% | 3 | 0.21 | 8.2% | 64.6% | 0.21 | 10.1% |
| 9 | 0.11 | 15.2% | 117.9% | 0.11 | 72.5% | 19 | 0.11 | 7.8% | 23.8% | 0.11 | 19.8% | 11 | 0.18 | 6.6% | 106.1% | 0.18 | 27.0% |
| 3 | 1.71 | 5.4% | 11.4% | 1.71 | 5.8% | 1 | 0.07 | 14.0% | 41.1% | 0.07 | 34.7% | 1 | 0.15 | 9.1% | 96.5% | 0.15 | 16.9% |
| 12 | 4.69 | 2.6% | 7.7% | 4.69 | 5.4% | 11 | 0.04 | 11.2% | 32.9% | 0.04 | 23.1% | 9 | 0.10 | 8.0% | 40.1% | 0.10 | 28.1% |
{5}
The inter-lot reproducibility was evaluated with fifteen (15) samples in triplicates on three (3) lots of Plexus EBV kit. The results of the study are summarized in the table below:
| Plexus VCA IgG | | | Plexus EBNA IgG | | | Plexus EA-D IgG | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean | %CV | ID | Mean | %CV | ID | Mean | %CV |
| 5 | 6.00 | 3.2% | 12 | 7.35 | 3.6% | 12 | 4.51 | 5.3% |
| 19 | 5.88 | 2.3% | 15 | 4.76 | 4.6% | 4 | 2.86 | 3.3% |
| 20 | 5.57 | 2.4% | 8 | 4.01 | 4.5% | 16 | 1.84 | 2.0% |
| 12 | 5.08 | 3.7% | 4 | 2.62 | 4.8% | 15 | 1.36 | 9.0% |
| 6 | 4.66 | 3.3% | 18 | 2.39 | 6.7% | 19 | 1.00 | 4.6% |
| 4 | 3.61 | 1.3% | 5 | 1.66 | 3.5% | 8 | 0.85 | 7.2% |
| 18 | 2.08 | 3.7% | 6 | 1.44 | 5.8% | 5 | 0.68 | 4.8% |
| 2 | 2.01 | 2.4% | 2 | 0.93 | 5.0% | 20 | 0.59 | 2.3% |
| 16 | 1.77 | 4.8% | 3 | 0.74 | 2.3% | 18 | 0.30 | 8.6% |
| 3 | 1.72 | 4.0% | 20 | 0.58 | 3.5% | 6 | 0.29 | 4.2% |
| 11 | 1.00 | 3.8% | 16 | 0.36 | 3.2% | 2 | 0.21 | 8.3% |
| 8 | 0.75 | 2.8% | 19 | 0.10 | 7.7% | 3 | 0.20 | 5.8% |
| 15 | 0.31 | 7.8% | 1 | 0.06 | 5.7% | 11 | 0.18 | 14.4% |
| 1 | 0.11 | 7.7% | 11 | 0.04 | 8.1% | 1 | 0.15 | 10.8% |
| 9 | 0.02 | 0.0% | 9 | 0.02 | 30.0% | 9 | 0.11 | 6.4% |
b. Linearity/assay reportable range:
Not Applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Not Applicable
d. Detection limit:
Not Applicable
e. Analytical specificity:
The sponsor evaluated the potential cross-reactivity of the assay as follows: samples positive for similar disease states and potentially cross-reactive factors as determined by an FDA cleared device were tested with the Plexus EBV kit for each of the three (VCA, EA-D and EBNA-1) IgG analytes. Additionally 41 samples negative for EBV by an FDA cleared device and positive for some of possible cross reacting agents were included. The panel consisted of $(\mathrm{ANA} = 28, \mathrm{CMV} = 31, \mathrm{HSV-1} = 29, \mathrm{HSV-2} = 13, \mathrm{HSV-6} = 4, \mathrm{Rubeola Virus} = 1, \mathrm{Mumps} = 1, \mathrm{Rubella Virus} = 39, \mathrm{Toxoplasma gondii} = 19,$ and $\mathrm{VZA} = 35)$ . Because of the high prevalence of EBV IgG antibodies in the normal population, the test samples were also evaluated on commercially available ELISA. The majority of all samples that did elicit a positive result were also confirmed positive by the corresponding commercially available
{6}
ELISA, indicating reactivity to EBV IgG antibodies rather than cross reactivity with a potentially interfering factor. ANA showed possible cross reactivity with the EBNA-1 analyte, and HSV2 showed possible cross reactivity with the VCA analyte.
Potential cross reactivity with *E. coli* and *Pichia pastoris* which are the recombinant vector for the EAD and EBNA-1 antigens used in the assay was not assessed, due to difficulties in obtaining the appropriate samples.
| Cross-Reactivity | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Cross Reactives | N | Method | EBV VCA IgG | | | EBV EBNA IgG | | | EBV EAD IgG | | |
| | | | Positive | Equivocal | Negative | Positive | Equivocal | Negative | Positive | Equivocal | Negative |
| ANA | 28 | Plexus | 27 | 0 | 1 | 28 | 0 | 0 | 8 | 0 | 20 |
| | | ELISA | 28 | 0 | 0 | 28 | 0 | 0 | 5 | 5 | 18 |
| | | Discrepants | 1 | | | 0 | | | 6^{5} | | |
| Cytomegalovirus (CMV) | 31 | Plexus | 24 | 1 | 6 | 24 | 0 | 7 | 4 | 0 | 27 |
| | | ELISA | 26 | 0 | 5 | 25 | 0 | 6 | 3 | 1 | 27 |
| | | Discrepants | 2^{1} | | | 1 | | | 2^{1} | | |
| HSV-1 | 29 | Plexus | 27 | 1 | 1 | 26 | 0 | 2 | 3 | 1 | 25 |
| | | ELISA | 27 | 0 | 2 | 28 | 1 | 1 | 3 | 0 | 26 |
| | | Discrepants | 2^{1} | | | 2^{1} | | | 1^{1} | | |
| HSV-2 | 13 | Plexus | 13 | 0 | 0 | 12 | 0 | 1 | 2 | 3 | 8 |
| | | ELISA | 13 | 0 | 0 | 13 | 0 | 0 | 2 | 1 | 10 |
| | | Discrepants | 0 | | | 1 | | | 4^{4} | | |
| HHV-6 | 4 | Plexus | 0 | 0 | 4 | 0 | 0 | 4 | 0 | 0 | 4 |
| | | ELISA | 0 | 0 | 4 | 0 | 0 | 4 | 0 | 0 | 4 |
| | | Discrepants | 0 | | | 0 | | | 0 | | |
| Measles (Rubeola) | 1 | Plexus | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 |
| | | ELISA | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 |
| | | Discrepants | 0 | | | 0 | | | 0 | | |
| Mumps | 1 | Plexus | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 |
| | | ELISA | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 |
| | | Discrepants | 0 | | | 0 | | | 0 | | |
| Rubella Virus | 39 | Plexus | 26 | 0 | 13 | 25 | 1 | 13 | 4 | 1 | 34 |
| | | ELISA | 26 | 1 | 12 | 27 | 0 | 12 | 3 | 2 | 34 |
| | | Discrepants | 8^{1} | | | 2^{1} | | | 1^{1} | | |
| Toxoplasma gondii | 19 | Plexus | 17 | 0 | 2 | 18 | 0 | 1 | 1 | 4 | 14 |
| | | ELISA | 19 | 0 | 0 | 18 | 0 | 1 | 1 | 2 | 16 |
| | | Discrepants | 2 | | | 0 | | | 4^{4} | | |
| Varicella-zoster (VZV) | 35 | Plexus | 26 | 0 | 9 | 22 | 0 | 13 | 4 | 1 | 30 |
| | | ELISA | 24 | 0 | 11 | 22 | 0 | 13 | 4 | 2 | 29 |
| | | Discrepants | 4 | | | 0 | | | 4^{3} | | |
¹One Equivocal Sample; ²Two Equivocal Samples; ³Three Equivocal Samples; ⁴Four Equivocal Samples; ⁵Five Equivocal Samples
{7}
The sponsor assessed the test's performance with potentially interfering substances by spiking four samples with two levels of four different potentially interfering substances. Four samples, two positive and two negative for EBV IgG antibodies by Plexus EBV IgG were used in the study. Baseline levels for triglycerides, albumin, bilirubin, and hemoglobin were established for each sample. The remaining serum was spiked with purchased interfering substances at levels that exceeded the expected human range. The spiked samples were tested again in the assay to determine if the elevated levels of interfering substances affected the assay. It was thus concluded that no interference was observed for any of the interfering substances in either the positive or negative sample.
f. Assay cut-off:
Establishment of the cutoff values for the EBV IgG and IgM Plexus was performed using 585 patient serum samples submitted for EBV testing. These samples were first tested on the predicate devices (Diamedix ELISA for VCA IgG, VCA IgM, EA, EBNA, and the Accutest for infectious mononucleosis). Each sample was classified as positive, negative or equivocal for each of these assays. The serum samples were then run on the EBV IgG and IgM Plexus assay. Comparisons were made for each analyte with its respective predicate test (excluding equivocal samples on the predicated device) on a Receiver Operating Characteristics (ROC) analysis. Based on the ROC analysis graphs a cutoff value was obtained.
| Plexus™ EBV IgG Multi-Analyte Diagnostics (MP0500G) | | | | | |
| --- | --- | --- | --- | --- | --- |
| Antigen | Positive With predicate Device | % Positive Agreement (sensitivity) | Negative With predicate Device | % Negative Agreement (specificity) | Cutoff score |
| EBNA | 359 | 96.1%
345/359 | 219 | 100%
219/219 | 0.301 |
| EA | 130 | 82.3%
107/130 | 409 | 94.6%
387/409 | 0.874 |
| VCA IgG | 417 | 95.7%
399/417 | 150 | 68%
102/150 | 0.600 |
2. Comparison studies:
a. Method comparison with reference method:
Performance of the Plexus EBNA-1 IgG and Plexus EA-D IgG analytes was compared to the Diamedix EBNA-1 and EA-D ELISA tests. The performance of the Plexus EBV VCA IgG analyte was compared to a consensus comparator consisting of the predicate device the Diamedix VCA IgG ELISA and 2 other devices; Athena Multi-Lyte EBV IgG Test System and Focus
{8}
EBV-VCA Antibody (IgG) IFA. For each sample, a consensus based algorithm (2/3) was used to determine the predicate result for comparison with the Plexus VCA IgG result. The studies were conducted at three United States testing sites: a hospital laboratory located in Northeast (n = 350), a pediatric hospital laboratory located in the Mid-West (n=249), and Focus (n=124) with serum samples in which EBV tests were ordered. The sera were sequentially submitted to the laboratory, archived, and masked. Samples were collected at three sites and include both prospective (n = 723) and retrospective (n = 150) specimens all tested by the Mid-West investigator. Retrospective samples were pre-selected based on EBV VCA IgM positive results from a FDA cleared device. Results are summarized per analyte, broken by the serological classification.
Serological status was determined by the use of the Diamedix ELISA assays for the EBV analytes EBNA-1 IgG, VCA IgG, EA-D IgG and VCA IgM and a commercially available heterophile rapid test for the heterophile antibody, and following a generally accepted classification chart.
EBV VCA IgG vs. Consensus Predicate: Comparison by Serological Status (Prospective Population Samples N = 723)
| EBV VCA IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Consensus Predicate | | Plexus | | | |
| Serostatus by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 57 | 57 | 0 | 0 | 100%(57/57), 95% CI:93.7-100% |
| | | Negative | 1 | 0 | 0 | 1 | 33.3%(1/3, 95% CI:6.1-79.2% |
| | | No consensus^{1} | 2 | 2 | 0 | 0 | NA |
| | Late Acute | Positive | 72 | 70 | 1 | 1 | 97.2%(70/72), 95% CI:90.4-99.2% |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
| Recovering | Positive | 1 | 1 | 0 | 0 | 100%(1/1), 95% CI:20.7-100% | |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
| Previous Infection | Positive | 292 | 282 | 1 | 9 | 96.6%(282/292), 95% CI:93.8-98.1% | |
| | | Negative | 6 | 1 | 0 | 5 | 83.3%(5/6), 95% CI:43.6-97% |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
{9}
10
| EBV VCA IgG Results | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | Consensus Predicate | | Plexus | | | |
| Serostatus by Predicates | | n | Positive | Equivocal | Negative | % Agreement |
| No Infection | Positive | 9 | 3 | 0 | 6 | 30.0%(3/10), 95% CI:10.8-60.3% |
| | Negative | 217 | 13 | 1 | 203 | 93.5%(203/217), 95% CI:89.5-96.1% |
| | No consensus¹ | 1 | 0 | 0 | 1 | NA |
| Indeterminate | Positive | 50 | 49 | 0 | 1 | 98%(49/50), 95% CI:89.5-99.6% |
| | Negative | 15 | 0 | 0 | 15 | 100%(15/15),95% CI:79.6-100% |
| | No consensus | 0 | 0 | 0 | 0 | NA |
¹ No consensus results: the combination of three predicates could not yield a conclusive result for these samples – a 2/3 majority could not be obtained.
EBV EBNA-1 vs. Predicate: Comparison by Serological Status (Prospective Population Samples N = 723)
| EBV EBNA-1 IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 0 | 0 | 0 | 0 | NA |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 60 | 0 | 0 | 60 | 100%(60/60), 95% CI:94-100% |
| | Late Acute | Positive | 69 | 65 | 0 | 4 | 94.2%(65/69), 95% CI:86-97.7% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 3 | 0 | 0 | 3 | 100%(3/3), 95% CI:43.8-100% |
| Recovering | Positive | 0 | 0 | 0 | 0 | NA | |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 1 | 0 | 0 | 1 | 100%(1/1), 95% CI:20.7-100% |
| Previous Infection | Positive | 284 | 266 | 2 | 16 | 93.7%(266/284), 95% CI:90.2-96% | |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 14 | 1 | 0 | 13 | 92.9%(13/14), 95% CI:68.5-98.7% |
{10}
EBV EBNA-1 IgG Results
| | Predicate ELISA | | Plexus | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Serological Status by Predicates | | n | Positive | Equivocal | Negative | % Agreement |
| No Infection | Positive | 0 | 0 | 0 | 0 | NA |
| | Equivocal | 0 | 0 | 0 | 0 | NA |
| | Negative | 227 | 1 | 0 | 226 | 99.6%(226/227), 95% CI:97.5-99.9% |
| Indeterminate | Positive | 36 | 29 | 0 | 7 | 76.3%(29/38), 95% CI:60.8-87% |
| | Equivocal | 2 | 0 | 0 | 2 | 0%(0/2), 95% CI:0-65.8% |
| | Negative | 27 | 0 | 0 | 27 | 100%(27/27), 95% CI:87.5-100% |
EBV EA-D vs. Predicate: Comparison by Serological Status (Prospective Population Samples N = 723)
| EA-D IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 43 | 40 | 0 | 3 | 93%(40/43), 95% CI:81.4-97.6% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 17 | 4 | 0 | 13 | 76.5%(13/17), 95% CI:52.7-90.4% |
| | Late Acute | Positive | 51 | 41 | 1 | 9 | 80.4%(41/51), 95% CI:67.5-89% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 21 | 2 | 2 | 17 | 81%(17/21), 95% CI:60-92.3% |
| Recovering | Positive | 1 | 0 | 0 | 1 | 0%(0/1), 95% CI:0-79.3% | |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| Previous Infection | Positive | 0 | 0 | 0 | 0 | NA | |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 298 | 11 | 1 | 286 | 96%(286/298), 95% CI:93.1-97.7% |
{11}
12
| EA-D IgG Results | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | n | Positive | Equivocal | Negative | % Agreement |
| No Infection | Positive | 0 | 0 | 0 | 0 | NA |
| | Equivocal | 0 | 0 | 0 | 0 | NA |
| | Negative | 227 | 1 | 3 | 223 | 98.2%(223/227), 95% CI:95.6-99.3% |
| Indeterminate | Positive | 12 | 7 | 0 | 5 | 26.9%(7/26), 95% CI:13.7-46.1% |
| | Equivocal | 30 | 14 | 2 | 14 | 6.3%(2/32), 95% CI:1.7-20.1% |
| | Negative | 23 | 0 | 0 | 23 | 62.2%(23/37), 95% CI:46.1-75.9% |
EBV VCA IgG vs. Consensus Predicate: Comparison by Serological Status (Retrospective Presumed Acute Population Samples N = 150)
| EBV VCA IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Consensus Predicate | | Plexus | | | |
| Serostatus by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 106 | 99 | 1 | 6 | 93.4%(99/106), 95% CI:87-96.8% |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
| | Late Acute | Positive | 8 | 8 | 0 | 0 | 100%(8/8), 95% CI:67.6-100% |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
| No Infection | Positive | 1 | 1 | 0 | 0 | 100%(1/1), 95% CI:20.7-100% | |
| | | Negative | 1 | 1 | 0 | 0 | 0%(0/1), 95% CI:0-79.3% |
| | | No consensus | 0 | 0 | 0 | 0 | NA |
| Indeterminate | Positive | 33 | 31 | 0 | 2 | 93.9%(31/33), 95% CI:80.4-98.3% | |
| | | Negative | 0 | 0 | 0 | 0 | NA |
| | | No consensus¹ | 1 | 1 | 0 | 0 | NA |
¹ No consensus results: the combination of three predicates could not yield a conclusive result for these samples – a 2/3 majority could not be obtained.
{12}
EBV EBNA-1 vs. Predicate: Comparison by Serological Status (Retrospective Presumed Acute Population Samples N = 150)
| EBV EBNA-1 IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 0 | 0 | 0 | 0 | NA |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 106 | 1 | 0 | 105 | 99.1%(105/106), 95% CI:94.8-99.8% |
| | Late Acute | Positive | 4 | 0 | 0 | 4 | 0%(0/4), 95% CI:0-49% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 4 | 0 | 0 | 4 | 100%(4/4), 95% CI:51-100% |
| No Infection | Positive | 0 | 0 | 0 | 0 | NA | |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 2 | 0 | 0 | 2 | 100%(2/2), 95% CI:34.2-100% |
| Indeterminate | Positive | 4 | 0 | 0 | 4 | 0%(0/8), 95% CI:0-32.4% | |
| | | Equivocal | 4 | 0 | 0 | 4 | 0%(0/4), 95% CI:0-49.0% |
| | | Negative | 26 | 0 | 0 | 26 | 100%(26/26), 95% CI:87.1-100% |
EBV EA-D vs. Predicate: Comparison by Serological Status (Retrospective Presumed Acute Population Samples N = 150)
| EBV EA-D IgG Results | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | | n | Positive | Equivocal | Negative | % Agreement |
| Acute | Primary Acute | Positive | 61 | 57 | 1 | 3 | 93.4%(57/61), 95% CI:84.3-97.4% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 45 | 7 | 3 | 35 | 77.8%(35/45), 95% CI:63.7-87.5% |
| | Late Acute | Positive | 3 | 3 | 0 | 0 | 100%(3/3), 95% CI:43.8-100% |
| | | Equivocal | 0 | 0 | 0 | 0 | NA |
| | | Negative | 5 | 1 | 0 | 4 | 80%(4/5), 95% CI:37.6-96.4% |
{13}
| EBV EA-D IgG Results | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | Predicate ELISA | | Plexus | | | |
| Serological Status by Predicates | | n | Positive | Equivocal | Negative | % Agreement |
| No Infection | Positive | 0 | 0 | 0 | 0 | NA |
| | Equivocal | 0 | 0 | 0 | 0 | NA |
| | Negative | 2 | 0 | 0 | 2 | 100%(2/2), 95% CI:34.2-100% |
| Indeterminate | Positive | 10 | 8 | 0 | 2 | 66.7%(8/12), 95% CI:39.1-86.2% |
| | Equivocal | 14 | 12 | 0 | 2 | 0%(0/14), 95% CI:0-21.5% |
| | Negative | 10 | 0 | 1 | 9 | 40.9%(9/22), 95% CI:23.3-61.3% |
b. Matrix comparison:
Not Applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not Applicable
b. Clinical specificity:
Not Applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not Applicable
4. Clinical cut-off:
See 1 f
5. Expected values/Reference range:
Expected values for the EBV IgG kit are presented by age and gender in the following tables for (723) serum samples from patients for which EBV tests were ordered.
For all analytes, index values of $< 0.90$ are negative, $\geq 0.90$ to $\leq 1.10$ are equivocal and $>1.10$ are positives.
{14}
Expected Values Plexus VCA IgG:
| Age | Gender | Positive | | Equivocal | | Negative | | Total |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | n | % | n | % | n | % | |
| <5 | F | 8 | 53.3 | 0 | 0.0 | 7 | 46.7 | 15 |
| <5 | M | 17 | 47.2 | 0 | 0.0 | 19 | 52.8 | 36 |
| 5-12 | F | 43 | 43.0 | 1 | 1.0 | 56 | 56.0 | 100 |
| 5-12 | M | 46 | 48.4 | 0 | 0.0 | 49 | 51.6 | 95 |
| 13-20 | F | 118 | 70.7 | 0 | 0.0 | 49 | 29.3 | 167 |
| 13-20 | M | 82 | 63.1 | 1 | 0.8 | 47 | 36.2 | 130 |
| 21-30 | F | 37 | 97.4 | 0 | 0.0 | 1 | 2.6 | 38 |
| 21-30 | M | 15 | 83.3 | 0 | 0.0 | 3 | 16.7 | 18 |
| 31-40 | F | 14 | 87.5 | 0 | 0.0 | 2 | 12.5 | 16 |
| 31-40 | M | 13 | 92.9 | 0 | 0.0 | 1 | 7.1 | 14 |
| 41-50 | F | 19 | 100 | 0 | 0.0 | 0 | 0.0 | 19 |
| 41-50 | M | 12 | 92.3 | 0 | 0.0 | 1 | 7.7 | 13 |
| 51-60 | F | 15 | 93.8 | 0 | 0.0 | 1 | 6.3 | 16 |
| 51-60 | M | 8 | 72.7 | 0 | 0.0 | 3 | 27.3 | 11 |
| 61-70 | F | 9 | 100 | 0 | 0.0 | 0 | 0.0 | 9 |
| 61-70 | M | 8 | 80.0 | 0 | 0.0 | 2 | 20.0 | 10 |
| >70 | F | 7 | 100 | 0 | 0.0 | 0 | 0.0 | 7 |
| >70 | M | 7 | 77.8 | 1 | 11.1 | 1 | 11.1 | 9 |
| Total | | 478 | 66.1 | 3 | 0.4 | 242 | 33.5 | 723 |
Expected Values Plexus EBNA-1 IgG:
| | | Positive | | Equivocal | | Negative | | Total |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Age | Gender | n | % | n | % | n | % | |
| <5 | F | 3 | 20.0 | 0 | 0.0 | 12 | 80.0 | 15 |
| <5 | M | 12 | 33.3 | 0 | 0.0 | 24 | 66.7 | 36 |
| 5-12 | F | 28 | 28.0 | 0 | 0.0 | 72 | 72.0 | 100 |
| 5-12 | M | 36 | 37.9 | 1 | 1.1 | 58 | 61.1 | 95 |
| 13-20 | F | 85 | 50.9 | 0 | 0.0 | 82 | 49.1 | 167 |
| 13-20 | M | 52 | 40.0 | 0 | 0.0 | 78 | 60.0 | 130 |
| 21-30 | F | 27 | 71.1 | 0 | 0.0 | 11 | 28.9 | 38 |
| 21-30 | M | 10 | 55.6 | 0 | 0.0 | 8 | 44.4 | 18 |
| 31-40 | F | 15 | 93.8 | 0 | 0.0 | 1 | 6.3 | 16 |
{15}
Expected Values Plexus EA-D IgG:
| | | Positive | | Equivocal | | Negative | | Total |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Age | Gender | n | % | n | % | n | % | |
| <5 | F | 1 | 6.7 | 1 | 6.7 | 13 | 86.7 | 15 |
| <5 | M | 4 | 11.1 | 0 | 0.0 | 32 | 88.9 | 36 |
| 5-12 | F | 11 | 11.0 | 0 | 0.0 | 89 | 89.0 | 100 |
| 5-12 | M | 9 | 9.5 | 1 | 1.1 | 85 | 89.5 | 95 |
| 13-20 | F | 27 | 16.2 | 2 | 1.2 | 138 | 82.6 | 167 |
| 13-20 | M | 25 | 19.2 | 2 | 1.5 | 103 | 79.2 | 130 |
| 21-30 | F | 9 | 23.7 | 0 | 0.0 | 29 | 76.3 | 38 |
| 21-30 | M | 5 | 27.8 | 0 | 0.0 | 13 | 72.2 | 18 |
| 31-40 | F | 5 | 31.3 | 0 | 0.0 | 11 | 68.8 | 16 |
| 31-40 | M | 2 | 14.3 | 0 | 0.0 | 12 | 85.7 | 14 |
| 41-50 | F | 5 | 26.3 | 1 | 5.3 | 13 | 68.4 | 19 |
| 41-50 | M | 1 | 7.7 | 1 | 7.7 | 11 | 84.6 | 13 |
| 51-60 | F | 3 | 18.8 | 0 | 0.0 | 13 | 81.3 | 16 |
| 51-60 | M | 3 | 27.3 | 1 | 9.1 | 7 | 63.6 | 11 |
| 61-70 | F | 4 | 44.4 | 0 | 0.0 | 5 | 55.6 | 9 |
| 61-70 | M | 3 | 30.0 | 0 | 0.0 | 7 | 70.0 | 10 |
| >70 | F | 3 | 42.9 | 0 | 0.0 | 4 | 57.1 | 7 |
| >70 | M | 0 | 0.0 | 0 | 0.0 | 9 | 100.0 | 9 |
| Total | | 120 | 16.6% | 9 | 1.2% | 594 | 82.2% | 723 |
{16}
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
17
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.