Published clinical literature (A. Moro et al.); Clinical patient cohort (medical records/histology)
The sponsor utilized a published clinical study of patients at risk for oral cancer to demonstrate the device's ability to detect fluorescence in a clinical setting, supporting the device's intended use and performance equivalence.
Oral cancer screening; Autofluorescence; Histological confirmation; Clinical cohort
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Autofluorescence and Early Detection of Mucosal Lesions in Patients at Risk for Oral Cancer (A. Moro et al.); Retrospective clinical cohort study
32 patients at risk for oral cancer (12 with potentially malignant diseases, 20 previously operated for oral cancer); Sample Size: 32
Not applicable for this study
Detection of suspected cancer via autofluorescence confirmed by histological analysis
Indications for Use
G.o.c.c.l.e.s. is intended to be used by a qualified health-care providers to enhance the identification and visualization of the oral mucosal abnormalities that may not be apparent or visible to the naked eye, such as oral cancer and premalignant dysplasia. G.o.c.c.l.e.s. eyewear is reusable filtered eyewear that is worn by a health care professional to enhance the visual effects of blue light during oral exam.
Device Story
G.o.c.c.l.e.s. is reusable filtered eyewear used by healthcare professionals during oral examinations. Device functions in combination with a proprietary light source (440-490nm emission) to induce autofluorescence in oral tissues. Blue-violet light (450nm) excites Flavin Adenine Dinucleotide (FAD) in mucosal cells, which emits fluorescence at ~515nm. Eyewear filters transmit this fluorescence (470-610nm range) to the clinician's eyes, allowing visualization of tissue abnormalities (e.g., dysplasia, carcinoma) as areas of fluorescence loss. Clinicians use visual output to identify suspicious lesions for surgical excision and histological confirmation. Device aids in early detection of oral cancer and premalignant lesions, potentially improving diagnostic accuracy compared to naked-eye inspection.
Clinical Evidence
Bench testing verified filter transmittance (max 518nm, 470-610nm bandwidth). Clinical validation included two studies: 1) A. Moro et al. (n=32) using autofluorescence to detect suspected cancer, confirming 14/15 cases histologically. 2) Multicenter study (n=35 suspected cases) using G.o.c.c.l.e.s. with various light sources, confirming 29/35 cases as dysplasia or carcinoma via histology. Results demonstrate device efficacy in detecting fluorescence loss corresponding to oral lesions.
Technological Characteristics
Reusable filtered eyewear. Sensing principle: optical fluorescence visualization. Transmittance range: 470-610nm. Light source: external proprietary LED (440-490nm). No integrated electronics or software.
Indications for Use
Indicated for qualified healthcare providers to enhance identification/visualization of oral mucosal abnormalities (e.g., oral cancer, premalignant dysplasia) not apparent to the naked eye during oral exams.
Regulatory Classification
Identification
An ultraviolet detector is a device intended to provide a source of ultraviolet light which is used to identify otherwise invisible material, such as dental plaque, present in or on teeth.
{0}------------------------------------------------
Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002
September 15, 2015
Pierrel Pharma S.r.l. c/o Mr. Maurizio Pantaleoni Isemed Srl Via A. Bonetti 3/A Imola, 40026 BO ITALY
Re: K151630 Trade/Device Name: G.o.c.c.l.e.s. Regulation Number: 21 CFR 872.6350 Regulation Name: Ultraviolet Detector Regulatory Class: II Product Code: NXV Dated: June 10, 2015 Received: June 17, 2015
Dear Mr. Pantaleoni:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food. Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
{1}------------------------------------------------
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical devicerelated adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to
http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.
Sincerely yours,
Tina
Kiang -S
for Erin I. Keith, M.S. Director Division of Anesthesiology. General Hospital. Respiratory. Infection Control, and Dental Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known)
K151630
Device Name G.o.c.c.l.e.s.
Indications for Use (Describe)
G.o.c.c.l.e.s. is intended to be used by a qualified health-care providers to enhance the identification of the oral mucosal abnormalities that may not be apparent or visible to the naked eye, such as oral cancer and premalignant dysplasia. G.o.c.l.e.s. eyewear is reusable filtered eyewear that is worn by a health care professional to enhance the visual effects of blue light during oral exam
Type of Use (Select one or both, as applicable)
X Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
### 510(k) Summary
# G.o.c.c.l.e.s.
This 510(k) Summary is being submitted in accordance with the requirements of the SMDA 1990 and 21 CFR 807.92.
#### 2.1. General Information
| Submitter: | PIERREL PharmaS.r.l.<br>Strada Statale 48/48<br>81043 Capua (CE)<br>Italy |
|-----------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| ContactPerson in Italy: | Maurizio Pantaleoni<br>ISEMED srl<br>Via Altobelli Bonetti 3/a<br>40026 Imola (BO)<br>Italy<br>Mob.phone: +39-348 4435155<br>Telephone: +39-0542 683803<br>Fax: +39-0542 698456<br>Email: regulatory@isemed.eu |
| Summary Preparation Date: | June 10, 2015 |
| Names | |
| Device Name:<br>Classification Name:<br>Product Code:<br>Regulation number: | G.o.c.c.l.e.s.<br>Ultraviolet Detector<br>NXV<br>872.6350 |
#### 2.3. Predicate Device
Classification:
2.2.
G.o.c.c.l.e.s. is substantially equivalent to the following devices:
| Applicant | Device name | 510(k) Number |
|----------------------------|-------------------------------------|---------------|
| TRIMIRA LCC | TRIMIRA Identafi 3000, Remicalm LCC | K090135 |
| LED Dental<br>Incorporated | VELscopeVx, LED Dental Incorporated | K102083 |
II
{4}------------------------------------------------
#### Device Description 2.4.
The G.o.c.c.l.e.s device consist of one eyewear with specific filtering features that shall be used with the G.o.c.c.l.e.s. light proprietary light source (emission range 440-490nm), in order to allow the examination of autofluorescence of the oral cavity and consequently detect oral abnormalities such as dysplastic or anaplastic lesions (carcinomas of the oral mucosa).
The device looks like a pair of glasses, characterized by reduced dimensions, good wearability, easy portability and proper filtering performances in order to allow to filter the fluorescence emission, resulting from the fluorophore of interest (Flavin Adenine Dinucleotide (FAD)), which in its oxidized form responds to a light of 450nm (blue-violet) emitting a fluorescence wavelength of around 515nm (green).
#### 2.5. Indications for Use
G.o.c.c.l.e.s. is intended to be used by a qualified health-care providers to enhance the identification and visualization of the oral mucosal abnormalities that may not be apparent or visible to the naked eye, such as oral cancer and premalignant dysplasia. G.o.c.c.l.e.s. eyewear is reusable filtered eyewear that is worn by a health care professional to enhance the visual effects of blue light during oral exam.
Such intended use is equivalent to the intended use of the predicate devices K090135.
Also, both the subject and the predicate (K090135 and K102083) are for prescription use, to be used by physicians.
#### 2.6. Comparison of technological characteristics with the predicate devices.
At high level the subject and the predicate devices are based on the following same technological elements:
- · Device Composition: Similar to the predicate devices K090135 and K102083, theG.o.c.c.l.e.s consists of a filtering system to be used with a proprietary light source in order to allow illumination of the oral cavity and the transmission of the fluorescence of the fluorophore of interest. Similarly to the predicate K090135 the filtering system of the G.o.c.c.l.e.s. is represented by a pair of eyewear and the light source is a proprietary light not integrated into the vision system.
- · Performance features: Simmilar to the predicate devices K090135 and K102083, the G.o.o.c.l.e.s. performance is based on the capacity of the filtering system to detect and transmit the fluorescence emitted by the fluorophore of interest (FAD).
- · Light source- emission range: the subject as well as the predicate devices define proper emission range which has to be compatible with the excitation of the fluorophore of interest.
{5}------------------------------------------------
Specifically the fluorophore FAD is characterized by an excitation peak at 450 nm and a maximum emission around 515-530 nm. Consistently, both the subject and the predicate devices are to be used with a light source with an emission spectrum including 450 nm.
- · Transmittance range:G.o.c.c.l.e.s. is characterized by a filtering system with a transmittance range 470-610 nm which include the emission wavelengths of the fluorophore FAD (around 515 nm). Equivalently, the predicate devices are characterized by a transmittance range including 515nm.
The following technological differences exist between the subject and the predicate devices:
- · Light source emission range: Equivalently to the predicate device K090135, the G.o.c.l.e.s. is provided with a proprietary light source separated from the vision system in order to illuminate the cells of the oral cavity so that they can be excited and emit fluorescence. The specific emission range of the G.o.c.c.l.e.s. light is 440-490 nm while the emission range of the predicate devicesK090135 and K102083arearound 380-460 nm and 400-460 nm respectively. Despite the specific emission range both the G.o.c.c.l.e.s' and the predicate devices' emission range includes the excitation peak of the fluorophore of interest (FAD) which is around 450 mm. Also the performance of the subject device has been tested through a specific performance (clinical test) demonstrating the ability of the G.o.c.c.l.e.s. to transmit the fluorescence of FAD after illumination of cells by the G.o.c.c.l.e.s. light (see below), according to its intended use.
- · Transmittance range: the specific transmittance range of the G.o.c.c.l.e.s. is 470-610 nm while the transmittance range of the predicate is different (400-460nm). However the transmittance range of the subject as well as the predicate devices include the emission peak of the fluorophore of interest (FAD's emission peak around 515 nm). Also, the intended use of the G.o.c.c.l.e.s. filtering system has been proved through specific performance tests underlining the capacity of the G.o.c.c.l.e.s. to properly filter and transmit the FAD's fluorescence after the excitation by the G.o.c.c.l.e.s. light emitting at 450 nm (corresponding to the excitation peak of FAD). See below for performance tests.
#### 2.7. Performance Data
The following performance tests have been conducted with the purpose of: 1) verifying the transmittance characteristics of the G.o.c.l.e.s. device in order to verify their compatibility with regard to the excitation and emission spectrum of the FAD which is the fluorophore of interest; 2) validating the performance of the G.o.c.c.l.e.s. device when used in combination with either the G.o.c.c.l.e.s. light or a non proprietary light source emitting in a range compatible with the FAD's excitation.
- · Verification of the Transmittance range of the G.o.c.c.l.e.s.
Evaluation: the transmittance % for the G.o.c.c.l.e.s eyewear was measured by scanning the light spectrum from 1400 to 200nm and measuring the quantity of UV transmitted
{6}------------------------------------------------
by the G.o.c.c.l.e.s eyewear filter. The transmittance % was calculated as the ratio between the intensity of the incident light (e = 100) and that of light passing the filter expressing it as%.
Results: The result of the measurements of this performance study shows that the transmittance % for the G.o.c.c.l.e.s evewear filter has its maximum at 518mm with a % of transmittance of 66.842 with a bandwith between 470 and 610 mm and with a transmittance % that remains over the 90% of its max value (60.000) from 500nm to 541nm covering the typical bandwidth that allows to enable the visualization of the response signal of FAD which is maximum at the wavelengthsaround515-530 nm.
Discussion and Conclusion: the obtained results demonstrate that the G.o.c.c.l.e.s.'s transmittance range covers exactly the excitation curve of the fluorophore of interest (FAD) allowing the detection and transmission of the related fluorescence. Therefore such evidence corroborates the intended use of the subject device and validates its performance equivalently to the predicate devices.
- · Validation of the non-proprietary light source
- 1- Aim: A specific test was conducted to demonstrate the performance of the G.o.c.c.l.e.s. device used with a common non proprietary light source.
The study was carried out by A. Moro et al. that led to the publication "Autofluorescence and Early Detection of Mucosal Lesions in Patients at Risk for Oral Cancer
Methods: In this study, 32 patients with risk for oral cancer underwent autofluorescence test. Of these patients,12 (group A) experienced potentially malignant diseases. The other 20 patients (group B) were previously operated for oral cancer.
The autofluorescence was detected using a light source consisting of an LED emitting in the band of 400-500nm with a peak at 450nm and a pass-band filtering system identical to the filtering system used for the manufacturing of the G.o.c.c.l.e.s device.
The lesions suspected to be tumors by the autofluorescence inspection were surgically excised and histologically analyzed to confirm the diagnosis
Results: overall the autofluorescence detected 15 suspected cancer of which 14 were confirmed by the histological analyses.
Discussion and Conclusion: the clinical test demonstrates that the subject device detects the fluorescence of the cells of the oral cavity when illuminating by a light source emitting in a range including FAD's excitation peak (450 mm). Such evidence supports the intended use of the G.o.c.c.l.e.s. and also, they corroborate the mechanism of action and final performance of the subject device is equivalent to those of the predicate devices: in all cases the fundamental aspect to be satisfied is guaranteeing the excitation of FAD (by a light source emitting at 450 nm) and the transmission of FAD's fluorescence (by a filtering system transmitting around 515 nm, according to FAD's emission peak).
{7}------------------------------------------------
- 2- Aim: A specific performance clinical test has been conducted in order to prove the ability of the subject device to detect oral cavity cancer when used with its proprietary compatible light source (G.o.c.c.l.e.s. light) as well as with other two light sources (curing lights), accordingly to the consideration that the light source to be used with G.o.c.c.l.e.s. needs to have an emission spectrum including the excitation peak of FAD (450 nm).
Methods: Multicenter studyrecruiting patients affected by diseases of the oral cavity that are suspected of being cancer or may lead to cancer, as well as patients in follow-up process after surgical operation for oral carcinoma.
All patients were examined by Goccles in combination with three light sources that are legally marketed and FDA-cleared:
- → Optilux 501 (K020091)- emission range: 400 nm-505nm
- -> G.o.o.c.c.l.e.s. light (which correspond to the light cleared under K080025) - emission range 440 nm- 490 nm
- -> Eliparfreelight (K011154)-emission range 440-490 nm
All the lesions as detected by G.o.c.c.l.e.s. (spots of fluorescence loss) with either the lights were surgically removed and histologically analyzed to confirm the diagnosis of dysplasia/cancer as detected in the previous step and to evaluate the size and the infiltration rate of each lesion
Results: the visual inspection by G.o.c.c.l.e.s. identified loss of fluorescence in a total of 35 cases (false positive) of which 29 were confirmed by the histological analyses to be real dysplasia or carcinoma in situ or invasive cancer (true positive). There were no relevant differences in the G.o.c.c.l.e.s. performance depending on the specific light that was used.
Discussion and Conclusion: the results support the use of G.o.c.c.l.e.s. with the G.o.c.c.l.e.s. light. Such evidence underline that the capacity of emitting at 450 nm represents the fundamental criteria that the light to be used with G.o.c.c.l.e.s must satisfy and thus they support the performance of the G.o.c.c.l.e.s. light, according to its intended use. In conclusion the obtained results demonstrate the performance of the G.o.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c. the G.o.c.c.l.e.s light since it emits in a range including the maximum excitation peak of the FAD (450 nm), equivalently to the predicate devices.
** Please note that even though both studies included other proprietary light sources, only the G.o.c.c.l.e.s. light is intended to be used with the G.o.c.c.l.e.s. eyewear. This study serves to prove the more important concept that the eyewear measurably transmits FAD fluorescence.
#### 2.8 Conclusions
The performance data described above demonstrate that the G.o.c.c.l.e.s. device performs as intended in the specific use conditions. The considerations discussed above underline the equivalence of the subject device to the predicate devices K090135 and K102083 concerning the intended use, the device composition and mechanism of action. Indeed the subject as well
{8}------------------------------------------------
as the predicate devices are based on similar performance features and are characterized by equivalent filtering system with a transmittance range including the emission peak of the fluorophore of interest (around 515nm). Further, the performance tests demonstrate the performance of the G.o.c.c.l.e.s. device when used in combination with the G.o.c.c.l.e.s. light. Thus, on the basis of evidence discussed above, the G.o.c.c.l.e.s. device may be found substantially equivalent to the predicate devices K090135 and K102083.
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.