Clinical throat swab specimens from symptomatic patients
The clinical study evaluated the diagnostic performance (sensitivity and specificity) of the Wondfo One Step Strep A Swab Test by comparing results against standard bacterial culture in a cohort of 349 symptomatic patients.
Prospective clinical evaluation comparing rapid test results to bacterial culture
Patients exhibiting symptoms of pharyngitis; Sample Size: 349
Bacterial culture (sheep blood agar plate)
Clinical sensitivity and specificity
Indications for Use
The Wondfo® Strep A Rapid Test is a chromatographic immunoassay for the qualitative detection of Strep A antigen from throat swab specimens from symptomatic patients to aid in the diagnosis of Group A Streptococcal infection. All negative test results should be confirmed by bacterial culture because negative results do not preclude Group A Strep infection and should not be used as the sole basis for treatment. This test is intended for professional and laboratory use, only.
Device Story
Wondfo One Step Strep A Swab Test is a lateral flow immunoassay for qualitative detection of Strep A carbohydrate antigen from throat swabs. Device uses extraction tube containing dried lytic enzyme and colloidal gold-conjugated rabbit anti-Strep A antibodies. Throat swab is inserted into tube with Reagent 1; antigen is extracted; test strip is immersed in extract. If Strep A antigen is present, it binds to gold-conjugated antibody; complex is captured by anti-Strep A antibody on strip, forming visible red test line. Onboard procedural control uses blue-to-red color change. Used in clinical/laboratory settings by professional operators. Results read visually after 10 minutes. Positive result indicates presence of Strep A antigen; negative results require culture confirmation. Device aids clinical diagnosis of Group A Streptococcal infection.
Clinical Evidence
Multicenter prospective clinical study (n=349) comparing device results to sheep blood agar culture. Sensitivity: 95.0% (95% CI: 88.9–97.9%); Specificity: 98.4% (95% CI: 95.9–99.4%). Performance stratified by age (0-5, 5-21, 21+).
Technological Characteristics
Lateral flow immunochromatographic assay. Materials: plastic housing, nitrocellulose membrane, rabbit polyclonal anti-Strep A (test line), goat anti-rabbit antibody (control line). Extraction reagents: 2.0 M sodium nitrite, 0.4 M acetic acid. Detection limit: 1.5 x 10^5 CFU/mL. No instrumentation required.
Indications for Use
Indicated for symptomatic patients presenting with pharyngitis to aid in the diagnosis of Group A Streptococcal infection via throat swab specimens.
Regulatory Classification
Identification
Streptococcus spp. serological reagents are devices that consist of antigens and antisera (excluding streptococcal exoenzyme reagents made from enzymes secreted by streptococci) used in serological tests to identify Streptococcus spp. from cultured isolates derived from clinical specimens. The identification aids in the diagnosis of diseases caused by bacteria belonging to the genus Streptococcus and provides epidemiological information on these diseases. Pathogenic streptococci are associated with infections, such as sore throat, impetigo (an infection characterized by small pustules on the skin), urinary tract infections, rheumatic fever, and kidney disease.
{0}
1
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY TEMPLATE
A. 510(k) Number:
K133343
B. Purpose for Submission:
To obtain substantial equivalence for the Wondfo® One Step Strep A Swab Test
C. Measurand:
Group A Streptococcal antigen
D. Type of Test:
Lateral Flow Immunochromatographic assay
E. Applicant:
Guangzhou Wondfo Biotech Co., Ltd.
F. Proprietary and Established Names:
Wondfo® One Step Strep A Swab Test
G. Regulatory Information:
1. Regulation section:
21 CFR 866.3740 – Streptococcus spp. Serological Reagents
2. Classification:
Class I
3. Product code:
GTY - Antigens, All Groups, Streptococcus spp.
4. Panel:
83 Microbiology
{1}
H. Intended Use:
1. Intended Use(s):
The Wondfo® Strep A Rapid Test is a chromatographic immunoassay for the qualitative detection of Strep A antigen from throat swab specimens from symptomatic patients to aid in the diagnosis of Group A Streptococcal infection. All negative test results should be confirmed by bacterial culture because negative results do not preclude Group A Strep infection and should not be used as the sole basis for treatment. This test is intended for professional and laboratory use, only.
2. Indication(s) for Use:
The Wondfo® Strep A Rapid Test is a chromatographic immunoassay for the qualitative detection of Strep A antigen from throat swab specimens from symptomatic patients to aid in the diagnosis of Group A Streptococcal infection. All negative test results should be confirmed by bacterial culture because negative results do not preclude Group A Strep infection and should not be used as the sole basis for treatment. This test is intended for professional and laboratory use, only.
3. Special conditions for use statement(s):
For in vitro diagnostic use only
For prescription use only
4. Special instrument requirements:
None
I. Device Description:
The Wondfo® One Step Strep A Swab Test is a qualitative, lateral flow immunoassay for the detection of Strep A carbohydrate antigen directly from a throat swab sample. To perform the test, Reagent 1 (R1) is added to the extraction tube which is coated with a mixture of conjugate antibodies and a lytic enzyme extraction reagent. The lytic enzyme is mixed with colloidal gold conjugated to rabbit anti-Strep A and a second colloidal gold control conjugate antibody. The reagents are dried onto the bottom of an extraction tube forming a red spot. The extraction/conjugate pellet is re-suspended with R1 and the throat swab is added to the extraction tube. The Strep A antigen is extracted from the sample and the swab is removed. The test strip is immediately placed in the extracted sample. If Group A Streptococcus is present in the sample, it will react with the anti-Strep A antibody conjugated to the gold particle. The complex will then be bound by the anti-Strep A capture antibody and a visible red test line will appear, indicating a positive result. To serve as an onboard procedural control, the blue line observed at the control site prior to running the assay will turn red, indicating that the test has been performed properly. If Strep A antigen is not present, or
2
{2}
present at very low levels, only a red control line will appear. If the red control line does not appear, or remains blue, the test result is invalid.
## Materials provided:
- 25 individual sealed pouches, each containing:
- Test device (Strip)
- Desiccant pouch
- 25 extraction tubes
- 25 throat swabs
- Extraction Reagent A (5mL): 2.0 M sodium nitrite solution (Warning: R25Toxic if swallowed)
- Extraction Reagent B (5mL): 0.4M acetic acid solution
- Standard controls:
- Positive control (0.5 mL): Extracted (non-infective) group A streptococcus antigen in phosphate buffer containing 0.1% NaN3. (Warning: R22 Harmful if swallowed)
- Negative control (0.5 mL): Phosphate buffer containing 0.1% NaN3 (Warning:R22 Harmful if swallowed)
- Leaflet with instructions for use
## Materials required but not provided
- Timer
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Status First™ Strep A
2. Predicate 510(k) number(s):
K040708
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device (K133343) | Predicate (K040708) |
| Intended Use | For the qualitative detection of group A streptococcal antigen directly from throat swabs | Same |
| Specimen Type | Throat swab | Same |
| Assay Technology | Immunochromatographic | Same |
| Test Antibodies | Rabbit polyclonal anti-Strep A | Same |
{3}
| Similarities | | |
| --- | --- | --- |
| Item | Device (K133343) | Predicate (K040708) |
| Limit of Detection | 1.5 x 10^{5} CFU/mL | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device (K133343) | Predicate (K040708) |
| Control Antibodies | Goat polyclonal anti-Strep A | Rabbit polyclonal anti-Strep A |
| Clinical Sensitivity | 95 %: 95% CI (88-98%) | 96.2%: 95% CI (95-98.9%) |
| Clinical Specificity | 98%: 95% CI (96-99%) | 98.7%: 95% CI (98-100%) |
| Wait Time for Results Read | 10 minutes | 5 minutes |
| Extraction Method | Extraction performed in a test tube and transferred to test device | Extraction performed within extraction wells in the test device |
K. Standard/Guidance Document Referenced (if applicable):
Not applicable
L. Test Principle:
The Wondfo® One Step Strep A Test utilizes double antibodies sandwich immunoassay for the detection of Group A Streptococcal antigen. The test device consists of plastic housing containing a test strip which has been pre-coated with rabbit anti-Strep A antibody on the test band region and goat anti-rabbit antibody on the control band region. When the device is immersed into the specimen, the specimen is absorbed into the device by capillary action, mixes with the antibody-dye conjugate, and flows across the pre-coated membrane. When the group A streptococcal antigen levels in specimens are at or above the target cutoff (the detection limit of the test), the antigen binds to the antibody-dye conjugate and are captured by rabbit anti-Strep A antibody immobilized in the Test region (T) of the device. This produces a colored Test band and indicates a positive result. When the group A streptococcal antigen levels are zero or below the target cut off, there is not a visible colored band in the Test region (T) of the device. This indicates a negative result. To serve as a procedure control, a colored line will appear at the Control region (C), if the test has been performed properly.
M. Performance Characteristics:
1. Analytical performance:
a. Precision/Reproducibility:
Precision/Reproducibility was assessed with three lots of the Wondfo One Step Strep A Swab Test at three testing sites (one in-house) for five days, with two runs per day. The test panel consisted of a true negative sample (diluent only), a moderate positive sample (2.3 × 10<sup>6</sup> organisms /mL), a low positive cut-off sample (1.5 × 10<sup>5</sup> organisms /mL, C95 concentration, approximately positive 95% of the time), and a low negative
{4}
sample (0.4 x 10⁵ organisms /mL). Six blinded operators (two at each site) performed the studies. A total of 30 determinations by each operator at each concentration were made.
The overall results were as follows:
| Samples | Site A detection | Site B detection | Site C detection | Overall detection |
| --- | --- | --- | --- | --- |
| Diluent (true negative) | 0% (0/60) | 0% (0/60) | 0% (0/60) | 0% (0/180) |
| 2.3 ×10⁶ (moderate positive) | 100% (60/60) | 100% (60/60) | 100% (60/60) | 100% (180/180) |
| 1.5 ×10⁵ (C_{95} concentration) | 98.3% (59/60) | 95.0% (57/60) | 91.9% (55/60) | 95.0% (171/180) |
| 0.4 ×10⁵ (low negative) | 43.3% (26/60) | 55.0% (33/60) | 33.3% (20/60) | 43.9% (79/180) |
The results suggest that there are no significant differences between different users, different sites and different lots in different days. Reproducibility studies appear acceptable.
b. Linearity/assay reportable range:
Not applicable – This assay is qualitative.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
Not applicable
Stability:
Reagents are Stable at 4-30 for 18 months based on the accelerated stability study at 500C and real time stability determination at both 40C and 300C. Eighteen swabs with antigen concentration near the limit of detection (LoD) of S. pyogenes, and 18 blank swabs, were each equally and stored at 40C and 300C. The two sets were then tested with three lots of Wondfo One Step Strep A at 4 hours, 24 hours and 48 hours. Additionally, all swabs were extracted and tested immediately at each time point. For the LoD swabs, three swabs per time point and temperature were evaluated in the assay. For blank swabs (no bacteria), three replicates were evaluated.
Results showed that all blank swabs (no bacteria) tested negative in the Wondfo One Step Strep A Swab Test. The LoD swabs generated a positive result when stored for 4 hours. Expected results were obtained at all temperatures when stored for up to 4 hours.
Stability results are acceptable.
{5}
d. Detection limit:
(See section F, Assay cut-off)
e. Analytical specificity:
Cross-Reactivity:
The following organisms likely to be found in the respiratory tract were tested at $1 \times 10^{8}$ organisms per mL with the Wondfo One Step A Swab Test, in order to investigate the analytical specificity (cross-reactivity) of Wondfo One Step A Swab Test. Three laboratory assistants with relevant experience, who are blind to the samples, read the results per batch. Three lots of the assay were used in these studies.
Streptococcus Group B, Streptococcus Group C, Streptococcus Group F, Streptococcus Group G, Streptococcus salivarius, Streptococcus anginosus, Streptococcus mitis, Streptococcus mutans, Streptococcus oralis, Streptococcus pneumoniae, Streptococcus sanguis, Arcanobacterium haemolyticum, Bordetella pertussis, Branhamella catarrhalis, Candida albicans, Corynebacterium diphtheriae, Enterococcus faecalis, Enterococcus faecium, Escherichia coli, Fusobacterium necrophorum, Haemophilus parahaemolyticus, Haemophilus parainfluenzae, Haemophilus influenzae, Klebsiella pneumoniae, Moraxella catarrhalis, Moraxella lacunata, Neisseria gonorrhoeae, Neisseria lactamica, Neisseria meningitides, Neisseria mucosa, Neisseria sicca, Neisseria subflava, Proteus vulgaris, Pseudomonas aeruginosa, Serratia marcescens, Staphylococcus marcescens, Staphylococcus aureus, Staphylococcus epidermidis, Staphylococcus haemolyticus, Lactobacillus sp (Lactobacillus casei), Mycobacterium tuberculosis (avirulent), Yersinia enterocolitica, Streptococcus sp. (bovis II) Group D, Adenovirus Type I, Adenovirus Type II, Cytomegalovirus, Enterovirus (VR-28 Human Coxsackievirus), Epstein Barr Virus, HSV Type 1 (HF), Human coronavirus OC43, Human metapneumovirus (HMPV-27 A2), Human parainfluenza (Types 1-4), Measles, Mumps, Respiratory Syncytial virus VR-26, Rhinovirus
Cross reactivity studies are acceptable as no cross reactivity was observed.
Interference:
The potentially interfering substances including blood, mucus, saliva, and clinically relevant levels of medications used to relieve a sore throat, such as over-the-counter cough drops, lozenges, cough syrups, throat sprays, mouth wash, etc. were tested with Wondfo One Step A Swab Test. Each potentially interfering substance was diluted and split into two aliquots. One aliquot was spiked with S. pyogenes to a final concentration of $2.3 \times 10^{6}$ organisms/mL. The second aliquot contained no bacteria. These aliquot samples were tested by three lots of Wondfo One Step A Swab Test. Three laboratory assistants with relevant experience operated the three tests. Results showed no interference by the substances shown below.
{6}
| Substance | Concentration Tested |
| --- | --- |
| Mucin (Bovine Submaxillary Gland, type I-S) | 60 μg/mL |
| Blood (human), EDT anticoagulated | 2% (vol/vol) |
| OTC Mouthwashes | |
| Listerine Antiseptic | 20%(vol/vol) |
| Listerine Cool Mint | 20%(vol/vol) |
| Crest Pro-Health Clean Night Mint | 20%(vol/vol) |
| OTC Lozenges | |
| Sucrets Complete (Cool Citrus) | 10%(vol/vol) |
| Halls Cherry Mentholyptus | 10%(vol/vol) |
| Halls Plus Mentholyptus | 10%(vol/vol) |
| Cepacol Cherry Sore Throat | 10%(vol/vol) |
| OTC Throat Sprays | |
| Cepacol Dual Relief | 20%(vol/vol) |
| Chloraseptic Max | 20%(vol/vol) |
| OTC Cough Syrups | |
| Tylenol Cough and Sore Throat | 10%(vol/vol) |
| Tussin (Guaifenesin Syrup) Rite | 0.1%(vol/vol) |
| Robitussin (Guaifenesin Syrup) | 1%(vol/vol) |
| Robitussin Nighttime Cough | 10%(vol/vol) |
| Children's Dimetapp Cough Plus | 10%(vol/vol) |
| Children's Dimetapp DM Elixir | 10%(vol/vol) |
| Active Ingredients | |
| Acetaminophen (Tylenol) | 10mg/mL |
| Brompheniramine Maleate | 5mg/mL |
| Chlorpheniramine Maleate | 5mg/mL |
| Dextromethorphan HBr | 5mg/mL |
| Diphenhydramine HCI | 5mg/mL |
| Doxylamine Succinate | 1mg/mL |
| Guaifenesin (Guaiacol Glyceryl) | 20mg/mL |
| Ibuprofen (Advil) | 10mg/mL |
| Phenylephrine HCI | 5mg/mL |
An additional study was performed to investigate the potential of Agar Interference on the performance of the Wondfo One Step Strep A Swab Test. In this study, a positive stock of inactivated Streptococcus pyogenes and a negative stock of Streptococcus agalactiae were grown on blood agar media plates, from three different manufacturers. Thirty plates, ten from each manufacturer, were used. Using a clean swab, an organism was selected from the stock positive testing plate and streaked on each of the agar plates. The swab was then run through the Rapid Strep A Test. The plates were then cultured for 48 hours. The same was done using the stock negative testing plates.
Results showed 100% agreement between culture and rapid test results. This suggests that agar did not interfere with the performance of the Wondfo Strep A test.
{7}
Interference studies are acceptable.
f. Assay cut-off:
In order to determine the assay cut-off concentration, a concentrated stock (2.3x10⁷ organisms/mL) of inactivated Streptococcus pyogenes (ATCC #20159) was serially diluted in the solution of extraction reagents. Each dilution was tested by seven operators each with three batches of Wondfo One Step Strep A Swab Test. A total of 21 determinations at each dilution were made. The test results are shown in the following table.
| Levels (organisms /mL) | 2.3x10⁶ | 1.5x10⁵ | 0.8x10⁵ | 0.4x10⁵ | 1x10³ |
| --- | --- | --- | --- | --- | --- |
| Positive # | 21 | 20 | 16 | 10 | 0 |
| Negative # | 0 | 1 | 5 | 11 | 18 |
| % Detection | 100 | 95.2 | 76.2 | 47.6 | 0 |
The assay cut-off was determined to be 1.5 x 10⁵ organisms/mL.
Assay cut-off studies appear to be acceptable.
2. Comparison studies:
a. Method comparison with predicate device:
Not applicable
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
The clinical performance of the Wondfo One Step Strep A Swab Test was established in a multicenter prospective clinical study in 2011 – 2012 at six geographically diverse sites. A total of 349 throat swabs were collected from patients exhibiting symptoms of pharyngitis. Each swab was rolled onto a sheep blood agar plate for culture tests, and then tested by the Wondfo One Step Strep A Swab Test. Of the 349 total specimens, 248 were found to be negative (-) by culture and 101 were found to be positive (+) by culture. These test results are summarized in the following tables.
{8}
9
Clinical Performance
| | Culture | | |
| --- | --- | --- | --- |
| Wondfo Strep A Test | Positive | Negative | Total |
| Positive | 96 | 4 | 100 |
| Negative | 5 | 244 | 249 |
| Total | 101 | 248 | 349 |
Sensitivity (96/101) = 95.0%; 95% CI = 88.9 – 97.9%
Specificity (244/248) = 98.4%; 95% CI = 95.9 – 99.4%
Clinical Performance Stratified By Age
| Age | Sensitivity | Sensitivity (95% CI) | Specificity | Specificity (95% CI) |
| --- | --- | --- | --- | --- |
| 0-5 | 84% | 60%-96% | 100% | 87%-100% |
| 5-21 | 97% | 88%-99% | 98% | 93%-99% |
| 21+ | 100% | 80%-100% | 99% | 92%-100% |
| All | 95% | 88%-98% | 98% | 96%-99% |
b. Clinical specificity:
See Section 3a.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values:
Group A Streptococcus bacteria are responsible for about 19% of all upper respiratory tract infections. Infection is most prevalent in winter and early spring, with most cases arising in patients living in highly populated areas. In the multi-center clinical study conducted by Wondfo in 2011-2012, 28.9% (101/349) of the patients presenting with pharyngitis were found to be culture positive for Strep A.
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.
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.