K123567 · Church & Dwight Co., Inc. · LCX · Sep 10, 2013 · Clinical Chemistry
Device Facts
Record ID
K123567
Device Name
FIRST RESPONSE GOLD DIGITAL PREGNANCY TEST
Applicant
Church & Dwight Co., Inc.
Product Code
LCX · Clinical Chemistry
Decision Date
Sep 10, 2013
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1155
Device Class
Class 2
Indications for Use
The FIRST RESPONSE™ Gold Digital Pregnancy Test is an over-the-counter chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine. The device is intended for use as an aid in early detection of pregnancy, in some cases as early as five (5) days before the expected period, i.e., as early as six (6) days before the day of the missed period. Important note regarding negative results: Some pregnant women will not be able to detect hCG in their urine 5 days before the expected period. If you test negative before your missed period, but think you may still be pregnant, you should re-test again a few days after your missed period. All results should be confirmed by your healthcare provider, especially when making decisions about future medical care.
Device Story
Device is a digital, lateral-flow, qualitative immunoassay for urine hCG detection. User applies urine to absorbent tip; immunochromatographic strip utilizes streptavidin-biotin chemistry with mouse monoclonal and goat anti-mouse polyclonal antibodies. Integrated electronic components, including a microprocessor and optical sensor, analyze the strip's reaction; algorithm processes signals to display 'YES+' or 'NO-' on an LCD screen. Used at home by lay users; provides immediate results within 3 minutes. Digital output replaces visual line interpretation, reducing user error. Results aid in early pregnancy detection; users advised to confirm with healthcare providers for medical decisions.
Clinical Evidence
Bench testing included analytical sensitivity (10 mIU/mL cut-off), specificity, and high-dose hook effect (up to 500 IU/mL hCG and 1,000,000 pmol/L hCG βcf). Method comparison with predicate showed 100% accuracy (600/600 samples). Clinical study of 50 conceptive cycles showed 60% detection 5 days before expected period, reaching 100% by the day of the expected period. Lay-user study (n=102) showed 100% agreement between consumer interpretation and lab technicians. No positive results in 306 non-pregnant samples across pre-, peri-, and post-menopausal cohorts.
Indicated for lay users for qualitative detection of hCG in urine to aid in early pregnancy detection. Can be used as early as 6 days before the day of the missed period. Negative results before the missed period do not rule out pregnancy; re-testing after the missed period is recommended.
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
FIRST RESPONSE™ Early Result Pregnancy Test (K083716)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k123567
B. Purpose for Submission:
Modification of device (change in hCG antibody)
C. Measurand:
Human chorionic gonadotropin (hCG)
D. Type of Test:
Qualitative chromatographic immunoassay
E. Applicant:
Church & Dwight Co., Inc.
F. Proprietary and Established Names:
FIRST RESPONSE Gold Digital Pregnancy Test
G. Regulatory Information:
| Product code | Classification | Regulation section | Panel |
| --- | --- | --- | --- |
| LCX | Class II | 21 CFR 862.1155
Human chorionic gonadotropin (hCG) test system | Chemistry (75) |
H. Intended Use:
1. Intended use(s):
See Indications for use below.
2. Indication(s) for use:
The FIRST RESPONSE™ Gold Digital Pregnancy Test is an over-the-counter chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine. The device is intended for use as an aid in early detection of pregnancy, in some cases as early as five (5) days before the expected period, i.e., as early as six (6) days before the day of the missed period.
Important note regarding negative results:
Some pregnant women will not be able to detect hCG in their urine 5 days before the expected period. If you test negative before your missed period, but think you may still be pregnant, you should re-test again a few days after your missed period.
{1}
All results should be confirmed by your healthcare provider, especially when making decisions about future medical care.
3. Special conditions for use statement(s):
For over-the-counter use
4. Special instrument requirements:
None
I. Device Description:
The FIRST RESPONSE Gold Digital Pregnancy Test is a screening device intended for the early detection of pregnancy by the lay user through the qualitative detection of human chorionic gonadotropin (hCG) hormone in urine, in some cases as early as 5 days before the expected period. The FIRST RESPONSE Gold Digital Pregnancy Test consists of a plastic housed test stick containing an immunochromatographic strip and electronic and optical components along with a microprocessor and specific algorithms to digitally display test results. The test strip contains streptavidin-biotin chemistry, mouse monoclonal and goat anti-mouse polyclonal antibodies.
J. Substantial Equivalence Information:
1. Predicate device name(s):
FIRST RESPONSE Early Result Pregnancy test
2. Predicate 510(k) number(s):
k083716
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Proposed Device | Predicate Device (k083716) |
| Intended use | Early detection of pregnancy | Same |
| Target User | Over-the-counter | Same |
| Analyte | hCG | Same |
| Test principle | Lateral flow sandwich immunochromatographic assay | Same |
| Specimen | Urine | Same |
| Time to Result | 3 minutes | Same |
{2}
| Differences | | |
| --- | --- | --- |
| Item | Proposed device | Predicate device (k083716) |
| Results | YES+ = pregnant
NO- = not pregnant | 2 pink lines = pregnant
1 pink line = not pregnant |
| Electronic components | Microprocessor with specific circuitry and algorithm. LCD readout with battery as power source | None |
| hCG isoforms detected | intact hCG
hyperglycosylated hCG
hCG β-subunit
hCG β-core fragment | intact hCG
hyperglycosylated hCG
hCG β-subunit |
K. Standard/Guidance Document Referenced (if applicable):
None referenced
L. Test Principle:
The detection of hCG in urine is accomplished by a series of immunochemical reactions via component reagents that are deposited onto a chromatographic strip contained within the plastic housing.
A digital component integral with the chromatographic strip reads and displays the result of the immunochemical reaction on an LCD (Liquid Crystal Display) screen of the device.
The test is performed by placing the absorbent collection tip of the device into the urine stream for 5 seconds (or alternatively by fully immersing the collection tip for 5 seconds in a urine sample that was collected in a cup). A clock symbol will begin to blink in about 30 seconds after the urine is applied to indicate to the consumer that the test is working. The test result is read on the LCD screen of the device within 3 minutes. A "YES+" test result indicates that the pregnancy hormone (hCG) was detected (pregnant) and a "NO-" test result indicates that no hCG was detected (not pregnant).
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Urine standards containing hCG at concentrations of 0, 3, 6, 10, 15, and 25 mIU/mL prepared in negative urine pool and calibrated against the WHO 4th International Standard (IS) for hCG were tested using five different lots of the First Response® Gold Digital Pregnancy Test. Each sample was tested in replicates of ten for a total of sixty devices per lot. Testing was performed over three consecutive days, each day using a different technician.
{3}
| hCG level | Lot# 1 | Lot# 2 | Lot# 3 | Lot# 4 | Lot# 5 | % Positive |
| --- | --- | --- | --- | --- | --- | --- |
| 0 mIU/mL | 30/30
NO- | 30/30
NO- | 30/30
NO- | 30/30
NO- | 30/30
NO- | 0% |
| 3 mIU/mL | 30/30
NO- | 30/30
NO- | 30/30
NO- | 30/30
NO- | 30/30
NO- | 0% |
| 6 mIU/mL | 13/30
YES+ | 14/30
YES+ | 13/30
YES+ | 14/30
YES+ | 13/30
YES+ | 45% |
| 10 mIU/mL | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 100% |
| 15 mIU/mL | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 100% |
| 25 mIU/mL | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 30/30
YES+ | 100% |
b. Linearity/assay reportable range:
Not applicable. This is a qualitative device.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The device is standardized to the World Health Organization’s 4th International Standard for Chorionic Gonadotropin.
The devices are stable until the expiration date printed on box when stored in the pouch at room temperature (30°C).
Stability testing protocols and sponsor’s acceptance criteria were reviewed and found to be acceptable. The claimed shelf life of the devices stored in pouches at room temperature is 2 years.
d. Detection limit:
To determine the detection limit and analytical cut-off of the FIRST RESPONSE® Gold™ Digital Pregnancy Test, hCG urine standards of known concentration were tested. Urine standards containing hCG at concentrations of 0, 3, 6, 10, 15, and 25 mIU/mL were tested by laboratory technicians according to package insert instructions with three lots of devices in replicates of 20. The results show that the analytical sensitivity of the device (the lowest concentration that yields 100% positive results) is 10 mIU /mL and the analytical cut-off level at which approximately half of the devices yield positive results and the remainder yield negative results is 6 mIU /mL. All devices were negative at 0 and 3 mIU /mL.
{4}
5
| | hCG concentration (mIU/mL) | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | 0 | 3 | 6 | 10 | 15 | 25 |
| Lot# | 0/20 | 0/20 | 8/20 | 20/20 | 20/20 | 20/20 |
| 10671 | YES+ | YES+ | YES+ | YES+ | YES+ | YES+ |
| Lot# | 0/20 | 0/20 | 10/20 | 20/20 | 20/20 | 20/20 |
| 10681 | YES+ | YES+ | YES+ | YES+ | YES+ | YES+ |
| Lot# | 0/20 | 0/20 | 9/20 | 20/20 | 20/20 | 20/20 |
| 10691 | YES+ | YES+ | YES+ | YES+ | YES+ | YES+ |
| TOTAL | 0/60 | 0/60 | 27/60 | 60/60 | 60/60 | 60/60 |
| | YES+ | YES+ | YES+ | YES+ | YES+ | YES+ |
| % Positive | 0% | 0% | 45% | 100% | 100% | 100% |
An additional study was performed to assess the analytical sensitivity and cut-off using a simulated mid-stream technique. Samples with known hCG concentrations were tested in replicates of 20 at each concentration using a technique to simulate the midstream testing method:
| hCG concentration (mIU/mL) | | | | |
| --- | --- | --- | --- | --- |
| | 0 | 3 | 6 | 10 |
| Test results | 0/20 YES+ | 0/20 YES+ | 10/20 YES+ | 20/20 YES+ |
| % Positive | 0% | 0% | 50% | 100% |
e. Analytical specificity:
To determine if the FIRST RESPONSE Gold Digital Pregnancy Test has a high dose hook effect, the test was challenged with samples with very high levels of hCG. Urine hCG standards at 0.1, 0.2, 0.5, 1, 5, 10, 25, 50, 100 and 500 IU /mL were evaluated with the FIRST RESPONSE® Gold™ Digital Pregnancy Test devices according to package insert instructions in replicates of 10 at each level. All devices tested with the hCG standards yielded the expected positive results. No "high-dose hook" effect was observed at hCG levels up to 500 IU /mL. The results are summarized below:
{5}
| hCG Concentration | Results |
| --- | --- |
| 0.1 IU/mL | 10/10 YES+ |
| 0.2 IU/mL | 10/10 YES+ |
| 0.5 IU/mL | 10/10 YES+ |
| 1 IU/mL | 10/10 YES+ |
| 5 IU/mL | 10/10 YES+ |
| 10 IU/mL | 10/10 YES+ |
| 25 IU/mL | 10/10 YES+ |
| 50 IU/mL | 10/10 YES+ |
| 100 IU/mL | 10/10 YES+ |
| 500 IU/mL | 10/10 YES+ |
In order to evaluate the potential for high concentrations of hCG beta core fragment (βcf) to cause false results, third trimester pregnancy urine samples prepared to contain 500,000 and 1,000,000 pmol/L of hCG βcf were each tested on 10 devices. All devices tested with the hCG standards yielded the expected positive results. No "high-dose hook" effect was observed at hCG βcf levels up to 1,000,000 pmol/L.
| hCG βcf concentration | Test results |
| --- | --- |
| 500,000 pmol/L | 10/10 YES+ |
| 1,000,000 pmol/L | 10/10 YES+ |
{6}
Various prescription and OTC drugs (acetaminophen, acetylsalicylic acid, ascorbic acid, ampicillin, atropine, caffeine, gentisic acid, phenothiazine, phenylpropanolamine and tytracycline, all at 10 µg/mL), potential endogenous interferents (glucose and albumin at 20 mg/mL, hemoglobin, bilirubin, and estriol at 10 µg/mL) and homologous hormones (hLH and hFSH at 1000 mIU/mL, hTSH at 1 mIU/mL) were added to aliquots of urine pools that tested negative for hCG and urine pools that contained hCG at 10 mIU/mL. Samples were tested in replicates of 10. No affects on test performance were observed.
f. Assay cut-off:
See detection limit section above.
2. Comparison studies:
a. Method comparison with predicate device:
A total of 600 urine samples were randomized and tested according to package insert instructions with three lots of the FIRST RESPONSE® Gold™ Digital Pregnancy Test (one subject device randomized from the three lots/per sample) and one lot of the predicate devices. The results are summarized below:
| Device | Correct Negative | Correct Positive | Accuracy |
| --- | --- | --- | --- |
| First Response® Gold Digital Pregnancy Test (Subject Device) | 300/300 | 300/300 | 100% (600/600) |
| First Response® Early Result Pregnancy Test (Predicate Device) | 300/300 | 300/300 | 100% (600/600) |
The results show no discrepancies between the FIRST RESPONSE Gold Digital Pregnancy Test and the predicate device, the FIRST RESPONSE Early Result Pregnancy Test.
b. Matrix comparison:
Not applicable.
{7}
8
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):
Detection of hCG in Early Pregnancy Clinical Samples
A total of 504 urine samples from 50 characterized cycle segments taken from conceptive cycles collected from 50 different pregnant women were tested according to package insert instructions. Every urine sample from each cycle segment was randomized. Each urine sample was tested with one device selected from three device lots according to a randomization table, and the three device lots were represented equally across all of the samples included within the study.
The FIRST RESPONSE Gold Pregnancy Test detected hCG in 60% of the cycles five days before the expected menstrual period and in 100% of the cycles on the day of the expected menstrual period. The table below summarizes detection of hCG with the FIRST RESPONSE Gold Digital Pregnancy Test relative to the day of the expected menstrual period (EMP) for the conceptive cycles tested.
| Day relative to Expected Menstrual Period | -11 | -10 | -9 | -8 | -7 | -6 | -5 | -4 | -3 | -2 | -1 | EMP |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Day relative to LH Peak | LH +4 | LH +5 | LH +6 | LH +7 | LH +8 | LH +9 | LH +10 | LH +11 | LH +12 | LH +13 | LH +14 | LH +15 |
| #Cycles positive for hCG | 0/2 | 0/8 | 1/18 | 1/35 | 6/45 | 15/48 | 30/50 | 42/49 | 48/50 | 50/50 | 49/49 | 50/50 |
| Cumulative % Cycles | 0% | 0% | 6% | 3% | 13% | 31% | 60% | 86% | 96% | 100% | 100% | 100% |
Note: EMP was calculated by adding 15 days to the day with the highest quantitative urinary concentration of luteinizing hormone (LH), i.e., day of LH peak plus 15 days (LH+15).
{8}
9
# Non-pregnant urine sample analysis
A study was performed to determine the incidence of positive results in urine from non-pregnant females when tested with the candidate device. A total of 306 urine samples (from 102 pre-menopausal women (ages 18-40), 102 perimenopausal women (ages 41-55), and 102 postmenopausal women (ages 56-75)) were tested with three lots of FIRST RESPONSE Gold Digital Pregnancy Tests according to package insert instructions. No pre-selection or prescreening based on hCG was performed prior to testing. The results of this study are presented below:
| Sub- population | No. of samples | Positive Results |
| --- | --- | --- |
| Pre-menopausal (18-40 yrs old) | 102 | 0/102 (0%) |
| Peri-Menopausal (41-55 yrs old) | 102 | 0/102 (0%) |
| Post-Menopausal (> 55 yrs old) | 102 | 0/102 (0%) |
# Lay-user Study
The purpose of this study was to determine the ability of consumers to perform a self-test using the FIRST RESPONSE® Early Result Pregnancy Test, and read and interpret their test results following package insert instructions. One hundred and two female subjects between the ages of 18 and 45 were recruited. Consumer interpretation of results compared to lab technicians are tabulated below:
| Result | Number of samples | Consumer vs. Technicians |
| --- | --- | --- |
| Pregnant | 13 | 13/13 (100%) |
| Non-Pregnant | 89 | 89/89 (100%) |
| TOTAL | 102 | 102/102 (100%) |
A second study was performed to evaluate the FIRST RESPONSE Gold Digital Pregnancy test around the cut-off in the hands of the intended user. Female lay-users (ages 18-45) were recruited to test one masked hCG sample (8 or 12 mIU/mL). Participants varied in education level. The test results were as follows:
{9}
| hCG Standards (mIU/mL) | | |
| --- | --- | --- |
| | 8 | 12 |
| Test results | 15/20 YES+ | 20/20 YES+ |
| % Positive | 75% | 100% |
All lay-users answered in the affirmative to questions regarding the ease of interpretation of test results and ease of following the package insert instructions.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Not applicable.
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.
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.