LYHER® Urine Marijuana (THC) Test Kit (Strip), LYHER® Urine Marijuana (THC) Test Kit (Cassette)
Applicant
Hangzhou Laihe Biotech Co., Ltd.
Product Code
LDJ · Clinical Toxicology
Decision Date
Jan 10, 2024
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.3870
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K232604 · Jan 10, 2024
LYHER® Urine Marijuana (THC) Test Kit (Strip), LYHER® Urine Marijuana (THC) Test Kit (Cassette)
Hangzhou Laihe Biotech Co., Ltd.
Unaltered clinical human urine samples
Clinical urine samples were used to evaluate the performance of the LYHER® Urine Multi-Drug Test Kit (Cup, Cassette, and Dipcard) by comparing test results against GC/MS reference methods.
Method comparison study; Retrospective method comparison using clinical samples
Human urine samples; Sample Size: Not explicitly stated as a total, but includes multiple replicates across 3 operators per device type; Number of Sites: In-house (1 site)
GC/MS (Gas Chromatography/Mass Spectrometry)
Qualitative detection of drugs of abuse (AMP, COC, MET, OPI, PCP, THC)
Indications for Use
The LYHER® Urine Multi-Drug Test Kit (Cup), LYHER® Urine Multi- Drug Test Kit (Cassette), and LYHER® Urine Multi-Drug Test Kit (Dipcard) are rapid lateral flow immunoassays for the qualitative detection of d-Amphetamine, d-Methamphetamine, Benzoylecgonine, Morphine, Phencyclidine and THC-COOH in human urine. The test cut-off concentrations and the compounds the tests are calibrated to are as follows: Test Calibrator Cut-off (ng/mL) Amphetamine (AMP) d-Amphetamine 1000 Cocaine (COC) Benzoylecgonine 300 Marijuana (THC) 11-nor-Δ9-THC-9-COOH 50 Methamphetamine (MET) d-Methamphetamine 1000 Opiates(OPI) Morphine 2000 Phencyclidine (PCP) Phencyclidine 25 The single or multi-test panels can consist of the above listed analytes in any combination, up to a maximum of 6 analytes. The drug screen tests are intended for prescription use only. The tests provide only a preliminary result. A more specific alternative chemical method should be used in order to obtain a confirmed presumptive result. Gas Chromatography/Mass Spectrometry (GC/MS), Liquid Chromatography / Mass Spectrometry (LC/MS) and their tandem mass-spectrometer versions are the preferred confirmatory methods. Careful consideration and judgment should be applied to any drugs of abuse screen test result, particularly when evaluating preliminary positive results.
Device Story
Rapid lateral flow immunochromatographic assays for qualitative detection of drugs of abuse in human urine. Device formats include cup, cassette, and dipcard. Principle of operation: competitive binding between drug-protein conjugates on membrane strips and drug metabolites in urine sample for limited antibody binding sites. Colloidal gold particles coated with mouse monoclonal antibodies and rabbit IgG used as tracers. If drug present below cutoff, burgundy T-line appears; if above, no T-line develops. C-line serves as internal control. Used in clinical settings by healthcare professionals. Provides preliminary results requiring confirmation via GC/MS or LC/MS. Benefits include rapid screening for drugs of abuse to inform clinical decision-making.
Clinical Evidence
Bench testing only. Precision/reproducibility evaluated across three labs using 50 replicates per concentration level (0-100 ng/mL). Analytical specificity/cross-reactivity tested against structural analogues and common interfering substances. Method comparison performed against LC/MS using 80+ urine samples per device type, showing high concordance. No clinical studies performed.
Technological Characteristics
Lateral flow immunochromatographic assay; competitive binding principle. Membrane strips coated with drug-protein conjugates; conjugate pad contains colloidal gold-labeled monoclonal antibodies. Form factors: cup, cassette, dipcard. Storage: 2-30°C. No electronic components or software algorithms.
Indications for Use
Indicated for qualitative detection of d-Amphetamine, d-Methamphetamine, Benzoylecgonine, Morphine, Phencyclidine, and THC-COOH in human urine for prescription use. Intended for professional use to obtain preliminary drug screening results.
Regulatory Classification
Identification
A cannabinoid test system is a device intended to measure any of the cannabinoids, hallucinogenic compounds endogenous to marihuana, in serum, plasma, saliva, and urine. Cannabinoid compounds include delta-9-tetrahydrocannabinol, cannabidiol, cannabinol, and cannabichromene. Measurements obtained by this device are used in the diagnosis and treatment of cannabinoid use or abuse and in monitoring levels of cannabinoids during clinical investigational use.
Special Controls
*Classification.* Class II (special controls). A cannabinoid test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (*e.g.,* programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K232604
B Applicant
Hangzhou Laihe Biotech Co., Ltd.
C Proprietary and Established Names
LYHER® Urine Marijuana (THC) Test Kit (Strip), LYHER® Urine Marijuana (THC) Test Kit (Cassette)
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| LDJ | Class II | 21 CFR 862.3870 - Cannabinoid Test System | TX - Clinical Toxicology |
## II Submission/Device Overview:
A Purpose for Submission:
New device
B Measurand:
11-nor-Δ9-THC-9-COOH
C Type of Test:
Qualitative, lateral flow immunoassay
## III Intended Use/Indications for Use:
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K232604 - Page 2 of 8
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The LYHER® Urine Marijuana (THC) Test Kit (Strip) and LYHER® Urine Marijuana (THC) Test Kit (Cassette) are rapid lateral flow immunoassays for the qualitative detection of THC-COOH in human urine. The test cut-off concentrations and the compounds the tests are calibrated to are as follows:
| Test | Calibrator | Cut-off (ng/mL) |
| --- | --- | --- |
| Marijuana (THC) | 11-nor-Δ9-THC-9-COOH | 50 |
The drug screen tests are intended for prescription use only.
The tests provide only a preliminary result. A more specific alternate chemical method must be used in order to obtain a confirmed analytical test result. Gas Chromatography/Mass Spectrometry (GC/MS), Liquid Chromatography/Mass Spectrometry (LC/MS) and their tandem mass-spectrometer versions are the preferred confirmatory methods. Careful consideration and judgment should be applied to any drugs of abuse screen test result, particularly when evaluating preliminary positive results.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
D Special Instrument Requirements:
None
IV Device/System Characteristics:
A Device Description:
The LYHER® Urine Marijuana (THC) Test Kit (Strip) and LYHER® Urine Marijuana (THC) Test Kit (Cassette) are immunochromatographic assays that use a lateral flow system for the qualitative detection of THC-COOH in human urine. The LYHER® Urine Marijuana (THC) Test Kit (Cassette) device consists of a cassette device, dropper, and package insert. The LYHER® Urine Marijuana (THC) Test Kit (Strip) device consists of a test strips and package insert.
B Principle of Operation:
The Urine Marijuana (THC) Test Kit is an immunoassay based on the principle of competitive binding. The metabolite of Marijuana (11-nor-Δ9-THC-9-COOH) which may be present in the
{2}
urine specimen compete against its respective drug conjugate for binding sites on their specific antibody.
During testing, a urine specimen migrates upward by capillary action. A drug, if present in the urine specimen below its cut-off concentration, will not saturate the binding sites of its specific antibody. The antibody will then react with the drug-protein conjugate and a visible colored line will show up in the test line region of the specific drug strip. The presence of drug above the cut-off concentration will saturate all the binding sites of the antibody. Therefore, the colored line will not form in the test line region.
A drug-positive urine specimen will not generate a colored line in the specific test line region of the strip because of drug competition, while a drug-negative urine specimen will generate a line in the test line region because of the absence of drug competition.
To serve as a procedural control, a colored line will always appear at the control line region, indicating that proper volume of specimen has been added and membrane wicking has occurred.
V Substantial Equivalence Information:
A Predicate Device Name(s):
BIOEASY Marijuana Test Dip Card 40, BIOEASY Marijuana Test Dip Card 20, BIOEASY Marijuana Test Strip 40, BIOEASY Marijuana Test Strip 20
B Predicate 510(k) Number(s):
K192515
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K232604 | K192515 |
| --- | --- | --- |
| Device Trade Name | LYHER® Urine Marijuana (THC) Test Kit (Strip) and LYHER® Urine Marijuana (THC) Test Kit (Cassette) | BIOEASY Marijuana Test Dip Card 40, BIOEASY Marijuana Test Dip Card 20, BIOEASY Marijuana Test Strip 40, BIOEASY Marijuana Test Strip 2 |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | For the qualitative determination of Marijuana metabolites in human urine. | Same |
| Test Principle | Lateral flow immunochromatographic assay based on | Same |
K232604 - Page 3 of 8
{3}
K232604 - Page 4 of 8
VI Standards/Guidance Documents Referenced:
None referenced.
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Precision of the product was characterized at three different labs using 3 operators for strips or cassettes. The specimens were prepared for this study using drug-free urine specimens collected from volunteers. 11-nor-Δ9-THC-9-COOH was added to the drug-free urine to the following concentrations: 100 ng/ml (+100% cut off), 87.5 ng/ml (+75% cut off), 75 ng/ml (+50% cut off), 62.5 ng/ml (+25% cut off), 50 ng/ml (cut off), 37.5 ng/ml (-25% cut off), 25 ng/ml (-50% cut off), 12.5 ng/ml (-75% cut off), 0 ng/ml (-100% cut off). Each specimen was analyzed in 50 replicates (2 runs/day, 25 days) by each of the testing personnel at each lab by using three lots of the product according to the product labeling. The test results of the specimens at the concentrations at and below -25% of the cut off obtained by all the three personnel were all negative while the test results of the specimens at the concentration at and above +25% of the cut off value were all positive, see the representative results from one operator with strips below.
| Lot | -100% cut off | -75% cut off | -50% cut off | -25% cut off | Cut off | 25% cut off | 50% Cut off | 75% cut off | 100% cut off |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Lot1:2303321 | 0+/50- | 0+/50- | 0+/50- | 0+/50- | 39+/11- | 50+/0- | 50+/0- | 50+/0- | 50+/0- |
| Lot2:2303322 | 0+/50- | 0+/50- | 0+/50- | 0+/50- | 40+/10- | 50+/0- | 50+/0- | 50+/0- | 50+/0- |
| Lot3:2303323 | 0+/50- | 0+/50- | 0+/50- | 0+/50- | 39+/11- | 50+/0- | 50+/0- | 50+/0- | 50+/0- |
2. Linearity:
Not applicable
3. Analytical Specificity/Interference:
a. Cross-reactivity
{4}
11-nor-Δ9-THC-9-COOH and structural analogues of 11-nor-Δ9-THC-9-COOH were spiked into negative urine. These urine specimens were tested by three different batches of the strips and cassettes according to the product labeling and each concentration of specimen was tested for 20 replicates. The lowest concentration that caused a positive result for each compound are listed below. There were no differences observed for stripes and cassettes.
| Compound | Concentration (ng/mL) | %Cross Reactivity |
| --- | --- | --- |
| Cannabinol | 20000 | 0.25% |
| 11-nor- Δ 8-THC-9 COOH | 30 | 167% |
| 11-nor- Δ 9 -THC-9 COOH | 50 | 100% |
| Δ 8 -THC | 15000 | 0.33% |
| Δ 9 -THC | 15000 | 0.33% |
| (±)-11-Hydroxy-Δ9-THC | 5000 | 1% |
| Cannabidiol | 20000 | 0.25% |
## b. Interferences
The potential interference from compounds chemically dissimilar to target analyte, and known endogenous agents was also determined for the LYHER® Urine Marijuana (THC) Test Kit (Strip) and LYHER® Urine Marijuana (THC) Test Kit (Cassette). The potential interfering substances (the final concentration 100 µg/ml) were added at concentrations of 100 µg/ml to drug-free urine and target drugs urine with 11-nor-Δ9-THC-9-COOH concentrations at 25% below (37.5 ng/ml) and 25% above (62.5 ng/ml) cut-off levels. These urine samples were tested using three batches of each device. Compounds that showed no interference at a concentration of 100 µg/mL are summarized in the following tables. There were no differences observed for 3 different lots of devices (both strips and cassettes).
| Substance | Substance | Substance |
| --- | --- | --- |
| Acetaminophen | Erythromycin | Penicillin-G |
| Acetone | Ethanol | Pheniramine |
| Acetylsalicylic acid | Furosemide | Phenothiazine |
| Albumin | Gabapentin | Pregablin |
| Ampicillin | Glucose | Procaine |
| Ascorbic acid | Guaiacol
glyceryl ether | Propoxyphene |
| Aspartame | Hemoglobin | Quinidine |
| Atropine | Ibuprofen | Ranitidine |
| Benzocaine | Isoproterenol | Riboflavin |
| Bilirubin | Isoproterenol | Sertraline |
| Caffeine | Ketamine | Sodium chloride |
| Chloroquine | Lidocaine | Sulindac |
| Chlorpheniramine | l-Phenylephrine | Theophylline |
| Creatine | Methadone | Tyramine |
| Dexbrompheniramine | Methylephedrine | β-Phenylethylamine |
| Dextromethorphan | Naproxen | Phencyclidine(PCP) |
| Dimenhydrinate | Niacinamide | Cocaine |
| Dimethylaminoantipyrine | Nicotine | Morphine |
| Diphenhydramine | Norephedrine | Methylamphetamine |
K232604 - Page 5 of 8
{5}
K232604 - Page 6 of 8
| Dopamine | Oxalic acid | MDMA |
| --- | --- | --- |
| EDDP | Oxycodone | Amphetamine |
| Ephedrine | Pantoprazole | |
c. Urine pH and specific gravity
To evaluate the potential effect of variances of urine specific gravity on the assays, sodium chloride was added to urine specimens containing target drugs at -/+25% of the cut off concentrations to achieve specific gravity results of 1.003, 1.006, 1.0125, 1.019, 1.021, 1.025 and 1.032. Each solution was tested on 3 lots of the stripes and cassettes. The specimens were tested in 10 replicates.
To evaluate the potential effect of variances of urine pH on the assays, 0.1mol/L HCl or 0.1mol/l NaOH was added to urine specimens containing target drugs at -/+25% of the cut off concentrations to achieve pH 3, 4, 5, 6, 7, 8, 9. Each solution was tested on 3 lots of the candidate product. The specimens were tested in 10 replicates.
The results demonstrated that pH levels of 3 to 9 and specific gravity levels of 1.006 to 1.032 do not affect any cassette and strip results.
4. Assay Reportable Range:
Not applicable.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The device is traceable commercially available standards.
6. Detection Limit:
Not applicable.
7. Assay Cut-Off:
See the precision study in section VII A1 above.
B Comparison Studies:
1. Method Comparison with LC/MS:
Method comparison studies for the LYHER® Urine Marijuana (THC) Test Kit (Strip) and LYHER® Urine Marijuana (THC) Test Kit (Cassette) were performed in-house with three operators for each device. Operators ran at least 80 (40 negative and 40 positive) unaltered urine samples. The samples were blind labeled and compared to LC/MS results. The results are presented in the tables below:
| Cassettes | Test result | Negative urine | <-50% cut off | -50% cut off~cut off | Cut off~+50%cut off | >+50%cut off |
| --- | --- | --- | --- | --- | --- | --- |
{6}
| Operator 1 | Negative | 44 | 4 | 17 | 1 | 0 |
| --- | --- | --- | --- | --- | --- | --- |
| | Positive | 0 | 0 | 0 | 24 | 15 |
| Operator 2 | Negative | 44 | 4 | 16 | 2 | 0 |
| | Positive | 0 | 0 | 1 | 23 | 15 |
| Operator 3 | Negative | 44 | 4 | 17 | 0 | 0 |
| | Positive | 0 | 0 | 0 | 25 | 15 |
Discordant Results of THC Cassettes
| Operator | Specimen No. | LC/MS results | Results of Lyher kit |
| --- | --- | --- | --- |
| Operator 1 | 202301036 | 50.5 | Neg |
| Operator 2 | 202301060 | 52.3 | Neg |
| Operator 2 | 202301069 | 49.6 | Pos |
| Operator 2 | 202301651 | 51.1 | Neg |
| Strips | Test result | Negative urine | <-50% cut off | -50% cut off~cut off | Cut off~+50%cut off | >+50%cut off |
| --- | --- | --- | --- | --- | --- | --- |
| Operator 1 | Negative | 44 | 4 | 17 | 2 | 0 |
| | Positive | 0 | 0 | 0 | 23 | 15 |
| Operator 2 | Negative | 44 | 4 | 17 | 0 | 0 |
| | Positive | 0 | 0 | 0 | 25 | 15 |
| Operator 3 | Negative | 44 | 4 | 16 | 2 | 0 |
| | Positive | 0 | 0 | 1 | 23 | 15 |
Discordant Results of THC Strips
| Operator | Specimen No. | LC/MS results | Results of Lyher kit |
| --- | --- | --- | --- |
| Operator 3 | 202301036 | 50.5 | Neg |
| Operator 3 | 202301060 | 52.3 | Neg |
| Operator 1 | 202301099 | 52.3 | Neg |
| Operator 1 | 202301651 | 51.1 | Neg |
2. Matrix Comparison:
Not applicable
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable
2. Clinical Specificity:
Not applicable
K232604 - Page 7 of 8
{7}
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable
D. Clinical Cut-Off:
Not applicable.
E. Expected Values/Reference Range:
Not applicable.
VIII. Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K232604 - Page 8 of 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.
