hCG Urine Test Strip, hCG Urine Test Cassette, hCG Urine Test Midstream
Applicant
Safecare Biotech (Hangzhou) Co., Ltd.
Product Code
LCX · Clinical Chemistry
Decision Date
Aug 13, 2020
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1155
Device Class
Class 2
Indications for Use
The hCG Urine Test Strip is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy. The hCG Urine Test Cassette is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy. The hCG Urine Test Midstream is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy.
Device Story
Lateral flow sandwich immunochromatographic assay for qualitative hCG detection in urine; early pregnancy indicator. Available in strip, cassette, and midstream formats. Device contains membrane coated with mouse monoclonal anti-βhCG antibody and pad with mouse monoclonal anti-α-hCG antibody colloidal gold conjugate; goat anti-rabbit IgG used for control. User applies urine sample (dip or midstream); results read visually within 3-5 minutes. Used by lay persons in home settings or professionals in clinical settings. Provides qualitative positive/negative result; aids in pregnancy confirmation. Benefits include rapid, accessible, and easy-to-interpret pregnancy testing.
Clinical Evidence
Bench testing only. Precision/reproducibility study (n=30 per concentration/lot) confirmed 25 mIU/mL sensitivity. Interference/cross-reactivity studies showed no interference from common substances, hCG beta-core fragments, pH (3-9), or specific gravity (1.001-1.039). Hook effect absent up to 850,000 mIU/mL. Method comparison study (n=120) showed 100% agreement with predicate. Lay-user study (n=360) demonstrated 100% agreement between lay-user results and professional-user results across all formats.
Technological Characteristics
Lateral flow sandwich immunoassay. Components: nitrocellulose membrane coated with mouse monoclonal anti-beta-hCG antibody; pad with mouse monoclonal anti-alpha-hCG antibody-colloidal gold conjugate. Control line: goat anti-rabbit IgG. Formats: strip, cassette, midstream. Qualitative visual readout. Shelf life: 30 months at 4-30°C. Traceable to WHO 5th IS.
Indications for Use
Indicated for qualitative detection of hCG in urine for early pregnancy detection in women. Over-the-counter use.
Regulatory Classification
Identification
A human chorionic gonadotropin (HCG) test system is a device intended for the early detection of pregnancy is intended to measure HCG, a placental hormone, in plasma or urine. A human chorionic goadotropin (HCG) test system is a device intended for any uses other than early detection of pregnancy (such as an aid in the diagnosis, prognosis, and management of treatment of persons with certain tumors or carcinomas) is intended to measure HCG, a placental hormone, in plasma or urine.
Predicate Devices
One Step HCG Urine Pregnancy Test (k043443)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY
I Background Information:
A. 510(k) Number
K200133
B. Applicant
Safecare Biotech (Hangzhou) Co., Ltd.
C. Proprietary and Established Names
hCG Urine Test Strip
hCG Urine Test Cassette
hCG Urine Test Midstream
D. Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| LCX | Class II | 21 CFR 862.1155 - Human Chorionic Gonadotropin (HCG) Test System | CH - Clinical Chemistry |
II Submission/Device Overview:
A. Purpose for Submission:
New device
B. Measurand:
Human Chorionic Gonadotropin (hCG)
C. Type of Test:
Qualitative chromatographic immunoassay
- Page 1 of 9
{1}
- Page 2 of 9
## III Intended Use/Indications for Use:
A. Intended Use(s):
See Indications for Use below.
B. Indication(s) for Use:
The hCG Urine Test Strip is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy.
The hCG Urine Test Cassette is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy.
The hCG Urine Test Midstream is a rapid one step assay designed for qualitative detection of human chorionic gonadotropin (hCG) in urine for early detection of pregnancy.
C. Special Conditions for Use Statement(s):
OTC - Over The Counter
D. Special Instrument Requirements:
None
## IV Device/System Characteristics:
A. Device Description:
The hCG Urine Test strip and the hCG Urine Test midstream kits consist of one test device and a package insert. The hCG Urine Test cassette kit consists of one test device, a disposable plastic dropper, and a package insert. Each test device contains mouse monoclonal anti-βhCG antibody coated membrane and a pad containing mouse monoclonal anti-α-hCG antibody colloidal gold conjugate. The control antibodies are goat anti-rabbit IgG.
B. Principle of Operation:
This device operates by detecting human chorionic gonadotropin (hCG), the hormone produced during pregnancy, in urine using a lateral flow sandwich chromatographic immunoassay. The assay of each device uses a double antibody sandwich method. During the test procedures, hCG in the urine specimen reacts with the dye conjugate (mouse anti-α-hCG antibody-colloidal gold conjugate specific to the beta subunit of hCG) and forms a complex. Because of capillary and chromatographic effects of the nitrocellulose membrane, the complex migrates along the membrane to the β-hCG antibody line (T) and remains captured in the T line. When hCG is present in the urine sample two red colored bands develops, one in the test (T) region and another in the control (C) region, indicating a positive result. If there is no hCG in the urine, there is only one red line in the control (C) region and no red band in the test (T) region, indicating a negative result. An invalid result produces either no lines on the device (i.e. no test or control lines) or one test line in the test region (i.e. a test line but no control line).
{2}
- Page 3 of 9
V Substantial Equivalence Information:
A. Predicate Device Name(s):
One Step HCG Urine Pregnancy Test
B. Predicate 510(k) Number(s):
K043443
C. Comparison with Predicate(s):
| Device & Predicate Device(s): | K200133 | K043443 |
| --- | --- | --- |
| Device Trade Name | hCG Urine Test Cassette
hCG Urine Test Strip
hCG Urine Test Midstream | One Step HCG Urine Pregnancy Test |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Qualitative detection of hCG to aid in the early detection of pregnancy | Same |
| General Device Characteristic Differences | | |
| Read time | 3-5 minutes | 5 minutes |
VI Standards/Guidance Documents Referenced:
FDA Guidance for Over-the-Counter (OTC) Hum an Chorionic Gonadotropin (hCG) 510(k)s, dated July 22, 2000.
VII Performance Characteristics (if/when applicable):
A. Analytical Performance:
1. Precision/Reproducibility:
A precision study was performed using urine samples from normal, nonpregnant females spiked with hCG, traceable to the 5th WHO International Standard to obtain samples with hCG concentrations of 0, 12.5, 18.75, 25, 50, and 100 mIU/mL. The tests were performed over the course of 10 days by 3 operators using 3 lots of each device. The samples were blinded and randomized.
{3}
Results for the hCG Urine Test Strip
| hCG concentration | LOT 1 | | LOT 2 | | LOT 3 | |
| --- | --- | --- | --- | --- | --- | --- |
| | positive | negative | positive | negative | positive | negative |
| 0 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 12.5 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 18.75 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 25 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 50 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 100 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
Results of precision for the hCG Urine Test Cassette
| hCG concentration | LOT 1 | | LOT 2 | | LOT 3 | |
| --- | --- | --- | --- | --- | --- | --- |
| | positive | negative | positive | negative | positive | negative |
| 0 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 12.5 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 18.75 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 25 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 50 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 100 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
Results of precision for the hCG Urine Test Midstream (using the dip method)
| hCG concentration | LOT 1 | | LOT 2 | | LOT 3 | |
| --- | --- | --- | --- | --- | --- | --- |
| | positive | negative | positive | negative | positive | negative |
| 0 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 12.5 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 18.75 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 25 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 50 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 100 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
Results of precision for the hCG Urine Test Midstream (using the simulated midstream method)
| hCG concentration | LOT 1 | | LOT 2 | | LOT 3 | |
| --- | --- | --- | --- | --- | --- | --- |
| | positive | negative | positive | negative | positive | negative |
| 0 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 12.5 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 18.75 mIU/mL | 0 | 30 | 0 | 30 | 0 | 30 |
| 25 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 50 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
| 100 mIU/mL | 30 | 0 | 30 | 0 | 30 | 0 |
- Page 4 of 9
{4}
- Page 5 of 9
2. **Linearity:**
Linearity is not applicable since this is a qualitative test.
3. **Analytical Specificity/Interference:**
**Cross-reactivity:**
To evaluate potential cross-reactivity relevant challenge doses of closely-related human luteinizing hormone (hLH), human follicle stimulating hormone (hFSH) or human thyroid stimulating hormone (hTSH) were tested using 30 fresh urine specimens obtained from healthy non-pregnant females. At each hCG concentration (0 mIU/mL and 25mIU/mL), 3 lots (90 replicates) of urine from non-pregnant female samples for each cross-reactant (hLH/hTSH/hFSH) was tested. The results demonstrated no cross reaction with LH at 500 mIU/mL, FSH at 1000 mIU/mL, and TSH at 1000 µIU/mL.
**Interference:**
To evaluate the potential for interference by certain exogenous compounds and potentially interfering clinical conditions, the substances listed were prepared by diluting stock interference material to the desired concentration. Normal, nonpregnant female urine specimens containing 0 and 25 mIU/mL hCG were spiked with the interferents to obtain the desired test concentration. Three lots of each format were tested. The results show that no interferences were observed from substance at the following concentrations for both negative and positive hCG urine samples.
| Interfering substances | Substances concentration |
| --- | --- |
| Acetaminophen | 20 mg/mL |
| Aspirin | 20 mg/dL |
| Ascorbic acid | 20 mg/mL |
| Caffeine | 20 mg/dL |
| Glucose | 200 mg/dL |
| Hemoglobin | 1 mg/mL |
| Tetracycline | 20 mg/dL |
| Ampicillin | 20 mg/dL |
| Albumin | 2000 mg/dL |
| Bilirubin | 2 mg/mL |
| Erythrocytes | >250 /μL |
| Leukocyte | >500 /μL |
| Uric acid | 450 mmol/L |
| Ketone | >80 mg/dL |
| Ethanol | 1% |
{5}
- Page 6 of 9
## Effect of hCG β-core fragment:
To evaluate the effects of the hCG β-core fragment normal nonpregnant female urine specimens containing 0 and 25 mIU/mL hCG were spiked with the hCG β-core fragment at concentrations of 125,000, 250,000, 500,000 and 1,000,000 pmol/mL. Three lots of each format were tested. The data demonstrated that there is no interference when the hCG β-core fragment was tested at a concentration of 1,000,000 pmol/L.
## Effect of urine pH and Specific Gravity:
The pH of an aliquot negative urine pool was adjusted to a pH range of 3 to 9 in 1 pH unit increments and spiked with hCG at 0 and 25 mIU/mL and 3 lots of hCG Urine Test were tested. The results showed no interference in samples ranging from pH 3 to 9.
## Specific gravity:
Negative specimen containing 0 mIU/mL and specimen with hCG 25 mIU/mL were adjusted to specific gravities of 1.001, 1.020, 1.031, 1.039. Three lots of hCG Urine Test were tested. The results showed no interference in samples with specific gravity ranging from 1.001-1.039.
## Hook effect study:
To evaluate high dose hook effect, 30 hCG-free specimens spiked with hCG at 5,000, 10,000, 100,000, 500,000, 650,000, 850,000, 950,000 and 1,000,000 mIU/mL were tested on three lots of devices for each format. The results showed no hook effect up to 850,000 mIU/mL.
## 4. Assay Reportable Range:
Not applicable. This is a qualitative test.
## 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
### Traceability:
The hCG Urine Test Strip, hCG Urine Test Cassette and hCG Urine Test Midstream are traceable to the WHO 5th IS material.
### Stability:
The stability data supports that the products have the shelf life of 30 months when stored at 4-30°C.
## 6. Detection Limit:
Refer to the Precision and Reproducibility section above for additional information. The sensitivity of hCG Urine Test is 25 mIU/mL.
{6}
7. Assay Cut-Off:
The sensitivity of hCG Urine Test Strip, hCG Urine Test Cassette, and hCG Urine Test Midstream is 25 mIU/mL. See precision section above.
B. Comparison Studies:
1. Method Comparison with Predicate Device:
Urine samples were collected from 120 women at a hospital laboratory. These samples were collected from women between the ages of 18 to 44 who were suspected they were pregnant, experienced late periods or were pregnant. Samples were collected at various time throughout the day and were randomized prior to testing. Testing was performed by laboratory professionals at two laboratory sites. Results of the professional using the candidate device were compared to results obtained from the predicate device. Summary of results is presented in the tables below:
The results of professional method comparison (strip)
| Candidate device | Predicate device professional | | |
| --- | --- | --- | --- |
| | | Positive | Negative |
| Professional A | Positive | 53 | 0 |
| | Negative | 0 | 67 |
| Professional B | Positive | 53 | 0 |
| | Negative | 0 | 67 |
The results of professional method comparison (cassette)
| Candidate device | Predicate device professional | | |
| --- | --- | --- | --- |
| | | Positive | Negative |
| Professional A | Positive | 53 | 0 |
| | Negative | 0 | 67 |
| Professional B | Positive | 53 | 0 |
| | Negative | 0 | 67 |
The results of professional method comparison (midstream, using dip method)
| Candidate device | Predicate device professional | | |
| --- | --- | --- | --- |
| | | Positive | Negative |
| Professional A | Positive | 53 | 0 |
| | Negative | 0 | 67 |
| Professional B | Positive | 53 | 0 |
| | Negative | 0 | 67 |
- Page 7 of 9
{7}
The results of professional method comparison (midstream, using the simulated method)
| Candidate device | Predicate device professional | | |
| --- | --- | --- | --- |
| | | Positive | Negative |
| Professional A | Positive | 53 | 0 |
| | Negative | 0 | 67 |
| Professional B | Positive | 53 | 0 |
| | Negative | 0 | 67 |
2. Matrix Comparison: Not Applicable. The device is intended for urine samples only.
C. Clinical Studies:
1. Clinical Sensitivity: Not Applicable.
2. Clinical Specificity: Not Applicable.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
A lay user study was conducted with women who each tested their own urine with only one test method, and the results of their test were compared to results reported by a laboratory professional. A total of 360 lay users test their own urine by following instructions provided in the package insert (in English). This study included 90 lay users using test strip, 90 lay users using test cassette, 90 lay users using the actual midstream method and 90 lay users using the dip method to test for midstream. Samples were also randomized prior to testing and specimens were collected throughout the day and tested.
Results of the lay user method comparison for the hCG Urine Test Strip
| Candidate device | Candidate device - Professional user | | Total | |
| --- | --- | --- | --- | --- |
| | | Positive | | Negative |
| Lay users | Positive | 33 | 0 | 33 |
| | Negative | 0 | 57 | 57 |
| Total | | 33 | 57 | 90 |
{8}
- Page 9 of 9
Results of the lay user method comparison for the hCG Urine Test Cassette
| Candidate device | Candidate device professional | | Total | |
| --- | --- | --- | --- | --- |
| | | Positive | | Negative |
| Lay users | Positive | 29 | 0 | 29 |
| | Negative | 0 | 61 | 61 |
| Total | | 29 | 61 | 90 |
Results of the lay user method comparison for the hCG Urine Test Midstream (using dip method)
| Candidate device | Candidate device professional | | Total | |
| --- | --- | --- | --- | --- |
| | | Positive | | Negative |
| Lay users | Positive | 23 | 0 | 23 |
| | Negative | 0 | 67 | 67 |
| Total | | 23 | 67 | 90 |
Results of the lay user method comparison for the hCG Urine Test Midstream (using actual midstream method)
| Candidate device | Candidate device professional | | Total | |
| --- | --- | --- | --- | --- |
| | | Positive | | Negative |
| Lay users | Positive | 26 | 0 | 26 |
| | Negative | 0 | 64 | 64 |
| Total | | 26 | 64 | 90 |
D. Clinical Cut-Off:
Not applicable
E. Expected Values/Reference Range:
Not applicable
VIII Proposed Labeling:
The labeling does support 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.
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.