K193246 · Nova Biomedical Corporation · CHL · Jan 24, 2020 · Clinical Chemistry
Device Facts
Record ID
K193246
Device Name
Stat Profile Prime Plus Analyzer System
Applicant
Nova Biomedical Corporation
Product Code
CHL · Clinical Chemistry
Decision Date
Jan 24, 2020
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1120
Device Class
Class 2
Indications for Use
The Stat Profile Prime Plus Analyzer System is intended for use by healthcare professionals in clinical laboratory settings and for point-of-care usage for quantitative determination of pH, Partial Pressure of Carbon Dioxide (pCO2) and Partial Pressure of Oxygen (pO2) in heparinized arterial and venous whole blood. pH, pCO2 and pO2 Measurements are used in the diagnosis and treatment of life-threatening acid base disturbances.
Device Story
Stat Profile Prime Plus Analyzer is an automated blood gas analyzer for clinical laboratory and point-of-care (POC) use. Device accepts heparinized arterial or venous whole blood samples (135 μL) via syringe or open tube. System utilizes sensor cartridges (potentiometric for pH/pCO2; amperometric for pO2) to measure analytes. POC operators (nurses, respiratory therapists) perform analysis by scanning barcodes or manual touchscreen entry. Device provides quantitative results for pH, pCO2, and pO2, aiding clinicians in diagnosing and treating life-threatening acid-base disturbances. System includes onboard printer and internal/external quality control materials.
Clinical Evidence
Clinical performance was evaluated via a Point-of-Care (POC) study at three sites (CTICU, ED, Respiratory Therapy Lab) with 74 personnel. Method comparison (n=432 samples) against laboratory standards showed high correlation (r > 0.99 for pH, pO2, pCO2). Precision studies (within-run and total imprecision) using quality control materials and native whole blood demonstrated acceptable SD and %CV across all analytes, confirming performance consistency in POC environments.
Technological Characteristics
System utilizes electrochemical sensing: hydrogen ion-selective glass membrane (pH), Severinghaus-type gas permeable membrane (pCO2), and polarographic Clark-type cathode (pO2). Hardware includes a 10.1" WXGA touch screen, peristaltic pump with TPE tubing, and precision analog front-end with potentiometric/amperometric amplifiers. Connectivity includes integrated 1D/2D barcode scanner. System is modular with primary/auxiliary sensor cartridge slots. Calibration and quality control are managed via onboard QMS and dedicated cartridges.
Indications for Use
Indicated for healthcare professionals in clinical laboratory and point-of-care settings for quantitative determination of pH, pCO2, and pO2 in heparinized arterial and venous whole blood to diagnose and treat life-threatening acid-base disturbances.
Regulatory Classification
Identification
A blood gases (PCO2 , PO2 ) and blood pH test system is a device intended to measure certain gases in blood, serum, plasma or pH of blood, serum, and plasma. Measurements of blood gases (PCO2 , PO2 ) and blood pH are used in the diagnosis and treatment of life-threatening acid-base disturbances.
{0}
K193246 - Page 1 of 9
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
k193246
B Applicant
Nova Biomedical Corporation
C Proprietary and Established Names
Stat Profile Prime Plus Analyzer System
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CHL | Class II | 21 CFR 862.1120 - Blood gases (pCO₂, pO₂) and blood pH test system | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Modification of a previously cleared device (k173797) – modify the intended use of the device to include Point-of-Care (POC) use.
B Measurand:
pH, pO₂ and pCO₂.
C Type of Test:
pH and pCO₂ – quantitative, potentiometry
pO₂ – quantitative, amperometric technology
{1}
K193246 - Page 2 of 9
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
The Stat Profile Prime Plus Analyzer System is indicated for use by healthcare professionals in clinical laboratory settings and for point-of-care usage for quantitative determination of pH, Partial Pressure of Carbon Dioxide (pCO2), and Partial Pressure of Oxygen (pO2) in heparinized arterial and venous whole blood.
pH, pCO₂ and pO₂ measurements are used in the diagnosis and treatment of life-threatening acid base disturbances.
### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
For clinical laboratory and point of care use.
### D Special Instrument Requirements:
Stat Profile Prime Plus Analyzer System
## IV Device/System Characteristics:
### A Device Description:
The Stat Profile Prime Plus Analyzer System is a small automatic blood gas analyzer for laboratory and point of care setting. It consists of the analyzer, sensor cartridges, calibrator packs, auto-cartridge quality control packs (internal controls), ampule quality control materials (external controls) and thermal paper for an onboard printer. Specimens may be identified by scanning a barcode or by manually entering the information via the touchscreen.
The Stat Profile Prime Plus Analyzer has slots to accommodate two sensor cartridges (Primary and Auxiliary). The analyzer will determine the configuration of the system by detecting which sensor cards are installed. The reporting of CO-Oximeter parameters (or not reporting them) will also be determined by the selection of the Sensor Cards, for which there are two options:
- Primary Sensor Card 1 reports the following analytes: pO₂, pCO₂, pH, Hct, tHb, Na, Cl, K, iCa, iMg, Glu, SO₂, O₂Hb, COHb, MetHb, HHb, tBil, HbF
- Primary Sensor Card 2 reports the following analytes: pO₂, pCO₂, pH, Hct, tHb, Na, Cl, K, iCa, iMg, Glu, SO₂
{2}
B Principle of Operation:
pH: pH is measured using a hydrogen ion selective glass membrane. One side of the glass is in contact with a solution of constant pH. The other side is in contact with a solution of unknown pH. A change in potential develops which is proportional to the pH difference of these solutions. This change in potential is measured against a reference electrode of constant potential. The magnitude of the potential difference is a measure of the pH of the unknown sample.
pCO₂: pCO₂ is measured with a modified pH sensor. Carbon dioxide in the sample makes contact with a gas permeable membrane mounted on a combination measuring/ reference electrode. CO₂ diffuses across the membrane into a thin layer of electrolyte solution in response to partial pressure difference. This solution then becomes equilibrated with the external gas pressure. CO₂ in the solution becomes hydrated producing carbonic acid, which results in a change in hydrogen ion activity, according to the equation:
$$
\mathrm{CO}_{2} + \mathrm{H}_{2}\mathrm{O} \rightleftharpoons \mathrm{H}_{2}\mathrm{CO}_{3} \rightleftharpoons \mathrm{H}^{+} + [\mathrm{HCO}_{3}^{-}]
$$
The electrolyte solution behind the membrane is in contact with a glass hydrogen ion selective sensor. The change in hydrogen ion activity in the electrolyte solution produces a potential which is measured against the internal filling solution. This change in potential is measured against the constant potential of the reference electrode half-cell and is logarithmically related to the pCO₂ of the unknown sample.
pO₂: pO₂ is measured amperometrically by the generation of a current at the sensor surface. As oxygen diffuses through a gas permeable membrane, the oxygen molecules are reduced at the cathode, consuming 4 electrons for every molecule of oxygen reduced. This flow of electrons is then measured by the sensor and is directly proportional to the partial pressure of oxygen in the sample.
V Substantial Equivalence Information:
A Predicate Device Name(s): Stat Profile Prime Plus Analyzer System
B Predicate 510(k) Number(s): k173797
K193246 - Page 3 of 9
{3}
K193246 - Page 4 of 9
C Comparison with Predicate:
| Device & Predicate Device(s): | k193246 | k173797 |
| --- | --- | --- |
| Device Trade Name | Stat Profile Prime Plus Analyzer | Stat Profile Prime Plus Analyzer |
| General Device Characteristic Similarities | | |
| Intended Use/Indications for Use | For in vitro diagnostic use for the determination of pH, Partial Pressure of Carbon Dioxide, and Partial Pressure of Oxygen in heparinized arterial and venous whole blood. | Same |
| Acceptable Sample Types | Lithium heparin whole blood from syringes and open tubes. | Same |
| Sample Volume | 135 μL | Same |
| General Device Characteristic Differences | | |
| Settings for use | Clinical laboratories and point-of-care settings | Clinical laboratories |
VI Standards/Guidance Documents Referenced:
CLSI EP05-A2 – Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition.
IEC 61010-1:2010 – Safety Requirements for Electrical Equipment for Measurement, Control, and Laboratory Use - Part 1: General Requirements.
IEC 60601-1-2:2014 – Medical Electrical Equipment – Part 1-2: General Requirements for Basic Safety and Essential Performance – Collateral Standard: Electromagnetic Disturbances – Requirements and Tests.
VII Performance Characteristics:
A Analytical Performance:
1. Precision/Reproducibility:
Three separate studies were conducted to evaluate the precision of Stat Profile Prime Plus Analyzer for pH, pCO₂ and pO₂. The studies were conducted at three point of care (POC)
{4}
sites including a Cardiothoracic Intensive Care Unit, an Emergency Department and a Respiratory Therapy Lab. A total of 61 respiratory care, 12 nursing, and 1 exercise physiology POC personnel participated from the 3 POC settings over the course of the studies.
a) Within-Run Precision
Within-run precision of the Stat Profile Plus Analyzer System in the hands of POC operators was assessed using a combination of three levels of Quality Control (QC) material and two levels of linearity materials to cover the measuring range for each analyte. Each sample was analyzed in replicates of 20 using three Stat Profile Plus Analyzer Systems. All three POC sites produced similar results. Representative within-run precision results from one site are summarized in the table below:
Within Run Precision with Controls and Linearity Materials – one representative POC site
| Within-Run Precision | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Parameter | n=20 | Level 1 QC | Level 2 QC | Level 3 QC | Level 1 LN | Level 2 LN |
| pH | Mean | 7.227 | 7.420 | 7.616 | 6.754 | 7.726 |
| | SD | 0.008 | 0.003 | 0.006 | 0.012 | 0.004 |
| | % CV | 0.12 | 0.04 | 0.07 | 0.18 | 0.05 |
| pCO_{2} (mm Hg) | Mean | 63.2 | 38.9 | 20.2 | 118.6 | 18.7 |
| | SD | 2.2 | 0.7 | 0.2 | 3.9 | 0.1 |
| | % CV | 3.4 | 1.9 | 1.0 | 3.3 | 0.5 |
| pO_{2} (mm Hg) | Mean | 78.2 | 115.0 | 145.7 | 44.7 | 476.4 |
| | SD | 1.1 | 1.2 | 2.5 | 2.2 | 6.4 |
| | % CV | 1.5 | 1.0 | 1.7 | 4.9 | 1.3 |
b) Total Imprecision
Total imprecision of the Stat Profile Prime Plus Analyzer System in the hands of POC operators was assessed using three levels of QC materials and three Stat Profile Plus Analyzer Systems. For each run, each sample was run in duplicate each day for a total of 20 days (a total of 40 results on each of the three Stat Profile Prime Plus Analyzers). All three POC sites produced similar results. Representative total imprecision results from one site are summarized in the table below:
K193246 - Page 5 of 9
{5}
Total Imprecision – one representative POC site
| Level 1 QC | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | n | Mean | Within Run SD | Within Run %CV | Total SD | Total %CV |
| pH | 40 | 7.223 | 0.004 | - | 0.008 | - |
| pCO₂ (mmHg) | 40 | 60.0 | 1.6 | 2.6 | 3.6 | 5.9 |
| pO₂ (mmHg) | 40 | 76.5 | 1.3 | 1.6 | 2.4 | 3.1 |
| Level 2 QC | | | | | | |
| pH | 40 | 7.428 | 0.003 | - | 0.006 | - |
| pCO₂ (mmHg) | 40 | 37.2 | 1.1 | 3.0 | 2.3 | 6.1 |
| pO₂ (mmHg) | 40 | 112.2 | 1.6 | 1.4 | 3.0 | 2.6 |
| Level 3 QC | | | | | | |
| pH | 40 | 7.627 | 0.006 | - | 0.008 | - |
| pCO₂ (mmHg) | 40 | 20.1 | 0.6 | 3.1 | 1.0 | 4.8 |
| pO₂ (mmHg) | 40 | 148.9 | 1.6 | 1.1 | 3.4 | 2.3 |
c) Precision using whole blood samples
A whole blood within-run precision study was performed at three POC sites by two POC operators using one Stat Profile Prime Plus Analyzer System at each site. Five fresh, native arterial whole blood samples were analyzed in replicates of ten. Each whole blood specimen was maintained in a syringe for the duration of the testing. The POC operator performed all sample analysis steps including sample analysis, removal of resultant air bubble(s) from the syringe, recapping of the syringe and mixing prior to the next sample analysis. The results from each site are presented in the tables below.
Point of care site 1
| Analyte | Sample | N | Mean | SD | %CV |
| --- | --- | --- | --- | --- | --- |
| pH | 1 | 10 | 7.342 | 0.003 | - |
| | 2 | 10 | 7.389 | 0.005 | - |
| | 3 | 10 | 7.293 | 0.002 | - |
| | 4 | 10 | 7.384 | 0.002 | - |
| | 5 | 10 | 7.465 | 0.005 | - |
| pCO₂ (mmHg) | 1 | 10 | 44.3 | 1.59 | 3.58 |
| | 2 | 10 | 34.5 | 0.36 | 1.03 |
| | 3 | 10 | 37.7 | 0.27 | 0.71 |
| | 4 | 10 | 24.4 | 0.67 | 2.77 |
| | 5 | 10 | 27.9 | 0.24 | 0.85 |
| pO₂ (mmHg) | 1 | 10 | 41.8 | 0.23 | 0.56 |
| | 2 | 10 | 80.8 | 1.01 | 1.25 |
| | 3 | 10 | 338.2 | 13.48 | 3.98 |
| | 4 | 10 | 41.2 | 0.45 | 1.08 |
| | 5 | 10 | 150.1 | 5.04 | 3.36 |
K193246 - Page 6 of 9
{6}
Point of care site 2
| Analyte | Sample | N | Mean | SD | %CV |
| --- | --- | --- | --- | --- | --- |
| pH | 1 | 10 | 7.287 | 0.011 | - |
| | 2 | 10 | 7.282 | 0.003 | - |
| | 3 | 10 | 7.405 | 0.005 | - |
| | 4 | 10 | 7.347 | 0.006 | - |
| | 5 | 10 | 7.396 | 0.003 | - |
| pCO_{2} (mmHg) | 1 | 10 | 50.6 | 0.82 | 1.62 |
| | 2 | 10 | 19.7 | 0.26 | 1.31 |
| | 3 | 10 | 31.0 | 0.22 | 0.70 |
| | 4 | 10 | 38.2 | 0.33 | 0.86 |
| | 5 | 10 | 34.5 | 0.39 | 1.14 |
| pO_{2} (mmHg) | 1 | 10 | 57.9 | 0.46 | 0.80 |
| | 2 | 10 | 66.7 | 1.34 | 2.01 |
| | 3 | 10 | 91.4 | 1.72 | 1.88 |
| | 4 | 10 | 643.0 | 30.44 | 4.73 |
| | 5 | 10 | 84.0 | 1.62 | 1.93 |
Point of care site 3
| Analyte | Sample | N | Mean | SD | %CV |
| --- | --- | --- | --- | --- | --- |
| pH | 1 | 10 | 7.390 | 0.002 | - |
| | 2 | 10 | 7.287 | 0.002 | - |
| | 3 | 10 | 7.513 | 0.004 | - |
| | 4 | 10 | 7.230 | 0.002 | - |
| | 5 | 10 | 7.160 | 0.002 | - |
| pCO_{2} (mmHg) | 1 | 10 | 34.3 | 0.47 | 1.38 |
| | 2 | 10 | 48.9 | 0.69 | 1.40 |
| | 3 | 10 | 18.3 | 0.18 | 0.99 |
| | 4 | 10 | 50.3 | 0.99 | 1.97 |
| | 5 | 10 | 63.8 | 1.27 | 2.00 |
| pO_{2} (mmHg) | 1 | 10 | 101.7 | 0.61 | 0.60 |
| | 2 | 10 | 42.7 | 0.35 | 0.81 |
| | 3 | 10 | 147.4 | 2.12 | 1.44 |
| | 4 | 10 | 74.2 | 1.14 | 1.54 |
| | 5 | 10 | 44.7 | 0.34 | 0.75 |
2. Linearity:
Previously established in k173797.
3. Analytical Specificity/Interference:
Previously established in k173797.
4. Assay Reportable Range:
Previously established in k173797.
K193246 - Page 7 of 9
{7}
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Previously established in k173797.
6. Detection Limit:
Previously established in k173797.
7. Assay Cut-Off:
Not applicable.
## B Comparison Studies:
1. Method Comparison with Predicate Device:
Method comparison studies were conducted at three POC sites - a Cardiothoracic Intensive Care Unit, an Emergency Department and a Respiratory Therapy Lab. Lithium heparinized arterial and venous whole blood specimens were analyzed in singlet using three Stat Profile Prime Plus analyzers (one at each site) by 65 POC staff members (13, 21 and 31 POC staff members within each testing site, respectively, including a total of 52 respiratory care, 12 nursing, and 1 exercise physiology POC personnel). In order to cover the claimed measuring range for each analyte, less than 10% of samples for each analyte were altered. The clinical results obtained by POC staff members were compared to results obtained by trained healthcare professionals from the same whole blood specimens. Each of the three sites produced similar method comparison data. Linear regression analysis for venous and arterial whole blood method comparison for all POC sites combined is presented in the table below.
Venous and arterial whole blood method comparison – POC vs. Laboratory Operators (combined sites)
| Analyte | n | Sample concentration range | Slope | Intercept | r |
| --- | --- | --- | --- | --- | --- |
| pH | 432 | 6.832-7.931 | 0.9930 | 0.0050 | 0.9976 |
| pCO_{2} (mm Hg) | 432 | 14.0-199.2 | 0.9848 | 0.9958 | 0.9963 |
| pO_{2} (mm Hg) | 428 | 11.5-565.2 | 1.0109 | -1.5391 | 0.9989 |
2. Matrix Comparison:
Not applicable. The only acceptable sample type for this device is lithium heparin whole blood.
K193246 - Page 8 of 9
{8}
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable.
2. Clinical Specificity:
Not applicable.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
D Clinical Cut-Off:
Not applicable.
E Expected Values/Reference Range:
Reference ranges for pH, pCO₂ and pO₂ are cited from literature¹,²,³:
pH: 7.350 - 7.450 (pH units)
pCO₂: 35 - 45 mm Hg
pO₂: 83 - 108 mm Hg
1. Statland, Bernard, Clinical Decision Levels for Lab Tests, Medical Economics Books, 1987.
2. Burtis, Carl A. and Ashwood, Edward R., ed. 1994. Tietz Textbook of Clinical Chemistry, W. B. Saunders Co. Philadelphia, PA.
3. Tietz, Norbert W., ed. 1983. Clinical Guide to Laboratory Tests, W. B. Saunders Co., Philadelphia, PA.
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K193246 - Page 9 of 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.