DEN100013 · Vioguard · OSZ · Dec 20, 2011 · General Hospital
Device Facts
Record ID
DEN100013
Device Name
VIOGUARD SELF-SANITIZING KEYBOARD, MODEL UVKB50
Applicant
Vioguard
Product Code
OSZ · General Hospital
Decision Date
Dec 20, 2011
Decision
DENG
Submission Type
Post-NSE
Regulation
21 CFR 880.6600
Device Class
Class 2
Attributes
Therapeutic
Indications for Use
Indicated for use in a healthcare environment to reduce microbial populations typically found on a computer keyboard.
Device Story
Vioguard UVKB50 is a motorized keyboard/touchpad enclosure for healthcare settings. Device uses infrared proximity sensor to automatically extend keyboard for user; retracts into light-tight aluminum enclosure for disinfection. Internal 254 nm UV-C lamps irradiate keyboard surface. Microcontroller-based firmware manages motorized slide, monitors safety interlocks, and controls UV exposure duration (80-120s) via light sensor feedback. LED status indicator provides cycle status. Designed to reduce nosocomial pathogen populations by 4.0 log10. Prevents user UV-C exposure via dual safety interlocks. Benefits include automated surface disinfection of high-touch computer interfaces in clinical environments.
Clinical Evidence
No clinical data. Bench testing only. Independent laboratory testing demonstrated 4.0 log10 or greater reduction of E. coli, P. aeruginosa, S. aureus, and K. pneumonia at 240 mW-s/cm2 power setting. Testing performed under simulated use conditions with pathogens dried on surfaces for 45-50 minutes.
Technological Characteristics
Ultraviolet radiation (UV) chamber disinfection device. Uses UV-C irradiation for low-level surface disinfection of non-porous equipment. Features include safety interlocks, UV lamp, and user interface displays. Requires electrical safety and electromagnetic compatibility (EMC) compliance. Must meet ozone generation limits per 21 CFR 801.415.
Indications for Use
Indicated for use in healthcare environments to reduce microbial populations on computer keyboards.
Regulatory Classification
Identification
An ultraviolet (UV) radiation chamber disinfection device is intended for the low-level surface disinfection of non-porous equipment surfaces by dose-controlled UV irradiation. This classification does not include self-contained open chamber UV radiation disinfection devices intended for whole room disinfection in a health care environment.
Special Controls
In combination with the general controls of the Food, Drug, and Cosmetic Act, the Ultraviolet radiation (UV) chamber disinfection device is subject to the following special controls: 1. Performance testing must demonstrate the following: a. The chamber's ability to control the UV radiation dose during operation. b. The chamber's disinfection performance through microbial challenge testing. c. Evidence that the equipment intended to be processed is UV compatible. d. Validation of the cleaning and disinfection procedures. e. The ability of the device to continue to perform to all specification after cleaning and disinfection. f. Whether the device generates ozone (if so, 21 CFR 801.415, Maximal acceptable level of ozone, applies). 2. Appropriate software verification, validation, and hazard analysis must be performed. 3. Appropriate analysis and/or testing must validate electrical safety, mechanical safety, and electromagnetic compatibility of the device in its intended use environment. 4. The labeling must include: a. UV hazard warning labels. b. Explanation of all displays and/or labeling on user interface. c. Explanation of device safety interlocks. d. Explanation of all disinfection cycle signals, cautions and warnings. e. Device operating procedures. f. Identification of the expected UV lamp operational life and instructions for procedures on replacement of the UV lamp when needed. g. Procedures to follow in case of UV lamp malfunction or failure. h. Procedures for disposing of mercury-containing UV lamps, if applicable. i. Identification of specific equipment that is compatible with the UV radiation dose generated by the device and can safely undergo UV lowlevel disinfection in the chamber device. j. Description of the required preparation of equipment for disinfection in the UV chamber device. k. Identification of the specific microbes used in successful performance testing of the device. l. Validated instructions for cleaning and disinfection of the device.
*Classification* —Class II (special controls). The special controls for this device are:(1) Performance testing must demonstrate the following:
(i) The chamber's ability to control the UV radiation dose during operation.
(ii) The chamber's disinfection performance through microbial challenge testing.
(iii) Evidence that the equipment intended to be processed is UV compatible.
(iv) Validation of the cleaning and disinfection procedures.
(v) The ability of the device to continue to perform to all specification after cleaning and disinfection.
(vi) Whether the device generates ozone (if so, 21 CFR 801.415, Maximum acceptable level of ozone, applies).
(2) Appropriate software verification, validation, and hazard analysis must be performed.
(3) Appropriate analysis and/or testing must validate electrical safety, mechanical safety, and electromagnetic compatibility of the device in its intended use environment.
(4) The labeling must include:
(i) UV hazard warning labels.
(ii) Explanation of all displays and/or labeling on user interface.
(iii) Explanation of device safety interlocks.
(iv) Explanation of all disinfection cycle signals, cautions and warnings.
(v) Device operating procedures.
(vi) Identification of the expected UV lamp operational life and instructions for procedures on replacement of the UV lamp when needed.
(vii) Procedures to follow in case of UV lamp malfunction or failure.
(viii) Procedures for disposing of mercury-containing UV lamps, if applicable.
(ix) Identification of specific equipment that is compatible with the UV radiation dose generated by the device and that can safely undergo UV radiation low-level disinfection in the chamber device.
(x) Description of the required preparation of equipment for disinfection in the UV radiation chamber device.
(xi) Identification of the specific microbes used in successful performance testing of the device.
(xii) Validated instructions for cleaning and disinfection of the device.
Submission Summary (Full Text)
{0}------------------------------------------------
### EVALUATION OF AUTOMATIC CLASS III DESIGNATION (DE NOVO) FOR VIOGUARD SELF-SANITIZING KEYBOARD
### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Ultraviolet radiation (UV) chamber disinfection device. An ultraviolet radiation (UV) chamber disinfection device intended for the low-level surface disinfection of non-porous equipment surfaces by dose-controlled UV irradiation. This classification does not include self-contained open chamber UV disinfection devices intended for whole room disinfection in a healthcare environment.
### NEW REGULATION NUMBER: 21 CFR 880.6600
CLASSIFICATION: II
PRODUCT CODE: OSZ
#### BACKGROUND
DEVICE NAME: VIOGUARD SELF-SANITIZING KEYBOARD ( MODEL UVKB50)
### SUBMISSION NUMBER: DEN100013
DATE OF DE NOVO : NOVEMBER 2, 2010
## REQUESTOR'S CONTACT: VIOGUARD 401 PARKPLACE CENTER, SUITE 200 KIRKLAND, WASHINGTON 98033
#### REQUESTOR'S RECOMMENDED CLASSIFICATION: II
#### INDICATIONS FOR USE
Indicated for use in a healthcare environment to reduce microbial populations typically found on a computer keyboard.
#### Device Effectiveness
In laboratory testing, the Vioguard UVKB50 Self-Sanitizing Keyboard has been shown to be effective at reducing populations of the following microorganisms when operated at its factory power setting of 240 mW-s/cm2:
• Escherichia coli
- Pseudomonas aeruginosa
- Staphylococcus aureus
{1}------------------------------------------------
# • Klebsiella pneumonia
# LIMITATIONS
Limitations on device use are also achieved through the following statements included in the Instructions for Use Manual, as well as the applicable special controls:
Warning: Do not use the Vioguard UVKB50 for disinfecting any other objects. The Vioguard UVKB50 is a self-sanitizing keyboard and not intended for any other use.
Warning: Failure to properly set up, use, and care for the Vioguard UVKB50 can increase the risk of serious injury or death, or damage to the Vioguard UVKB50. Read the manual for important safety and health information.
Warning: DO NOT pour any liquid cleaner or disinfectant directly on any surface of the Vioguard UVKB50.
Warning: No User-Serviceable Parts Inside; Do not attempt to take apart, open, service or modify the internal components of the Vioguard UVKB50.
Caution: When visibly dirty the effectiveness of the disinfection cycle might be inhibited.
Danger: Do not use any flammable or combustible liquids to clean the Vioguard UVKB50.
Danger: The Vioguard UVKB50 employs a powerful UV-C lamp source to kill germs. Light from the UV-C lamp should never be visible to the user.
### Danger
- . Ultraviolet (UV-C) Radiation Hazard
- Any exposure may cause significant eye damage and may cause skin damage ●
- Do not look into UV-C light source ●
## PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS AND CAUTIONS.
### DEVICE DESCRIPTION
The Vioguard self-sanitizing keyboard, or UVKB50, is a keyboard with touchpad which resides in a motorized tray. The tray retracts into an enclosed UV-C treatment device which irradiates the keyboard with UV-C light of ~ 254 nm wavelength generated by two 25 watt ultraviolet germicidal lamps. The device includes dual safety interlocks intended to prevent operation of the UV lamps unless the keyboard is fully retracted into the unit and the unit door is completely closed. This feature is intended to prevent the device user from exposure to UV-C light. The device operations are controlled by a small 8-bit microcontroller. Reading instructions and data stored permanently in its own internal memory and controlling the hardware directly, the tasks accomplished by device firmware/software are the following:
- Controlling the motorized slide by activating the DC motor and reading the limit
{2}------------------------------------------------
switches which are part of the slide mechanism;
- . Controlling the UV-C lamp exposure time, by reading the light sensor and integrating the dosage until a preset exposure is reached;
- Determining the dosage setting by reading an internal potentiometer;
- I Controlling and reading the state of the proximity sensor;
- 트 Calibrating the light sensor at the factory and storing the calibration information in internal non-volatile memory;
- 트 Controlling the LED status indicator;
- 트 Determining if there is keyboard or touch pad activity; and
- l Monitoring the state of the front door.
The default disinfection cycle takes 80 to 120 seconds to complete.
A summary of the key device features is as follows:
### ENCLOSURE:
The UVKB50 keyboard and touchpad are stored in a mechanized enclosure when not in use for keyboard data entry functions. Please refer to Figure 1 below; the diagram shows that the keyboard extends from the enclosure to allow for keyboard use. The enclosure is made of aluminum, which can be surface cleaned, and is designed to support a computer monitor on top to save desk space.
Image /page/2/Picture/12 description: The image shows a drawing of a computer with a keyboard and trackpad. The computer is white and has a rectangular shape. The keyboard is black and has a standard layout. The trackpad is located to the right of the keyboard. Two hands are shown using the keyboard and trackpad. The drawing is simple and has a clean style.
Figure 1: Vioguard unit with keyboard slide exter
### TOUCHLESS SENSOR AND MOTORIZED DRAWER:
When the user sits at the computer workstation to use the keyboard, the user waves a hand near an infrared proximity sensor located on the enclosure's front panel. A reversible DC motor opens the enclosure's door when the sensor is activated and automatically extends the keyboard from the enclosure into a working position for the user.
### AUTOMATIC/MANUAL UV-C DISINFECTION MODES:
The UVKB50 can be set to automatically retract the keyboard and run a disinfection cycle after a 10 minute period of keyboard inactivity, or when operated in the manual
{3}------------------------------------------------
mode. When the user is finished at the keyboard workstation, the user can manually initiate a disinfection cycle by pressing the "close" button on the keyboard. This causes the keyboard tray to retract into the enclosure and initiate a disinfection cycle.
### DISINFECTION CYCLE:
Disinfection is performed using two 25-watt ultraviolet germicidal lamps. The UVKB50 electronics consist of a power supply and lamp ballast, which operate on standard AC (line) power. The reflector and diffuser inside the enclosure are used to distribute the light over the keyboard surface during a disinfection cycle. The ultraviolet light used is known as UV-C, at ~254 nm wavelength.
## DISINFECTION CYCLE CONTROL:
Once inside the enclosure, the keyboard and touchpad are illuminated with the UV-C germicidal light. Software in the Vioguard UVKB50 monitors the output of the UV-C bulbs and adjusts the disinfection cycle duration. The default disinfection cycle takes 80 to 120 seconds to complete.
## LED STATUS INDICATOR:
A multicolor LED status indicator on the enclosure's front panel provides the device user with information on disinfection cycle completion, servicing needs, etc. For example: A green LED means the disinfection cycle has been completed and the keyboard is ready for use; a flashing red LED indicates that a UV bulb needs replacement, etc.
### SAFETY INTERLOCKS:
When the keyboard tray is retracted into the enclosure, the enclosure's spring-loaded front door shuts and the enclosure remains "light-tight." The "light-tight" door has been designed to protect the user against inadvertent UV-C exposure.
### SUMMARY OF NONCLINICAL/BENCH STUDIES/OTHER TESTING
### Microbial Reduction Testing
Antimicrobial performance testing under simulated conditions of use for the device was performed by an independent laboratory. Using both gram positive and gram negative pathogens, the requestor provided adequate justification for the selection of test organisms. A wide range of microbes such as tubercle bacilli. streptococci, pneumococci and staphylococci have been demonstrated to be present on keyboards used in patient care areas. The requestor noted that the 4 bacteria studied, Escherichia coli, Staphylococcus aureus, Pseudomonas aeruginosa and Klebsiella pneumonia are major nosocomial pathogens, which can be transmitted by direct contact. The requestor also noted that all of the above bacteria are used by the Environmental Protection Agency (EPA) in its efficacy testing of disinfectants.
The independent laboratory studied the 4 pathogens listed above and the testing demonstrated that the device was effective at reducing populations of the 4 bacteria when operated at its factory power setting of b(4)
{4}------------------------------------------------
diluted b(4) b(4)
through a small
syringe and allowed to dry for 45 to 50 minutes before treatment. The final antibacterial UV-C irradiation test data showed that the device achieves a 4.0 log10 or greater reduction of each of the challenge pathogens at each of the "worst case" device sites irradiated. These results support the device claim to reduce the populations of the tested challenge pathogens by at least 4.0 log10 CFU/ml.
## Biocompatibility/Materials
Not applicable. The device is not patient-contacting.
### Animal Studies
No animal testing was completed nor deemed necessary for the Vioguard selfsanitizing keyboard to support a reasonable assurance of safety and effectiveness.
## Electrical and Mechanical Safety
The Vioguard self-sanitizing keyboard operates at 100-240 VAC, 80 watts, and 50/60 Hz. It has a microprocessor that controls the disinfection times and operation of the proximity sensor and motor, and monitors the safety interlock switches and lamp status. Two 25-watt germicidal fluorescent lamps provide output at 254 nm, resulting in disinfection of the keyboard and touch-pad. The lamp is designed to operate for 1-2 years with moderate use before needing a replacement.
The requestor conducted testing according to the following Agency recognized standards:
- · IEC 60601-1: Medical electrical equipment Part 1: General requirements for safety
- IEC 60601-1-2: Medical Electrical Equipment Part 1-2: General Requirements for Safety; Electromagnetic Compatibility - Requirements and Tests
Testing conducted by an independent lab verified that the device meets IEC 60601-1 and IEC 60601-1-2. The electromagnetic compatibility tests included radiated emissions, surge, conducted immunity, electrical fast transient burst, voltage dips and interrupts. All the results demonstrate that the device passes the tests without any malfunction. The requestor provided data to demonstrate that atmospheric ozone generation is prevented by use of lamps designed to suppress ozone-generation wavelengths. In the event that ozone were generated, it would be necessary to meet the maximal acceptable level ozone in accordance with 21 CFR 801.415. Additionally, the requestor also provided certification from an independent lab that the device passed the Federal Communications Commission conducted emissions and radiated emissions test successfully. Based on the Agency recognized electrical safety standards which includes fire hazard testing, the requestor demonstrated electrical safety of the device.
### SOFTWARE
The device firmware is a set of embedded instructions for a small, 8bit microcontroller which form a customized control system for the operation of the UVKB50. b(4)
{5}------------------------------------------------
b(4) . The instructions are contained in a nonvolatile internal flash memory and are potentially re-programmable by a service technician with the proper specialized equipment but not by an end user.
Per the recommendations of the FDA document, Guidance for the Content of Premarket Submission of Software Contained in Medical Devices" (dated 5/11/2005), the de novo included the following information:
- Level of concern (Minor)
- Software description ●
- Device/system level hazards analysis
- Software requirements specification ●
- Architecture design chart ●
- . Software design specifications
- . Traceability analysis/matrix
- Software development summary
- The results of verification and validation testing
- The revision level history (showing the latest revision level) ●
- Identification and description of all unresolved anomalies ●
Based on the identified level of concern, all necessary information was provided and deemed sufficient.
# CLINICAL DATA
No clinical testing was provided nor deemed necessary for the Vioguard self-sanitizing keyboard UVKB50 to support a reasonable assurance of safety and effectiveness.
# LABELING
The de novo contains appropriate Instructions for Use labeling and User's Manual. The directions for use include the indications for use. setup instructions, product specifications, detailed operating instructions, appropriate contraindications/warnings/cautions statements, safety information, recommended cleaning procedures and disinfectants for cleaning the device. The Vioguard UVKB50 is available as an over-the-counter (OTC) device. The labeling adequately addresses the necessary information to ensure conformity with the special controls.
# RISKS TO HEALTH
Table 1 identifies the risks to health associated with the use of Ultraviolet radiation (UV) chamber disinfection devices and the measures necessary to mitigate these risks.
| Identified Risks | Mitigation Measures |
|-----------------------------------|---------------------------------|
| Inadequate Equipment Disinfection | Performance Testing<br>Labeling |
{6}------------------------------------------------
| Identified Risks | Mitigation Measures |
|-------------------------------------|---------------------------------------------------------------------|
| UV Radiation Exposure | Performance Testing<br>Labeling |
| Electrical Shock | Electrical Safety Testing |
| Electromagnetic Interference | Electromagnetic Compatibility (EMC) Testing<br>Labeling |
| Ozone Exposure | Ozone Generation Limits<br>Labeling |
| Processed Equipment Incompatibility | Performance Testing<br>Labeling |
| Contamination of Device | Cleaning and Disinfection Validation<br>Labeling |
| Software Malfunction | Hazard Analysis of Software<br>Software Verification and Validation |
### SPECIAL CONTROLS
In combination with the general controls of the Food, Drug, and Cosmetic Act, the Ultraviolet radiation (UV) chamber disinfection device is subject to the following special controls:
- 1. Performance testing must demonstrate the following:
- The chamber's ability to control the UV radiation dose during operation. a.
- The chamber's disinfection performance through microbial challenge b. testing.
- C. Evidence that the equipment intended to be processed is UV compatible.
- Validation of the cleaning and disinfection procedures. d.
- e. The ability of the device to continue to perform to all specification after cleaning and disinfection.
- f. Whether the device generates ozone (if so, 21 CFR 801.415, Maximal acceptable level of ozone, applies).
- 2. Appropriate software verification, validation, and hazard analysis must be performed.
- 3. Appropriate analysis and/or testing must validate electrical safety, mechanical safety, and electromagnetic compatibility of the device in its intended use environment.
- 4. The labeling must include:
- a. UV hazard warning labels.
- b. Explanation of all displays and/or labeling on user interface.
{7}------------------------------------------------
- c. Explanation of device safety interlocks.
- d. Explanation of all disinfection cycle signals, cautions and warnings.
- Device operating procedures. e.
- f. Identification of the expected UV lamp operational life and instructions for procedures on replacement of the UV lamp when needed.
- Procedures to follow in case of UV lamp malfunction or failure. g.
- h. Procedures for disposing of mercury-containing UV lamps, if applicable.
- Identification of specific equipment that is compatible with the UV i. radiation dose generated by the device and can safely undergo UV lowlevel disinfection in the chamber device.
- Description of the required preparation of equipment for disinfection in i. the UV chamber device.
- k. Identification of the specific microbes used in successful performance testing of the device.
- Validated instructions for cleaning and disinfection of the device. 1.
### CONCLUSION
The de novo for the Vioguard Self-Sanitizing Keyboard (Model UVKB50) is granted and the device is classified under the following:
Product Code: OSZ Device/Product Name: Ultraviolet Radiation (UV) Chamber Disinfection Device Class: II Regulation: 21 CFR 880.6600
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.
