The Cozart® EIA Amphetamines Oral Fluid Microplate Kit is intended for use in clinical and forensic laboratories when used in conjunction with the Cozart® RapiScan Oral Fluid collection system. Using this collection system it provides qualitative screening results for amphetamines in human oral fluid at a cutoff concentration of 15ng/ml. This is equal to 45ng/ml in neat oral fluid as the collection system involves a 1:3 dilution of the sample. This assay is for professional use only and provides only a preliminary analytical test result. Clinical consideration and professional judgement must be applied to any drug of abuse test result, particularly in evaluating a preliminary positive result. In order to obtain a more confirmed analytical result a more specific alternative chemical method is needed. Gas Chromatography/Mass Spectrometry (GCMS) is the preferred confirmatory method.
Device Story
The Cozart® EIA Amphetamines Oral Fluid Microplate Kit is a laboratory-based competitive ELISA for detecting amphetamines in human oral fluid. Input consists of oral fluid samples collected via the Cozart® RapiScan system (1:3 dilution). The assay utilizes a microtitre plate coated with antibody and a Horse Radish Peroxidase enzyme conjugate. The reaction is measured spectrophotometrically at 450nm. The device is operated by laboratory professionals in clinical or forensic settings. Results are qualitative; positive findings require confirmation by GC/MS. The device aids in identifying potential amphetamine presence, supporting clinical or forensic decision-making.
Clinical Evidence
Bench testing only. Method comparison study of 163 oral fluid samples compared to GC/MS confirmation. Results: 67 samples screened positive (62 confirmed positive, 5 false positives); 96 samples screened negative (94 confirmed negative, 2 false negatives). Overall agreement with GC/MS was 96%. Precision studies (within-assay, within-day, between-assay, between-day) showed CVs ranging from 2.7% to 12.4%. Specificity testing evaluated 20 unrelated substances (no cross-reactivity) and 11 related compounds (cross-reactivity observed for MDA, MAMP, MBDB, MDMA, MDEA, Fenfluramine, Tyramine).
Technological Characteristics
Competitive ELISA; microtitre plate coated with antibody; Horse Radish Peroxidase enzyme conjugate; substrate/stop solutions; 450nm spectrophotometric detection. Calibrators: 0, 2, 15, 50ng/mL. Manual assay. Standards: BS EN ISO 9001:2000; EN 46001:1996.
Indications for Use
Indicated for qualitative screening of amphetamines in human oral fluid in clinical and forensic laboratory settings. Professional use only; provides preliminary analytical results requiring confirmation by GC/MS.
Regulatory Classification
Identification
An amphetamine test system is a device intended to measure amphetamine, a central nervous system stimulating drug, in plasma and urine. Measurements obtained by this device are used in the diagnosis and treatment of amphetamine use or overdose and in monitoring levels of amphetamine to ensure appropriate therapy.
Special Controls
*Classification.* Class II (special controls). An amphetamine 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}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
DEVICE ONLY TEMPLATE
A. 510(k) Number: K033743
B. Purpose for Submission:
Premarket Notification 510(k) of intention to manufacture and market the Cozart® EIA Amphetamines Oral Fluid Microplate Kit.
C. Analyte: Amphetamine
D. Type of Test: Qualitative competitive enzyme immunoassay for the detection of amphetamines in human oral fluid.
E. Applicant: Cozart Bioscience, Ltd.
F. Proprietary and Established Names:
Cozart® EIA Amphetamines Oral Fluid Microplate Kit
G. Regulatory Information:
1. Regulation section: 21CFR §862.3100 Amphetamine test system
2. Classification: Class II
3. Product Code: DKZ
4. Panel: Toxicology (91)
H. Intended Use:
1. Intended use(s):
The Cozart® EIA Amphetamines Oral Fluid Microplate Kit is intended for use in clinical and forensic laboratories when used in conjunction with the Cozart® RapiScan Oral Fluid collection system. Using this collection system it provides qualitative screening results for amphetamines in human oral fluid at a cutoff concentration of 15ng/mL. This is equal to 45ng/mL in neat oral fluid as the collection system involves a 1:3 dilution of the sample.
2. Indication(s) for use:
The Cozart® EIA Amphetamines Oral Fluid Microplate Kit is intended for use in clinical and forensic laboratories when used in conjunction with the Cozart® RapiScan Oral Fluid collection system. Using this collection system it provides qualitative screening
{1}
Page 2 of 9
results for amphetamines in human oral fluid at a cutoff concentration of 15ng/mL. This is equal to 45ng/mL in neat oral fluid as the collection system involves a 1:3 dilution of the sample.
3. Special condition for use statement(s):
This assay is for professional use only and provides only a preliminary analytical result. Clinical consideration and professional judgement must be applied to any drug of abuse test result, particularly in evaluating a preliminary positive result. In order to obtain a more confirmed analytical result a more specific alternative chemical method is needed. Gas Chromatography/ Mass Spectrophotometry (GC/MS) is the preferred confirmatory method.
4. Special instrument Requirements:
Automated microtitre plate reader with a 450nm filter. Automated microtitre plate washing machine, manual microtiter plate washer or 350μL eight-channel pipette for dispensing diluted wash buffer.
I. Device Description:
The Cozart® EIA Amphetamine Oral Fluid Microplate Kit is supplied with the following reagents –
- a microtitre plate coated with antibody
- enzyme conjugate reagent
- wash buffer
- substrate solution
- stop solution
- four calibrators (0, 2, 15, and 50 ng/mL Amphetamine in synthetic oral fluid matrix)
Materials required but not provided –
- positive and negative controls
- automated microtitre plate reader with a 450nm filter
- precision pipettes with disposable tips.
- automated microtitre plate washing machine
- manual microtitre plate washer or 350μL eight-channel pipette for dispensing diluted wash buffer
- a timer for timing 30 minute intervals
- a clean measuring cylinder for dilution of wash buffer concentrate
- distilled or deionized water
J. Substantial Equivalence Information:
1. Predicate device name(s):
Amphetamine-Specific Intercept™ MICRO-PLATE EIA
{2}
Page 3 of 9
2. Predicate K number(s): K992918
3. Comparison with predicate:
| Parameter | Cozart® EIA Amphetamine Oral Fluid Microplate Kit | Amphetamine-Specific Intercept™ MICRO-PLATE EIA |
| --- | --- | --- |
| Intended Use | Qualitative test for amphetamines in human oral fluid with a 45ng/mL cutoff. Recommended confirmation of positive results by GC/MS. | Qualitative test for amphetamines in human oral fluid with a 100ng/mL cutoff. Recommended confirmation of positive results by GC/MS. |
| Target Population | Clinical and forensic samples. | Clinical samples |
| Design | Competitive ELISA | Competitive ELISA |
| Enzyme | Horse Radish Peroxidase | Horse Radish Peroxidase |
| Results | Read spectrophotometrically at 450nm. | Read spectrophotometrically at 450nm. |
| Calibrators | 0, 2, 15, 50ng/mL | 0, 100ng/mL |
| Matrix | Human Oral Fluid | Human Oral Fluid |
| Controls | None supplied but Cozart recommends using external controls. | 50, 200 ng/mL |
| Method Comparison | 163 samples were tested, 67 screened positive for amphetamines, of which 62 were confirmed positive by GC/MS. 96 samples screened negative for amphetamines and 94 were confirmed negative by GC/MS. 96% Agreement as compared to GC/MS. | 89% Agreement as compared to GC/MS. |
| Precision | CV (%) of 2.7 – 12.4% | CV (%) of 3.5 – 7.9% |
| Sensitivity | 1.2 ng/mL | Unknown |
| Specificity | 20 potential interferents tested – none cross-reacted. | 47 potential interferents tested – none cross-reacted. |
K. Standard/Guidance Document Referenced (if applicable):
Cut-Off validation Study was conducted with cutoff concentration of $\pm 50\%$ of the value. Interference screening to identify exogenous and endogenous compounds was done in accordance with the NCCLS EP7-A.
{3}
Page 4 of 9
L. Test Principle: The Cozart® EIA Amphetamine Oral Fluid Microplate Kit is a competitive enzyme immunoassay for the detection of amphetamines in human oral fluid. The wells of the microtitre strips are coated with anti-Amphetamine antibody. During the first incubation, the horseradish peroxidase (HRP) labelled amphetamine derivative competes with the free amphetamine in the patients sample for the anti-Amphetamine antibody binding sites on the microtitre strips. The wells are washed to remove any excess enzyme material prior to addition of the TMB substrate solution. Addition of the stop solution terminates the reaction and absorbances are read spectrophotometrically at 450nm.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Four calibrators (0, 2, 15, and 50ng/mL) and three samples (0, 7.7 and 22.5ng/mL) were tested in duplicate every day for twenty days. The samples were a negative, a negative sample fortified with amphetamine at 50% below the cutoff and a negative sample fortified with amphetamine at 50% above the cutoff. The within assay, within day, between assay, between day and total precision for the absorbance readings is displayed below.
## Inter-Assay Precision
| Sample | Between Assay | | |
| --- | --- | --- | --- |
| | Mean | SD | CV% |
| Cal 1 | 2.287 | 0.140 | 6.11 |
| Cal 2 | 1.406 | 0.099 | 7.02 |
| Cal 3 | 0.848 | 0.069 | 8.11 |
| Cal 4 | 0.575 | 0.063 | 10.91 |
| Sample 1 | 2.252 | 0.159 | 7.05 |
| Sample 2 | 1.090 | 0.104 | 9.55 |
| Sample 3 | 0.771 | 0.075 | 9.73 |
## Inter-Assay Precision
| Sample | Between Day | | |
| --- | --- | --- | --- |
| | Mean | SD | CV% |
| Cal 1 | 2.287 | 0.132 | 5.79 |
| Cal 2 | 1.406 | 0.092 | 6.54 |
| Cal 3 | 0.848 | 0.066 | 7.84 |
| Cal 4 | 0.575 | 0.061 | 10.59 |
| Sample 1 | 2.252 | 0.153 | 6.78 |
| Sample 2 | 1.090 | 0.094 | 8.66 |
| Sample 3 | 0.771 | 0.073 | 9.41 |
{4}
Page 5 of 9
# Intra-Assay Precision
| Sample | Within Assay | | |
| --- | --- | --- | --- |
| | Mean | SD | CV% |
| Cal 1 | 2.320 | 0.06 | 2.74 |
| Cal 2 | 1.427 | 0.041 | 2.96 |
| Cal 3 | 0.861 | 0.029 | 3.35 |
| Cal 4 | 0.586 | 0.036 | 7.11 |
| Low | 2.286 | 0.063 | 2.85 |
| Medium | 1.109 | 0.042 | 3.62 |
| High | 0.784 | 0.03 | 3.94 |
# Intra-Assay Precision
| Sample | Within Day | | |
| --- | --- | --- | --- |
| | Mean | SD | CV% |
| Cal 1 | 2.350 | 0.076 | 3.38 |
| Cal 2 | 1.446 | 0.057 | 4.14 |
| Cal 3 | 0.872 | 0.033 | 3.98 |
| Cal 4 | 0.593 | 0.036 | 6.97 |
| Low | 2.315 | 0.077 | 3.47 |
| Medium | 1.122 | 0.065 | 5.81 |
| High | 0.794 | 0.036 | 4.75 |
# Total Precision
| Sample | Within Assay | | |
| --- | --- | --- | --- |
| | Mean | SD | CV% |
| Cal 1 | 2.287 | 0.154 | 6.73 |
| Cal 2 | 1.406 | 0.110 | 7.82 |
| Cal 3 | 0.848 | 0.075 | 8.84 |
| Cal 4 | 0.575 | 0.071 | 12.35 |
| Low | 2.252 | 0.173 | 7.68 |
| Medium | 1.090 | 0.118 | 10.83 |
| High | 0.771 | 0.081 | 10.54 |
b. Linearity/assay reportable range:
Not applicable. This test is for qualitative determinations.
c. Traceability (controls, calibrators, or method):
Each of the four cocaine calibrators supplied with the Cozart EIA Amphetamines Oral Fluid Microplate Kit were confirmed by GC/MS, the results are displayed below.
{5}
Page 6 of 9
| Calibrator Value (ng/mL) | GC/MS Cocaine Concentration (ng/mL) |
| --- | --- |
| 0 | 0 |
| 2 | 1.67 |
| 15 | 14.67 |
| 50 | 50.33 |
The sponsor will make available to the user a calibrator (control) protocol through Cozart Technical Services. Information for technical assistance is provided in the package insert.
d. Detection limit:
The sensitivity was calculated by testing the 0 calibrator twenty times in a single assay. A calibration curve was plotted with the four calibrators. The mean absorbance of the 20 zeros minus two standard deviations was calculated. The sensitivity was calculated by reading this absorbance value off the calibration curve. The sensitivity of the Cozart EIA Amphetamines Oral Fluid Microplate EIA is 1.2ng/mL.
e. Analytical specificity:
Twenty potentially interfering unrelated substances were tested for cross reactivity in the Cozart Amphetamine Oral Fluid Kit and none were found to cross react. Eleven related compounds were tested and seven showed a level of cross reactivity. The substances were prepared in a negative oral fluid sample prior to testing in the assay. A calibration curve was plotted using the four calibrators to estimate the concentration of each sample.
{6}
Page 7 of 9
| Compound | ng/mL Tested | Apparent Amphetamine ng/mL | % Cross Reactivity |
| --- | --- | --- | --- |
| MDA | 5 | 10.8 | 216 |
| | 10 | 18.8 | 188 |
| MAMP | 1,000 | 9.1 | 0.91 |
| | 5,000 | 86.6 | 1.73 |
| MBDB | 5,000 | 5.2 | 0.10 |
| | 10,000 | 19.9 | 0.20 |
| MDMA | 1,000 | 10.0 | 1.00 |
| | 5,000 | 90.0 | 1.80 |
| MDEA | 5,000 | 7.7 | 0.15 |
| | 10,000 | 22.3 | 0.22 |
| Fenfluramine | 100,000 | 6.2 | 0.01 |
| Tyramine | 1,000 | 3.1 | 0.31 |
| | 5,000 | 42.9 | 0.86 |
| (+) Ephedrine | 10,000 | 0.9 | 0.009 |
| | 100,000 | 26.4 | 0.026 |
| (-) Ephedrine | 100,000 | 2.8 | 0.003 |
| (+) Pseudo Ephedrine | 100,000 | 10.3 | 0.010 |
| (-) Pseudo Ephedrine | 100,000 | <2 | <0.002 |
| | | | |
| Morphine | 100,000 | <2 | <0.002 |
| Temazepam | 100,000 | <2 | <0.002 |
| Cocaine | 100,000 | <2 | <0.002 |
| Chloroquine | 100,000 | <2 | <0.002 |
| Diazepam | 100,000 | <2 | <0.002 |
| Amitriptyline HCL | 100,000 | <2 | <0.002 |
| Dextromethorphan | 100,000 | <2 | <0.002 |
| Ranitidine | 100,000 | 6.6 | 0.007 |
| Ascorbic acid | 100,000 | <2 | <0.002 |
| DL-Propranolol | 100,000 | <2 | <0.002 |
| Caffeine | 100,000 | <2 | <0.002 |
| Acetylsalicylic acid (Aspirin) | 100,000 | <2 | <0.002 |
| Acetaminophen (Paracetamol) | 100,000 | <2 | <0.002 |
| Quinalbarbitone | 100,000 | <2 | <0.002 |
| Methylphenidate | 100,000 | <2 | <0.002 |
| Buprenorphine | 10,000 | <2 | <0.002 |
| Phenobarbital | 100,000 | <2 | <0.002 |
| Nicotine | 100,000 | <2 | <0.002 |
| LSD | 100,000 | <2 | <0.002 |
| Cotinine | 100,000 | <2 | <0.002 |
{7}
# f. Assay cut-off:
Testing samples at the cutoff concentration, $50\%$ above and $50\%$ below was carried out to validate the cutoff concentration. The $50\mathrm{ng / mL}$ calibrator was diluted with a negative oral fluid sample to 7.5, 15, and $22.5\mathrm{ng / mL}$ . Ten replicates of each concentration were tested along with the four calibrators. The mean absorbance of the ten replicates of the $15\mathrm{ng / mL}$ calibrator was used as the cutoff. The absorbances obtained for the $7.5\mathrm{ng / mL}$ calibrator were all higher than the $15\mathrm{ng / mL}$ cutoff calibrator. Similarly the absorbances obtained for the $22.5\mathrm{ng / mL}$ calibrator were all lower than the $15\mathrm{ng / mL}$ cutoff calibrator.
| Sample Concentration | 7.5ng/mL |
| --- | --- |
| Mean Absorbance | 0.857 |
| SD | 0.04 |
| CV (%) | 4.51 |
| Sample Concentration | 15ng/mL |
| --- | --- |
| Mean Absorbance | 0.723 |
| SD | 0.03 |
| CV (%) | 4.74 |
| Sample Concentration | 22.5ng/mL |
| --- | --- |
| Mean Absorbance | 0.654 |
| SD | 0.02 |
| CV (%) | 3.29 |
# 2. Comparison studies:
# a. Method comparison with predicate device:
163 samples were tested through the Cozart® EIA Amphetamine Oral Fluid Microplate Kit. 67 samples screened positive for amphetamines, these consisted of 62 samples from drug users attending drug dependency units. And 5 samples spiked at $60\mathrm{ng / mL}$ to give samples around the cutoff. 62 of the samples that screened positive for amphetamines were then confirmed positive y GC/MS. 3 of the unconfirmed positive samples were confirmed positive for MDMA at $>180\mathrm{ng / mL}$ and $149\mathrm{ng / mL}$ but negative for MDA and amphetamine and therefore classed as negative for the reason stated above. However they screened positive due to the small cross reactivity of the kit to MDMA. 96 samples screened negative and 94 were confirmed negative by GC/MS. Of the 163 samples tested 17 were between $-50\%$ cutoff and $+50\%$ cutoff.
| New Device | | GC/MS Negs | GC/MS Negs between -50% Cutoff and Cutoff | GC/MS between +50% Cutoff and Cutoff | Total GC/MS Pos | Percent Agreement with GC/MS |
| --- | --- | --- | --- | --- | --- | --- |
| Pos | 67 | 5 | 0 | 8 | 62 | 93 |
| Neg | 96 | 94 | 9 | 0 | 2 | 98 |
96% overall agreement as compared with GC/MS
{8}
Page 9 of 9
b. Matrix comparison:
Not applicable. This device is indicated only for oral fluid specimens.
3. Clinical studies:
a. Clinical sensitivity:
Not applicable. Clinical studies are not typically submitted for this device type.
b. Clinical specificity:
Not applicable. Clinical studies are not typically submitted for this device type.
c. Other clinical supportive data (when a and b are not applicable):
3. Clinical cut-off:
Analytical characterization of performance around the cut-off was demonstrated in the precision studies.
5. Expected values/Reference range:
Not applicable.
N. Conclusion:
The submitted material in this premarket notification is complete and supports a substantial equivalence decision.
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.
