K052649 · Drg Intl., Inc. · CDZ · Jan 27, 2006 · Clinical Chemistry
Device Facts
Record ID
K052649
Device Name
DRG SLV TESTOSTERONE ELISA TEST
Applicant
Drg Intl., Inc.
Product Code
CDZ · Clinical Chemistry
Decision Date
Jan 27, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1680
Device Class
Class 1
Indications for Use
An Enzyme Immunoassay for the in vitro diagnostic quantitative measurement of free active testosterone in saliva. Measurement of testosterone is used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and, in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
Device Story
The DRG Salivary Testosterone ELISA Kit is an in vitro diagnostic assay for professional use. It utilizes a competitive enzyme immunoassay principle to measure free active testosterone in human saliva samples. The device consists of a microtiter plate coated with mouse anti-testosterone antiserum, enzyme-conjugated testosterone (horseradish peroxidase), substrate solution (TMB), and stop solution. During the assay, testosterone in the patient sample competes with the enzyme-conjugated testosterone for binding sites on the plate. After incubation and washing, a substrate is added, producing a colorimetric signal measured at 450nm via a calibrated EIA reader. The intensity of the color is inversely proportional to the testosterone concentration in the sample. Healthcare providers use the quantitative output to assist in diagnosing and monitoring androgen-related conditions such as hypogonadism, puberty disorders, and virilization. The assay provides a standardized method for assessing hormonal status in clinical settings.
Clinical Evidence
Bench testing only. Performance validated via method comparison studies (n=99 and n=81) against a commercial LIA method, yielding correlation of 0.904 and R2=0.9866. Analytical sensitivity: 1.857 pg/mL (lowest detectable); functional sensitivity: 7.1 pg/mL. Specificity evaluated via cross-reactivity testing against 12 steroids; minimal cross-reactivity observed. Reproducibility (intra-assay, inter-assay, inter-lot) demonstrated with CVs generally <10%. Linearity established from 7.1 to 4500 pg/mL.
Technological Characteristics
Competitive enzyme immunoassay; microtiter plate coated with mouse monoclonal anti-testosterone antiserum; horseradish peroxidase conjugate; TMB substrate; colorimetric detection at 450nm. Requires calibrated EIA reader. Standards prepared in artificial saliva matrix; traceability to GC-MS methods. No electronic connectivity; standalone manual assay.
Indications for Use
Indicated for in vitro diagnostic quantitative measurement of free active testosterone in saliva for diagnosis and treatment of androgen-related disorders in males (hypogonadism, puberty disorders, impotence) and females (hirsutism, virilization due to tumors, polycystic ovaries, adrenogenital syndromes).
Regulatory Classification
Identification
A testosterone test system is a device intended to measure testosterone (a male sex hormone) in serum, plasma, and urine. Measurement of testosterone are used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and, in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY TEMPLATE
A. 510(k) Number:
k052649
B. Purpose for Submission:
Premarket Notification 510(k) of intention to manufacture and market the DRG Salivary Testosterone Elisa Kit.
C. Measurand:
Testosterone
D. Type of Test:
Enzyme Immunoassay
E. Applicant:
DRG International, Inc.
F. Proprietary and Established Names:
DGR Salivary Testosterone Elisa Kit
G. Regulatory Information:
1. Regulation section:
21 CFR §862.1680 Testosterone Test System
2. Classification:
Class 1 (reserved)
3. Product code:
CDZ
4. Panel:
75 (Chemistry)
{1}
2
H. Intended Use:
1. Intended use(s):
See Indications for use below.
2. Indication(s) for use:
An Enzyme Immunoassay for the *in vitro diagnostic* quantitative measurement of free active testosterone in saliva. Measurement of testosterone is used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and, in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
3. Special conditions for use statement(s):
For Professional use only. For in-vitro diagnostic use only
4. Special instrument requirements:
Calibrated EIA reader adjusted to read at 450nm.
I. Device Description:
The DRG Salivary Testosterone Elisa Kit consists of the following:
1. Microtiter plate, 8 well snap-off strips, 12 strips, coated with (mouse) anti-Testosterone antiserum.
2. Reference Standard Set, 1 ml each, 0.0; 10; 50; 100; 500; 1000; 5000 pg/ml.
3. Enzyme-Conjugate, 26 ml, Testosterone conjugated to horseradish peroxidase, ready to use.
4. Substrate Solution - TMB, 25 ml, ready to use.
5. Stop Solution, 0.5M H₂SO₄, 14 ml, ready to use.
6. Wash Solution, 30 ml, Concentrate for 1200 ml.
J. Substantial Equivalence Information:
1. Predicate device name(s):
IMMUNO BIOLOGICAL LABORATORIES, IBL Testosterone LIA
2. Predicate 510(k) number(s):
k033786
{2}
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Predicate Device | New Device |
| Device Name | IBL Testosterone LIA | DRG SLV Testosterone ELISA |
| Analyte | Free active Testosterone | Same |
| Specimen | Serum or Saliva | Saliva |
| Method | Luminescence Immunoassay | Enzyme Immunoassay |
| Test Principle | Competitive Immunoassay. Competition is between a labeled and non-labeled antigen for a fixed number of antibody binding sites. The amount of labeled analyte bound to the antibody is inversely proportional to the concentration of the analyte present in the sample. | Same |
| Detection | Luminescence detection | Colorimetric detection |
| Calculation | Quantitative determination with standard curve | Same |
| Quality Control | 2 Controls at different levels | Recommended separate external controls |
| Indications for Use | Measurements of testosterone are used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and , in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes. | Same |
| Detection Limit | 1.757 pg/mL | 1.857 pg/mL |
K. Standard/Guidance Document Referenced (if applicable):
Haeckel, R., R.F. Walker and D. Colic (1989): Reference ranges for mixed saliva collected from literature. J. Clin. Chem. Clin. Biochem. 27, 249-252
{3}
L. Test Principle:
The DRG Salivary Testosterone ELISA Kit is based on the competition principle and the microplate separation. An unknown amount of free testosterone present in the sample and a fixed amount of testosterone conjugated with horseradish peroxidase compete for the binding sites of mouse monoclonal testosterone antiserum coated onto the wells. After one-hour incubation the microplate is washed to stop the competition reaction. After addition of the substrate solution the concentration of testosterone is inversely proportional to the optical density measured.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
INTRA-ASSAY PRECISION
The intra-assay (within-run) variation of the DRG SLV Testosterone ELISA was determined by repeated measurements of four saliva samples.
| | Saliva 1 | | Saliva 2 | | Saliva 3 | | Saliva 4 | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Measurement | OD450 | Conc. pg/ml | OD450 | Conc. pg/ml | OD450 | Conc. pg/ml | OD450 | Conc. pg/ml |
| 1 | 1.789 | 2.94 | 1.665 | 13.82 | 1.438 | 44.07 | 1.539 | 6.75 |
| 2 | 1.785 | 3.22 | 1.683 | 11.99 | 1.429 | 45.58 | 1.561 | 5.19 |
| 3 | 1.816 | 1.18 | 1.700 | 10.35 | 1.430 | 45.41 | 1.542 | 9.50 |
| 4 | 1.778 | 3.73 | 1.711 | 9.32 | 1.471 | 38.76 | 1.579 | 4.95 |
| 5 | 1.791 | 2.80 | 1.654 | 14.97 | 1.462 | 40.17 | 1.540 | 9.41 |
| 6 | 1.802 | 2.05 | 1.641 | 16.37 | 1.455 | 41.29 | 1.560 | 6.50 |
| 7 | 1.789 | 2.94 | 1.690 | 11.31 | 1.472 | 38.60 | 1.538 | 9.22 |
| 8 | 1.795 | 2.52 | 1.658 | 14.55 | 1.449 | 42.26 | 1.557 | 8.50 |
| 9 | 1.769 | 4.41 | 1.647 | 15.72 | 1.431 | 45.28 | 1.562 | 5.59 |
| 10 | 1.791 | 2.80 | 1.689 | 11.40 | 1.479 | 37.52 | 1.563 | 6.67 |
| 11 | 1.785 | 3.22 | 1.662 | 14.13 | 1.438 | 44.07 | 1.574 | 8.41 |
| 12 | 1.815 | 1.24 | 1.665 | 13.82 | 1.446 | 42.75 | 1.550 | 5.11 |
| 13 | 1.786 | 3.15 | 1.691 | 11.21 | 1.471 | 38.76 | 1.156 | 8.68 |
| 14 | 1.792 | 2.73 | 1.670 | 13.30 | 1.450 | 42.10 | 1.202 | 5.92 |
| 15 | 1.775 | 3.95 | 1.667 | 13.61 | 1.435 | 44.57 | 1.159 | 7.52 |
| 16 | 1.772 | 4.18 | 1.681 | 12.19 | 1.428 | 45.74 | 1.156 | 7.18 |
| 17 | 1.771 | 4.26 | 1.668 | 13.51 | 1.440 | 43.73 | 1.144 | 5.84 |
| 18 | 1.801 | 2.12 | 1.673 | 13.00 | 1.456 | 41.13 | 1.173 | 5.92 |
| 19 | 1.810 | 1.54 | 1.682 | 12.09 | 1.467 | 39.38 | 1.161 | 7.61 |
| 20 | 1.794 | 2.59 | 1.681 | 12.19 | 1.440 | 43.73 | 1.202 | 6.67 |
| | Saliva 1 | Saliva 2 | Saliva 3 | Saliva 4 |
| --- | --- | --- | --- | --- |
| Mean (pg/ml) | 2.88 | 12.94 | 42.25 | 7.06 |
| SD | 0.946 | 1.787 | 2.655 | 1.485 |
| CV (%) | 32.87 | 13.81 | 6.28 | 21.04 |
| n = | 20 | 20 | 20 | 20 |
{4}
The functional sensitivity of the assay is $7.1~\mathrm{pg / mL}$ . This assumes that the lowest concentration having a $\mathrm{CV\%}$ of approximately $20\%$ is considered the functional sensitivity.
# INTER ASSAY PRECISION: LOT TO LOT
The inter-assay (between-run) variation was determined by triplicate measurements of five saliva samples in three different kit lots. Results reported in the table below:
| | Sample 1 | Sample 2 | Sample 3 | Sample 4 | Sample 5 |
| --- | --- | --- | --- | --- | --- |
| Mean (pg/ml) | 64.5 | 352.89 | 517.65 | 44.00 | 116.54 |
| SD (pg/ml) | 3.77 | 13.44 | 15.01 | 1.53 | 5.00 |
| CV (%) | 5.85 | 3.81 | 2.90 | 3.47 | 4.29 |
| n = | 9 | 9 | 9 | 9 | 9 |
# b. Linearity/assay reportable range:
Two saliva samples containing different amounts of analyte were serially diluted with zero standard and assayed using DRG SLV testosterone ELISA. Percentage recovery was calculated by comparing the expected and observed values for SLV testosterone.
| Sample | Dilution | OD 450 nm | Observed conc. pg/ml | Expected Conc. pg/ml | Recovery % |
| --- | --- | --- | --- | --- | --- |
| 1(spiked) | undiluted | 0.113 | >5000 | 9000 | |
| | 1:2 | 0.139 | 4410.07 | 4500.00 | 98.00 |
| | 1:4 | 0.247 | 2285.54 | 2250.00 | 101.58 |
| | 1:8 | 0.435 | 1108.65 | 1125.00 | 98.55 |
| | 1:16 | 0.670 | 582.77 | 562.50 | 103.60 |
| | 1:32 | 1.025 | 265.73 | 281.30 | 94.46 |
| | 1:64 | 1.350 | 132.78 | 140.60 | 94.44 |
| | 1:128 | 1.622 | 67.89 | 70.30 | 96.57 |
| 2 (spiked) | undiluted | 0.457 | 1033.58 | 1033.58 | |
| --- | --- | --- | --- | --- | --- |
| | 1:2 | 0.730 | 505.48 | 516.79 | 97.81 |
| | 1:4 | 1.030 | 262.95 | 258.40 | 101.76 |
| | 1:8 | 1.385 | 122.69 | 129.20 | 94.96 |
| | 1:16 | 1.660 | 60.89 | 64.60 | 94.26 |
| | 1:32 | 1.855 | 30.84 | 32.30 | 95.48 |
| | 1:64 | 1.985 | 15.46 | 16.15 | 95.73 |
| | 1:128 | 2.125 | 2.78 | 8.07 | 34.45 |
{5}
| | Sample 1 | Sample 2 |
| --- | --- | --- |
| Concentration pg/ml | 9000.00 | 1033.58 |
| Average % recovery | 98.20 | 96.70 |
| Range of from | 94.4 | 94.3 |
| % recovery to | 103.6 | 101.7 |
| Accepted from | 85% | 85% |
| recovery to | 115% | 115% |
The upper end detectability of SLV testosterone is 4410 pg/mL. These results demonstrate that the test system is performing equivalent to original.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The standards prepared for the SLV Testosterone kits are buffer based (artificial saliva matrix). The range of calibrators were prepared by appropriate dilution from the maximum standard (Smax: 5000 pg/mL). The testosterone for the standards is purchased from a commercially available source, and is weighed in to make the 5000 pg/mL.
The reference values (calibrators/controls) were established using (Gas chromatography-mass spectrophotometry) GC-MS methods, as per the guidelines for quality assurance in medical laboratories, Instand E.V. Germany (L.D. Dikkesche. Et al. 1988: De toepassing kwaliteitcontroleprogramma's voor progesterone-, cortisol-, testosterone- en oestradiolbe[alingen in serums. Tijdschr NVKC 13: 148-155).
WHO standard is not available.
The functional quality of the kit lots were tested using the Lyphochek controls from BioRad, but controls are not included in the kit. These controls are commercially available and can be purchased by the customers.
Real time stability, Accelerated stability, and Saliva sample stability were validated for this assay.
d. Detection limit:
The analytical sensitivity of SLV Testosterone ELISA was calculated from the mean minus 2SD of 20 replicate analyses of the zero standard.
| Mean | 1.718 |
| --- | --- |
| SD | 0.018 |
| 2 x SD | 0.035 |
| Mean – 2SD | 1.683 corresponds to 1.857 pg/ml |
| N | 20 |
{6}
e. Analytical specificity:
Cross reactivity was tested with the following compounds whose chemical structure could potentially cause interference with the SLV Testosterone ELISA. The specificity of the antiserum used for the ELISA was evaluated by determination of the cross-reactivity at 50% displacement of various compounds listed in the table below.
The cross-reactivity is defined as:
Concentration of testosterone at 50% B/BO x 100
Concentration of cross-reactant giving 50% B/BO
| Steroid | % Cross reaction |
| --- | --- |
| Testosterone | 100% |
| 5α-Dihydrotestosterone | 0.80% |
| Androstenedione | 0.90% |
| 11β-hydroxysterone | 3.30% |
| 17α-methyltestosterone | 0.10% |
| 19-Nortestosterone | 3.30% |
| Epitestosterone | 0.10% |
| Estradiol | 0.10% |
| Progesterone | < 0, 10% |
| Cortisol | < 0, 10% |
| Estrone | < 0, 10% |
| Danazol | < 0, 10% |
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
COMPARISON TO IBL LIA
Concentration of testosterone in 81 saliva samples collected from 40 - 65 year old men and women using DRG SLV testosterone kit. The results were compared with those obtained from IBL-LIA method.
Correlation Coefficient = 0.99328
{7}

Number of XY Pairs = 81
Pearson $r = 0.9933$
95% confidence interval = 0.9895 to 0.9957
R squared = 0.9866
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
4. Clinical cut-off:
Not applicable
{8}
9
5. Expected values/Reference range:
In order to determine the normal range of SLV Testosterone, saliva samples from 187 adult male and 188 adult female apparently healthy subjects, age 21 to 75 years, were collected in the morning and analyzed using the DRG SLV Testosterone ELISA kit. The following range was calculated from this study.
| | Men ♂ | | | Women ♀ | | |
| --- | --- | --- | --- | --- | --- | --- |
| Age Group Years | Range (5-95%) | Median | n | Range (5-95%) | Median | n |
| 21-30 | 47.2-136.2 | 92.8 | 42 | 7.9-50.4 | 20.8 | 40 |
| 31-40 | 46.8-106.8 | 73.6 | 37 | <7.0-44.8 | 17.1 | 40 |
| 41-50 | 36.5-82.7 | 58.8 | 34 | <7.0-39.4 | 18.3 | 38 |
| 51-60 | 19.2-89.0 | 44.5 | 36 | <7.0-29.8 | 19.2 | 38 |
| 61-75 | 12.2-68.6 | 38.9 | 38 | <7.0-29.3 | 16.0 | 32 |
N. Proposed Labeling:
The labeling is sufficient and it 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}
10
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.