Patient urine specimens from routine clinical practice
The sponsor conducted a method comparison study using 120 clinical patient urine specimens to demonstrate the diagnostic accuracy of the y.b.t. Pregnancy Test compared to routine clinical diagnostic methods.
Patients providing urine specimens at two certified hospitals; Sample Size: 120 (60 positive, 60 negative); Number of Sites: 2
Routine diagnostic method
Positive and negative agreement (diagnostic accuracy)
Indications for Use
The y.b.t. Pregnancy Test is an immunochromatographic assay for the qualitative determination of HCG in human urine. The test is intended for use as an aid in the early detection of pregnancy.
Device Story
The y.b.t. Pregnancy Test (strip or cassette format) is a lateral-flow immunochromatographic assay used to detect hCG in human urine. The device utilizes monoclonal antibodies: mouse anti-hCG-beta (test line) and mouse anti-hCG-alpha coupled to red-colored gold particles (indicator). When urine is applied, hCG binds to the gold-labeled antibody; the complex migrates along a nitrocellulose membrane to the test zone, where it is captured by the immobilized anti-hCG-beta antibody, forming a visible red line. A procedural control line (goat anti-mouse IgG) confirms proper flow. The test is performed by healthcare professionals in clinical settings. Results are interpreted visually by the clinician after 5 minutes. A positive result indicates the presence of hCG, aiding in pregnancy confirmation. The device provides a qualitative assessment of pregnancy status.
Clinical Evidence
Bench testing only. Sensitivity confirmed at 25 mIU/ml using WHO Third I.S. standards. Specificity validated against 20 postmenopausal urine samples and various potentially interfering substances (e.g., acetaminophen, glucose, hormones like LH, FSH, TSH) with no interference observed. Method comparison study conducted at two hospitals with 120 patient urine specimens (60 positive, 60 negative) showed 100% agreement with routine diagnostic methods. Precision studies (intra-assay and inter-assay) using 0, 25, and 250 mIU/ml hCG concentrations demonstrated 100% consistency.
Technological Characteristics
Qualitative immunochromatographic assay. Materials: mouse monoclonal anti-beta-hCG gold-conjugated antibody, goat anti-mouse anti-alpha-hCG polyclonal antibody, goat anti-mouse IgG control. Cut-off: 25 IU/L. Traceability: WHO 3rd International Standard for hCG. Form factor: test strip or cassette. Storage: 2-30°C. Shelf-life: 18 months.
Indications for Use
Indicated for the qualitative detection of human chorionic gonadotropin (hCG) in human urine to aid in early pregnancy detection. Intended for prescription 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
Acon One Step Pregnancy Test Strip (Urine) (k993203)
Submission Summary (Full Text)
{0}
k112315
# SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k112315
B. Purpose for Submission:
New device
C. Measurand:
Human chorionic gonadotropin (hCG) in human urine
D. Type of Test:
Qualitative immunochromatographic assay
E. Applicant:
NewScen Coast Bio-Pharmaceutical Co., Ltd.
F. Proprietary and Established Names:
The y.b.t. Pregnancy Test Strip; The y.b.t. Pregnancy Test Cassette
G. Regulatory Information:
1. Regulation section:
21 CFR§ 862.1155, Human chorionic gonadotropin (hCG) test system
2. Classification:
Class II
3. Product code:
JHI
4. Panel:
Clinical Chemistry (75)
1
{1}
H. Intended Use:
1. Intended use(s):
See indication for use below
2. Indication(s) for use
The y.b.t. Pregnancy Test Strip is an immunochromatographic assay for the qualitative determination of hCG in human urine. The test is intended for use as an aid in the early detection of pregnancy.
The y.b.t. Pregnancy Test Casette is an immunochromatographic assay for the qualitative determination of hCG in human urine. The test is intended for use as an aid in the early detection of pregnancy.
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
None
I. Device Description:
The y.b.t. Pregnancy Test will be marketed in two formats: cassette and test strip. The test strip kit consists of one test device and a package insert. The cassette kit consists of one test device and a disposable plastic dropper, and a package insert. The device is a qualitative assay based on immunochromatography principle used to detect levels of hCG over the cut-off value (25 IU/L) of the device. The device utilizes mouse monoclonal anti-β-hCG gold conjugated antibody as a signal reagent and a goat anti-mouse anti-α-hCG polyclonal antibody as solid phase capture antibody. The control antibodies are goat anti-mouse IgG.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Acon One Step Pregnancy Test Strip (Urine)
2. Predicate 510(k) number(s):
k993203
k112315
{2}
k112315
3. Comparison with predicate:
| Items | NewScen y.b.t. Pregnancy Test k112315 (Candidate Device) | Acon One Step Pregnancy Test k993203 (Predicate Device) |
| --- | --- | --- |
| Similarities | | |
| Intended Use | Same | Qualitative detection of hCG in human urine to aid in the early detection of pregnancy. |
| Methodology | Same | Chromatographic immunoassay |
| Storage | Same | 2 °C to 30 °C |
| Assay cut-offs | Same | 25 IU/L |
| Traceability | Same | 3rd IRP WHO |
| Differences | | |
| Specimen | urine | urine or serum |
| Format | Strip and Cassette | Strip |
K. Standard/Guidance Document Referenced (if applicable):
None were referenced.
L. Test Principle:
The test utilizes monoclonal gold conjugated antibody as a signal reagent and a polyclonal antibody as solid phase capture antibody. As the urine sample flows through the absorbent sample pad, the urine reconstitutes the dried beta hCG conjugate. The hCG in the urine sample will bind to this conjugate antibody and migrate further up the membrane to the test line immobilized with capture hCG antibody. A complex is formed at this site indicated by a pink line. When the concentration of hCG is lower than 25 IU/L no complex is formed and no pink line is observed.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
An in-house precision study was performed by 1 laboratory technician using male urine samples spiked with different concentrations of hCG. Ten different concentrations (0, 25,
3
{3}
50, 100, 6,250, 12,500, 25,000, 50,000, 100,000, and 500,000 IU/L) were tested on two lots of strips and one lot of cassettes. The samples were masked and randomized prior to analysis. The test was performed 10 times on each concentration for each lot as per package insert instructions. Results are summarized as follows:
| hCG concentrations | Strip | | Cassette | |
| --- | --- | --- | --- | --- |
| IU/L | Positive | Negative | Positive | Negative |
| 0 | 0 | 20 | 0 | 10 |
| 25 | 20 | 0 | 10 | 0 |
| 50 | 20 | 0 | 10 | 0 |
| 100 | 20 | 0 | 10 | 0 |
| 6,250 | 20 | 0 | 10 | 0 |
| 12,500 | 20 | 0 | 10 | 0 |
| 25,000 | 20 | 0 | 10 | 0 |
| 50,000 | 20 | 0 | 10 | 0 |
| 100,000 | 20 | 0 | 10 | 0 |
| 500,000 | 20 | 0 | 10 | 0 |
A point-of-care precision study was performed at three different sites by three intended users using 3 lots of each device format and 30 measurements per each hCG concentration listed in the table below. All the samples were randomized and masked before giving to users to test and interpret the result. Results are summarized as follows:
| hCG concentrations | Strip | | | | | | Cassette | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Unit | Site 1 | | Site 2 | | Site 3 | | Site 1 | | Site 2 | | Site 3 | |
| IU/L | Pos | Neg | Pos | Neg | Pos | Neg | Pos | Neg | Pos | Neg | Pos | Neg |
| 0 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 |
| 25 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 |
| 50 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 |
| 100 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 |
| 100,000 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 | 10 | 0 |
b. Linearity/assay reportable range:
Linearity is not applicable since this is a qualitative test.
A hook effect study was performed at levels of 0- 500,000 IU/L (0, 25, 50, 100, 6,250, 12,500, 25,000, 50,000, 100,000, and 500,000 IU/L) for each format of test in
k112315
{4}
combination with the precision study in section 1.a. No hook effect was observed up to 500,000 IU/L of hCG.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The devices are traceable to the WHO 3rd International Standard for hCG.
Stability testing protocols and acceptance criteria were reviewed and found to be acceptable. Accelerated stability and real-time stability studies were performed on both test strip and cassette formats. The sponsor states that the shelf-life of the device is 18 months when stored at 25° C.
d. Detection limit:
Not applicable to qualitative test
e. Analytical specificity:
Interference studies were conducted on common interfering substances listed in the table below using two human male urine pools: 1) negative male urine control (0 IU/L of hCG) and 2) male urine samples spiked with 25 IU/L of hCG, with both strips and cassettes. Various concentrations of each interferent listed below were added to the tested urine pools to see if the interferent will affect the reading of the tested specimens. For each interferent tested, the highest concentration without resulting in interference for the device is summarized below:
| Interference substance | Concentration | Results 0 IU/L hCG (Negative) | Results after Spiked with 25 IU/L hCG (Positive) |
| --- | --- | --- | --- |
| Acetylsalicylic acid | 20 mg/dl | Negative | Positive |
| Acetaminophen | 20 mg/dl | Negative | Positive |
| Ampicillin | 20 mg/dl | Negative | Positive |
| Ascorbic acid | 20 mg/dl | Negative | Positive |
| Atropin | 20 mg/dl | Negative | Positive |
| Bilirubin | 1000 mg/dl | Negative | Positive |
| Caffeine | 20 mg/dl | Negative | Positive |
| Gentisic acid | 20 mg/dl | Negative | Positive |
| Glucose | 2 mg/dl | Negative | Positive |
| Hemoglobin | 1 mg/dl | Negative | Positive |
| Tetracycline | 20 mg/dl | Negative | Positive |
| Cortisol | 200 ng/dl | Negative | Positive |
| Albumin | 2000 mg/dl | Negative | Positive |
| DHEAS | 500 ng/dl | Negative | Positive |
k112315
{5}
k112315
| Estradiol (E-2) | 25 ng/dl | Negative | Positive |
| --- | --- | --- | --- |
| Estriol (E-3) | 25 ng/dl | Negative | Positive |
| Uric acid | 10 mg/dl | Negative | Positive |
Cross-reactivity studies were performed to evaluate the interferences from other glycoprotein hormones, hFSH, hLH, and hTSH. Human FSH (1000 IU/L, WHO 2nd HMG), hLH (1000 IU/L, WHO 68/38), and hTSH (1000 IU/L, WHO 2nd HMG) were added to male urine samples at two hCG concentrations (0 and 25 IU/L). Each sample was run on three lots of strips and cassettes and a total of 90 urine samples were tested. The results of these studies showed that there is no cross-reactivity at 1000 IU/L hFSH, 1000 IU/L hLH, or 1000 IU/L hTSH.
Cross-reactivity studies to β-core hCG were also performed; the results indicate there was no cross-reactivity with β-core hCG up to 20,000,000 pmol/L.
The effects of pH and specific gravity were evaluated by testing urine samples spiked with hCG (at 0, 25 and 100 IU/L) at pH 4-8 or specific gravity of 1.010-1.027. No interference was observed for these pH or specific gravities tested.
f. Assay cut-off:
The sponsor performed an in-house cut-off study separately from the precision study for the test strip and cassette formats. The claimed cut-off is 25 IU/L. Negative human urine samples were spiked with purified hCG traceable to the WHO International 3rd Standard to reach 5, 10, 20 (-20% cutoff), 23, 25, 30(+20% cutoff), 50 and 100 IU/L of hCG final concentrations. For each concentration, the performance was evaluated 40 times using three lots of the test strips and cassettes. The results are shown in the table below.
| hCG Concentration (IU/L) | Strip | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | 0 | 5 | 10 | 20 | 23 | 25 | 30 | 50 | 100 |
| No. of Positive Specimens | 0 | 0 | 2 | 22 | 39 | 40 | 40 | 40 | 40 |
| | 0% | 0% | 5% | 55% | 97.5% | 100% | 100% | 100% | 100% |
| No. of Negative Specimens | 40 | 40 | 38 | 18 | 1 | 0 | 0 | 0 | 0 |
| | 100% | 100% | 95% | 45% | 2.5% | 0% | 0% | 0% | 0% |
| Total number | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| hCG Concentration (IU/L) | Cassette | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | 0 | 5 | 10 | 20 | 23 | 25 | 30 | 50 | 100 |
| No. of Positive Specimens | 0 | 0 | 2 | 22 | 39 | 40 | 40 | 40 | 40 |
| | 0% | 0% | 5% | 55% | 97.5% | 100% | 100% | 100% | 100% |
| No. of Negative Specimens | 40 | 40 | 38 | 18 | 1 | 0 | 0 | 0 | 0 |
| | 100% | 100% | 95% | 45% | 2.5% | 0% | 0% | 0% | 0% |
| Total number | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
6
{6}
POC precision near cutoff
The detection limit was evaluated in 3 point-of-care sites by testing 40 hCG-negative urine samples per site by three intended users. Freshly collected urine samples, from healthy men were spiked with 0, 5, 8, 10, 20, 23, 25, and 50 IU/L of hCG. The samples were masked and randomized prior to analysis. The intact hCG used in this study is traceable to WHO 3rd standard. The results are shown below:
| hCG IU/L | strips | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Lot# 1 | | | | Lot # 2 | | | | Lot # 3 | | | |
| | Pos | | Neg | | Pos | | Neg | | Pos | | Neg | |
| 0 | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% |
| 5 | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% |
| 8 | 0 | 0% | 120 | 100% | 3 | 2.5% | 117 | 97.5% | 1 | 2.5% | 117 | 97.5% |
| 10 | 6 | 5% | 114 | 95% | 6 | 5% | 114 | 95% | 6 | 5% | 114 | 95% |
| 20 | 65 | 54.2% | 55 | 45.8% | 66 | 55% | 54 | 45% | 65 | 54.2% | 55 | 45.8% |
| 23 | 117 | 97.5% | 3 | 2.5% | 115 | 95.8% | 5 | 4.2% | 116 | 96.7% | 4 | 3.3 |
| 25 | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% |
| 30 | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% |
| hCG IU/L | cassettes | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Lot# 1 | | | | Lot # 2 | | | | Lot # 3 | | | |
| | Pos | | Neg | | Pos | | Neg | | Pos | | Neg | |
| 0 | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% |
| 5 | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% |
| 8 | 0 | 0% | 120 | 100% | 3 | 2.5% | 117 | 97.5% | 1 | 2.5% | 117 | 97.5% |
| 10 | 6 | 5% | 114 | 95% | 6 | 5% | 114 | 95% | 6 | 5% | 114 | 95% |
| 20 | 64 | 53.3% | 56 | 46.7% | 66 | 55% | 54 | 45% | 65 | 54.2% | 55 | 45.8% |
| 23 | 117 | 97.5% | 3 | 2.5% | 116 | 96.7% | 4 | 3.3% | 114 | 95% | 6 | 5% |
| 25 | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% |
| 30 | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% | 120 | 100% | 0 | 0% |
The device reached a 97.5% positive rate at 23 IU/L hCG, 95% negative rate at 10 IU/L hCG and 100% positive rate at 25 IU/L hCG (the cutoff).
2. Comparison studies:
a. Method comparison with predicate device:
Comparison studies between 1) the test strip and predicate device; 2) the test cassette and predicate device, were conducted by total of 7 healthcare professionals at 3 clinical sites on 3 lots of each device format. Each site collected 60 samples (N=180) for each format. The samples were collected from women who were of childbearing age, perimenopausal, or suspected of being pregnant, and those in their early or late pregnancy. All samples were masked and randomized prior to analysis. Users performed the testing according to the labeling. Test results are summarized below:
k112315
{7}
| | Predicate Device, strips | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total Agreement |
| Test Strips (N=180) | Positive | 90 | 0 | 100% |
| | Negative | 0 | 90 | |
| | Total | 90 | 90 | |
| | Predicate Device, cassette | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total Agreement |
| Test Cassette (N=180) | Positive | 90 | 0 | 100% |
| | Negative | 0 | 90 | |
| | Total | 90 | 90 | |
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Healthy non-pregnant women should not have any detectable hCG.
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.
k112315
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.