Patient samples were used in a split-sample method comparison study to evaluate the performance of the Dimension Vista Ammonia (AMM) assay against the predicate device.
The AMM method is an in vitro diagnostic test for the quantitative measurement of ammonia in human plasma on the Dimension Vista® System. Ammonia measurements are used in the diagnosis and treatment of severe liver disorders such as cirrhosis, hepatitis and Reye's syndrome. The CHEM 3 CAL is an in vitro diagnostic product for the calibration of Ammonia (AMM), Carbon Dioxide (CO₂) and Ethyl Alcohol (ETOH) methods on the Dimension Vista® System.
Device Story
Dimension Vista® Ammonia (AMM) Flex® reagent cartridge is an in vitro diagnostic device for quantitative ammonia measurement in human plasma. Input: lithium heparin or EDTA plasma samples. Principle: enzymatic bichromatic rate method using glutamate dehydrogenase (GLDH), α-ketoglutarate, and NADPH analog; reaction monitored at 340/700 nm. Output: ammonia concentration (μg/dL or μmol/L). Used in clinical laboratories on Siemens Dimension Vista® systems; operated by laboratory technicians. Healthcare providers use results to diagnose and monitor severe liver disorders. Benefits: rapid, automated quantitative assessment of ammonia levels to support clinical decision-making in liver disease management.
Clinical Evidence
Bench testing only. Precision evaluated per CLSI EP5-A2 (n=20 days, 2 runs/day). Linearity evaluated per CLSI EP6-A (range 0-1392 μg/dL). LoB, LoD, and LoQ determined per CLSI EP17-A. Method comparison (n=100) against predicate showed slope 1.03, intercept 13.6, r=0.993. Matrix comparison (n=49) between lithium heparin and EDTA plasma showed slope 0.96, intercept 3.3, r=1.00. Interference testing performed per CLSI EP7-A2.
Indicated for quantitative measurement of ammonia in human plasma for patients with suspected or diagnosed severe liver disorders, including cirrhosis, hepatitis, and Reye's syndrome.
Regulatory Classification
Identification
An ammonia test system is a device intended to measure ammonia levels in blood, serum, and plasma, Ammonia measurements are used in the diagnosis and treatment of severe liver disorders, such as cirrhosis, hepatitis, and Reye's syndrome.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k123677
B. Purpose for Submission:
New device
C. Measurand:
Ammonia
D. Type of Test:
Quantitative, Enzymatic
E. Applicant:
Siemens Healthcare Diagnostics, Inc.
F. Proprietary and Established Names:
Dimension Vista® Ammonia Flex® reagent cartridge (AMM)
Dimension Vista® Chem 3 Calibrator (CHEM 3 CAL)
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| JIF | I, reserved | 21 CFR 862.1065, Ammonia Test System | Chemistry (75) |
| JIX | II | 21 CFR 862.1150, Calibrator | Chemistry (75) |
H. Intended Use:
1. Intended use(s):
See Indications for Use below.
{1}
2. Indication(s) for use:
The AMM method is an *in vitro* diagnostic test for the quantitative measurement of ammonia in human plasma on the Dimension Vista® System. Ammonia measurements are used in the diagnosis and treatment of severe liver disorders such as cirrhosis, hepatitis and Reye's syndrome.
The CHEM 3 CAL is an *in vitro* diagnostic product for the calibration of Ammonia (AMM), Carbon Dioxide (CO₂) and Ethyl Alcohol (ETOH) methods on the Dimension Vista® System.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
For Use on Siemens Dimension Vista® systems only.
I. Device Description:
The Dimension Vista® Ammonia (AMM) Flex® reagent cartridge is an *in vitro* diagnostic device that consists of prepackaged reagents in a plastic cartridge for use on the Dimension Vista® System. Flex® reagent cartridges hold reagents for a test method. Each Dimension Vista® Flex has twelve wells. Each well contains α-ketoglutarate (10 mmol/L), GLDH (≥ 24 KU/L), NADPH (0.2 mmol/L) as well as buffers, stabilizers and preservatives. Reagent preparations are performed automatically on the instrument. A barcode label on the cartridge identifies the test method, lot number, expiration date and maximum number of tests for which the cartridge can supply reagent.
The Dimension Vista® Chemistry 3 Calibrator (CHEM 3 CAL) is a two level, liquid calibrator. It is packaged as a kit of six vials with three vials each of Level A and B, containing 2.5 mL per vial. The product is a multi-analyte, aqueous product containing ammonium bicarbonate, sodium carbonate and ethyl alcohol. CAL A is made by adding preservatives to purified water and CAL B is made by adding the calculated quantity of ammonium bicarbonate to purified water with preservatives, along with alcohol and sodium carbonate. This product is sold separately from the Flex® reagent cartridge.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Dimension® Ammonia (AMON)
Dimension Vista® Chemistry 3 Calibrator (CHEM 3 CAL)
2
{2}
2. Predicate 510(k) number(s):
k863840 (AMON)
k062334 (CHEM 3 CAL)
3. Comparison with predicate:
Dimension Vista® AMM assay:
| Similarities | | |
| --- | --- | --- |
| Item | Device Dimension Vista Ammonia Flex® reagent cartridge (AMM) | Predicate Dimension® Ammonia Flex® reagent cartridge (AMON) k863840 |
| Intended Use | An in vitro diagnostic test for the quantitative measurement of ammonia in human plasma. | Same |
| Format | Prepackaged for use on an automated system | Same |
| Measurement Principle | Bichromatic rate | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device Dimension Vista Ammonia Flex® reagent cartridge (AMM) | Predicate Dimension® Ammonia Flex® reagent cartridge (AMON) k863840 |
| Measuring Range | 17–1277 μg/dL | 0-1700 μg/dL |
| Sample Type | Plasma (Lithium Heparin and EDTA) | Plasma (EDTA, Lithium Heparin, Sodium Fluoride) |
| Reagent Form | Liquid | Tablet |
| Units | μg/dL and μmol/L | μmol/L |
| Sample Size | 20 μL | 53 μL |
{3}
Dimension Vista® CHEM 3 CAL:
| Similarities | | |
| --- | --- | --- |
| Item | Device Dimension Vista® Chem 3 Calibrator (CHEM 3 CAL) (KC130A) | Predicate Dimension Vista® Chem 3 Calibrator (CHEM 3 CAL) (KC130) k062334 |
| Intended Use | The CHEM 3 CAL is an in vitro diagnostic product for the calibration of Ammonia (AMM), Carbon Dioxide (CO2) and Ethyl Alcohol (ETOH) methods on the Dimension Vista® System. | Same |
| Preparation | Liquid: Ready to use | Same |
| Storage | 2 – 8 °C | Same |
| Traceability | AMM - ASC Grade Ammonium Sulfate ECO2 - NIST SRM 351 ETOH - USP Grade Ethyl Alcohol | Same |
| Matrix | Aqueous product containing ethyl alcohol, ammonium bicarbonate and sodium carbonate | Same |
| Target Concentrations | CO2: CAL A - 0 mmol/L CAL B - 50 mmol/L ETOH: CAL A - 0 mg/dL CAL B - 315 mg/dL | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device Dimension Vista® Chem 3 Calibrator (CHEM 3 CAL) (KC130A) | Predicate Dimension Vista® Chem 3 Calibrator (CHEM 3 CAL) (KC130) k062334 |
| Target Concentrations | Calibrator A: 0 μg/dL Calibrator B: 1405 μg/dL | Calibrator A: 0 μg/dL Calibrator B: 1700 μg/dL |
{4}
5
K. Standard/Guidance Document Referenced (if applicable):
- Clinical and Laboratory Standards Institute (CLSI) Guideline EP5-A2: Evaluation of Precision Performance of Quantitative Measurement in Methods
- CLSI Guideline EP6-A: Evaluation of the Linearity of Quantitative Measurement Procedures; A Statistical Approach
- CLSI Guideline EP7-A2: Interference Testing in Clinical Chemistry
- CLSI Guideline EP9-A2: Method Comparison and Bias Estimation Using Patient Samples
- CLSI Guideline EP17-A: Protocols for Determination of Limits of Detection and Quantitation
- CLSI Guideline C28-A3: Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory
- CLSI Guideline EP6-A: Evaluation of Stability of In-Vitro Diagnostic Reagents
L. Test Principle:
The Dimension Vista® Ammonia assay (AMM) is an enzymatic method that uses glutamate dehydrogenase (GLDH) and a stabilized NADPH analog. Ammonia reacts with α-ketoglutarate and reduced cofactor to form L-glutamate and the cofactor. The reaction is catalyzed by glutamate dehydrogenase. The decrease in absorbance due to the oxidation of the reduced cofactor is monitored at 340/700 nm and is proportional to the ammonia concentration.
$$
\alpha\text{-ketoglutarate} + \mathrm{NH_4^+} + \text{reduced cofactor} \xrightarrow{\text{GLDH}} \text{L-glutamate} + \text{cofactor} + \mathrm{H_2O}
$$
M. Performance Characteristics (if/when applicable):
The following performance data were collected on a Dimension Vista 1500 System.
1. Analytical performance:
a. Precision/Reproducibility:
Precision testing was performed in accordance with CLSI EP5-A2. Samples consisted of three levels of Bio-Rad® Liquichek™ Ethanol/Ammonia Control and represented clinically relevant ranges of normal and elevated ammonia levels in plasma. Testing was performed over 20 days, two separate runs with two test samples for each test material. Analysis of variance (ANOVA) was used to evaluate the data consistent with the recommendations of EP5-A2. The data are summarized in the following table:
{5}
| Material | Mean (μg/dL) | Repeatability | | Within Lab | |
| --- | --- | --- | --- | --- | --- |
| | | Standard Deviation | % CV | Standard Deviation | % CV |
| Level 1 | 44 | 2.7 | 6.1 | 3.3 | 7.5 |
| Level 2 | 186 | 2.3 | 1.2 | 3.2 | 1.7 |
| Level 3 | 563 | 3.5 | 0.6 | 5.0 | 0.9 |
b. Linearity/assay reportable range:
The linear range was determined according to CLSI EP-6A. Linearity testing was performed using commercial Dimension Vista® CHEM 3 CAL Level B (high level) and was diluted by sequential mixing with CHEM 3 CAL Level A (0 calibrator). Seventeen (17) levels were prepared and tested. The observed values in each case represent the mean of 5 replicates. The range of plasma samples tested was $0 - 1392\mu \mathrm{g / dL}$ . Linear regression results are summarized below.
| Slope | Intercept | Correlation Coefficient (r) |
| --- | --- | --- |
| 0.99 | 3.74 | 1.00 |
Based on the results of this testing and the Limit of Quantitation testing, the sponsor claims that the measurement range of the ammonia assay is 17 -1277 $\mu \mathrm{g} / \mathrm{dL}$ .
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
Ammonia in the CHEM 3 CAL calibrator is traceable to ACS grade ammonium sulfate by gravimetric method. $\mathrm{CO}_{2}$ is traceable to NIST SRM 351. Ethyl alcohol is traceable to US Pharmacopeia Grade ethyl alcohol.
Stability:
CHEM 3 Calibrator:
Calibrator shelf life is determined in real-time. Protocols and acceptance criteria were reviewed and determined to be acceptable. The testing supports the sponsor's claimed shelf life stability of 12 months when stored at $2 - 8^{\circ}\mathrm{C}$ .
Calibrator open and punctured vial stability are determined in real-time. Protocols and acceptance criteria were reviewed and determined to be acceptable. The testing supports the sponsor's claimed opened vial stability of 30 days when stored at $2 - 8^{\circ}\mathrm{C}$ , and punctured vial stability of 24 hours when stored on board the Dimension Vista instrument.
{6}
Storage Recommendations are provided in the package insert.
## Value Assignment:
CHEM 3 CAL calibrator is a two level calibrator product. Calibrator Level A is a nominal zero calibrator. Calibrator Level B is value assigned using standard for each analyte.
Ammonia – the assigned values for ammonia ethanol are based on results from multiple instruments and reagent lots. The ammonia assigned values for CHEM 3 CAL are the mean of a minimum of 45 replicates per level. Target ranges for ammonia are $0 \pm 15 \ \mu \mathrm{g} / \mathrm{dL}$ (LoD) for Level A and $1405 \pm 43 \ \mu \mathrm{g} / \mathrm{dL}$ for Level B.
$\mathrm{CO}_{2}$ – the assigned values for ethanol are based on results from 3 instruments, 3 reagent lots, and 3 sample pools for a total of 9 test runs. Each run generates 5 replicates per calibrator level; 45 total replicates per level. The $\mathrm{CO}_{2}$ assigned values for CHEM 3 CAL are the mean of a minimum of 30 replicates per level. Target ranges for $\mathrm{CO}_{2}$ are $0 \pm 5 \ \mathrm{mmol} / \mathrm{L}$ for Level A and $46 - 53 \ \mathrm{mmol} / \mathrm{L}$ for Level B.
Ethyl Alcohol – the assigned values for ethanol are based on results from 3 instruments, 3 reagent lots, and 3 sample pools for a total of 9 runs. Each run generates 5 replicates per calibrator level; 45 total replicates per level. The ethyl alcohol assigned values for CHEM 3 CAL Levels A and B are the mean of a minimum of 30 replicates per level. Target ranges for ethanol are $0 \pm 3 \ \mathrm{mg} / \mathrm{dL}$ for Level A and $307 - 322 \ \mathrm{mg} / \mathrm{dL}$ for Level B.
## d. Detection limit:
The LoB, LoD, and LoQ were evaluated in accordance with CLSI EP17-A. LoQ is defined as the value where inter-assay imprecision $< 20\%$ CV. The table below summarizes the protocol and provides the value for each limit.
| Limit | Protocol | Value |
| --- | --- | --- |
| LoB | 4 blank samples were tested for 3 days, 1 run per day, 2 replicates per run, 2 reagent lots, 1 instrument | 4 μg/dL |
| LoD | 4 low level ammonia samples were tested for 3 days, 1 run per day, 2 replicates per run, 2 reagent lots, 1 instrument | 15 μg/dL |
| LoQ | 3 low level samples diluted with purified water were tested for 3 days, 1 run per day, 3 replicates per run, 2 reagent lots, 1 instrument | 17 μg/dL |
{7}
# e. Analytical specificity:
The AMM method was evaluated for interference according to CLSI EP7-A2 guideline. Bias is the difference in the results between the control sample (without the interferent) and the test sample (contains the interferent) expressed in percent. Bias exceeding $10\%$ is considered significant interference. Testing was performed with two ammonia levels (85 and 426 $\mu \mathrm{g} / \mathrm{dL}$ ). The following substances do not cause significant interference ( $>10\%$ bias) with the AMM method when present in serum at the concentrations indicated.
| Interferent | Test concentration mg/dL |
| --- | --- |
| Acetaminophen | 20 |
| Amikacin | 8 |
| Ampicillin | 5. |
| Ascorbic acid | 6 |
| Caffeine | 6 |
| Carbamazepine | 3 |
| Cefoxitine | 0.3 |
| Chloramphenicol | 5 |
| Chlordiazepoxide | 1 |
| Chlorpromazine | 0.2 |
| Cimetidine | 2 |
| Diazepam | 0.5 |
| Digoxin | 0.61 |
| Erythromycin | 6 |
| Ethanol | 600 |
| Ethosuximide | 25 |
| Furosemide | 6 |
| Gentamicin | 1 |
| Heparin | 3.0 U/mL |
| Ibuprofen | 50 |
| Lidocaine | 1.2 |
| Lithium | 2.2 |
| Nicotine | 0.1 |
| Penicillin G | 25 U/mL |
| Pentobarbital | 8 |
| Phenobarbital | 10 |
| Phenytoin | 5 |
| Primidone | 4 |
| Propoxyphene | 0.16 |
| Protein, Total | 14,000 |
| Salicylic acid | 60 |
{8}
For Hemolysis, Icterus, and Lipemia (HIL) Interferences:
| Substance Tested | Substance Concentration | Ammonia concentration (μg/dL) | Bias (%) |
| --- | --- | --- | --- |
| Hemoglobin (hemolysate) | 75 mg/dL | 85 | +12 |
| | 500 mg/dL | 426 | +17 |
| Bilirubin (unconjugated) | 80 mg/dL | 85 | < 10 |
| | 80 mg/dL | 426 | < 10 |
| Bilirubin (conjugated) | 60 mg/dL | 85 | -16 |
| | 80 mg/dL | 426 | < 10 |
| Lipemia (Intralipid®) | 50 mg/dL | 85 | + 13 |
| | 50 mg/dL | 426 | < 10 |
The sponsor has the following limitations stated in the package insert:
Do not use hemolyzed samples. Bilirubin (conjugated) at 60 mg/dL decreases ammonia results by 16% at ammonia concentration of 85 μg/dL. Lipemia (Intralipid) at 50 mg/dL increases ammonia results by 13% at ammonia concentration of 85 μg/dL.
For some endogenous substances, the sponsor performed a dose-response study to evaluate interference using real patient sample pools that contained the interference substances. Non-significant interference was defined by having the observed recovery within 10% of expected value. The following substances did not cause >10% recovery at the concentrations tested.
| Substance Tested | Test concentration | Ammonia Concentration (μg/dL) |
| --- | --- | --- |
| Albumin | 5.4 g/dL | 182 |
| Cholesterol | 364 mg/dL | 232 |
| Creatinine | 31.1 mg/dL | 233 |
| Immunoglobulin G | 3.4 g/dL | 308 |
| Triglyceride | 1102 mg/dL | 354 |
| Uric Acid | 9.3 mg/dL | 196 |
{9}
f. Assay cut-off:
Not applicable.
# 2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study was performed between the Siemens Dimension Vista® Ammonia (AMM) assay and the predicate Siemens Dimension® Ammonia (AMON) method following the CLSI EP9-A2 guideline.
For this study, 100 excess, de-identified lithium heparin plasma samples containing measurable amounts of ammonia and were purchased from multiple vendors as well as supplemented by normal samples collected in-house and tested at an internal site. Samples were run in duplicate and the first replicate was used in the data analysis. The range of ammonia values in the comparison study was $19 - 1273\mu \mathrm{g / dL}$ . Least squares linear regression was performed and the results of the regression are summarized below.
| Device | Predicate | Slope | Intercept | Correlation Coefficient (r) | n |
| --- | --- | --- | --- | --- | --- |
| Dimension Vista® AMM | Dimension ® AMON | 1.03 | 13.6 | 0.993 | 100 |
b. Matrix comparison:
To demonstrate equivalency between lithium heparin plasma and EDTA plasma for Dimension Vista® AMM, comparison testing of 49 fresh matched lithium heparin and EDTA plasma samples was tested on the Dimension Vista® System. Samples were run in duplicate and the first replicate was used to compare AMM lithium heparin plasma versus EDTA plasma. The range of values in the comparison study was $39 - 1085\mu \mathrm{g / dL}$ . Least squares linear regression was used as the statistical method in the analysis of the data.
| Lithium Heparin Plasma vs. | Slope | Intercept | Correlation Coefficient (r) | n |
| --- | --- | --- | --- | --- |
| EDTA plasma | 0.96 | 3.3 | 1.00 | 49 |
# 3. Clinical studies:
a. Clinical Sensitivity:
{10}
Not applicable.
b. Clinical specificity:
Not applicable.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Expected Values: 19- 54 µg/dL¹
¹The literature reference used was the Textbook of Clinical Chemistry by NW Tietz; WB Saunders Co., Philadelphia, PA; pages 1487-1488.
The reference interval of 19- 54 µg/dL was also validated for use with the Dimension Vista® Ammonia (AMM) assay by transference following CLSI C28-A3. The sponsor performed a validation study using 30 healthy adults (15 male and 15 female) to confirm the reference interval.
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.
11
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.