Peer-reviewed clinical literature; Routine clinical patient data (intraoperative monitoring)
The sponsor provided published clinical literature to support the new indication for intraoperative use of the Elecsys PTH and PTH STAT assays. These studies evaluated the assay's performance in patients undergoing parathyroidectomy in a clinical setting.
Intraoperative monitoring; Parathyroidectomy; Hyperparathyroidism; Clinical literature
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Ohe et al. (2006) - Arq Bras Endocrinol Metab; Retrospective analysis of clinical intraoperative data
Seehofer et al. (2001) - Langenbecks Arch Surg; Clinical evaluation of intraoperative PTH measurement
34 patients undergoing parathyroidectomy for renal hyperparathyroidism; Sample Size: 34
DPC Immulite assay and Nichols Quick PTH assay
>50% decrease from baseline levels
Seehofer et al. (2005) - Langenbecks Arch Surg; Clinical evaluation of intraoperative PTH measurement
153 patients undergoing parathyroid surgery for renal hyperparathyroidism; Sample Size: 153
Not applicable for this study
PTH level at 15 minutes 150 pg/mL or less; relative PTH decrease of 30% or less
Indications for Use
The Elecsys PTH Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia. The Elecsys PTH Immunoassay can be used intraoperatively. The Elecsys PTH STAT Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia. The Elecsys PTH STAT Immunoassay can be used intraoperatively.
Device Story
Two-step sandwich immunoassay using streptavidin microparticles and electrochemiluminescence (ECLIA) detection; measures intact parathyroid hormone (PTH) in human serum/plasma. Used on Elecsys and cobas e immunoassay analyzers in clinical laboratory settings. Input: patient serum/plasma sample. Transformation: automated sandwich formation with labeled antibodies; electrochemiluminescence signal generation proportional to analyte concentration. Output: quantitative PTH concentration (pg/mL). Results interpreted by clinicians alongside medical history and clinical findings to diagnose hypercalcemia/hypocalcemia or monitor intraoperative PTH levels. Benefits: rapid, accurate hormone quantification aiding clinical decision-making.
Clinical Evidence
Clinical evidence provided via three peer-reviewed studies (n=109, n=34, n=153) evaluating intraoperative PTH monitoring during parathyroidectomy. Primary endpoint: >50% decrease in PTH from baseline post-resection. Study 1 (n=109): 107/109 patients showed sufficient decay; 2/2 follow-up surgeries successful. Study 2 (n=34): 34/34 patients showed >50% decrease at 15 minutes. Study 3 (n=153): Mean PTH decay 81% at 15 minutes; assay successfully predicted surgical outcomes in renal hyperparathyroidism patients. Bench testing confirmed hemoglobin interference thresholds.
Technological Characteristics
Two-step sandwich immunoassay; electrochemiluminescence detection; streptavidin-coated microparticles. Analyzers: Elecsys 1010, 2010, MODULAR ANALYTICS E170, cobas e 411, cobas e 601. Measuring range: 1.20–5,000 pg/mL. Standardized against commercial RIA. No specific material standards or software architecture details provided.
Indications for Use
Indicated for in vitro quantitative determination of intact parathyroid hormone in human serum and plasma to aid differential diagnosis of hypercalcemia and hypocalcemia; can be used intraoperatively.
Regulatory Classification
Identification
A parathyroid hormone test system is a device intended to measure the levels of parathyroid hormone in serum and plasma. Measurements of parathyroid hormone levels are used in the differential diagnosis of hypercalcemia (abnormally high levels of calcium in the blood) and hypocalcemia (abnormally low levels of calcium in the blood) resulting from disorders of calcium metabolism.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k070709
B. Purpose for Submission:
Add an indication for use for intra-operative use and include hemoglobin interference information for both the Elecsys PTH Test System and the Elecsys PTH STAT Test System.
C. Measurand:
Intact parathyroid hormone
D. Type of Test:
Quantitative, electro-chemiluminescence (ECLIA) assay
E. Applicant:
Roche Diagnostics
F. Proprietary and Established Names:
Roche Diagnostics Elecsys PTH Test System
Roche Diagnostics Elecsys PTH STAT Test System
G. Regulatory Information:
1. Regulation section:
21CFR 862.1545 – Parathyroid hormone test system
2. Classification:
Class II
3. Product code:
CEW
4. Panel:
Chemistry (75)
{1}
H. Intended Use:
1. Intended use(s):
See Indications for Use below
2. Indication(s) for use:
The Elecsys PTH Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia. The Elecsys PTH Immunoassay can be used intraoperatively.
The Elecsys PTH STAT Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia. The Elecsys PTH STAT Immunoassay can be used intraoperatively.
3. Special conditions for use statement(s):
For prescription use only.
The sponsor has the following limitations in the Elecsys PTH Immunoassay regarding the hemoglobin interference:
Do not analyze samples that show visible signs of hemolysis.
The assay is affected by hemolysis > or equal to 0.10 g/dL. For PTH results < 50 pg/mL, hemolysis (Hg < 0.0932 mmol/L or ≥ 0.10 g/dL) can lead to a reduction by 3 to 5 pg/mL. For PTH results ≥ 50 pg/mL, hemolysis (Hg < 0.0932 mmol/L or ≥ 0.15 g/dL) affect the results by less than 10 percent.
The sponsor has the following limitations in the Elecsys PTH STAT Immunoassay regarding the hemoglobin interference:
Do not analyze samples that show visible signs of hemolysis.
The assay is affected by hemolysis > or equal to 0.25g/dL.
4. Special instrument requirements:
The Elecsys PTH Immunoassay can be used on the Elecsys 2010, MODULAR ANALYTICS E170, cobas e411 and cobas e601 analyzers.
The Elecsys PTH STAT Immunoassay can be used on the Elecsys 1010, 2010, cobas e411 analyzers.
2
{2}
I. Device Description:
Each cartridge of PTH or PTH STAT reagent consists of the following:
- Streptavidin-coated microparticles 0.72 mg/mL; preservative – in a 6.5 mL bottle with a transparent cap.
- Biotinylated monoclonal anti-PTH antibody (mouse) 2.3 mg/L; phosphate buffer 100 mmol/L, pH 7.0; preservative – in a 10 mL bottle with a gray cap.
- Monoclonal anti-PTH antibody (mouse) labeled with ruthenium complex 2.0 mg/L; phosphate buffer 100 mmol/L, pH 7.0; preservative – in a 10 mL bottle with a black cap.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Elecsys PTH Test System and Elecsys PTH STAT Test System
2. Predicate 510(k) number(s):
k992680, k070391
3. Comparison with predicate:
| Similarities and Differences between modified device and the predicate device)-k992680 | | | |
| --- | --- | --- | --- |
| Item | Elecsys PTH assay Predicate device (k992680) | Elecsys PTH assay (18 minutes appl.) Modified device | Elecsys STAT PTH assay (9 minutes appl.) Modified device |
| Indications for Use | Immunoassay for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia. | The Elecsys PTH Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia and can be used intraoperatively. | The Elecsys PTH STAT Immunoassay is for the in vitro quantitative determination of intact parathyroid hormone in human serum and plasma for the differential diagnosis of hypercalcemia and hypocalcemia and can be used intraoperatively. |
{3}
| Platform(s) | Elecsys 1010, 2010, Modular analytics E170, cobas e411 and cobas e601 analyzers. | Elecsys 2010, Modular analytics E170, cobas e411 and cobas e601 analyzers. | Elecsys 1010, 2010, cobas e411 analyzer |
| --- | --- | --- | --- |
| Assay Protocol | Sandwich assay | same | Same |
| Total assay duration | Elecsys 1010: 9 minute application Elecsys 2010, Modular analytics E170, cobas e411 and cobas e601 analyzers: 18 minute application | 18 minute | 9 minute |
| Detection Protocol | Electro-chemiluminescence | same | same |
| Sample Type | Human serum and plasma treated with K3-EDTA. | same | same |
| Calibrator | Elecsys PTH CalSet | Elecsys PTH CalSet | Elecsys PTH STAT CalSet |
| Measuring Range | 1.20-5,000 pg/mL | same | same |
| Analytical Sensitivity | 1.20 pg/mL | same | same |
| Analytical Specificity | No cross-reactivities were found for: Osteocalcin, PTH fragment 1-37, bone-specific alkaline phosphatase, and β-Crosslaps | same | same |
| Traceability | Standardized against a commercially available PTH test (RIA) | Standardized against a commercially available PTH test (RIA) | This method has been standardized against Elecsys PTH. This in turn was standardized against a commercially available PTH test (RIA) |
| Hook effect | No high dose hook effect at PTH concentrations up to 17,000 pg/mL | Same | Same |
| Limitations | Assay is unaffected by icterus (bilirubin <65 mg/dL), hemolysis (hemoglobin < 1.5 g/dL), lipemia (intralipid< 1500 mg/dL), Biotin <50 ng/mL, or RF < 1500 IU/mL. In patients receiving therapy with high biotin | Same for bilirubin, lipemia, biotin and RF. Labeling change to state: Do not analyze samples that show visible signs of hemolysis. Hemolysis ≥ 0.10 g/dL will have an affect on the assay. For PTH results < 50 pg/mL, | Same for bilirubin, lipemia, biotin and RF. Labeling change to state: Do not analyze samples that show visible signs of hemolysis. Hemolysis ≥ 0.25 g/dL will have an affect on the assay. |
| | intralipid < 1500 mg/dL | intralipid < 500 ng/mL | |
{4}
5
| | dose (i.e > 5mg/day), no sample should be taken until at least 8 hrs after the last biotin administration. | hemolysis (Hg < 0.0932 mmol/L or ≥ 0.10 g/dL) can lead to a reduction by 3 to 5 pg/mL. For PTH results ≥ 50 pg/mL, hemolysis (Hg < 0.0932 mmol/L or ≥ 0.15 g/dL) affect the results by less than 10 percent. | |
| --- | --- | --- | --- |
K. Standard/Guidance Document Referenced (if applicable):
None referenced
L. Test Principle:
The Elecsys PTH Assay is a two step sandwich immunoassay with streptavidin microparticles and electrochemiluminescence detection. Results are determined using a calibration curve that is generated specifically on each instrument by a 2 point calibration and a master curve provided with the reagent bar code. The assay time is 18 minutes.
The Elecsys PTH STAT Assay is a two step sandwich immunoassay with streptavidin microparticles and electrochemiluminescence detection. Results are determined using a calibration curve that is generated specifically on each instrument by a 2 point calibration and a master curve provided with the reagent bar code. The assay time is 9 minutes.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
There were no changes to the technology or the assay reaction time. See performance characteristics established in k992680 and k070391.
b. Linearity/assay reportable range:
There were no changes to the technology or the assay reaction time. See performance characteristics established in k992680 and k070391.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
There were no changes to the technology or the assay reaction time. See performance characteristics established in k992680 and k070391.
d. Detection limit:
There were no changes to the technology or the assay reaction time. See performance characteristics established in k992680 and k070391.
{5}
e. Analytical specificity:
Additional interference studies on hemoglobin were performed using the Elecsys PTH assay and Elecsys PTH STAT assay on the Elecsys 2010 analyzer.
For Elecsys PTH assay, 9 samples ranging from 13.6 to 854.0 pg/mL of PTH concentration were tested for the hemoglobin interference. The acceptance criterion is recovery ± 10% of the initial value. The sponsor claimed that the assay is affected by a reduction of 3 to 5 pg/mL with hemolysis ≥ 0.10 g/dL for PTH < 50 pg/mL and assay is affected by less than 10 percent with hemolysis ≥ 0.15 g/dL for PTH ≥ 50 pg/mL.
For Elecsys PTH STAT assay, 6 samples ranging from 19.9 to 372.0 pg/mL of PTH concentration were tested for the hemoglobin interference. The acceptance criterion is recovery ± 10% of the initial value. The sponsor claimed that the assay is affected by hemolysis ≥ 0.25 g/dL.
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
Performance characteristics were established in k992680
b. Matrix comparison:
Performance characteristics were established in k992680
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):
Published literature was provided to support the intraoperative claim 1,2,3. Studies were conducted on patients undergoing parathyroidectomy to evaluate the Elecsys PTH STAT assay (on Elecysy 1010 analyzer) and the Elecsys PTH assay (on Elecsys 2010 analyzer). The assay results were compared to clinical data and reported in the following peer reviewed journals:
{6}
1. Ohe, Monique Nakayama, Santos, Rodrigo Oliveira, Kunii, Ilda Shizue et al. "Usefulness of intra-operative PTH measurement in primary and secondary hyperparathyroidism: experience with 109 patients" Arq Bras Endocrinol Metab. 2006; 50 (5): 869-75.
2. Seehofer D, rayes N, Ulrich F, Muller C, Lang M, Neuhaus P, Steinmuller T. "Intra-operative measurement of intact parathyroid hormone in renal hyperparathyroidism by an inexpensive routine assay" Langenbecks Arch Surg. 2001; 386 (6): 440-3.
3. Seehofer D, Rayes N, Klupp J, Steinmuller T, Ulrich F, Muller C, Schindler R, Frei U, Neuhaus P. "Predictive value of intact parathyroid hormone measurement during surgery for renal hyperparathyroidism" Langenbecks Arch Surg. 2005; 390 (3): 222-9.
**Study#1:**
The study evaluated the Elecsys PTH assay for its intraoperative applicability in 109 patients with either a diagnosis of Primary Hyperparathyroidism (n=33), or Secondary Hyperparathyroidism due to renal disease (n=76). Of the latter cohort, 52 patients were on dialysis and 24 had a renal transplant. This study was conducted using the currently marketed Elecsys PTH STAT assay on the Elecsys 1010 instrument.
Blood samples were drawn after administration of anesthesia for baseline measurements and at 10 minutes and 20 minutes post resection of the parathyroid glands. The study used the generally accepted guidelines that a >50% decrease in PTH value from baseline suggests complete tumor removal. Of the 109 patients in the study group, 107 showed sufficient decrease by the second draw with an average decay of PTH of 79.2% of basal level within 10 minutes for the primary hyperparathyroid group, and 83.8% of basal level by 20 minutes. Among the renal patients the decay averaged 85.8% of basal level by 10 minutes and 87.2% by 20 minutes. Among the renal transplant patients the average decay from baseline was 87.6% in 10 minutes and 89.8% from baseline in 20 minutes.
Two patients did not show the sufficient 50% drop by the second draw at 20 minutes and therefore were classified correctly as unsuccessful surgeries. However, in both cases a second surgery was required and both surgeries were successful based on the required decay of 50% of the PTH value.
The assay met the generally accepted criterion of a >50% decrease from baseline (before incision) with complete tumor removal for 107 out of 109 patients initially and 2 out of 2 patients in follow-up surgeries.
**Study #2:**
The study was conducted using the currently marketed Elecsys PTH assay on the Elecsys 2010 instrument. In total, 34 patients underwent parathyroidectomy surgery for renal hyperparathyroidism, 31 of which underwent subtotal parathyroidectomy and 3 total parathyroidectomy. The study was divided into two parts. The first part
{7}
used the first 12 patients to compare the Elecsys PTH assay with the DPC Immulite assay and the Nichols Quick PTH assay. The second part of the study tested the ability of the Elecsys PTH assay to be used intraoperatively using the criterion of a decrease of 50% from baseline as the guideline for designation of a successful surgery, and combined the remaining 22 patients tested with only the Elecsys PTH assay giving a total of 34 patients evaluated.
The results of the comparisons are as follows: The Elecsys PTH assay was compared to the DPC Immulite assay and showed a correlation coefficient of 0.997 with no significant differences. The Elecsys PTH assay was then compared to the Nichols Quick assay using the same samples and showed a correlation coefficient of 0.987 with no significant differences.
For the 34 patients evaluated for successful parathyroidectomies based on PTH values, 33 patients showed >50% decrease from baseline levels at 5 minutes. The average level of decrease was 74% of the baseline level at 5 minutes post resection. At 15 minutes post resection, all patients showed >50% with an average level decrease of 82% of baseline level.
The assay met the generally accepted criterion of a >50% decrease from baseline (before incision) with complete tumor removal in 34 out of 34 patients in this study.
Study #3:
In this study, the investigators used two successive criteria of PTH decrease at the 15 minute time point. The first criterion was a PTH level at 15 minutes 150 pg/mL or less. If this was not achieved, the second criterion of a relative PTH decrease of 30% or less was used.
153 patients underwent parathyroid surgery for renal hyperparathyroidism and had blood drawn both pre- (before preparation of the parathyroid glands) and post (15 minutes after completion of the parathyroid resection) resections of the parathyroid glands to determine the applicability of the Elecsys PTH assay to predict a successful resection. 123 patients underwent subtotal parathyroidectomy and 13 patients underwent total parathyroidectomy during initial surgeries. Of the 153 patients, 24 had normal kidney function after transplant and 129 suffered from terminal renal failure. The samples were assayed on the Elecsys 2010 instrument and the per cent decrease was calculated from the baseline measurements.
The mean PTH decay from baseline for all patients was 81% at 15 minutes (862 pg/ml to 167 pg/mL). All 24 patients with compensated renal failure had PTH levels decrease >50% predicting successful operations. Of the 129 patients with terminal renal failure, the Elecsys PTH test showed 114 patients met both criteria. Of these, 108 had a true decline in PTH with no postoperative hyperparathyroidism, and 6 had a false decline in PTH with no persistent hyperparathyroidism. On the other hand, 15 patients did not meet both criteria and in whom only 3 parathyroid glands were found during surgery. Of these, 13 were classified as true failure to decline and 2 were classified as false failure to decline.
The assay met the generally accepted criterion of a >50% decrease from baseline with complete tumor removal.
{8}
4. Clinical cut-off:
Not Applicable
5. Expected values/Reference range:
Performance characteristics were established in k992680
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.