K103673 · Techlab Inc., Corporate Research Center · MHI · Aug 18, 2011 · Microbiology
Device Facts
Record ID
K103673
Device Name
GIARDIA/ CRYPTOSPORIDIUM QUIK CHEK
Applicant
Techlab Inc., Corporate Research Center
Product Code
MHI · Microbiology
Decision Date
Aug 18, 2011
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3220
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K103673 · Aug 18, 2011
GIARDIA/ CRYPTOSPORIDIUM QUIK CHEK
Techlab Inc., Corporate Research Center
Retrospective human fecal specimens (fresh, frozen, and preserved)
Clinical performance evaluation comparing the device to Microscopy (IFA) and commercial ELISA predicate devices using retrospective patient fecal specimens.
Clinical Performance Evaluation; Retrospective clinical performance study
Patients with gastrointestinal symptoms; Sample Size: 791 (Microscopy comparison); 849 (ELISA comparison); Number of Sites: 3
Microscopy (IFA) and commercially available ELISAs
Sensitivity, specificity, and correlation/agreement
Indications for Use
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK™ test is a rapid membrane enzyme immunoassay for the simultaneous qualitative detection and differentiation of Giardia cyst antigen and Cryptosporidium oocyst antigen in a single test device. It is intended for use with human fecal specimens from patients with gastrointestinal symptoms to aid in the diagnosis of Giardia and/or Cryptosporidium gastrointestinal infection. The test results should be considered in conjunction with the patient history.
Device Story
Rapid membrane enzyme immunoassay for simultaneous qualitative detection/differentiation of Giardia cyst antigen and Cryptosporidium oocyst antigen in human fecal specimens. Device utilizes monoclonal and polyclonal antibodies immobilized on a membrane within a test cassette. Sample mixed with diluent and conjugate (polyclonal antibodies coupled to horseradish peroxidase) is added to the device; antigen-antibody-conjugate complexes migrate to test lines where they are captured. After washing and substrate addition, results are read visually by the presence of blue lines. Used in clinical laboratory settings by trained personnel. Provides rapid diagnostic aid for gastrointestinal infection; results interpreted alongside patient history to guide clinical management.
Clinical Evidence
Clinical performance evaluated at three sites (N=791) comparing to reference microscopy/IFA. Giardia sensitivity 98.9%, specificity 100%. Cryptosporidium sensitivity 100%, specificity 99.8%. Method comparison (N=849) against predicate ELISA showed 99.5% overall agreement for both analytes. Analytical sensitivity: 6000 cysts/oocysts per mL. No cross-reactivity observed with 40+ common enteric pathogens/parasites. Interference testing showed no effect from common medications or fecal components.
Technological Characteristics
Rapid membrane enzyme immunoassay. Employs mouse monoclonal antibodies against Giardia and Cryptosporidium, and anti-HRP antibodies for control. Conjugate consists of polyclonal antibodies coupled to horseradish peroxidase. Visual readout via blue line appearance. Manual test procedure with 25-30 minute incubation. No electronic components or software.
Indications for Use
Indicated for patients with gastrointestinal symptoms to aid in the diagnosis of Giardia and/or Cryptosporidium gastrointestinal infection using human fecal specimens.
Regulatory Classification
Identification
Entamoeba histolytica serological reagents are devices that consist of antigens and antisera used in serological tests to identify antibodies to Entamoeba histolytica in serum. Additionally, some of these reagents consist of antisera conjugated with a fluorescent dye (immunofluorescent reagents) used to identify Entamoeba histolytica directly from clinical specimens. The identification aids in the diagnosis of amebiasis caused by the microscopic protozoan parasite Entamoeba histolytica and provides epidemiological information on diseases caused by this parasite. The parasite may invade the skin, liver, intestines, lungs, and diaphragm, causing disease conditions such as indolent ulcers, an amebic hepatitis, amebic dysentery, and pulmonary lesions.
Special Controls
*Classification.* Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 866.9.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
K103673
B. Purpose for Submission:
To obtain a substantial equivalence determination for the detection of Giardia and Cryptosporidium antigens in human stool
C. Measurand:
Giardia and Cryptosporidium antigens
D. Type of Test:
Qualitative membrane enzyme immunoassay
E. Applicant:
TechLab® Inc.
F. Proprietary and Established Names:
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK™ test
G. Regulatory Information:
1. Regulation section:
21 CFR Part 866.3220 Entamoeba histolytica Serological Reagents
2. Classification:
II
3. Product code:
MHJ - Cryptosporidium spp.
MHI - Giardia spp.
{1}
4. Panel:
83, Microbiology
H. Intended Use:
1. Intended use(s):
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test is a rapid membrane enzyme immunoassay for the simultaneous qualitative detection and differentiation of Giardia cyst antigen and Cryptosporidium oocyst antigen in a single test device. It is intended for use with human fecal specimens from patients with gastrointestinal symptoms to aid in the diagnosis of Giardia and/or Cryptosporidium gastrointestinal infection. As with other Giardia and/or Cryptosporidium tests, results should be considered in conjunction with the patient history.
FOR IN VITRO DIAGNOSTIC USE.
2. Indication(s) for use:
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test is a rapid membrane enzyme immunoassay for the simultaneous qualitative detection and differentiation of Giardia cyst antigen and Cryptosporidium oocyst antigen in a single test device. It is intended for use with human fecal specimens from patients with gastrointestinal symptoms to aid in the diagnosis of Giardia and/or Cryptosporidium gastrointestinal infection. As with other Giardia and/or Cryptosporidium tests, results should be considered in conjunction with the patient history.
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
None
I. Device Description:
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK™ test device contains 25 pouches, each containing a membrane filter pad. Each device has a Reaction Window with three vertical lines of immobilized antibodies. The Giardia test line ("Giar") contains mouse monoclonal antibodies against Giardia. The Crypto test line ("Cryp") contains mouse monoclonal antibodies against Cryptosporidium. The control line ("C") is a dotted line that contains anti-horseradish peroxidase (HRP) antibodies. The
2
{2}
Conjugate consists of polyclonal antibodies coupled to horseradish peroxidase. The antigen-antibody-conjugate complexes migrate through a filter pad to a membrane where they are captured by the immobilized Giardia and/or Cryptosporidium-specific antibodies in the test lines. After addition of substrate and proper incubation, the reaction is examined visually for the appearance of a vertical blue line on either side of the Reaction Window. A blue line indicates a positive test. A positive "control" reaction, indicated by a vertical dotted blue line under the "C" portion of the Reaction Window, confirms that the test is working properly and the results are valid.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
GIARDIA II
CRYPTOSPORIDIUM II
2. Predicate 510(k) number(s):
K033274
K052932
3. Comparison with predicate:
| Similarities | | | |
| --- | --- | --- | --- |
| Item | Device | Predicate 1 | Predicate 2 |
| Intended Use | Detection of Giardia cyst and Cryptosporidium oocyst antigen | Detection of Giardia cyst antigen | Detection of Cryptosporidium oocyst antigen |
| Technology | Enzyme Immunoassay | Enzyme Immunoassay | Enzyme Immunoassay |
| Antibody Format | Monoclonal/Polyclonal | Monoclonal/Polyclonal | Monoclonal/Polyclonal |
| Specimen Types | Human Fecal Specimens- fresh, frozen, or preserved in 10% Formalin or SAF | Human Fecal Specimens- fresh, frozen, or preserved in 10% Formalin or SAF | Human Fecal Specimens- fresh, frozen, or preserved in 10% Formalin or SAF |
{3}
| Differences | | | |
| --- | --- | --- | --- |
| Item | Device | Predicate 1 | Predicate 2 |
| Intended Use | Detection and differentiation of *Giardia* cyst antigen and *Cryptosporidium* oocyst antigen | Detection *Giardia* cyst antigen only | Detection *Cryptosporidium* oocyst antigen only |
| Technology | Membrane Enzyme Immunoassay | Enzyme Immunoassay – Microassay Plate ELISA | Enzyme Immunoassay – Microassay Plate ELISA |
| Amount of Specimen required | 25 μL – fresh
100 μL - preserved | 100 μL – fresh or preserved | 100 μL – fresh or preserved |
| Incubation time | 15 minutes | 1 hour | 1 hour |
| Time to Result | 30 minutes | 1 hour 45 minutes | 1 hour 45 minutes |
## K. Standard/Guidance Document Referenced (if applicable):
Not applicable
## L. Test Principle:
The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK™ test is a membrane enzyme immunoassay that uses monoclonal and polyclonal antibodies to cell-surface antigens of the organisms. The polyclonal antibodies are coupled to horseradish peroxidase which are contained in the diluent. Specific mouse monoclonal antibodies against Giardia and Cryptosporidium antigens are bound on different location of the membrane. A fecal specimen is added to the diluent and transferred to the sample well and incubated. During the incubation, cyst and/or oocyst antigens in the sample bind the antibody-peroxidase conjugates. The antigen-antibody-conjugate complexes migrate through a filter pad to a membrane where they are captured by the immobilized Giardia and/or Cryptosporidium-specific antibodies in the test lines.
## M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A total of 22 fecal specimens were pre-characterized by commercially available predicate devices. The samples included six Giardia-positive specimens (three mid-range positives), six Cryptosporidium-positive
{4}
specimens (three low positives), and four Giardia/Cryptosporidium-positive specimens (two of which were low Giardia-positives and two of which were low Cryptosporidium-positives), and six specimens negative for both parasites. All specimens were coded to prevent their identification during testing. Testing was performed at three sites. The samples were tested, twice a day over a 5-day period by multiple technicians at each site using two different kit lots. A positive and negative control was run with each panel of the masked samples. The results were consistent among the different locations, and exhibited a correlation of 100%.
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Not applicable.
d. Detection limit:
The analytical sensitivity of the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test was determined by spiking various dilutions of purified Giardia cysts or Cryptosporidium oocysts into negative human stool. The cyst/oocyst preparations were quantified using the reference assay of IFA microscopy. Test results determined the limit of detection to be 6000 Giardia cysts per mL (133 cysts/test) and 6000 Cryptosporidium oocysts/mL (133 cysts/test).
e. Analytical specificity:
Cross- Reactivity Study
No cross reactions were seen with the following organisms: Aeromonas hydrophila, Bacillus cereus, Bacillus subtilis, Bacteroides fragilis, Campylobacter coli, Campylobacter fetus, Campylobacter jejuni, Candida albicans, Clostridium bifermentans, Clostridium difficile (strain 630), Enterococcus faecalis, Escherichia coli, Escherichia coli 0157:H7, Escherichia coli ETEC (enterotoxic), Escherichia coli EPEC (enteropathogenic), Escherichia coli EIEC (enteroinvasive), Klebsiella pneumoniae, Salmonella typhimurium, Shigella dysenteriae, Shigella flexneri, Shigella sonnei, Staphylococcus aureus, Staphylococcus aureus (Cowan's), Staphylococcus epidermidis, Vibrio parahaemolyticus, Yersinia enterocolitica
Human Adenovirus 1 and 3, Adenovirus, Type 2, 5, 40 and 41, Human Coxsackievirus B2, B3, and B4, Coxsackievirus B5, Human Coronavirus, Echovirus 11, 18, 33, Human Echovirus 9, Human paraechovirus 1 (Echovirus 22), Enterovirus 68, 69, Human Enterovirus 70, 71, Human rotavirus
5
{5}
Additionally, the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK™ test was tested using fecal specimens documented to be positive for other parasites by microscopy; *Ascaris lumbricoides* eggs, *Dientamoeba fragilis*, *Entamoeba hartmanni*, *Blastocystis hominis*, *Diphyllobothrium latum* eggs, *Entamoeba histolytica/E. dispar*, *Chilomastix mesnili*, *Endolimax nana*, Hookworm eggs, *Cyclospora cayetanensis*, *Entamoeba coli*, *Iodamoeba butschlii*, and *Trichuris trichiura* eggs. No cross-reactivity was seen with the following organisms for either the *Giardia*-portion or the *Cryptosporidium*-portion of the test.
Cross-reactivity to Astrovirus and Caliciviruses has not been evaluated.
The results obtained from the cross reactive study is acceptable.
## Interference Study
The following substances had no effect on positive or negative test results analyzed at the concentrations indicated: Hog gastric mucin (3.5% w/v), Human blood (40% v/v), Barium sulfate (5% w/v), Imodium (5% v/v), Kaopectate (5% v/v), Pepto-Bismol (5% v/v), Steric/Palmitic Acid (40% w/v), Metronidazole (0.25% w/v), Vancomycin (0.25% w/v).
The results obtained from the interference study is acceptable.
### f. Assay cut-off:
Not Applicable
### 2. Comparison studies:
#### a. Method comparison with predicate device:
The performance of the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test was evaluated at three geographically diverse sites. Two sites compared the performance to commercially available ELISA (separate devices for *Giardia* and *Cryptosporidium*). A total of 849 specimens were evaluated and included 349 fresh, 322 frozen, 36 preserved (formalin) and 142 preserved (SAF).
Two hundred and fifteen (215) specimens were positive for *Giardia* by ELISA. The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test exhibited a 99.1% agreement for *Giardia* positive specimens, a 99.7% agreement for *Giardia* negative specimens, with an overall agreement of 99.5%.
One hundred thirty one (131) specimens were positive for *Cryptosporidium* by ELISA. The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test exhibited a 99.2% agreement for *Cryptosporidium* positive specimens, 99.6% agreement for *Cryptosporidium* negative specimens, and an overall
6
{6}
agreement of 99.5%.
The results obtained from the method comparison study are acceptable.
b. Matrix comparison:
Not Applicable
3. Clinical studies:
a. Clinical Sensitivity:
The performance of the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test was evaluated at three geographically diverse sites. Two sites compared performance to the reference microscopy/immunofluorescence (IFA). A total of 791 were evaluated and included 220 fresh, 140 frozen, 216 preserved (formalin) and 215 preserved (SAF).
One hundred eighty three (183) specimens were positive for Giardia by IFA. The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test exhibited a sensitivity of 98.9%, a specificity of 100%, and an overall correlation of 99.7% with microscopy.
One hundred forty (140) specimens were positive for Cryptosporidium by IFA. The GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test exhibited a sensitivity of 100%, a specificity of 99.8%, and an overall correlation of 99.9% with Microscopy.
The results obtained from the clinical study appear to be acceptable.
Combined Results - Clinical Performance Comparing the Giardia Line of the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK Test to Microscopy - IFA
| N = 791 | Microscopy - IFA
Giardia positive | Microscopy - IFA
Giardia negative |
| --- | --- | --- |
| GIARDIA/CRYPTOSPORIDIUM
QUIK CHEK
Giardia Line Positive | 181 | 0 |
| GIARDIA/CRYPTOSPORIDIUM
QUIK CHEK
Giardia Line Negative | 2 | 608 |
| | | 95% Confidence Limits |
| --- | --- | --- |
| Sensitivity | 98.9% | 95.7 – 99.8% |
| Specificity | 100% | 99.2 – 100% |
| Correlation | 99.7% | 99.7 – 99.7% |
{7}
8
# Combined Results - Clinical Performance Comparing the Cryptosporidium Line of the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK Test to Microscopy – IFA
| N = 791 | Microscopy - IFA Crypto. positive | Microscopy - IFA Crypto. negative |
| --- | --- | --- |
| GIARDIA/CRYPTOSPORIDIUM QUIK CHEK
Cryptosporidium Line Positive | 140 | 1 |
| GIARDIA/CRYPTOSPORIDIUM QUIK CHEK
Cryptosporidium Line Negative | 0 | 650 |
| | | 95% Confidence Limits |
| --- | --- | --- |
| Sensitivity | 100% | 96.7 – 100% |
| Specificity | 99.8% | 99.0 – 100% |
| Correlation | 99.9% | 100 – 100% |
b. Clinical specificity:
See section M.3.a
c. Other clinical supportive data (when a. and b. are not applicable):
Not Applicable
4. Clinical cut-off:
Not Applicable
5. Expected values/Reference range:
Normal healthy individuals should not be infected with Giardia or Cryptosporidium and should test negative in the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test. A positive test result in the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test indicates that the person is shedding detectable amounts of Giardia and/or Cryptosporidium antigen. The incidence of Giardia and Cryptosporidium infection varies significantly between populations and geographic regions. Children in daycare settings have exhibited higher rates of infection with Giardia than the normal population. In addition, homosexual men have shown higher rates of infection. In general, laboratory-confirmed incidence of cryptosporidiosis in developed countries ranges from 1 to 2% overall with a higher incidence in children.
Prospective studies to evaluate the GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test were conducted at an Asian hospital specializing in diarrheal diseases. The studies included 129 freshly collected fecal specimens. A positive test result in the
{8}
GIARDIA/CRYPTOSPORIDIUM QUIK CHEK test was obtained in 22.5% for Giardia and in 5.4% for Cryptosporidium antigen.
N. Proposed Labeling:
The labeling is sufficient and 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.
9
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.