Portrait Toxigenic C. difficile Assay, a prescription device under 21 CFR Part 801.109 that is indicated for the detection of toxigenic Clostridium difficile in human fecal samples collected from patients suspected of having Clostridium difficile infection (CDI). The test utilizes automated blocked primer enabled helicase-dependent amplification (bpHDA) to detect toxin gene sequences associated with toxin producing C. difficile. The Portrait Toxigenic C. difficile Assay is intended as an aid in the diagnosis of CDI.
Device Story
Bench-top, fully automated in vitro diagnostic system; includes Portrait Analyzer, control laptop, and single-use test cartridges. Input: human fecal sample. Process: automated sample extraction (cell lysing), blocked primer mediated thermophilic helicase-dependent amplification (bpHDA), and chip-based detection. Integrated sample processing control (SPC) ensures adequate extraction/amplification. Output: interpreted detection of tcdB (toxin B gene) sequences. Used in clinical laboratories; operated by trained personnel. Results aid clinicians in diagnosing CDI; informs antibiotic treatment decisions. Benefits: rapid (approx. 85 min) automated detection of toxigenic C. difficile.
Clinical Evidence
Multi-site clinical evaluation (4 US institutions, N=540 specimens) compared Portrait Assay to reference culture/cell cytotoxicity (TBC/CCNA). Results: 98.0% sensitivity (95% CI: 92.4-99.6%), 90.9% specificity (95% CI: 87.7-93.3%), 71.4% PPV, 99.5% NPV. Analytical studies confirmed LoD using multiple toxinotypes and demonstrated no cross-reactivity with 40+ bacterial, viral, fungal, and parasitic organisms. Reproducibility and precision studies showed high agreement across sites and operators.
Technological Characteristics
Automated bench-top analyzer; uses single-use cartridges for sample prep, bpHDA amplification, and chip-based detection. Integrated thermal PID module and optical sense module. Software-controlled hardware drivers. No sterility requirements for analyzer. Connectivity via control laptop PC.
Indications for Use
Indicated for detection of toxigenic Clostridium difficile in human fecal samples from patients suspected of having Clostridium difficile infection (CDI).
Regulatory Classification
Identification
A microorganism differentiation and identification device is a device intended for medical purposes that consists of one or more components, such as differential culture media, biochemical reagents, and paper discs or paper strips impregnated with test reagents, that are usually contained in individual compartments and used to differentiate and identify selected microorganisms. The device aids in the diagnosis of disease.
Submission Summary (Full Text)
{0}------------------------------------------------
## EVALUATION OF AUTOMATIC CLASS III DESIGNATION (DE NOVO) FOR PORTRAIT TOXIGENIC C. DIFFICILE ASSAY
### REGULATORY INFORMATION
FDA identifies this generic type of device as:
A Clostridium difficile toxin gene amplification assay is a device that consists of reagents for the amplification and detection of target sequences in Clostridium difficile toxin genes in fecal specimens from patients suspected of having Clostridium difficile infection (CDI). The detection of clostridial toxin genes, in conjunction with other laboratory tests, aids in the clinical laboratory diagnosis of CDI caused by Clostridium difficile.
NEW REGULATION NUMBER: 21 CFR 866.3130
CLASSIFICATION: II
PRODUCT CODE: OZN
## BACKGROUND
DEVICE NAME: PORTRAIT TOXIGENIC C. DIFFICILE ASSAY
510(K): K113358
DATE OF 510(K) NSE DECISION: FEBRUARY 3, 2012
DATE OF DE NOVO PETITION: MARCH 2, 2012
PETITIONER CONTACT: GREAT BASIN SCIENTIFIC, INC. – MR LARRY REA
PETITIONER'S RECOMMENDED CLASSIFICATION: II
## PETITIONER'S RECOMMENDED CONTROLS:
- · Class II Special Controls Guidance Document: Toxin Gene Amplification Assays for the detection of Clostridium difficile.
- · General controls
## INDICATIONS FOR USE
Portrait Toxigenic C. difficile Assay, a prescription device under 21 CFR Part 801.109 that is indicated for the detection of toxigenic Clostridium difficile in human fecal samples collected from patients suspected of having Clostridium difficile infection (CDI). The test utilizes automated blocked primer enabled helicase-dependent amplification (bpHDA) to detect toxin gene sequences associated with toxin producing C. difficile. The Portrait Toxigenic C. difficile Assay is intended as an aid in the diagnosis of CDI.
# LIMITATIONS
For prescription use only
{1}------------------------------------------------
## PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
## DEVICE DESCRIPTION
The Portrait Toxigenic C. difficile Assay as run on the Portrait Analyzer is a bench top fully automated in vitro diagnostics system that includes the Portrait Analyzer, control Laptop PC and single-use Portrait Toxigenic C. difficile Test Cartridges and sample preparation apparatus. The Portrait Analyzer is designed to perform automated sample extraction; blocked primer mediated thermophilic helicasedependent amplification (bpHDA); and chip-based detection with integrated data analysis in approximately 85 minutes.
The sample to be tested is inserted into the sample preparation that has been preloaded with buffer and briefly vortexed. The vortexed mixture is then loaded into the assay cartridge. The cartridge is loaded into the Portrait Analyzer which performs extraction (cell lysing), amplification, hybridization and signal formation on the detection chip. The resulting signal(s) are detected and interpreted by the automated Portrait Analyzer.
In addition to the necessary probes and primers to detect the presence of tcdB (toxin B gene) performance of the Portrait Toxigenic C. difficile Assay includes an integrated SPC to insure the adequate processing of the sample during preparation and subsequent extraction and amplification steps.
## SUMMARY OF NONCLINICAL/BENCH STUDIES
- a. The limit of detection (LoD) of the Portrait toxigenic C. difficile Assay for C. difficile was assessed and confirmed by using strains of two different toxinotypes: ATCC strain 43255 (CCUG 19126, VPI 10463), toxinotype 0 A+B+ and ATCC strain 43598 (1470), toxinotype VIII A-B+.
The following Table shows performance of the Portrait Toxigenic C. difficile assay on serial dilutions of two C. difficile strains for initial sensitivity study (CFU/test).
| <i>C. difficile</i> strains | Toxinotype | Tested Serial<br>Dilutions<br>(CFU/test) | <i>'C. difficile</i><br>detected |
|------------------------------------|----------------|------------------------------------------|----------------------------------|
| ATCC 43255 (CCUG 19126, VPI 10463) | Type 0 A+B+ | 53.5 | 1/1 |
| ATCC 43255 (CCUG 19126, VPI 10463) | Type 0 A+B+ | 5.35 | 3/4 |
| ATCC 43598 (1470) | Type VIII A-B+ | 177 | 3/3 |
| ATCC 43598 (1470) | Type VIII A-B+ | 88.5 | 3/3 |
| ATCC 43598 (1470) | Type VIII A-B+ | 17.7 | 1/3 |
The following Table shows performance of the Portrait Toxigenic C. difficile Assay on 20 replicates of two C. difficile strains for establishing LoD (CFU/test).
| <i>C. difficile</i> strains | Toxinotype | Tested<br>CFU/test | <i>C. difficile</i> detected |
|---------------------------------------|--------------------|--------------------|------------------------------|
| ATCC 43255 (CCUG 19126, VPI<br>10463) | Type 0 A+B+ | 39 | 20/20 |
| ATCC 43598 (1470) | Type VIII A-<br>B+ | 39 | 20/20 |
{2}------------------------------------------------
- b. In addition to the 2 strains used to determine the assay LOD, 44 additional strains of Toxigenic C. difficile were tested in replicates of 3 at concentrations just above the LOD (48 CFU/test), All strains were correctly identified as positive (including four NAP1/B1/027 strains: 2004013, 2004118, 2009292, and ATCC BAA-1805) by the Portrait Toxigenic C. difficile Assay. Toxinotypes and strains tested: Type 0 Strains: 2004111, 2004205, 2004206, 2005022, 2005283, 2006017, 2007070, 2007302, 2008222, 2009078, 2009087, 2009141, Type 0, A+B+: ATCC 9689(90556-M6S), Type A-B+: CCUG 37782 , Type A+B+: ATCC 17857 (870), ATCC43594 (1253), ATCC43594 (W1194), ATCC 43596 (545), ATCC43599 (2022), ATCC 43600 (2149), ATCC 51695 (BDMS 18 AN), ATCC 700792 (14797-2), ATCC BAA-1382 (630), CCUG 9004, CCUG 9018, CCUG 37766, CCUG 37770, CCUG 37774, CCUG 37776, CCUG 37783. CCUG 37784. ATCC BAA-1814. TYPE III: 2004013*, 2004118*, 2005359*, 2009292*, TYPE III A+B+: ATCC BAA-1805, TYPE V: 2005088*, 2005325*, 2007217*, 2007816*, 2007838*,TYPEVIII: 2006376*,TYPE X A-B+: CCUG 20309 (8864)
*C. difficile isolates obtained from the CDC
- c. These studies were done to assess the potential cross-reactivity of the Portrait Toxigenic C. difficile Assay with medically relevant levels of bacteria, viruses and
fungi. Bacteria and fungi were tested at concentrations > 6 x 106 CFU/mL or 1 x 105 TCID50/mL. No cross reactivity was observed. Bacterial strains tested: Aeromonas hydrophila, Bacteroides fragilis, Campylobacter coli, Campylobacter fetus, Campylobacter jejuni, Citrobacter freundii, Clostridium difficile (A-,B-), Clostridium perfringens. Clostridium sordellii. Enterobacter cloacae. Enterococcus faecalis. Enterococcus faecium van A, Escherichia coli, Escherichia coli 0157:H7, Escherichia fergusonii, Escherichia hermannii, Helicobacter pylori. Klebsiella pneumoniae, Lacotococcus lactis, Listeria monocytogenes, Peptostreptococcus anaerobius, Plesiomonas shigelloides, Proteus vulgaris, Pseudomonas aeruginosa, Pseudomonas fluorescens, Salmonella enterica, serovar Typhimurium (group B), Salmonella enterica, serovar Choleraesuis (group C1), Salmonella enterica, serovar Newport (group C2), Salmonella enterica, serovar Typhi (group D), Salmonella enterica, serovar Newington (group E), Serratia liquefaciens, Serratia marcescens, Shigella boydii, Shigella flexneri, Shigella sonnei, Staphylococcus aureus, Staphylococcus aureus Cowan 1, Staphylococcus epidermidis, Vibrio parahaemolyticus, Yersinia entercolitica. Viruses: Adenovirus Type 40, Adenovirus Type 41, Coxsackievirus Type B4, Echovirus Type 11, Rotavirus. Fungi: Candida albicans. Parasites: Cryptosporidium parvum (gDNA), Giardia intestinalis WB clone C6 gDNA.
- d. In addition to the Specificity/Cross reactivity testing, the Portrait toxigenic C. difficile Assay was tested against the same organisms that were used in the Analytical Specificity panel at the specified concentrations against two strains of toxigenic C. difficile spiked into the pooled human stool samples at two times the limit of detection (73 CFU/test). The strains tested were: ATCC 43255 (Toxinotype 0 A+B+) and ATCC 43598 (toxinotype VIII A-B+). All organisms were tested against each strain in triplicate and the Portrait results were positive for all microorganisms tested across both strains.
{3}------------------------------------------------
Interfering Substances:
The following potentially inhibiting substances were tested without showing Assay Interference:
| Substance | Active Ingredient | Substance | Active Ingredient |
|-----------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------|--------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Anusol® Plus (TUCKS) | Mineral oil, pramoxine HCl, Zinc<br>oxide | Moist Towelettes | water, aloe, glycerin, polysorbate 20,<br>disodium cocoamphodiacetate,<br>tocopheryl acetate,<br>methylchloroisothiazolinone,<br>methylisothiazolinone, quaternium-<br>15, potassium sorbate, disodium<br>EDTA, Citric acid, fragrance |
| Barium sulfate | Barium sulfate | Miconazole 2% cream (Rite Aid) | Miconazole nitrate 2% |
| Calcium carbonate (TUMS) | Calcium carbonate | Mucin (porcine) | |
| Cimetidine (Tagamet HB 200) | Cimetidine | Naproxen | Naproxen |
| Fecal fats | Stearic acid | (Prilosec OTC) | Omeprazole magnesium |
| Fleet® CB (liquid glycerin<br>laxative) | Glycerin | Pepto-Bismol® Proctor & Gamble | Bismuth subsalicylate |
| Hydrocortisone Cream<br>(Cortizone-10 max strength) | Hydrocortisone 1% | Preparation H® Wyeth | Glycerin, Phenylephrine HCl,<br>Pramoxine, White petrolatum |
| Imodium® McNeil-PPC | Loperamide HCl | Senna laxative (Rite Aid) | Sennosides |
| Kaopectate® Chattem | Bismuth subsalicylate | Vancomycin Fluka | Vancomycin |
| K-Y Jelly® McNeil-PPC | water, glycerin,<br>hydroxyethylcellulose, chlorhexidine<br>gluconate, gluconolactone,<br>methylparaben, sodium hydroxide | Vaseline Unilever | Petroleum jelly |
| Metranidazole Actavis (0.75%) | Metranidazole | Whole Blood | |
Reproducibility:
Reproducibility studies were performed in-house and at two external clinical sites which were provided with masked coded panels of low, moderate and high concentrations of C. difficile. Over the course of five days, two runs were performed with three replicates of each sample per run on each day. A minimum of two operators performed the runs at each site and two different lots of disposable Test Cartridges were used. Results of the Reproducibility studies are summarized in the table below.
{4}------------------------------------------------
### Reproducibility Study Results
| Sample Type | % agreement* | | | |
|-------------------|---------------|-------------------|-------------------|-------------|
| | In-house site | Site 1 (external) | Site 4 (external) | All Sites |
| Moderate Positive | 30/30 100% | 30/30 100% | 28/30 93.3% | 88/90 97.8% |
| Low Positive | 30/30 100% | 30/30 100% | 27/30 90.0% | 87/90 96.7% |
| High Negative | 27/30 90.0% | 29/30 96.7% | 30/30 100% | 86/90 95.6% |
* For Moderate Positive and Low Positive samples, % agreement = 'C. difficile positive' calls/total
runs. For High Negative samples, % agreement = 'C. difficile ' negative calls/total runs.
+ Site 1, Clarion Health Indianapolis, IN (Dr. Gerald Denys, PI)
‡ Site 4, Medical College of Wisconsin, Milwaukee, WI (Dr. Nate Ledeboer , PI)
A precision study was also performed in-house over the course of 12 days. Each day two runs were performed using different operators and two replicates of each sample per run.
| Sample Type | % agreement* | |
|-------------------|--------------|-------|
| Moderate Positive | 58/58 | 100% |
| Low Positive | 57/58 | 98.3% |
| High Negative | 54/58 | 93.1% |
Results of the in-house Precision Study were as follows:
* For Moderate Positive and Low Positive samples, % a greement = 'C. difficile positive' /total runs .
For High Negative samples , % agreement = 'C. difficile 'negative/total runs .
The results for the reproducibility and precision studies of the Portrait Toxigenic C. difficile Assay were within the expected percent across all three sites.
#### BIOCOMPATIBILITY/MATERIALS
N/A
### SHELF LIFE/STERILITY
The Portrait Analyzer has no sterility requirements. The Portrait Toxigenic C. difficile Assay cartridge will be tested to achieve a minimum of 26 weeks stability.
{5}------------------------------------------------
#### ANIMAL STUDIES
N/A
## ELECTROMAGNETIC COMPATIBILITY AND ELECTRICAL SAFETY
The Portrait Analyzer was tested and complied with the requirements for electromagnetic compatibility.
# MAGNETIC RESONANCE (MR) COMPATIBILITY N/A MECHANICAL SAFETY N/A SOFTWARE
| Version: Portrait Analyzer software version 1.5.23.19 | | |
|-------------------------------------------------------|-----|----|
| Level of Concern: Moderate | | |
| | Yes | No |
| Software description: | X | |
| Device Hazard Analysis: | X | |
| Software Requirements Specifications: | X | |
| Architecture Design Chart: | X | |
| Design Specifications: | X | |
| Traceability Analysis/Matrix: | X | |
| Development: | X | |
| Verification & Validation Testing: | X | |
| Revision level history: | X | |
| Unresolved anomalies: | X | |
The information provided is adequate for each of the items listed above.
Links and relationships between software requirements, specifications, testing and software related hazards are summarized in a Traceability Matrix. In summary, the Analyzer function is controlled by software communicating with hardware drivers and responding to signals from various sensors that monitor fluid, thermal and optical conditions on the assay cartridge. Performance of all individual modules (e.g. Thermal PID Module. Optical Sense Module, etc.) has undergone verification testing at the module level (Intra-Module and Regression Testing), All system related functions have undergone system level verification testing to confirm that all interrelated systems meet all performance specifications.
## SUMMARY OF CLINICAL INFORMATION
Clinical performance of the Portrait toxigenic C. difficile Assay was determined in a multi-site clinical evaluation at 4 US institutions by comparison of the Portrait Assay results to reference culture/cell cytotoxicity (TBC/CCNA) testing. A total of 540 eligible specimens were tested with the Portrait toxigenic C. difficile Assay vs.
{6}------------------------------------------------
TBC/CCNA. Relative to TBC/CCNA, Portrait toxigenic C. difficile Assay demonstrated a sensitivity of 98.0% and a specificity of 90.9% for toxigenic C. difficile when compared to the reference method. The resulting Negative predictive value NPV is 99.5 % and a Positive predictive value of 71.4%.
| | Cytotoxic bacterial | | |
|----------------|---------------------|----------|-------|
| Portrait<br>C. | Positive | Negative | Total |
| Positive | 100 | 40 | 140 |
| Negative | 2 | 398 | 400 |
| Totals | 102 | 438 | 540 |
| | | CI95 |
|-------------|---------------|------------|
| Sensitivity | 100/102 98.0% | 92.4-99.6% |
| Specificity | 398/438 90.9% | 87.7-93.3% |
| PPV | 71.4% | 63.1-78.6% |
| NPV | 99.5% | 98.0-99.9% |
CI95: confidence intervals at 95%
PPV: Positive predictive value NPV: Negative predictive value
# LABELING
Labeling has been provided which includes instructions for use and an appropriate prescription statement as required by 21 CFR 801.109(b)
# RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of the Clostridium difficile toxin gene amplification assay and the measures recommended to mitigate these risks.
| Identified Risk | Mitigation Method |
|-----------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
| A false positive test result for an<br>individual may lead to inappropriate use<br>of antibiotics for treatment | Kit includes quality control material and<br>instructions for use. |
| A false negative test result for an<br>individual may lead to a potential delay<br>in treatment | Kit includes quality control material and<br>instructions for use |
| Failure of the test to perform properly | Product labeling provides instructions<br>for use and limitations of the assay |
| Failure to properly interpret the test<br>results | Product labeling describes interpretation<br>of results |
{7}------------------------------------------------
# SPECIAL CONTROLS:
In combination with the general controls of the FD&C Act, the Portrait Toxigenic C. difficile Assay is subject to the following special controls:
- 1. The special controls for the Clostridium difficile toxin gene amplification assay are contained in the guidance document: "Class II Special Controls Guidance Document: Toxin Gene Amplification Assays for the Detection of Clostridium difficile."
## CONCLUSION
The De Novo petition for the Portrait Toxigenic C. difficile assay is granted and the device is classified under the following:
Product Code: OZN Device Type: Clostridium difficile toxin gene amplification assay Class: II Regulation: 21 CFR 866.3130
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.