K261379 · BD Diagnostic Solutions / Becton, Dickinson & Company · QVF · Oct 27, 2026 · Microbiology
Device Facts
Record ID
K261379
Device Name
BD Veritor System for SARS-CoV-2
Applicant
BD Diagnostic Solutions / Becton, Dickinson & Company
Product Code
QVF · Microbiology
Decision Date
Oct 27, 2026
Decision
SESE
Submission Type
Dual Track
Regulation
21 CFR 866.3982
Device Class
Class 2
Indications for Use
The BD Veritor™ System for SARS-CoV-2 is a chromatographic digital immunoassay for the rapid, qualitative detection of SARS-CoV-2 nucleocapsid protein antigens directly in anterior nasal swab specimens from individuals with signs and symptoms of upper respiratory infection (i.e., symptomatic). The test is intended for use as an aid in the diagnosis of SARS-CoV-2 infections (COVID-19) in symptomatic individuals when either: tested at least twice over three days with at least 48 hours between tests; or when tested once, and negative by the BD Veritor™ System for SARS-CoV-2 and followed up with a molecular test. A negative test result is presumptive, and does not preclude SARS-CoV-2 infection; it is recommended these results be confirmed by a molecular SARS-CoV-2 assay. Positive results do not rule out co-infection with other bacteria or viruses and should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Performance characteristics for SARS-CoV-2 were established between April 2024 and August 2024 when SARS-CoV-2 Omicron was the predominant SARS-CoV-2 variant in circulation. Performance characteristics may vary with newly emerging SARS-CoV-2 virus variants.
Device Story
Lateral flow immunochromatographic assay; detects SARS-CoV-2 nucleocapsid antigens in anterior nasal swabs. Sample processed in extraction buffer; applied to test cassette. BD Veritor Plus Analyzer (opto-electronic instrument) scans test strip; measures reflectance at specific zones (test, control, background). Proprietary algorithm subtracts nonspecific signal at negative control line from test line signal; compares result to cutoff. Instrument provides objective qualitative result (Positive/Negative/Invalid) on LCD. Used in laboratory or near-patient settings by healthcare providers. Enables rapid diagnosis; aids clinical management; requires molecular confirmation for negative results.
Clinical Evidence
Bench testing only. Specimen stability study evaluated negative and low-positive (2x LoD) samples across various temperatures (4°C, 30°C, 35°C, -20°C) and durations up to 26.4 hours. All samples yielded expected results (0/5 negative, 5/5 positive).
Technological Characteristics
Lateral flow immunochromatography; nitrocellulose membrane; colloidal gold nanoparticle conjugates. Reflectance-based opto-electronic measurement. Powered by Li-ion battery/wall transformer. Software-controlled interpretation via BD Veritor Plus Analyzer (firmware V6.10+). Standards: ISO 14971, ISO 20417, ISO 15223-1, CLSI EP25.
Indications for Use
Indicated for symptomatic individuals with signs of upper respiratory infection to aid in COVID-19 diagnosis. Requires serial testing (twice over 3 days, 48 hours apart) or single test followed by molecular confirmation if negative. Presumptive negative results; positive results do not rule out co-infection.
Regulatory Classification
Identification
The Sofia 2 SARS Antigen+ FIA is a lateral flow immunofluorescent sandwich assay used with the Sofia 2 instrument for the rapid, qualitative detection of SARS-CoV-2 nucleocapsid protein antigens directly in anterior nasal swab specimens from symptomatic individuals. It is intended as an aid in the diagnosis of SARS-CoV-2 infections (COVID-19) in symptomatic individuals when tested at least twice over three days with at least 48 hours between tests.
{1}
U.S. FOOD & DRUG
ADMINISTRATION
### 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
### DECISION SUMMARY
### ASSAY AND INSTRUMENT
### I Background Information:
A 510(k) Number
K261379
B Applicant
Becton, Dickinson and Company
C Proprietary and Established Names
BD Veritor System for SARS-CoV-2
D Regulatory Information
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QVF | Class II | 21 CFR 866.3982 Simple point-of-care device to directly detect SARS-CoV-2 viral targets from clinical specimens in near-patient settings | Microbiology |
### II Submission/Device Overview:
A Purpose for Submission:
To extend the specimen stability claim of BD Veritor System for SARS-CoV-2, cleared under K243872
B Measurand:
SARS-CoV-2 nucleocapsid antigens
C Type of Test:
Lateral flow immunochromatography
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{2}
### III Intended Use/Indications for Use:
#### A Intended Use(s):
See Indications for Use below.
#### B Indication(s) for Use:
The BD Veritor System for SARS-CoV-2 is a chromatographic digital immunoassay for the rapid, qualitative detection of SARS-CoV-2 nucleocapsid protein antigens directly in anterior nasal swab specimens from individuals with signs and symptoms of upper respiratory infection (i.e., symptomatic). The test is intended for use as an aid in the diagnosis of SARS-CoV-2 infections (COVID-19) in symptomatic individuals when either: tested at least twice over three days with at least 48 hours between tests; or when tested once, and negative by the BD Veritor System for SARS-CoV-2 and followed up with a molecular test.
A negative test result is presumptive and does not preclude SARS-CoV-2 infection; it is recommended these results be confirmed by a molecular SARS-CoV-2 assay.
Positive results do not rule out co-infection with other bacteria or viruses and should not be used as the sole basis for diagnosis, treatment, or other patient management decisions.
Performance characteristics for SARS-CoV-2 were established between April 2024 and August 2024 when SARS-CoV-2 Omicron was the predominant SARS-CoV-2 variant in circulation. Performance characteristics may vary with newly emerging SARS-CoV-2 virus variants.
#### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
IVD - For In Vitro Diagnostic Use Only
#### D Special Instrument Requirements:
The BD Veritor System for SARS-CoV-2 test is intended for use with the BD Veritor Plus Analyzer (hardware V2.00/firmware V6.10 or later).
### IV Device/System Characteristics:
#### A Device Description:
The BD Veritor System for SARS-CoV-2 is a rapid (approximately 15 minutes) qualitative chromatographic digital immunoassay for the direct detection of nucleocapsid protein antigens from SARS-CoV-2 in direct anterior nasal swab specimens collected from patients with signs and symptoms of COVID-19 by a healthcare provider. The test is intended for interpretation in laboratory and near patient testing environments only with the BD Veritor Plus Analyzer Instrument. The test is not intended to be interpreted visually.
The test package is composed of:
- 30 Test cassettes
K261379 - Page 2 of 10
{3}
• 30 Extraction reagent tubes
• 30 Specimen sampling swabs
- 1 SARS-CoV-2 (+) control swab (individually wrapped, single use control swab containing non-infectious, recombinant viral protein antigen with less than 0.1% sodium azide)
- 1 SARS-CoV-2 (-) control swab (individually wrapped, single use control swab containing buffer with less than 0.1% sodium azide)
• 1 Tube tray
• 1 Instructions for Use
• 1 Quick Reference Guide
### B Principle of Operation:
The test device is composed of a plastic housing, known as a cassette, that contains a test strip with the following parts: sample pad, conjugate pad, nitrocellulose membrane, and absorption pad. The patient sample is placed in the tube containing extraction buffer, where the virus particles in the sample are disrupted, exposing internal viral nucleoproteins. After disruption, the sample is dispensed into the sample well of the cassette.
When specimens are processed and added to the test device, SARS-CoV-2 antigens present in the specimen bind to biotinylated antibodies and antibodies conjugated to detector particles, colloidal gold nanoparticles, in the test strip. The biotinylated antibody-antigen-conjugate complexes migrate across the test strip to the reaction area and are captured by a line of streptavidin bound on the membrane.

Figure 1: Test device
The assay is only intended for use with an opto-electronic interpretation instrument, the BD Veritor Plus Analyzer Instrument and is not interpreted visually. The analyzer measures the amount of light reflected from various zones along the assay strip. The measurement of the assay background zone is an important factor during the test interpretation as the reflectance value is compared to that of the control and test zones. The instrument analyzes the reflectance data to provide the proper test interpretation.
The BD Veritor test devices are designed with four spatially distinct reaction zones (Figure 2).
K261379 - Page 3 of 10
{4}

Figure 2: Reaction zones on the test device: positive control position (C), test line position for SARS-CoV-2 (T), negative control position, and background zone.
A positive result is determined by the analyzer when antigen-conjugate is deposited at the Test "T" position and a control conjugate is deposited at the Control "C" position on the assay device. Two of the four distinct zones on the test device, negative control and background, are not labeled. The active negative control feature in each test identifies and compensates for specimen-related, nonspecific signal generation. The remaining zone is used to measure the assay background. The analyzer automatically scans the test strip, collects and analyzes the data, and then calculates and reports the result as either positive, negative, or invalid. The instrument analyzes and corrects for non-specific binding and detects positives not recognized by the unaided eye to provide an objective result. The analyzer uses a proprietary algorithm which subtracts nonspecific signal at the negative control line from the signal present at the test line. If the resultant test line signal is below the cutoff, the specimen is scored as negative. Use of the active negative control feature allows the BD Veritor System to correctly interpret test results that cannot be scored visually because the human eye is unable to accurately perform the subtraction of the nonspecific signal.

Figure 3: Test Device inserted into the BD Veritor Plus Analyzer
The analyzer is a portable, electronic instrument that uses a reflectance-based measurement method to evaluate line signal intensities on the assay test device. It applies assay-specific firmware algorithms to determine the presence or absence of target analyte(s). The analyzer is powered by a rechargeable Li-ion battery and compact wall transformer, is intended for tabletop or benchtop use, and follows the original BD Veritor instrument model of a calibration-free limited lifetime based on the number of tests performed, the number of days from first use, and/or the maximum shelf life from the date of manufacture. Procedures to evaluate test devices depend on the BD Veritor Plus Analyzer workflow configuration chosen. In Analyze Now mode, the instrument evaluates assay devices after manual timing of their development. In Walk Away mode, devices are inserted immediately after application of the specimen, and timing of assay development and analysis is automated. In either case, assay results are provided to the operator on the liquid crystal display (LCD) display screen. Additional result documentation capabilities
K261379 - Page 4 of 10
{5}
are possible with the use of a BD Veritor bar code scanning module, which can capture, display and/or integrate barcoded specimen, operator, or kit information in the test record.
# C Instrument Description Information:
1. Instrument Name:
BD Veritor Plus Analyzer (hardware V2.00/firmware V6.10 or later)
2. Specimen Identification:
Specimen IDs may be manually entered or scanned via the barcode scanner.
3. Specimen Sampling and Handling:
Anterior nasal swab samples are manually transferred to test kit reagent tubes for elution and drop-wise addition to the test cassette.
4. Calibration:
Not applicable
5. Quality Control:
The test includes a positive control to ensure adequate migration of the reagents through the test membrane to the desired test line locations for the reader. The test also contains a negative control to test for non-specific binding and a background region to measure assay background when calculating test line signal strength. 1 positive and 1 negative control swab are provided per kit. Additional external controls may also be purchased separately (BD Veritor SARS-CoV-2 Control Swabs). It is the manufacturer's recommendation that external quality controls be run after every new kit lot, when a new operator performs the test, a new shipment of test kits is received, and as required by local, state, and federal regulations. An analyzer verification cartridge is supplied to verify the BD Veritor Plus Analyzer is functioning within specifications.
# V Substantial Equivalence Information:
A Predicate Device Name(s):
BD Veritor System for SARS-CoV-2
B Predicate 510(k) Number(s):
K243872
K261379 - Page 5 of 10
{6}
C Comparison with Predicate(s):
| Device & Predicate Device(s): | CANDIDATE DEVICE K261379 | PREDICATE DEVICE K243872 |
| --- | --- | --- |
| Device Trade Name | BD Veritor System for SARS-CoV-2 | BD Veritor System for SARS-CoV-2 |
| **General Device Characteristic Similarities** | | |
| Intended Use/Indications For Use | The BD Veritor System for SARS-CoV-2 is a chromatographic digital immunoassay for the rapid, qualitative detection of SARS-CoV-2 nucleocapsid protein antigens directly in anterior nasal swab specimens from individuals with signs and symptoms of upper respiratory infection (i.e., symptomatic). The test is intended for use as an aid in the diagnosis of SARS-CoV-2 infections (COVID-19) in symptomatic individuals when either: tested at least twice over three days with at least 48 hours between tests; or when tested once, and negative by the BD Veritor System for SARS-CoV-2 and followed up with a molecular test. A negative test result is presumptive and does not preclude SARS-CoV-2 infection; it is recommended these results be confirmed by a molecular SARS-CoV-2 assay. Positive results do not rule out co-infection with other bacteria or viruses and should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Performance characteristics for SARS-CoV-2 were established between April 2024 and August 2024 when SARS-CoV-2 Omicron was the predominant SARS-CoV-2 variant in circulation. Performance characteristics may vary with newly emerging SARS-CoV-2 virus variants. | Same |
| Specimen type | Direct anterior nasal swab | Same |
K261379 - Page 6 of 10
{7}
| Device & Predicate Device(s): | CANDIDATE DEVICE K261379 | PREDICATE DEVICE K243872 |
| --- | --- | --- |
| Analyte | SARS-CoV-2 nucleocapsid protein | Same |
| Test Type | Lateral flow immunochromatographic | Same |
| Test Result Type | Qualitative | Same |
| Test Time | 15-20 minutes | Same |
| Analyzer | BD Veritor Plus Analyzer | Same |
| Results Interpretation | Instrument read - BD Veritor Plus Analyzer scans the test strip and analyzes the reflectance data to provide the proper test interpretation. The Analyzer displays the test results (Positive, Negative, or Invalid) on the screen. | Same |
# VI Standards/Guidance Documents Referenced:
| Document number | Title | Publishing Organization |
| --- | --- | --- |
| 14971 3^{rd} edition 2019-12 | Medical devices- Application of risk management to medical devices | ISO |
| 20417 1^{st} edition 2021-04, corrected version 2021-12 | Medical devices - Information to be supplied by the manufacturer | ISO |
| 15223-1 4^{th} edition 2021-07 | Medical devices- Symbols to be used with information to be supplied by the manufacturer- Part 1 | ISO |
| EP25 2^{nd} edition | Evaluation of Stability of In Vitro Medical Laboratory Test Reagents | CLSI |
# VII Performance Characteristics (if/when applicable):
# A Analytical Performance:
1. Precision/Reproducibility:
See Decision Summary for K243872.
2. Linearity:
This study is not applicable as this test device is a qualitative assay.
3. Analytical Specificity/Interference:
See Decision Summary for K243872.
K261379 - Page 7 of 10
{8}
#### 4. Assay Reportable Range:
This section is not applicable as this test device is a qualitative assay.
#### 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
See Decision Summary for K243872 for internal and external controls, reagent stability/shelf-life, and open-kit stability studies.
#### Specimen Stability Study:
Two test samples were prepared for the specimen stability study: a negative sample (i.e., negative clinical matrix (NCM) with no analyte), and a low positive sample (containing diluted SARS-CoV-2 at 2x LoD in NCM). Swabs were spiked with 50 \( \mu \) L of each sample, placed inside sterile containers, and transferred to a temperature chamber set to the specified temperatures for a specified duration of time summarized in the table below. The samples were extracted at room temperature where the extracted specimen (i.e. extraction tubes containing the extracted samples) were transferred to a temperature chamber set to the same specified temperature and stored in the chamber for the specified duration. Subsequently, the extracted sample swabs were tested using 5 replicates. Acceptable performance was observed at all time points tested as shown below.
Table 1: Specimen Stability Study Results
| Condition | Time (h) | NCM Positive/Total | SARS-CoV-2 Positive/Total |
| --- | --- | --- | --- |
| Room temperature (control) | 0 | 0/5 | 5/5 |
| 30°C | 0.4 | 0/5 | 5/5 |
| | 4 | 0/5 | 5/5 |
| | 24 | 0/5 | 5/5 |
| | 26.4 | 0/5 | 5/5 |
| 35°C | 4 | 0/5 | 5/5 |
| | 24 | 0/5 | 5/5 |
| | 26.4 | 0/5 | 5/5 |
| 4°C | 4 | 0/5 | 5/5 |
| | 24 | 0/5 | 5/5 |
| | 26.4 | 0/5 | 5/5 |
Formatted: Keep with next
K261379 - Page 8 of 10
{9}
| Condition | Time (h) | NCM Positive/Total | SARS-CoV-2 Positive/Total |
| --- | --- | --- | --- |
| -20°C | 4 | 0/5 | 5/5 |
| | 24 | 0/5 | 5/5 |
| | 26.4 | 0/5 | 5/5 |
Given that the device is intended for use in CLIA-waived environment, the freshly collected specimen should be processed as soon as possible after collection.
6. Detection Limit:
See Decision Summary for K243872.
7. High-Dose Hook Effect Study:
See Decision Summary for K243872.
8. Inclusivity (Analytical Reactivity):
See Decision Summary for K243872.
9. Assay Cut-Off:
See Decision Summary for K243872.
10. Accuracy (Instrument):
See Decision Summary for K243872.
11. Carry-Over:
See Decision Summary for K243872.
# B Comparison Studies:
1. Method Comparison with Predicate Device:
See Decision Summary for K243872.
2. Matrix Comparison:
See Decision Summary for K243872.
K261379 - Page 9 of 10
{10}
# **C Clinical Studies:**
1. Clinical Sensitivity:
See Decision Summary for K243872.
2. Clinical Specificity:
See Decision Summary for K243872.
3. Serial Testing:
See Decision Summary for K243872.
4. Clinical Cut-Off
This section is not applicable; there is no clinical cutoff related to the presence of SARS-CoV-2 in patient samples.
# **D Expected Values/Reference Range:**
A patient sample is expected to be negative for SARS-CoV-2.
# **VIII Proposed Labeling:**
The proposed 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.
K261379 - Page 10 of 10
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:
Guidance alerts
New and changed FDA guidance documents, emailed as a daily digest.
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 ? 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 as a Medical Device, 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 as a Medical Device), 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.