The clinical performance of the device was supported by a cohort including retrospective serum and plasma samples, as well as prospective samples and clinically diagnosed patient samples, originally evaluated under K173376.
Clinical performance for detection of reagin antibodies
Indications for Use
The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Syphilis Analyzer, is a qualitative and semi-quantitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis. All reactive RPR test samples should be further tested with a treponemal test. The ASI Automated RPR Test for Syphilis is for professional use only. The test is intended to be used for in vitro diagnostic testing and blood donor screening. The ASI Evolution is intended to be used as a fully automated analyzer to objectively interpret the results of the ASI Automated RPR test for Syphilis. The ASI Evolution is designed to provide standardized test interpretation and to provide for storage, retrieval, and transmittal of the test results. It is intended to be acquired, possessed and used only by health care professionals. The ASI Evolution analyzer, in conjunction with the ASI Automated RPR Test for Syphilis is intended to be used for in vitro diagnostic testing and blood donor screening.
Device Story
Automated nontreponemal flocculation test for reagin antibodies; uses carbon-based antigen (cardiolipin, lecithin, cholesterol, charcoal). System automates sample/reagent handling, mixing, and timing in 48-well microtiter plates. Internal CCD camera captures high-resolution images via light reflectance; embedded software analyzes agglutination patterns. Instrument reports qualitative (reactive/non-reactive) and semi-quantitative endpoint titers. Used in clinical laboratories by healthcare professionals. Output provides objective, standardized results; replaces subjective visual interpretation. Benefits include reduced human error, standardized reporting, and efficient high-throughput processing.
Clinical Evidence
Clinical performance evaluated under K173376 using 1068 prospective serum samples, 10 retrospective serum samples, 1003 retrospective plasma samples, 143 syphilis patients, and 250 pregnant women. Analytical validation for semi-quantitative claims performed using a randomized, blinded panel of 10 human serum samples (titers 1:1 to 1:256) tested 80 times each. Results showed 100% agreement within one dilution of known titers (95% CI: 95.49% - 100%) and 100% agreement for non-reactive samples.
Technological Characteristics
Nontreponemal macroscopic flocculation test. Reagents: cardiolipin, lecithin, cholesterol, activated charcoal, phosphate buffer, sodium azide. Instrument: ASI Evolution (integrated digital particle analyzer). Sensing: CCD camera, light reflectance. Connectivity: PC-based software for data storage/retrieval. Software: Pattern recognition algorithm. Sterilization: N/A (reagents).
Indications for Use
Indicated for professional use in the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis, including blood donor screening. For prescription use only.
Regulatory Classification
Identification
Treponema pallidum nontreponemal test reagents are devices that consist of antigens derived from nontreponemal sources (sources not directly associated with treponemal organisms) and control sera (standardized sera with which test results are compared) used in serological tests to identify reagin, an antibody-like agent, which is produced from the reaction of treponema microorganisms with body tissues. The identification aids in the diagnosis of syphilis caused by microorganisms belonging to the genus Treponema and provides epidemiological information on syphilis.
Predicate Devices
Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System (K150358)
Submission Summary (Full Text)
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K182391
B. Purpose for Submission:
To expand the intended use of the ASI Automated RPR (rapid plasma reagin) Test for Syphilis performed on the ASI Evolution instrument, previously 510(k)-cleared under K173376, to include a semi-quantitative claim for the determination of reagin antibody endpoint titers in human serum and plasma samples.
C. Measurand:
Antibodies to plasma reagin (cellular lipids and lecithin).
D. Type of Test:
The ASI Automated RPR Test for Syphilis run on the ASI Evolution instrument is a nontreponemal flocculation test that is performed in a 48-well microtiter plate and interpreted by the ASI Evolution instrument using a high-resolution camera and embedded pattern recognition software algorithm that analyzes the algglutination pattern of each microtiter well.
E. Applicant:
Arlington Scientific, Inc.
F. Proprietary and Established Names:
ASI Automated RPR Test for Syphilis
ASI Evolution Automated Syphilis Analyzer
ASI Evolution
G. Regulatory Information:
1. Regulation Section:
21 CFR §866.3820 – Treponema pallidum nontreponemal test reagents
2. Classification:
Class II
{1}
3. Product Code(s):
GMQ – Antigens, nontreponemal, all
JQT – Densitometer/scanner (integrating, reflectance, TLC, or radiochromatogram) for clinical use
4. Panel:
Microbiology (83)
H. Intended Use:
1. Intended Use(s):
The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Syphilis Analyzer, is a qualitative and semi-quantitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis. All reactive RPR test samples should be further tested with a treponemal test.
The ASI Automated RPR Test for Syphilis is for professional use only. The test is intended to be used for in vitro diagnostic testing and blood donor screening.
The ASI Evolution is intended to be used as a fully automated analyzer to objectively interpret the results of the ASI Automated RPR Test for Syphilis. The ASI Evolution is designed to provide standardized test interpretation and to provide for storage, retrieval, and transmittal of the test results. It is intended to be acquired, possessed and used only by health care professionals. The ASI Evolution analyzer, in conjunction with the ASI Automated RPR Test for Syphilis is intended to be used for in vitro diagnostic testing and blood donor screening.
2. Indication(s) for Use:
Same as intended use
5. Special Conditions for Use Statement(s):
For prescription use only
6. Special Instrument Requirements:
ASI Evolution
{2}
I. Device Description:
1. Overview:
The ASI Automated RPR Test for Syphilis performed on the ASI Evolution is an automated nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma. Reagin antibodies, if present in human serum or plasma, bind to the carbon RPR test antigen which is composed of complexed cardiolipin, lecithin, and cholesterol particles in the presence of activated charcoal. Flocculation of the antibody-antigen complex and coagglutination with charcoal particles allows visualization of an agglutination pattern that is distinguishable from non-reactive test samples.
The ASI Evolution instrument provides full automation of the sample and reagent handling steps of the test procedure, and objective interpretation of test results via a high-resolution internal CCD camera and an embedded agglutination pattern recognition software. The ASI Evolution reports a qualitative test result (reactive or non-reactive) for each microtiter well and semi-quantitative endpoint titers of serially diluted samples.
Performance data supporting the qualitative claim for the ASI Automated RPR Test for Syphilis run on the ASI Evolution was previously submitted and reviewed by FDA under K173376. Detailed descriptions of the analytical and clinical study designs and test results which were conducted to support the qualitative claim are available in the K173376 decision summary document. Data presented in the sections below are limited to the studies that were required to demonstrate that the ASI Auotmated RPR Test for Syphilis run on the ASI Evolution can accurately determine semi-quantitative reagin antibody endpoint titers.
2. Materials Provided:
The ASI Automated RPR Test for Syphilis includes the following reagents:
- Carbon Antigen - 0.003% cardiolipin, 0.020–0.022% lecithin, 0.09% cholesterol, charcoal (activated) as visual enhancer, phosphate buffer, 0.1% sodium azide as preservative and stabilizers.
- Controls (Reactive, Weak Reactive, Non-reactive) - Human serum or defibrinated plasma (liquid), with 0.1% sodium azide as preservative.
3. Materials Required but Not Provided:
Additional materials required for the ASI Auotmated RPR Test for Syphilis but not provided include:
- Deionized water
- ASI Evolution instrument system
{3}
J. Substantial Equivalence Information:
1. Predicate Device Name(s):
Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System
2. Predicate 510(k) Number(s):
K150358
3. Comparison with Predicate:
Table 1: Device Similarities
| | Similarities | |
| --- | --- | --- |
| | Device | Predicate |
| Item | ASI Automated RPR Test for Syphilis on the ASI Evolution K182391 | Gold Standard Diagnostics AIX1000 RPR Automated Test System K150358 |
| Regulation | 866.3820 | Same |
| Product Code | GMQ | Same |
| Device Class | II | Same |
| Technology | Nontreponemal macroscopic flocculation test | Same |
| Antigen | cardiolipin, lecithin, and cholesterol with activated carbon | Same |
| Intended Use | The ASI Automated RPR (rapid plasma reagin) Test for Syphilis, for use on the ASI Evolution Automated Syphilis Analyzer, is a qualitative and semi-quantitative nontreponemal flocculation test for the detection of reagin antibodies in human serum and plasma as a screening test for serological evidence of syphilis. All reactive RPR test samples should be further tested with a treponemal test.
The ASI Automated RPR Test for Syphilis is for professional use only. The test is intended to be used for in vitro diagnostic testing and blood donor screening.
The ASI Evolution is intended to be used as a fully automated analyzer to | The Gold Standard Diagnostics AIX1000 Rapid Plasma Reagin (RPR) Automated Test System is a non-treponemal flocculation test that can qualitatively determine the presence of reagin antibodies in human serum. It may be used to aid in the diagnosis of syphilis when used in conjunction with supplemental treponemal laboratory tests and other clinical information. This test may also be used to detect non-treponemal antibodies in samples serially diluted to establish titer information. This test is not intended for screening blood or tissue donors. |
{4}
| | Similarities | |
| --- | --- | --- |
| | Device | Predicate |
| | objectively interpret the results of the ASI automated RPR Test for Syphilis. The ASI Evolution is designed to provide standardized test interpretation and to provide for storage, retrieval, and transmittal of the test results. It is intended to be acquired, possessed and used only by health care professionals. The ASI Evolution analyzer, in conjunction with the ASI Automated RPR Test for Syphilis is intended to be used for in vitro diagnostic testing and blood donor screening. | |
| Sample Processing | Automated | Same |
| Result Interpretation | Automated | Same |
| Test Format | 48-well microtiter plate | Same |
| Test Capacity | 192 samples | Same |
| Result Reporting | Qualitative, semi-quantitative titers | Same |
Table 2: Device Differences
| | Differences | |
| --- | --- | --- |
| | Device | Predicate |
| Item | ASI Automated RPR Test for Syphilis on the ASI Evolution K182391 | Gold Standard Diagnostics AIX1000 RPR Automated Test System 510(k)# K150358 |
| Sample Type | Serum or plasma | Serum only |
| Indications for use | Used for in vitro diagnostic testing and blood donor testing | Used for in vitro diagnostic testing only |
| Controls | Reactive, weak reactive, non-reactive | Reactive and non-reactive |
| Instrumentation and Software | ASI Evolution equipped with a CCD camera and proprietary pattern recognition algorithm | AIX1000 equipped with an HD camera and proprietary pattern recognition algorithm |
# K. Standard/Guidance Document Referenced (if applicable):
- EP012-A2. User Protocol for Evaluation of Qualitative Test Performance: Approved Guideline-Second Edition.
- EP05-A3. Evaluation of Precision of Quantitative Measurement Methods: Approved Guideline-Third Edition.
# L. Test Principle:
The ASI Automated RPR Test for Syphilis is a fully automated, high-throughput
{5}
macroscopic nontreponemal flocculation test that detects reagin antibodies in human serum or plasma samples. The test kit is intended to be used with the ASI Evolution system.
The ASI Evolution is an integrated digital particle analyzer designed to automate the sample and reagent handling steps of the test procedure and objectively interpret the test results of the ASI Automated RPR Test for Syphilis. The result is analyzed through an image processing algorithm from images taken with an internal CCD camera. The camera first takes high quality images of each well in the microtiter plates using light reflectance. The image is then analyzed by software developed with an optical recognition feature that identifies each well boundary to ensure it is in the correct position, and interprets the agglutination pattern to determine the sample result.
To complete the ASI Automated RPR Test for Syphilis the user must perform the following tasks:
- Load sample tubes into the sample rack
- Load the sample rack into the unit
- Refill the prime bottle with deionized water
- Place the reagent and diluent in their respective positions in the permanent rack
- Load and unload 48-well microtiter plates.
To complete the ASI Autotmated RPR Test for Syphilis the analyzer automates the following steps:
- Aspirate and dispense sample fluid and carbon RPR antigen
- Perform mixing of the reaction
- Time each procedural step appropriately
- Capture and record images of each completed test
- Process and store data of the test result image
- Report and record the qualitative and numerical results of each test.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
Analytical studies supporting the qualitative detection of reagin antibodies in human plasma and serum by the ASI Automated RPR Test for Syphilis performed on the ASI Evolution were previously submitted and reviewed under K173376. Details pertaining to the study protocols and resulting data are available in the K173376 decision summary document. In addition to the previously conducted studies, validation testing to support the semi-quantitative claim for the determination of reagin antibody endpoint titers in human serum and plasma was performed. A description of the study protocol and a summary of the test results are provided below.
### Endpoint Titer Validation
A randomized and blinded panel of 10 human serum samples with known reagin antibody endpoint titers, as determined by the ASI RPR Card Test for Syphilis on the ASiManager-AT, was tested with the ASI Automated RPR Test for Syphilis on the ASI Evolution using
{6}
the semi-quantitative test procedure. The reactive samples had titers ranging from 1:1 to 1:256. Each sample panel member was tested a minimum of 80 times, in-house, on at least five different days by one operator using a single ASI Evolution instrument. To meet the acceptance criteria, all non-reactive samples were required to yield non-reactive test results, while all reactive samples were required to yield test results within one dilution above or below the known titer. The results of the semi-quantitative analysis are shown below.
Table 3: Results from Endpoint Titer Validation Study
| Endpoint Titer Results | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample Reactivity | Non-reactive | Neat (1:1) | 1:2 | 1:4 | 1:8 | 1:16 | 1:32 | 1:64 | 1:128 | 1:256 | 1:512 | % Agreement within +/- 1 titer (95% C.I.) |
| 06127 (Non-reactive) | 80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| N8E23 (Non-reactive) | 80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| W6A16R (1:2) | 0 | 7 | 69 | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| W8B01R (1:2) | 0 | 0 | 75 | 5 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| R7F01R (1:8) | 0 | 0 | 0 | 0 | 76 | 4 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| R8B01R (1:8) | 0 | 0 | 0 | 32 | 48 | 0 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| 07117 (1:16) | 0 | 0 | 0 | 0 | 5 | 75 | 0 | 0 | 0 | 0 | 0 | 100% (95.49% - 100%) |
| 08188 (1:64) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 87 | 1 | 0 | 0 | 100% (95.89% - 100%) |
| 07098 (1:128) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5 | 82 | 1 | 0 | 100% (95.89% - 100%) |
| 08296 (1:256) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 21 | 65 | 4 | 100% (95.98% - 100%) |
Non-reactive test results were observed for all 160 non-reactive samples. In addition, all reactive samples produced test results that were within one dilution of the known reagin antibody titer for an overall percent agreement of 100%.
## 2. Comparison studies:
Method comparison with predicate device
Clinical performance of the ASI Automated RPR Test for Syphilis on the ASI Evolution for the qualitative claim was evaluated under K173376. The study cohort consisted of 1068 prospective serum samples, 10 retrospective serum samples, 1003 retrospective plasma samples, 143 clinically diagnosed syphilis patients, and 250 pregnant women. For additional details and study results, please refer to the K173376 decision summary document.
## N. Instrumentation/System Description
### 1. Instrument Name
{7}
ASI Evolution
## 2. System Description
The ASI Evolution instrument system is an integrated digital particle analyzer designed to objectively interpret certain slide agglutination tests manufactured by Arlington Scientific, Inc. (ASI). The system is capable of fully automating the sample and reagent handling steps of test procedures as well as digital acquisition and interpretation of agglutination patterns. This system design removes assay subjectivity, reduces errors, enables the review of past data, and speeds up the overall test procedure.
## 3. Software
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types: YES_X or NO_
a. Level of Concern
Moderate
b. Software Description
The software for the ASI Evolution instrument analyzes agglutination tests, which are interpreted through image processing algorithms from images taken with a CCD camera. The image results are passed to an integrated PC and software to provide an easy to use application for reviewing and distributing results.
The ASI Evolution software algorithm determines a “Reactive” or “Non-reactive” result based on the following criteria:
- If the numerical number is less than or equal to 50 the result is “Non-reactive.”
- If the numerical number is greater than or equal to 51, the test is “Reactive.”
The “Reactive” or “Non-reactive” outputs of the software determine the qualitative assay result. When running the semi-quantitative titer protocol, the software uses the same cutoffs described above to distinguish between a “Reactive” and “Non-reactive” sample well. The endpoint titer value is equivalent to the highest dilution at which the serially diluted sample produces a “Reactive” test result.
c. Specimen Identification
Barcode labeled patient samples can be imported with the use of a hand-held barcode scanner.
d. Specimen Sampling and Handling
{8}
e. Calibration
The firm included in their latest software build the ability to calibrate exposures per well using a grey intensity target (on empty wells). Users can verify that the grey intensity (shade) stays within the allowed range when the picture is taken.
f. Quality Control
Quality control is conducted using external reactive, weak-reactive and non-reactive controls that are provided with the ASI Automated RPR Test for Syphilis.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Not Applicable
Q. Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
R. Conclusion:
The information submitted in this premarket notification is complete and supports a substantial equivalence decision.
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.