K072141 · Alfa Wassermann Diagnostic Technologies, Inc. · CEO · Jun 24, 2008 · Clinical Chemistry
Device Facts
Record ID
K072141
Device Name
S40 CLINICAL ANALYZER, S TEST IP, S TEST UA
Applicant
Alfa Wassermann Diagnostic Technologies, Inc.
Product Code
CEO · Clinical Chemistry
Decision Date
Jun 24, 2008
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1580
Device Class
Class 1
Indications for Use
The S-Test Inorganic Phosphorous Reagent is intended for the quantitative determination of inorganic phosphorous concentration in serum or heparin plasma using the S40 Clinical Analyzer. Measurements of phosphorus (inorganic) are used in the diagnosis and treatment of various disorders, including parathyroid gland and kidney diseases, and vitamin D imbalance. This test is intended for use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only. The S-Test Uric Acid Reagent is intended for the quantitative determination of uric acid concentration in serum or heparin plasma using the S40 Clinical Analyzer. Uric acid measurements are used in the diagnosis and treatment of numerous renal and metabolic disorders, including renal failure, gout, leukemia, psoriasis, starvation or other wasting conditions, and of patients receiving cytotoxic drugs. This test is intended for use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only.
Device Story
S-Test IP and UA reagent cartridges are used with the S40 Clinical Analyzer for in vitro diagnostic testing. IP reagent uses ammonium molybdate to form molybdenum blue; UA reagent uses uricase and peroxidase to form a reddish-purple pigment. Photometric analysis of these colorimetric reactions provides quantitative concentration values. Operated by laboratory personnel in clinical or physician office settings. Output assists clinicians in diagnosing and monitoring renal, metabolic, and parathyroid conditions. Benefits include rapid, automated diagnostic assessment of patient serum or heparin plasma samples.
Clinical Evidence
Bench testing only. Precision studies (22-day and 5-day POL site studies) showed IP total CV 1.2-4.0% and UA total CV 0.7-3.5%. Accuracy correlation studies (n=95 for IP, n=183 for UA) against comparison methods yielded correlation coefficients of 0.976 (IP) and 0.974 (UA). Sensitivity (detection limits) reported as 1.2 mg/dL for IP and 1.4 mg/dL for UA.
Technological Characteristics
Single-use reagent cartridges with 2-D barcode calibration. IP reagents: p-methylaminophenol sulfate, ammonium molybdate, sulfuric acid. UA reagents: uricase, peroxidase, 4-aminoantipyrine, TOOS. Photometric sensing principle. Energy source: S40 Clinical Analyzer. Connectivity: 2-D code label for lot-specific data input. Dimensions: cartridge form factor.
Indications for Use
Indicated for quantitative determination of inorganic phosphorus and uric acid in serum or heparin plasma for patients requiring diagnosis/treatment of renal, metabolic, or parathyroid disorders, vitamin D imbalance, gout, leukemia, psoriasis, or those receiving cytotoxic drugs. Intended for use in clinical or physician office laboratories.
Regulatory Classification
Identification
A phosphorus (inorganic) test system is a device intended to measure inorganic phosphorus in serum, plasma, and urine. Measurements of phosphorus (inorganic) are used in the diagnosis and treatment of various disorders, including parathyroid gland and kidney diseases, and vitamin D imbalance.
Predicate Devices
ACE plus ISE/Clinical Chemistry System (k931786)
Alfa Wassermann Piccolo xpress Chemistry Analyzer (k950164)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k072141
B. Purpose for Submission:
New device
C. Measurand:
Inorganic Phosphorous (IP) and Uric Acid (UA)
D. Type of Test:
Quantitative, Photometric
E. Applicant:
Alfa Wassermann Diagnostic Technology, Inc.
F. Proprietary and Established Names:
S Test Inorganic Phosphorous (IP) Reagent cartridge
S Test Uric Acid (UA) Reagent cartridge
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CEO – Phosphorous | Class I reserved | 21 CFR§ 862.1580 | 75 Chemistry |
| KNK – Uric Acid | Class I reserved | 21 CFR§ 862.1775 | 75 Chemistry |
H. Intended Use:
1. Intended use(s):
See indications for use below.
{1}
2. Indication(s) for use:
The S Test Inorganic Phosphorous Reagent is intended for the quantitative determination of inorganic phosphorous concentration in serum or heparin plasma using the S40 Clinical Analyzer. Measurements of phosphorus (inorganic) are used in the diagnosis and treatment of various disorders, including parathyroid gland and kidney diseases and vitamin D imbalance. This test is intended for use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only.
The S Test Uric Acid Reagent is intended for the quantitative determination of uric acid concentration in serum or heparin plasma using the S40 Clinical Analyzer. Uric Acid are used in the diagnosis and treatment of numerous renal and metabolic disorders, including renal failure, gout, leukemia, psoriasis, starvation or other wasting conditions and of patients receiving cytotoxic drugs. This test is intended for the use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only.
3. Special conditions for use statement(s):
For Prescription Use only
4. Special instrument requirements:
S40 Clinical Chemistry Analyzer
I. Device Description:
The Inorganic Phosphorous (IP) and Uric Acid (UA) are single use reagent cartridges having two reagent cells, Photometric reaction cuvette, film seal and a 2-D code label. The reagent cells contain the following reagents:
IP Reagent 1 – p-methylaminophenol sulfate and nonionic surface=active reagent, Reagent 2 – Ammonium molybdate and Sulfuric acid
UA Reagent 1 - N-ethyl-N-(2-hydroxy-3-sulfopropyl)-m-toluidine, sodium salt (TOOS), Peroxidase (POD) and 2-(N-morpholino) ethanesulfonic acid buffer (pH 6.9), Reagent 2 - Uricase (derived from yeast), 4-aminoantipyrine and 2-(N-morpholino) ethanesulfonic acid buffer (pH 6.9)
{2}
J. Substantial Equivalence Information:
1. Predicate device name(s):
ACE plus ISE/Clinical Chemistry System, Alfa Wassermann Piccolo xpress Chemistry Analyzer, Abaxis Inc.
2. Predicate 510(k) number(s):
k931786 and k950164 respectively
3. Comparison with predicate:
Inorganic Phosphorous:
The device and the predicate devices share a similar intended use, analytes measured, test principle, analysis temperature, reaction type and sample type.
| Differences | | | |
| --- | --- | --- | --- |
| Item | S40 Clinical Analyzer S Test ALP Reagent | ACE plus ISE Clinical Chemistry System | Piccolo xpress Chemistry Analyzer |
| Sample Volume | 12 μL | 3 μL | 100 μL |
| Measuring Range | 1.2-9.9 mg/dL | 0.2-20 mg/dL | 0.2-20 mg/dL |
| Detection Limit | 1.2 mg/dL | 0.2 mg/dL | 0.2 mg/dL |
Uric Acid (UA):
The device and the predicate devices share a similar intended use, analytes measured, test principle, analysis temperature, reaction type and sample type.
| Differences | | | |
| --- | --- | --- | --- |
| Item | S40 Clinical Analyzer S Test ALP Reagent | ACE plus ISE Clinical Chemistry System | Piccolo xpress Chemistry Analyzer |
| Sample Volume | 12 μL | 3 μL | 100 μL |
| Measuring Range | 1.4-20.4 mg/dL | 0.9-16 mg/dL | 1-15 mg/dL |
| Detection Limit | 1.4 mg/dL | 0.9 mg/dL | 1 mg/dL |
{3}
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP5-A2: Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition (2004)
CLSI EP10-A: Preliminary Evaluation of Quantitative Clinical Laboratory Methods; Approved Guideline –Second Edition (2002)
CLSI EP6-A: Evaluation of Linearity of Quantitative Measurement Procedures, A Statistical Approach: Approved Guideline (2003)
CLSI EP7-A: Interference Testing in Clinical Chemistry; Approved Guideline (2002)
CLSI EP17-A: Protocols for Determination of Limits of Detection and Limits of Quantitation; Approved Guideline (2004)
CLSI EP9-A2: Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline (2002)
CLSI C28-A2: How to Define and Determine Reference Intervals in the Clinical Laboratory; Approved Guideline-Second Edition (2000), Section 8.2: Transference and Validation
L. Test Principle:
S Test IP – Inorganic Phosphorous in a sample under acidic conditions reacts with ammonium molybdate to form an unreduced phosphomolybdate complex. The rate of increase in absorbance at 600 nm/700 nm is directly proportional to phosphorous concentration in the sample.
S Test UA – Uric Acid in a sample is oxidized by uricase to allantoin and hydrogen peroxide. The hydrogen peroxide oxidizes and condenses 4-aminoantipyrine and n-ethyl-N-(2-hydroxy-3-sulopropyl)-m-touluidine under the influence of peroxidase to produce a reddish-purple pigment. The rate of increase at absorbance at 600/800 nm, is directly proportional to the uric acid concentration in the sample.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Precision studies were conducted in-house and at three Physician Office Laboratories (POL) (with three trained operators typically found in these settings) by testing three serum samples. The samples were run once a day, three times per run for five days using one instrument at each site. The results are presented below:
{4}
| | IP mg/dL | | | |
| --- | --- | --- | --- | --- |
| | | | %CV or SD (unit) | |
| Lab | Sample | Mean | Within Run | Total |
| In-House | 1 | 1.9 | 2.1% | 2.4% |
| POL 1 | 1 | 1.9 | 2.2% | 2.2% |
| POL 2 | 1 | 1.9 | 1.9% | 1.9% |
| POL 3 | 1 | 1.8 | 3.4% | 3.4% |
| | | | | |
| In-House | 2 | 4.1 | 1.9% | 2.1% |
| POL 1 | 2 | 4.2 | 1.4% | 1.5% |
| POL 2 | 2 | 4.1 | 1.2% | 1.3% |
| POL 3 | 2 | 4.1 | 1.5% | 1.8% |
| | | | | |
| In-House | 3 | 8.3 | 1.7% | 1.6% |
| POL 1 | 3 | 8.5 | 0.9% | 1.2% |
| POL 2 | 3 | 8.4 | 1.4% | 1.7% |
| POL 3 | 3 | 8.3 | 1.3% | 1.4% |
| | UA mg/dL | | | |
| | | | %CV or SD (unit) | |
| Lab | Sample | Mean | Within Run | Total |
| | | | | |
| In-House | 1 | 2.9 | 2.1% | 2.3% |
| POL 1 | 1 | 3.0 | 2.2% | 2.2% |
| POL 2 | 1 | 2.9 | 1.4% | 1.6% |
| POL 3 | 1 | 2.9 | 1.5% | 1.5% |
| | | | | |
| In-House | 2 | 6.0 | 2.2% | 2.2% |
| POL 1 | 2 | 6.2 | 1.3% | 1.3% |
| POL 2 | 2 | 6.1 | 0.7% | 0.7% |
| POL 3 | 2 | 6.1 | 1.0% | 1.2% |
| | | | | |
| In-House | 3 | 15.5 | 1.0% | 1.0% |
| POL 1 | 3 | 15.7 | 1.0% | 1.1% |
| POL 2 | 3 | 15.8 | 0.3% | 0.9% |
| POL 3 | 3 | 15.6 | 0.8% | 1.2% |
{5}
b. Linearity/assay reportable range:
Linearity across the assay range was confirmed by testing commercial linearity standards with 5 levels each with known concentrations of IP and UA. Each level was tested in replicates of four. Results are presented below:
| Inorganic Phosphorous | | | |
| --- | --- | --- | --- |
| Sample | Assigned Value mg/dL | Measured Value mg/dL | % Recovery |
| 1 | 0.71 | 0.90 | +0.2 mg/dL |
| 2 | 2.84 | 3.35 | +0.5 mg/dL |
| 3 | 5.67 | 5.70 | 100.5% |
| 4 | 7.09 | 7.63 | +0.5 mg/dL |
| 5 | 9.93 | 9.93 | 100% |
| Linear regression y = 0.9739x + 0.366, r² = 0.9928 | | | |
| Uric Acid | | | |
| 1 | 0.92 | 0.90 | 98% |
| 2 | 2.76 | 2.70 | 98% |
| 3 | 4.22 | 3.48 | -0.7 mg/dL% |
| 4 | 6.79 | 6.30 | -0.5 mg/dL |
| 5 | 11.64 | 11.35 | 98% |
| 6 | 16.49 | 16.03 | 97% |
| 7 | 20.39 | 20.38 | 100% |
| Linear regression y = 1.005x - 0.264, r² = 0.9984 | | | |
The reportable range is 1.2–9.9 mg/dL for Inorganic Phosphorous (IP) and 1.4–20.4 mg/dL for Uric Acid (UA).
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The S Test IP and S Test UA cartridges are factory calibrated and traceable to the NIST standard Reference materials 200a and 913a respectively. The 2-D barcode printed on each cartridge provides the analyzer with lot-specific calibration data.
Real time stability studies have been conducted. Protocols and acceptance criteria were described and found to be acceptable. When stored at 2-8 °C the assay reagent is good until the expiration date.
d. Detection limit:
The Limit of Blank and Limit of Detection were determined for each analyte by running a low sample and saline sample for 3 days, 20 replicates/day for a total of 60 results. The testing was split between two instruments. The limits of detection were determined to be 1.2 mg/dL for inorganic phosphorus and 1.4 mg/dL for uric acid.
{6}
# e. Analytical specificity:
Interference studies to determine the effects of Unconjugated Bilirubin, Hemolysis and Lipemia were performed. Seven serum pools containing approximately $3.6\mathrm{mg / dL}$ IP and $4.8\mathrm{mg / dL}$ UA were spiked with various concentrations of unconjugated bilirubin $(0 - 50\mathrm{mg / dL})$ , hemoglobin (0-1000 mg/dL) and Intralipids $(0 - 2000\mathrm{mg / dL})$ . Sponsor states that interference is considered to be significant if the analyte result is different from the control by $\pm 10\%$ .
IP - There was no significant interference from bilirubin. No significant interference of lipemia at concentration of 63,125 and $250\mathrm{mg / dl}$ . There was a positive interference of $(>17\%)$ at $500\mathrm{mg / dL}$ and above. Hemoglobin testing showed a positive interference $(>14\%)$ at all levels. The sponsor states that users should not use hemolyzed specimens.
UA - There was no significant interference from bilirubin. A positive interference at any level of hemoglobin was observed. The sponsor states that users should not use hemolyzed specimens. Intralipid of $250\mathrm{mg / dL}$ and above may cause interference. There was a positive interference of $(>14\%)$ at 500 $\mathrm{mg / dL}$ and above.
# f. Assay cut-off:
Not applicable
# 2. Comparison studies:
# a. Method comparison with predicate device:
Clinical correlation studies were performed comparing the S-Test IP and UA results generated on the S40 Clinical analyzer against the results from the ACE Clinical analyzer using 95 IP and 183 UA serum samples. Of the 95 IP samples (77 were unaltered clinical patient samples, 9 were dilutes and 9 were spiked samples) and 183 UA samples (143 were unaltered clinical patient samples, 16 were dilutes and 24 were spiked samples). All the samples were measure in singlet.
The correlation study between the device and the predicate for yielded the following results.
| Test | n | Slope | Intercept | r | Sample range (U/L) |
| --- | --- | --- | --- | --- | --- |
| S Test IP | 95 | 1.088 | 0.16 | 0.976 | 1.1-8.9 |
| S Test UA | 183 | 1.045 | -0.76 | 0.974 | 2.9-20.2 |
{7}
Performance for the S Test IP and S Test UA was evaluated at three Physician Office Laboratories with a total of three operators who are typical operators at these sites. Operators ran for IP 40-41 unaltered clinical serum samples, site one also ran 8 diluted and 7 spiked, site 2 ran 8 diluted and 9 spiked and site 3 ran 8 diluted and 8 spiked samples. The UA assay all sites ran 40 unaltered clinical samples, site 1 additional ran 9 diluted and 5 spiked, site 2 ran 8 diluted and 8 spiked and site 3 ran 8 dilutes and 6 spiked samples. The S Test IP and UA test results were compared to the ACE results. The correlation study between the device and the predicate for serum yielded the following results.
| | | n | Slope | Intercept | r | Sample range (U/L) |
| --- | --- | --- | --- | --- | --- | --- |
| IP | Lab A | 57 | 1.044 | 0.15 | 0.998 | 0.9- 8.9 |
| | Lab B | 56 | 1.053 | 0.19 | 0.995 | 1.0-9.1 |
| | Lab C | 56 | 1.101 | 0.16 | 0.992 | 1.2-8.4 |
| UA | Lab A | 54 | 1.062 | -1.03 | 0.995 | 2.6-17.6 |
| | Lab B | 56 | 1.016 | -0.60 | 0.992 | 3.0-18.9 |
| | Lab C | 54 | 1.085 | -0.18 | 0.967 | 2.8-14.7 |
# b. Matrix comparison:
A serum / plasma comparison test was performed for the S-Test IP and S-Test UA assays. Thirty- three paired IP and thirty-two paired UA samples were assayed on the S40 System. The IP comparison eight of the samples were spiked and one sample was diluted, and the UA comparison had 8 spiked samples to help cover the assay range. The correlation is as follows:
$\mathrm{IPy} = 1.043\mathrm{x} - 0.08,\mathrm{r} = 0.996$ range $1.2 - 9.5\mathrm{mg / dL}$
UA $y = 1.052 - 0.21$ , $r = 0.9975$ , range $1.7 - 17.1 \, \mathrm{mg/dL}$
# 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):
Not applicable
{8}
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Eighty-one (81) normal serum samples for IP and UA were evaluated on the S40 Clinical Analyzer to determine if the reference ranges of the predicate (ACE Clinical Analyzer) could be transferred to the new assays. The sponsors' acceptance criterion is 90% of the assay results for the normal samples are within the predicate range. Analysis confirmed sufficient agreement (9.9% IP and 2.4% UA non-congruent results, sponsor specification ≤10%) to transfer the reference range.
IP – 2.7-4.5 mg/dL
UA – 2.6-7.2 mg/dL (3.5-7.2 male and 2.6-6.0 female)
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
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.