De-identified actigraph data from 180 participants
Retrospective analysis of existing actigraph data was used to validate the device's algorithm for differentiating between 'awake and moving about', 'in-bed', and 'off-wrist' states.
Phase 1 Scoring Validation; Retrospective analysis of de-identified actigraph data
180 participants; Sample Size: 180
Not applicable for this study
Agreement between algorithmic versus human classification of actigraphy into three states (awake/moving, in-bed, off-wrist)
Indications for Use
The SBV2 System is an activity monitor designed and intended for documenting physical movements associated with applications in physiological monitoring. The device's intended use is to analyze limb activity associated with movement during sleep and to extract information about certain sleep parameters from these movements. SBV2 can also be used to assess activity in any instance where quantifiable analysis of physical motion is desirable. The use of the SBV2 is indicated for adults 22 years of age and over.
Device Story
SBV2 System is a wrist-worn activity monitor; captures accelerometer data to characterize sleep/wake periods and physical activity. Device consists of a data recording unit, MultiCharger, ANT Dongle, and PC running SleepAnalyzer software. User wears unit on limb/torso; data transferred wirelessly via ANT protocol (2.4 GHz) to PC. Software processes raw accelerometer data to differentiate 'up-and-about' vs 'in-bed' states and classify sleep/wake episodes. Output is a sleep report providing metrics like sleep duration, latency, and efficiency. Intended for OTC use; dispensing agent retrieves data and generates report. Healthcare providers use report to assess sleep patterns; aids in monitoring physiological activity. Benefits include objective, quantifiable sleep/activity data for adult users.
Clinical Evidence
Two-phase validation study. Phase 1: 180 participants; compared algorithmic vs. human classification of 'up-and-about' vs 'in-bed' vs 'off-wrist' states; accuracy 87-95%. Phase 2: 50 patients; compared SBV2 actigraphy vs. in-bed polysomnography (gold standard). Results: 88% sensitivity, 55% specificity for sleep/wake classification. Overall agreement level of 93% when weighting sleep identification.
Technological Characteristics
Wrist-worn accelerometer; 16 Hz sampling interval; 2.4 milliGs sensitivity. Enclosure: Polycarbonate; Wrist band: Santoprene. Battery: 3.7V rechargeable Lithium Coin Cell. Connectivity: Wireless ANT protocol (2.4 GHz ISM band). Operating temperature: 0°C to +40°C. Water resistant.
Indications for Use
Indicated for adults 22 years of age and over for documenting physical movements, analyzing limb activity during sleep to extract sleep parameters, and assessing activity where quantifiable motion analysis is desired.
Regulatory Classification
Identification
A biofeedback device is an instrument that provides a visual or auditory signal corresponding to the status of one or more of a patient's physiological parameters (e.g., brain alpha wave activity, muscle activity, skin temperature, etc.) so that the patient can control voluntarily these physiological parameters.
Special Controls
*Classification.* Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter when it is a prescription battery powered device that is indicated for relaxation training and muscle reeducation and prescription use, subject to § 882.9.
{0}------------------------------------------------
# < 111514
DEC 1 6 2011
# 1. 510(k) Summary - Basic Information
- 1.1 Sponsor
Submitter: Address:
Company:
Voice:
FAX:
Cell:
Email:
Fatigue Science 700 Bishop Street, Suite 2000 Honolulu, Hawaii, 96813
### Contact:
Marc Goodman (on behalf of Fatigue Science) Noblitt & Rueland 5405 Alton Parkway, Suite A530 Irvine, CA 92604 (949) 398-5222 (949) 398-5223 (949) 872-1011 marcgood@ca.rr.com
Date Prepared:
November 21, 2011
# 1.2 Device Name
SBV2TM System Proprietary Name: Common Name: Activity Recording Device Classification Name: GWQ, Electroencephalograph, 882.1400, Class II
# 1.3 Identification of Legally Marketed Device
SBV2 is substantially equivalent to the ActiGraph device (K040554).
# 1.4 Device Description
The SBV2 System is a device that monitors activity. It relies on the measurement and analysis of wrist movements to detect and characterize sleep/wake periods. The device allows some aspects of sleep derived from the analysis of activity to be reported. The SBV2 System is graphically depicted in Figure 1.
# Figure 1: SBV2 System Graphic Depiction
Image /page/0/Figure/17 description: The image shows a diagram of a data recording system. The system includes an SBV2 data recording unit, a MultiCharger, an ANT Dongle, and a PC Computer. The SBV2 unit is connected to the ANT Dongle, which is connected to the PC Computer.
{1}------------------------------------------------
#### 1.4.1 Components
The following SBV2 System components (depicted in Figure 1) are briefly described as follows:
- SBV2 (Data Recording Unit); wristwatch-like device used to capture and store . accelerometer data from user.
- ANT Dongle; A PC peripheral that uses a proprietary wireless protocol to transfer . stored accelerometer data to SleepAnalyzer software application.
- PC Computer; standard PC used to host the SleepAnalyzer application. .
- MultiCharger; coin cell battery charger used to fully charge the Data Recording . Unit battery prior to use.
# 1.5 Intended Use
The SBV2 System is an activity monitor designed and intended for documenting physical movements associated with applications in physiological monitoring. The device's intended use is to analyze limb activity associated with movement during sleep and to extract information about certain sleep parameters from these movements. SBV2 can also be used to assess activity in any instance where quantifiable analysis of physical motion is desirable. The use of the SBV2 is indicated for adults 22 years of age and over.
# 1.6 Comparison to Cleared Device
SBV2 is substantially equivalent to the ActiGraph (K040554). Table 1 compares the features of SBV2 with those of ActiGraph.
| Characteristic | SBV2 | ActiGraph |
|---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | Usage Characteristics | |
| Intended Use | The SBV2 System is an activity monitor<br>designed and intended for documenting physical<br>movements associated with applications in<br>physiological monitoring. The device's intended<br>use is to analyze limb activity associated with<br>movement during sleep and to extract<br>information about certain sleep parameters from<br>these movements. SBV2 can also be used to<br>assess activity in any instance where<br>quantifiable analysis of physical motion is<br>desirable. The use of the SBV2 is restricted to<br>adults 22 years of age and over. | The ActiGraph is a small limb worn activity<br>monitor designed for documenting physical<br>movements associated with applications in<br>physiological monitoring. The device's intended<br>use is to analyze limb activity associated with<br>movement during sleep. The unit can also be<br>used to assess activity in any instance where<br>quantifiable analysis of physical motion is<br>desirable. |
| Principle of<br>Operation | Accelerometer used to collect actigraphy data to<br>determine a person's activity level during the<br>course of a day. | same |
| Components | Data recording unit (SBV2 activity monitor)<br>worn by patient<br>PC software application prepares data<br>recording unit, retrieves collected data, and<br>generates report. | same |
| Data Collection<br>Method | Data recording unit is attached to patient's limb<br>or torso and worn continuously during data<br>collection period. | same |
| Sampling Interval | 16 Hz | 1 Hz and up (web site indicates 30 Hz) |
| Recording Time | 1 to 30 days. Typically 7 days. | 2 hours to 180 days (end of battery life) |
# Table 1: Comparison of SBV2 to ActiGraph (K040554)
510(k) Summary (per 21 CFR 807.92)
{2}------------------------------------------------
| Characteristic | SBV2 | ActiGraph |
|----------------------------------------|--------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|
| Data Recording Unit<br>to PC Interface | Wireless communications using ANT protocol in<br>2.4 GHz ISM Band. | RS232 or USB |
| Commercial<br>Distribution | Indicated for Over the Counter Use. Patient<br>receives data recording unit from dispensing<br>agent such as pharmacist. | Prescription Use |
| Reporting | Dispensing agent retrieves collected data from<br>data recording unit and generates report based<br>on collected data. | Same |
| Physical Characteristics | | |
| Size | 1.5"x1.35"x.4" | 2" x 2" x 0.5" (does not include wrist band) |
| Weight | 1 oz. | 1.5 oz, with battery 2.5 oz |
| Battery | rechargeable 3.7V Lithium Coin Cell | same |
| Recharging Method | MultiCharger | connection to USB port |
| Accelerometer<br>Sensitivity | 2.4 milliGs | 16 milliGs |
| Enclosure | Polycarbonate | same |
| Wrist Band | Santoprene | Nylon w Velcro |
| Moisture<br>susceptibility | Water resistant | same |
| Storage<br>Temperature | -40°C to +60°C | -10°C to +50°C |
| Operating<br>Temperature | 0°C to +40°C | 0°C to +45°C |
### Differences between SBV2 and ActiGraph 1.6.1
The meaningful differences between SBV2 and the ActiGraph predicate device are their means of commercial distribution and their methods for communicating between data recording unit and PC software application.
- SBV2 is intended for Over-The-Counter commercial distribution. ActiGraph is ● indicated for Prescription Use.
- . SBV2 uses wireless communications between its data recording unit and its PC software. ActiGraph uses hardwired serial communications.
# 2. Performance Information
ਾਂ
Performance data produced by a two-phase investigation demonstrates substantial equivalence between polysomnographic sleep/wake classification and SBV2 actigraphic sleep/wake classification.
### 2.1 Substantial Equivalence Evaluations
The Fatigue Science SBV2 was validated against expert human actigraphy scoring and against polysomnography as a device for accurately measuring sleep/wake periods. Polysomnography is considered to be the accepted medical standard for conducting sleep evaluations. There were two phases of the evaluation. A detailed account may be found in the Fatigue Science White Paper entitled Validation of the Fatigue Science SBV2 authored by Russell, Caldwell, Arand, Myers, Wubbels, and Downs (2010).
#### 2.1.1 Overview
The first phase of the scoring validation effort was conducted by research personnel at Archinoetics, LLC. These personnel possessed substantial expertise in the visual
{3}------------------------------------------------
examination and classification of raw actigraphy data into various states such as "awake and moving about" versus "lying quietly in bed or elsewhere". The second phase of the classification yalidation effort was conducted by Dr. Donna Arand, Board Certified Sleep Specialist, Kettering Hospital; Dr. John Caldwell, Experimental Psychologist, Fatigue Science; and Dr. Chris Russell, Senior Scientist, Archinoetics, LLC; in conjunction with the Wallace Kettering Health Networks Sleep Disorders Center in Kettering Ohio.
#### 2.1.2 Phase 1 Summary
Since the SBV2 is designed to be worn 24-hours per day for several days at a time, it was first necessary to ensure that the "up-and-about periods" could be correctly differentiated from the "lying-in-bed periods." Using de-identified actigraph data from 180 participants, we determined the agreement between algorithmic versus human classification of actigraphy into the following states: 1) Awake and moving about, 2) In bed-Awake or Asleep, or 3) Actigraph off wrist. Results indicated that the SBV2 algorithm accurately differentiated among the 3 states of interest between 87% and 95% of the time (see Table 1).
| | Table 1. Identification accuracy of "up & about" vs "in bed" vs "off wrist" | | | | | | |
|--|-----------------------------------------------------------------------------|--|--|--|--|--|--|
|--|-----------------------------------------------------------------------------|--|--|--|--|--|--|
| AWAKE, up and about | IN BED, awake or asleep | OFF WRIST |
|---------------------|-------------------------|-----------|
| 95% | 95% | 87% |
### 2.1.3 Phase 2 Summary
Since once the "in-bed" state was determined to have occurred it was of utmost importance to show correct actigraphy-based classification of sleep and wake episodes, a second study focused on the comparison between in-bed polysomnography and in-bed actigraphy. Via the collection of actigraphy data simultaneously from 50 patients undergoing polysomnographic assessment at the Kettering Sleep Disorders Center, the specificity and sensitivity of actigraphic sleep/wake assessments were determined. Results indicated that SBV2 sleep/wake classification corresponded to night-time polysomnographic findings with a sensitivity of 88% and a specificity of 55% (see Table 2).
| | THE SE STAULTIONAL AND POST LA LE POLL CARTER STERES MICA | |
|----------------|-----------------------------------------------------------------|-------|
| Total accuracy | ensitivity | |
| 040 | 000 | 5 201 |
| Table 2: Classification accuracy of SBV2 vs polysomnography sleep/wake<br>and the contract of the contract and the comments of the comments of the contribution of the comments of the contribution of the comments of the contribution of the contribut | | |
|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|--|
|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|--|
#### 2.1.4 Final Result
Considering that for most people the majority of in-bed time would be spent sleeping, the in-bed sensitivity (correct identification of sleep) was weighted slightly more heavily than the in-bed specificity (correct identification of wake) by averaging the "in-bed state detection" of 95% with the "in-bed-asleep detection" of 88%. This yielded an overall SBV2 vs polysomnography agreement level of 93%.
{4}------------------------------------------------
### 2.2 Sleep Report Summary
The device allows some aspects of sleep derived from the analysis of activity to be described in a sleep report. The sleep report uses a set of parameters that describe the normal ranges for an average adult user. Any further interpretations of sleep from the report should only be performed by a qualified health care professional such as a physician with training in the normal and abnormal physiology of sleep. These normal ranges are supported by the following data.
### 2.2.1 Sleep Duration
The normal range of sleep duration for adults is set to 7-9 hours according to supporting data from Table 1 in Berger et al. (2005), Sleep/wake disturbances in people with cancer and their caregivers: State of the Science. Oncology Nursing Forum, 32(6):E98-E126. In addition, both the National Sleep Foundation and the Mayo Clinic state that 7-9 is the normal range for adults. The following table appears at http://www.sleepfoundation.org/article/howsleep-works/how-much-sleep-do-we-really-need:
| How Much Sleep Do You Really Need? | |
|------------------------------------|----------------|
| Age | Sleep Needs |
| Newborns (0-2 months) | 12-18 hours |
| Infants (3 to 11 months) | 14 to 15 hours |
| Toddlers (1-3 years) | 12 to 14 hours |
| Preschoolers (3-5 years) | 11 to 13 hours |
| School-age children (5-10 years) | 10 to 11 hours |
| Teens (10-17) | 8.5-9.25 hours |
| Adults | 7-9 hours |
### 2.2.2 Sleep Latency
The normal range of sleep latency is set to 10-20 minutes according to supporting data found in a published chapter by Kryger et al. in "Principles and practice of Sleep Medicine, 2nd edition, page 965."
Source: National Steep Foundation
#### Sleep Efficiency Range 2.2.3
The normal sleep efficiency range is stated as 95-80% according to supporting data found in Table 1 in Berger et al. (2005), Sleep/wake disturbances in people with cancer and their caregivers: State of the Science, Oncology Nursing Forum. 32(6):E98-E126; as well as in Table 2 in Bonnet and Arand (2007). EEG arousal norms by age, Journal of Clinical Sleep Medicine, 3(3):271-274.
### Bedtime Deviation 2.2.4
There are no established norms for this measure, however it is widely considered a general good-sleep-hygeine practice to minimize the deviation in bedtimes from night to night in order to promote quality restorative sleep.
{5}------------------------------------------------
Therefore, this metric (without displaying the norm) is shown in the sleep report to present users with an assessment of how well they are following this recommended practice (of adhering to a consistent bedtime).
### 2.3 Obtaining References
All referenced materials will be provided to dispensers in the form of hard copies in a binder. Below is a list of included references:
- => Russel, C.A, Caldwell, J.A., et al. (2011), "Validation of the Fatigue Science SBV2." Fatigue Science White Paper.
- > Carskadon, M.A. (1994). Guidelines for the Multiple Sleep Latency Test (MSLT): A Standard Measure of Sleepiness, in Kryger et al. (eds.), "Principles and practice of Sleep Medicine," pp 962-966. Philadelphia: WB Saunders Co.
- > Berger et al., (2005). Sleep/wake disturbances in people with cancer and their caregivers: State of the Science, "Oncology Nursing Forum," 32(6):E98-E126
- > Bonnet and Arand (2007), EEG arousal norms by age, "Journal of Clinical Sleep Medicine," 3(3):271-274
{6}------------------------------------------------
Image /page/6/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a stylized eagle with three stripes forming its body and wing. The eagle is positioned to the right of a circular border containing the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" in a sans-serif font.
Food and Drug Administration 10903 New Hampshire Avenue Document Control Room -WO66-G609 Silver Spring, MD 20993-0002
Sleep Performance D.B.A. Fatigue Science c/o Mr. Mark Goodmand, Senior Associate Noblit & Rueland 5405 Alton Parkway, Suite A530 Irvine, CA 92604
Re: K111514
Trade/Device Name: SVB2 System Regulation Number: Unclassified Regulation Name: Sleep Assessment Device Regulatory Class: Unclassified Product Code: LEL Dated: November 21, 2011 Received: November 23, 2011
DEC 1 6 2011
Dear Dr. Downs:
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.
{7}------------------------------------------------
Page 2 - J. Hunter Downs III, Ph.D.
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 device-related 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 go to http://www.fda.gov/AboutFDA/CentersOffices/CDRH/CDRHOffices/ucm115809.htm for the Center for Devices and Radiological Health's (CDRH's) Office of Compliance. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR 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 Small Manufacturers, International and Consumer Assistance 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.
for
Sincerely vours.
Malvina B. Eydelman, M.D.
Director
Division of Ophthalmic, Neurological,
and Ear, Nose and Throat Devices
Office of Device Evaluation
Center for Devices and Radiological Health
Enclosure
{8}------------------------------------------------
# Indications for Use Statement
510 (k) Number (if known) K111514
Device Name SBV2 System
Indications The SBV2 System is an activity monitor designed and intended for for Use documenting physical movements associated with applications in physiological monitoring. The device's intended use is to analyze limb activity associated with movement during sleep and to extract information about certain sleep parameters from these movements. SBV2 can also be used to assess activity in any instance where quantifiable analysis of physical motion is desirable. The use of SBV2 is indicated for adults 22 years of age and over.
Prescription Use (Part 21 CFR 801 Subpart D)
AND/OR
Over-The-Counter Use X (21 CFR 801 Subpart C)
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE OF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
(Division Sign-Off) Division of Ophthalmic, Neurological and Ear, Nose and Throat Devices
Page 1 of 1
Kii514
510(k) Number
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.