DIMENSION VISTA A1AT FLEX REAGENT CARTRIDGE AND PROTEIN 1 CALIBRATOR AND CONTROL MEDIUM AND HIGH
K063610 · Dade Behring, Inc. · DEM · Jan 11, 2007 · Immunology
Device Facts
Record ID
K063610
Device Name
DIMENSION VISTA A1AT FLEX REAGENT CARTRIDGE AND PROTEIN 1 CALIBRATOR AND CONTROL MEDIUM AND HIGH
Applicant
Dade Behring, Inc.
Product Code
DEM · Immunology
Decision Date
Jan 11, 2007
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5130
Device Class
Class 2
Indications for Use
Dimension Vista™ A1AT Flex® reagent cartridge: The A1AT method is an in vitro diagnostic test for the quantitative determination of a - antitrypsin in human serum, heparinized plasma or EDTA plasma on the Dimension Vista® System. Measurements of a-antitrypsin aid in the diagnosis of cirrhosis of the liver and pulmonary emphysema. Dimension Vista™ Protein 1 Calibrator: PROT1 CAL is an in vitro diagnostic product for the calibration of the a1antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), Immunoglobulin A (IGA), Immunoglobulin G (IGG), Immunoglobulin M (IGM), and Prealbumin (PREALB) methods on the Dimension Vista® System. Dimension Vista™ Protein 1 Control L. M and H: PROT1 CON L, M and H are assayed intralaboratory quality controls for assessment of precision and analytical bias in the determination of α1-antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), immunoglobulin A (IGA), immunoglobulin G (IGG), immunoglobulin M (IGM), and prealbumin (PREALB) on the Dimension Vista® System.
Device Story
The Dimension Vista A1AT Flex reagent cartridge is an in vitro diagnostic test used on the Dimension Vista System. It measures alpha-1-antitrypsin (A1AT) concentrations in human serum or plasma samples. The device operates via an immunochemical reaction where proteins in the sample form immune complexes with specific antibodies; these complexes scatter light passed through the sample. The intensity of scattered light is proportional to the protein concentration, which is then evaluated against a known standard. The system includes a multi-analyte calibrator and assayed quality controls (L, M, H) to ensure precision and analytical bias assessment. The device is intended for use in clinical laboratory settings by trained personnel. Results assist healthcare providers in diagnosing liver cirrhosis and pulmonary emphysema.
Clinical Evidence
No clinical studies performed. Evidence consists of analytical bench testing: precision (within-lab CV 2.28-3.80%), linearity (0.17-5.20 g/L reportable range), and method comparison against predicate (n=139, slope 1.000, r=0.996). Interference testing performed per CLSI EP7-A.
Technological Characteristics
Immunonephelometry assay. Reagents: rabbit polyclonal antiserum to human A1AT, phosphate buffer, polyethylene glycol. Form factor: liquid reagent cartridge. Connectivity: integrated with Dimension VISTA system. Standardization: traceable to ERM-DA470. Storage: 2-8°C.
Indications for Use
Indicated for quantitative determination of alpha-1-antitrypsin in human serum, heparinized plasma, or EDTA plasma to aid in the diagnosis of adult cirrhosis of the liver and pulmonary emphysema.
Regulatory Classification
Identification
An alpha-1-antitrypsin immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the alpha-1-antitrypsin (a plasma protein) in serum, other body fluids, and tissues. The measurements aid in the diagnosis of several conditions including juvenile and adult cirrhosis of the liver. In addition, alpha-1-antitrypsin deficiency has been associated with pulmonary emphysema.
Predicate Devices
Dade Behring N Antisera to Human α1-antitrypsin assay (k053072)
N Protein Standard SL (k012470)
N/T Protein Control SL (k012468)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k063610
B. Purpose for Submission:
This is a new device.
C. Measurand:
Human $\alpha_{1}$ – antitrypsin
D. Type of Test:
Quantitative immunonephelometry
E. Applicant:
Dade Behring Inc.
F. Proprietary and Established Names:
Dimension VISTA™ $\alpha_{1}$ – antitrypsin Flex® reagent cartridge (A1AT)
Dimension VISTA™ Protein 1 Calibrator
Dimension VISTA™ Protein 1 Control L
Dimension VISTA™ Protein 1 Control M
Dimension VISTA™ Protein 1 Control H
G. Regulatory Information:
1. Regulation section:
21CFR§ 866.5130, Alpha-1-antitrypsin Immunological Test System.
21CFR§ 862.1660, Quality Control Material (Assayed and Unassayed)
21CFR§ 862.1150, Calibrator
2. Classification:
Device and calibrator - Class II
Quality control material - Class I
1. Product code:
DEM, Alpha-1-antitrypsin, Antigen, Antiserum, Control
JJY, Multi-Analyte Controls (Assayed and Unassayed)
JIX, Calibrator, Multi-Analyte Mixture
4. Panel:
Immunology (82)
Chemistry (75)
H. Intended Use:
1. Intended use(s):
Dimension VISTA™ $\alpha_{1}$ – antitrypsin Flex® reagent cartridge (A1AT)
The A1AT method is an *in vitro* diagnostic test for the quantitative determination of alpha-1-antitrypsin in human serum, heparinized plasma or EDTA plasma on the Dimension VISTA™ system. Measurements of alpha-1-antitrypsin aid in the diagnosis of adult cirrhosis of the liver and pulmonary emphysema.
Dimension VISTA™ Protein 1 Calibrator:
{1}
PROT1 CAL is an in vitro diagnostic product for the calibration of the $\alpha_{1}$ – antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), Immunoglobulin A (IGA), Immunoglobulin G (IGG), Immunoglobulin M (IGM), and Prealbumin (PREALB) methods on the Dimension VISTA™ system.
## Dimension VISTA™ Protein 1 Control L, M and H
PROT1 CON L, M and H are assayed intralaboratory quality controls for assessment of precision and analytical bias in the determination of the $\alpha_{1}$ – antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), Immunoglobulin A (IGA), Immunoglobulin G (IGG), Immunoglobulin M (IGM), and Prealbumin (PREALB) on the Dimension VISTA™ system.
2. Indication(s) for use:
Same as above
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
For use in the Dimension VISTA™ system (k051087)
## I. Device Description:
The Dimension VISTA™ $\alpha_{1}$ – antitrypsin Flex® reagent cartridge (A1AT) consists of N antiserum to human $\alpha_{1}$ – antitrypsin, and reaction buffer with phosphate buffer and polyethylene glycol. All reagents are liquid and ready to use.
PROT1 CAL is a multi-analyte, liquid, human serum based product containing $\alpha_{1}$ – antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), Immunoglobulin A (IGA), Immunoglobulin G (IGG), Immunoglobulin M (IGM), and Prealbumin (PREALB).
PROT1 CAL is ready for use.
Dimension VISTA™ Protein 1 Control L,M and H are multi-analyte; liquid human serum-based products containing $\alpha_{1}$ – antitrypsin (A1AT), C3 Complement (C3), C4 Complement (C4), Immunoglobulin A (IGA), Immunoglobulin G (IGG), Immunoglobulin M (IGM), and Prealbumin (PREALB). The controls are ready for use.
The other analytes in the calibrator and controls were cleared under the following premarket notifications: C3 and C4 (k061852), IgA (k061338), IgG (k051087), IgM (k061845) and Prealbumin (k062055)
The controls and calibrator are sold separately.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Dade Behring N Antisera to Human $\alpha_{1}$-antitrypsin assay
N Protein Standard SL
{2}
N/T Protein Control SL
2. Predicate 510(k) number(s):
k053072
k012470
k012468
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Dimension VISTA™α1 - antitrypsin Flex® reagent | N Antisera to α1 - antitrypsin |
| Indications for Use | Aid in the diagnosis of adult cirrhosis of the liver and pulmonary emphysema in conjunction with other clinical and laboratory findings. | Same |
| Methodology | Nephelometry | Same |
| Storage conditions | Refrigerate at 2-8°C until expired | Same |
| Standardization | Traceable to ERM® DA470 | Same |
| Antibody | Rabbit polyclonal | Same |
| Sample type | human serum, heparinized plasma or EDTA plasma | Same |
| Components | Controls and standards are sold separately. | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Analyzer | Dimension VISTA™ system. | BN™ Systems |
| Calibrator | Dimension VISTA™PROT1 CAL | N Protein Standard SL |
| Calibrator constituents | A1AT, C3, C4, IgA, IgG, IgM and prealbumin | IgG, IgG1, IgG2, IgG3, IgG4, IgA, IgM, albumin, A1AT, α2-macroglobulin, α1acid glycoprotein, haptoglobin, prealbumin, hemopexin, ceruloplasmin, retinol binding protein, Ig light-kappa, Ig light-chain Lambda, soluble transferrin receptor, |
{3}
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | | ferritin, β₂-microglobulin and total protein |
| Controls | Dimension VISTA™ PROT1Control L, M and H | N/T Protein control SL L, M and H |
| Control constituents | A1AT, C3, C4, IgA, IgG, IgM and prealbumin | IgG, IgG1, IgG2, IgG3, IgG4, IgA, IgM, albumin, A1AT, α₂-macroglobulin, α₁acid glycoprotein, haptoglobin, prealbumin, hemopexin, ceruloplasmin, retinol binding protein, Ig Light-kappa, Ig Light-chain Lambda, soluble transferrin receptor, ferritin, β₂-microglobulin and total protein |
| Reportable range | 0.17-5.20 g/L | 0.16-5.20 g/L |
K. Standard/Guidance Document Referenced (if applicable):
CLSI Approved Guideline for Evaluation of Precision Performance of Clinical Devices: EP5-A2
CLSI EP7-A, Interference testing in Clinical Chemistry
L. Test Principle:
Proteins contained in human body fluids form immune complexes in an immunochemical reaction with specific antibodies. These complexes scatter a beam of light passed through the sample. The intensity of the scattered light is proportional to the concentration of the respective protein in the sample. The result is evaluated by comparison with a standard of known concentration.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Precision testing was done in accordance with CLSI Approved Guideline for Evaluation of Precision Performance of Clinical Devices: EP5-A. Specimens with concentrations close to the reportable range were analyzed in duplicate, twice a day, for 20 days. The within-run and total standard deviations (SD) and percent coefficient of variation (%CV) were calculated by the analysis of variance method. The data are summarized below
{4}
| Material | Mean (g/L) | Repeatability | | Within-lab | |
| --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV |
| PROT1 Con L | 0.99 | 0.03 | 2.95 | 0.03 | 3.36 |
| PROT1 Con M | 1.42 | 0.04 | 3.09 | 0.05 | 3.27 |
| PROT1 Con H | 2.21 | 0.05 | 2.20 | 0.06 | 2.68 |
| Serum pool | 0.33 | 0.01 | 2.74 | 0.01 | 3.61 |
| Serum pool | 4.48 | 0.07 | 1.63 | 0.10 | 2.28 |
| Plasma pool | 1.23 | 0.02 | 1.72 | 0.05 | 3.80 |
# b. Linearity/assay reportable range:
Linearity testing was performed on the Dimension VISTA® System by testing a calibrator with a concentration of $1.48\mathrm{g / L}$ $\alpha_{1}$ - antitrypsin. The calibrator was serially diluted with system diluent at the following six dilutions 1:3.8, 1:8, 1:20, 1:40, 1:90 and 1:200. Each dilution was tested in replicates of three and a median is calculated. Data was analyzed using linear regression analysis (x-axis: theoretical concentration and y-axis: measured concentration). The acceptance criteria of slope between 0.9 and 1.1 and correlation coefficient $\geq 0.95$ were met. Data showed a regression equation $\mathrm{y} = 1.019\mathrm{x} - 0.029$ , $\mathrm{r}^2$ of 1.00.
Additional linearity study for the Vista A1AT assay was performed by testing a serum sample with a high concentration of A1AT. The sample was serially diluted with system diluent down to the lower measuring range (4.52 to $0.22\mathrm{g / L}$ ). Each dilution was tested in replicates of five. Data was analyzed using linear regression analysis (x-axis: theoretical concentration and y-axis: measured concentration). The acceptance criteria of slope between 0.9 and 1.1 and correlation coefficient $\geq 0.95$ were met. Data showed a regression equation $\mathrm{y} = 1.015\mathrm{x} - 0.043$ , $\mathrm{r}^2$ of 0.99.
Linearity was observed at 0.15 to $7.978\mathrm{g / L}$ . Reportable range for the device was set at 0.17 to $5.20\mathrm{g / L}$
# Prozone effect
The possibility of Prozone effect occurring when using the device was evaluated with a serum sample above the assay range (10.2 g/L). The sample was analyzed on both the BN Prospec System and the Dimension Vista instrument, indicating no hook effect up to 11.03 g/L.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The reference material is the ERM®-DA470 (CRM 470). Master Calibrator and Master Control concentrated human serum pool were assayed against this reference material. Commercial Calibrator and Control Lots were prepared from human serum pool at target concentrations and assayed against the master lot. Three reference curves, 4 runs, 3 vials, 4 replicates per vial tested on two instruments for
{5}
a total of 144 values were used before release of shipment.
Stability studies were performed and the following conclusions were obtained:
- On-Board Instrument Stability of opened product:
- a. The Dimension VISTA™α₁ – antitrypsin Flex® reagent cartridge is stable on-board the instrument for 21 days.
- b. PROT1 CAL is stable for 9 days.
- c. Controls are stable for 9 days.
Study duration is 24 months. Product is stored at 2-8°C throughout the testing cycle and tested on day 0 and after 12, 18, and 24 months.
- Sealed reagent cartridge on board instrument is stable up to 90 days.
- Open Punctured well:
- a. Once the vial stopper is punctured, assigned values of PROT1 CAL and PROT1 Con L, M and H is stable for 9 days.
d. Detection limit:
The analytical sensitivity of the assay represents the lowest concentration of analyte that can be distinguished from zero. The value was calculated as the mean value (n=20) of System diluent plus two standard deviations. This was found to be 0.016 g/L.
e. Analytical specificity:
Interference: Interference testing was performed using guidance supplied by CLSI EP7-A, "Interference testing in Clinical Chemistry". No significant interference was observed in:
- Hemoglobin up to 1000 mg/dL
- Bilirubin (conjugated and unconjugated) up to 60 mg/dL
- Triglycerides up to 637 mg/dL
- Immunoglobulin G up to 5000 mg/dL
- Protein: Albumin up to 6000 mg/dL
- Urea up to 500 mg/dL
- Cholesterol up to 500 mg/dL
- Creatinine up to 100 mg/dL
- Uric acid up to 20 mg/dL
Non Interfering Substance section of the package insert provides a list of drugs and other exogenous substances that do not interfere with the assay.
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
The table below shows the comparison of 66 serum samples and 73 plasma samples ranging from 0.23 to 4.71 g/L that were tested with the Dimension Vista™ α₁ – antitrypsin Flex® reagent cartridge (A1AT) and the predicate device Dade Behring N Antisera to Human α₁ – antitrypsin
6
{6}
assay. No information about age and gender was provided. The results were summarized below:
| | Dimension Vista vs. BN system(Dade-Behring) |
| --- | --- |
| Slope | 1.000(95% CI: 0.9853 to 1.0283) |
| Intercept | 0.070 (95% CI: 0.0346 to 0.0938) |
| Range (g/L) | 0.23to 4.71g /L |
| r | 0.996 |
| N | 139 |
b. Matrix comparison:
Matrix comparison studies using matched serum, EDTA, lithium and sodium heparinized plasma samples covering the measuring range were performed on the Dimension Vista™ $\alpha_{1}$ - antitrypsin Flex® assay. The results of the linear regression analyses are seen on the table below.
| | n | Slope (95% CI) | Intercept | Correlation Coefficient |
| --- | --- | --- | --- | --- |
| Serum vs. Lithium Heparin | 10 | 1.0 (0.968-1.02) | 0.02 | 0.999 |
| Serum vs. Sodium Heparin | 10 | 1.03 (1.008-1.05) | -0.02 | 0.999 |
| Serum vs. EDTA | 10 | 0.99 (0.976-1.00) | -0.01 | 1.00 |
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
4. Clinical cut-off: Not applicable
5. Expected values/Reference range:
The reported expected range for Immunoglobulin A in adults $(0.9 - 2.0\mathrm{g / L})$ is from a literature (Dati F. Schumann G, Thomas L, et al. Consensus of a Group of Professional Societies and Diagnostic Companies on Guidelines for Interim Reference Ranges for 14 Proteins in Serum base on the Standardization against the IFCC/BCR/CAP Reference Material (CRM 470). Eur J Clin Chem Biochem 34:517-520, 1996).
Each laboratory should establish its own normal ranges since values may differ depending on the population studied.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
{7}
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
8
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
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.