Retrospective clinical samples were used to compare the performance of the modified xTAG RVP assay against the original predicate device to demonstrate substantial equivalence regarding Influenza A/H3 detection.
Retrospective clinical comparison; Follow-up/Duration: 2010-2011 influenza season; Study Period: 2010-2011
Patients suspected of respiratory tract infections; Sample Size: Not explicitly stated as a total, but includes 369 total samples based on agreement tables; Number of Sites: 14 clinical sites in the United States and Canada
Original xTAG RVP device
Positive and negative percent agreement between modified and original xTAG RVP devices
Indications for Use
The xTAG® Respiratory Viral Panel (RVP) is a qualitative nucleic acid multiplex test intended for the simultaneous detection and identification of multiple respiratory virus nucleic acids in nasopharyngeal swabs from individuals suspected of respiratory tract infections. The following virus types and subtypes are identified using RVP: Influenza B, Respiratory Syncytial Virus subtype A, Respiratory Syncytial Virus subtype B, Parainfluenza 1, Parainfluenza 2, and Parainfluenza 3 virus, Human Metapneumovirus, Rhinovirus, and Adenovirus. The detection and identification of specific viral nucleic acids from individuals exhibiting signs and symptoms of respiratory infection aids in the diagnosis of respiratory viral infection if used in conjunction with other clinical and laboratory findings. xTAG RVP can also differentiate the hemagglutinin (HA) gene of some Influenza A subtypes H1 and H3 strains. Differentiation of Influenza A HA subtypes is based on both a positive result for the Influenza A matrix gene and an accompanying positive result for the Influenza A HA subtype H1 (circulating prior to the emergence of 2009 H1N1pdm) or Influenza A HA subtype H3. This device cannot differentiate the Influenza A HA subtype 2009 H1N1pdm by design, and may not be able to differentiate potential newly emerging Influenza A HA subtypes.
Device Story
PCR-based multiplex nucleic acid test; detects viral DNA/RNA in nasopharyngeal swabs. Input: clinical specimen; process: multiplex end-point RT-PCR amplification followed by bead-based universal array sorting on Luminex 100/200 instrument; output: qualitative fluorescence-based detection of specific respiratory viruses. Used in clinical laboratories by trained personnel. Results aid diagnosis when combined with clinical/laboratory findings. Benefits: simultaneous identification of multiple respiratory pathogens to support clinical decision-making.
Clinical Evidence
Clinical comparison study using retrospective nasopharyngeal swab samples (n=14 sites, US/Canada) from 2010-2011 season. Compared modified RVP to original RVP. Primary endpoints: positive/negative percent agreement (PPA/NPA). Influenza A H3 PPA 100% (80/80), NPA 85.47% (247/289). Overall high agreement across all analytes. Sequencing used to resolve discordant results. No clinical data for novel strains; performance established for seasonal variants.
Technological Characteristics
Multiplex end-point RT-PCR assay. Uses xTAG OneStep Enzyme Mix and TaKaRa Taq Hot Start. Detection via fluorescence-based bead-based universal array on Luminex 100/200 instrument. Requires external/run controls (MS2 phage, Lambda DNA). Software: xTAG Data Analysis Software RVP (US).
Indications for Use
Indicated for individuals suspected of respiratory tract infections exhibiting signs and symptoms of respiratory infection. Used for qualitative detection and identification of viral nucleic acids in nasopharyngeal swabs. Not for use as sole basis for diagnosis or patient management.
Regulatory Classification
Identification
A respiratory viral panel multiplex nucleic acid assay is a qualitative in vitro diagnostic device intended to simultaneously detect and identify multiple viral nucleic acids extracted from human respiratory specimens or viral culture. The detection and identification of a specific viral nucleic acid from individuals exhibiting signs and symptoms of respiratory infection aids in the diagnosis of respiratory viral infection when used in conjunction with other clinical and laboratory findings. The device is intended for detection and identification of a combination of the following viruses:(1) Influenza A and Influenza B; (2) Influenza A subtype H1 and Influenza A subtype H3; (3) Respiratory Syncytial Virus subtype A and Respiratory Syncytial Virus subtype B; (4) Parainfluenza 1, Parainfluenza 2, and Parainfluenza 3 virus; (5) Human Metapneumovirus; (6) Rhinovirus; and (7) Adenovirus.
Special Controls
*Classification.* Class II (special controls). The special controls are:(1) FDA's guidance document entitled “Class II Special Controls Guidance Document: Respiratory Viral Panel Multiplex Nucleic Acid Assay;”
(2) For a device that detects and identifies Human Metapneumovirus, FDA's guidance document entitled “Class II Special Controls Guidance Document: Testing for Human Metapneumovirus (hMPV) Using Nucleic Acid Assays;” and
(3) For a device that detects and differentiates Influenza A subtype H1 and subtype H3, FDA's guidance document entitled “Class II Special Controls Guidance Document: Testing for Detection and Differentiation of Influenza A Virus Subtypes Using Multiplex Nucleic Acid Assays.” See § 866.1(e) for the availability of these guidance documents.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k112781
B. Purpose for Submission:
The xTAG® Respiratory Viral Panel (RVP) (K063765) has been modified to improve the detection of Influenza A subtype H3 strains that were in circulation in the 2010-2011 Influenza season.
C. Measurand:
Respiratory specimen virus nucleic acid (RNA or DNA) target sequences. Viruses targeted have been associated with respiratory infections in adults and/or children. Viral types and subtypes:
Influenza A, Influenza A H1, Influenza A H3, Influenza B, Respiratory Syncytial Virus Type A, Respiratory Syncytial Virus Type B, Parainfluenza virus 1, Parainfluenza virus 2, Parainfluenza virus 3, Human Metapneumovirus, Rhinovirus, Adenovirus
D. Type of Test:
A multiplexed nucleic acid test for the qualitative detection and identification of multiple respiratory pathogen nucleic acids in nasopharyngeal swabs.
E. Applicant:
Luminex Molecular Diagnostics, Inc.
F. Proprietary and Established Names
xTAG® Respiratory Viral Panel (RVP)
Common Name: Respiratory Viral Panel (RVP) Multiplex Nucleic Acid Detection Assay
G. Regulatory Information:
1. Regulation section:
21 CFR 866.3980 - Respiratory viral panel multiplex nucleic acid assay
2. Classification:
Class II
3. Product code:
OCC, OEM, OEP, NSU, JJH
4. Panel:
Microbiology (83)
H. Intended Use:
1. Intended use:
{1}
The xTAG® Respiratory Viral Panel (RVP) is a qualitative nucleic acid multiplex test intended for the simultaneous detection and identification of multiple respiratory virus nucleic acids in nasopharyngeal swabs from individuals suspected of respiratory tract infections. The following virus types and subtypes are identified using RVP: Influenza A, Influenza B, Respiratory Syncytial Virus subtype A, Respiratory Syncytial Virus subtype B, Parainfluenza 1, Parainfluenza 2, and Parainfluenza 3 virus, Human Metapneumovirus, Rhinovirus, and Adenovirus. The detection and identification of specific viral nucleic acids from individuals exhibiting signs and symptoms of respiratory infection aids in the diagnosis of respiratory viral infection if used in conjunction with other clinical and laboratory findings.
xTAG® RVP can also differentiate the hemagglutinin (HA) gene of some Influenza A subtypes H1 and H3 strains. Differentiation of Influenza A HA subtypes is based on both a positive result for the Influenza A matrix gene and an accompanying positive result for the Influenza A HA subtype H1 (circulating prior to the emergence of 2009 H1N1 pdm) or Influenza A HA subtype H3. This device cannot differentiate the Influenza A HA subtype 2009 H1N1 pdm by design, and may not be able to differentiate potential newly emerging Influenza A HA subtypes.
Positive results do not rule out bacterial infection, or co-infection with other viruses. The agent detected may not be the definite cause of disease. The use of additional laboratory testing (e.g. bacterial culture, immunofluorescence, radiography) and clinical presentation must be taken into consideration in order to obtain the final diagnosis of respiratory viral infection.
Negative results do not preclude respiratory virus infection and should not be used as the sole basis for diagnosis, treatment or other patient management decisions.
The RVP assay cannot adequately detect Adenovirus species C, or serotypes 7a and 41. It is recommended that specimens found to be negative for Adenovirus after examination using RVP be confirmed by an alternate method (e.g., FDA cleared molecular test or cell culture). The RVP primers for detection of rhinovirus cross-react with enterovirus. A rhinovirus reactive result should be confirmed by an alternate method (e.g. cell culture).
Performance characteristics for Influenza A virus were established when Influenza A HA subtype H3, subtype H1 (prior to the emergence of 2009 H1N1 pdm), and when subtype 2009 H1N1 pdm were the predominant Influenza A in circulation. When other Influenza A viruses are emerging, performance characteristics may vary.
If infections with a novel Influenza A virus is suspected based on current clinical and epidemiological screening criteria recommended by public health authorities, specimens should be collected with appropriate infection control precautions for
2
{2}
novel virulent Influenza viruses and sent to a state or local health department for testing. Viral culture should not be attempted in these cases unless a BSL 3+ facility is available to receive and culture specimens.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
Luminex® Instrument (100 IS and 200 systems) with IS or xPONENT software
I. Device Description:
See k063765
The modified xTAG RVP assays contains the primers identical to the predicate device with the addition of a new Human Influenza A subtype H3 reverse primer sequence. The concentration of the Influenza A H3 forward primers was doubled in order to balance the added reverse primer.
Materials Provided
See k063765
J. Substantial Equivalence Information:
1. Predicate device name(s):
Luminex Molecular Diagnostics, xTAG® Respiratory Viral Panel (RVP)
Common Name: Respiratory Viral Panel (RVP) Multiplex Nucleic Acid Detection Assay
2. Predicate 510(k) number(s):
See k063765
3. Comparison with predicate:
| Features | (Modified) Luminex RVP | Luminex RVP |
| --- | --- | --- |
| 510(k) | k112781 | k063765 |
| Regulation | 866.3980 | 866.3980 |
| Product Code | OCC, OEM, OEP, NSU, JJH | OCC, OEM, OEP |
| Device Class | Class II | Class II |
| Analytes Detected | Direct and differential qualitative detection of | Direct and differential qualitative detection of |
{3}
| Features | (Modified) Luminex RVP | Luminex RVP |
| --- | --- | --- |
| | influenza types A and B, RSV types A and B, Parainfluenza types 1, 2 and 3, Human Metapneumovirus Adenovirus and Rhinovirus viral nucleic acids. | influenza types A and B, RSV types A and B, Parainfluenza types 1, 2 and 3, Human Metapneumovirus, Adenovirus and Rhinovirus viral nucleic acids. |
| Technology/Detection | RT-PCR Detection: Amplified products are coupled to microspheres and detected using spectrofluorometric analysis. | RT-PCR Detection: Amplified products are coupled to microspheres and detected using spectrofluorometric analysis. |
| Specimen Types | NP swabs | NP swabs |
| Nucleic Acid Isolation | NucliSENS® miniMAG extraction Kit (bioMerieux)
NucliSENS® EasyMAG extraction Kit (bioMerieux)
QIAamp® MiniElute® Virus Spin Kit (Qiagen) | NucliSENS® miniMAG extraction Kit (bioMerieux)
NucliSENS® EasyMAG extraction Kit (bioMerieux)
QIAamp® MiniElute® Virus Spin Kit (Qiagen) |
| Instrument /Assay Platform | Luminex 100 or 200 | Luminex 100 or 200 |
| Assay Controls | Bacteriophage lambda positive control and E. coli MS2 phage Internal Control –ancillary reagents not provided | Bacteriophage lambda positive control and E. coli MS2 phage Internal Control –ancillary reagents not provided |
K. Standard/Guidance Document referenced (if applicable): See k063765
L. Test Principle: See k063765
Reporting Influenza A Results
- Report negative test results for Influenza A as "Influenza A Matrix gene target not detected, and hemagglutinin gene targets not detected". It is recommended that specimens found to be negative after examination using a respiratory viral panel nucleic acid detection assay be confirmed by an alternative method. Negative results do not preclude respiratory virus infection and should not be used as the sole basis for diagnosis, treatment or other patient management decisions."
- Report positive test results as "Influenza A positive, and (where applicable)
{4}
hemagglutinin gene target (specify hemagglutinin target detected, e.g. H1 (prior to circulation of Influenza A 2009 H1N1pdm), or H3).
NOTE: After the 2010-2011 season, when seasonal H1N1 has not been in circulation (following the emergency of 2009 H1N1pdm in 2009-2010), a positive RVP result for an Influenza A H1 should be verified using epidemiological information available through influenza surveillance programs.
- Positive for type (i.e., Influenza A), and negative or equivocal for hemagglutinin (HA) subtype. In the event that RVP positively identifies the Influenza A matrix gene target but fails to identify an HA gene target, this requires follow up. This result can be indicative of a device or user error, a known Influenza A HA subtype in circulation that the RVP can not differentiate by design (such as Influenza A HA subtype 2009 H1N1 pdm), or a novel Influenza A HA subtype. The end user should follow up with further testing and use the following algorithm:
a. To rule out device or user error, retest the sample with RVP from the extraction step with external controls for these analytes. Run sample extract in duplicate. In the case where the re-test on both replicates does not yield a positive HA subtype result and external controls are properly typed, further follow-up is required.
b. If a known Influenza A HA subtype is suspected and can not be differentiated by the assay (such as Influenza A HA subtype 2009 H1N1 pdm), the laboratory should test the sample with an alternative method to identify specific Influenza subtypes when required to definitively characterize Influenza A infections. If the sample still can not be characterized by the alternative method, that necessitates immediate notification of the appropriate local, state, or federal public health authorities to determine the necessary measures for verification of results.
- A "No Call" due to an equivocal or invalid result, should not be reported but re-tested as per recommendations. The re-test result should be considered the final RVP result for that analyte.
## M. Performance Characteristics (if/when applicable):
1. Analytical performance: See k063765
xTAG® RVP was modified to improve reactivity to influenza A/H3 strains. No differences between the modified and the original xTAG® RVP were observed in cross-reactivity and analytical reactivity studies.
a. Detection limits:
{5}
See k063765
xTAG® RVP was modified to improve reactivity to influenza A/H3 strains. The limits of detection (LoDs) of all the analytes for the modified RVP assay were identical to the original RVP assay, except for the influenza A/H3 analyte. The modified RVP demonstrated increased analytical sensitivity detecting the hemagglutinin gene of certain influenza A/H3 strains when compared to the original device.
Table 1. Summary of Comparison of Limit of Detection (LoD) for Influenza A/H3
| Strain ID Influenza A/H3 | Analyte | Modified xTAG® RVP | | Original xTAG® RVP | |
| --- | --- | --- | --- | --- | --- |
| | | TCID50/mL (at estimated LoD) | Average MFI from 22 replicates at LoD | TCID50/mL (at estimated LoD) | Average MFI from 22 replicates at LoD |
| Flu A/Victoria/3/75 | Flu A Matrix | 0.4768 | 1806.84 | 0.4768 | 1776.05 |
| | Flu A H3 | 0.4768 | 974.36 | 7.629 | 1219.64 |
| Flu A/Perth/16/2009 | Flu A Matrix | 0.1347 | 1225.16 | 0.5388* | 2796.07 |
| | Flu A H3 | 0.1347 | 706.39 | 8.621 | 1441.16 |
* This LoD level was achieved with 22 of 22 replicates making the correct influenza A matrix POS call. At 0.1347 TCID $_{50}$ /mL (one dilution level below 0.5388 TCID $_{50}$ /mL), 18 of 22 replicates made the correct influenza A matrix POS call with the original xTAG RVP. The remaining 4 replicates displayed MFI values of 226, 295, 249, and 219, just below the cut-off value of 300, thus generating "No Call" results for Influenza A matrix.
## 2. Comparison studies:
## Clinical Comparison Results
xTAG® RVP was modified to improve reactivity to influenza A/H3 strains and performance was evaluated by comparing the modified assay to the original RVP assay testing retrospective left-over clinical samples (nasopharyngeal swabs) collected from 14 clinical sites in the United States and Canada, primarily from the 2010-2011 influenza season.
All Influenza A matrix positive samples from either the original or modified xTAG® RVP were bi-directionally sequenced for influenza A subtype H3. In total, 158 influenza A positive samples by either the original or the modified xTAG® RVP were sequenced first using alternate primers outside of the kit primer binding region. All negative results with the first primer set were then re-sequenced using additional sequencing primers also outside the kit primer binding region. In addition, samples with discordant calls between the original and modified device were sequenced for the analyte(s) in question.
Positive agreement and negative agreement for each analyte were evaluated between the original and modified xTAG RVP devices (see Table 2).
{6}
Table 2. Clinical Comparison of Modified xTAG® RVP as compared to Original xTAG® RVP)
| Analyte | Positive Percent Agreement (PPA) | Confidence Interval | Negative Percent Agreement (NPA) | Confidence Interval |
| --- | --- | --- | --- | --- |
| Influenza A | 98.09% (154/157) | 94.52% - 99.60% | 99.06% (210/212) | 96.63% - 99.89% |
| Influenza A H1 | 100% (4/4) | 39.76% - 100.00%* | 100% (365/365) | 98.99% - 100.00% |
| Influenza A H3 | 100% (80/80) | 95.49% - 100.00% | 85.47% (247/289) | 80.87% - 89.32% |
| Influenza B | 100% (30/30) | 88.43% - 100.00% | 100% (339/339) | 98.92% - 100.00% |
| RSV A | 100% (23/23) | 85.18% - 100.00% | 99.71% (345/346) | 98.40% - 99.99% |
| RSV B | 96.30% (26/27) | 81.03% - 99.91% | 100% (342/342) | 98.93% - 100.00% |
| Parainfluenza 1 | 100% (6/6) | 54.07% - 100.00%* | 99.72% (362/363) | 98.47% - 99.99% |
| Parainfluenza 2 | 100% (8/8) | 63.06% - 100.00% | 99.72% (360/361) | 98.47% - 99.99% |
| Parainfluenza 3 | 100% (24/24) | 85.75% - 100.00% | 100% (345/345) | 98.94% - 100.00% |
| hMPV | 96.43% (27/28) | 81.65% - 99.91% | 100% (341/341) | 98.92% - 100.00% |
| Rhinovirus | 92.16% (47/51) | 81.12% - 97.82% | 99.69% (317/318) | 98.26% - 99.99% |
| Adenovirus | 100% (5/5) | 47.82% - 100.00%* | 100% (364/364) | 98.99% - 100.00% |
* Testing was performed on 6 or fewer positive samples for these analytes.
3. Clinical studies:
Clinical performance characteristics of the RVP Assay were established during a prospective study at three U.S. clinical laboratories and a retrospective study at one U.S. site during the 2005-2006 respiratory virus season. Please refer to previously FDA-cleared 510(k) Premarket Notification, k063765 for additional information.
4. Clinical cut-off: N/A
5. Expected values/Reference range:
See k063765
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
{7}
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
8
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.
