K182456 · Verily Life Sciences, LLC · DXH · Jan 17, 2019 · Cardiovascular
Device Facts
Record ID
K182456
Device Name
Study Watch
Applicant
Verily Life Sciences, LLC
Product Code
DXH · Cardiovascular
Decision Date
Jan 17, 2019
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 870.2920
Device Class
Class 2
Attributes
AI/ML
Indications for Use
The Study Watch is intended to record, store, transfer, and display single-channel electrocardiogram (ECG) rhythms. The Study Watch is intended for use by healthcare professionals, adult patients (22 years or older) with known or suspected heart conditions, and health conscious individuals.
Device Story
Study Watch is a wearable physiological monitoring device; captures single-channel ECG rhythms via two sensing electrodes and a right-leg drive (RLD) electrode for interference reduction. Patient initiates 60-second measurement by touching watch electrodes; data stored on device; transferred via USB through a charging cradle and Study Hub to a cloud server. Healthcare professionals (HCPs) access time-stamped ECG waveforms via a web portal. Device lacks automated analysis or patient-facing waveform display. Used by patients for daily monitoring; HCPs review data to inform clinical decision-making regarding heart conditions. Benefits include remote access to patient ECG data for professional review.
Clinical Evidence
Clinical testing demonstrated qualitative clinical equivalence to an industry-standard 12-lead ECG. Quantitative analysis of inter-beat intervals showed a bias of 1.2ms with 95% limits-of-agreement <20ms. A human factors assessment was conducted to identify potential use errors and validate risk management measures, confirming the device is safe and effective for its intended use.
Technological Characteristics
Wearable watch with two sensing electrodes and one right-leg drive (RLD) electrode. Frequency response: 0.16 Hz - 40 Hz; 240 samples/second; 16-bit resolution. Power: Lithium Polymer rechargeable battery (112 hours life). Connectivity: USB via Study Hub to cloud. Standards: ISO 14971, IEC 60601-1, IEC 60601-1-2, IEC 60601-2-47, IEC 62133, IEC 62304, ISO 10993-1, ISTA 2A.
Indications for Use
Indicated for adult patients (22 years or older) with known or suspected heart conditions, and health conscious individuals, for the recording, storage, transfer, and display of single-channel ECG rhythms.
Regulatory Classification
Identification
A telephone electrocardiograph transmitter and receiver is a device used to condition an electrocardiograph signal so that it can be transmitted via a telephone line to another location. This device also includes a receiver that reconditions the received signal into its original format so that it can be displayed. The device includes devices used to transmit and receive pacemaker signals.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logos of the U.S. Department of Health & Human Services and the U.S. Food & Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the FDA acronym in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
January 17, 2019
Verily Life Sciences LLC Shilpa Mydur Sr. Principal, Regulatory Affairs 269 E Grand Avenue South San Francisco, California 94080
Re: K182456
Trade/Device Name: Study Watch Regulation Number: 21 CFR 870.2920 Regulation Name: Telephone Electrocardiograph Transmitter And Receiver Regulatory Class: Class II Product Code: DXH, DPS Dated: December 20, 2018 Received: December 20, 2018
Dear Shilpa Mydur:
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. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. 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.
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
{1}------------------------------------------------
801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.htm); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
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 comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice
(https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
# Jessica E. Paulsen -S
for
Bram D. Zuckerman, M.D. Director Division of Cardiovascular Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known) K182456
Device Name Study Watch
Indications for Use (Describe)
The Study Watch is intended to record, store, transfer, and display single-channel electrocardiogram (ECG) rhythms. The Study Watch is intended for use by healthcare professionals, adult patients (22 years or older) with known or suspected heart conditions, and health conscious individuals.
| Type of Use (Select one or both, as applicable) |
|-------------------------------------------------|
|-------------------------------------------------|
| <div> <span>☑</span> Prescription Use (Part 21 CFR 801 Subpart D) </div> | <div> <span>☐</span> Over-The-Counter Use (21 CFR 801 Subpart C) </div> |
|-----------------------------------------------------------------------------|----------------------------------------------------------------------------|
|-----------------------------------------------------------------------------|----------------------------------------------------------------------------|
#### 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 -Study Watch
| Date Prepared: | January 11, 2019 |
|------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Submitter: | Verily Life Sciences LLC |
| Official Contact: | Shilpa Mydur<br>Sr. Principal, Regulatory<br>Affairs 269 E Grand Ave<br>South San Francisco, CA 94080, USA<br>Telephone: +1-415-736-0652<br>Fax: +1650-618-1499<br>E-Mail: smydur@google.com |
| Proprietary Name: | Study Watch |
| Common Name: | Telephone Electrocardiograph Transmitter and Receiver |
| Classification: | Class II Medical Device<br>Requlation Number: 21 CFR 870.2920<br>Product Code: DXH, DPS |
| Predicate Device: | AliveCor Kardia Band (K171816) |
| Reason For Submission: | New Device |
#### Indications for Use
The Study Watch is intended to record, store, transfer, and display single-channel electrocardiogram (ECG) rhythms. The Study Watch is intended for use by healthcare professionals, adult patients (22 years or older) with known or suspected heart conditions, and health conscious individuals.
#### Device Description
The Study Watch is a miniaturized physiological data monitoring device that is intended to record, store, transfer and display single-channel electrocardiogram (ECG) rhythms. The device utilizes a band and proprietary watch that incorporates two dedicated sensing electrodes to obtain a single-channel ECG measurement. In practice, a healthcare professional (HCP) may prescribe the Study Watch to a patient and recommend the capture and transmission of one or more ECG rhythms on a daily basis for analysis by the HCP. The patient uses prompts provided on the graphical user interface (GUI) of the watch to collect a real-time 60-second ECG measurement. While an animated ECG waveform is briefly displayed on the GUI of the watch, the patient will not have direct access to the collected waveform. Using the provided charging dock (Cradle) and Verily's Study Hub device, the ECG measurements are securely transferred to Verily's cloud server and are viewed by the HCP using a web portal. The web portal is solely intended for use by the HCP to view time-stamped ECG waveforms collected by the patient and does not include any analysis features. Collectively, the Study Watch consists of the wearable watch and band, the Study Hub (used to transfer data from the watch to the cloud), a Cradle, and the web portal.
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the word "verily" in red font. The font is a sans-serif font, and the letters are all lowercase. There is a line underneath the "ve" in the word. The background is white.
## Substantial Equivalence Discussion
The Study Watch has the following similarities to the previously cleared predicate device:
- Similar Intended Use A
- ♪ Similar Technological Characteristics
- ハ Similar Performance Specifications
A comparative summary of the technological characteristics of the Study Watch with the predicate device AliveCor Kardia Band (K171816) is presented below:
| Characteristic | AliveCor Kardia Band (K171816) | Study Watch (New Device) |
|--------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Indications for<br>Use | The Kardia Band System is intended to<br>record, store and transfer single-channel<br>electrocardiogram (ECG) rhythms. The<br>Kardia Band System also displays ECG<br>rhythms and detects the presence of<br>atrial fibrillation and normal sinus rhythm<br>(when prescribed or used under the care<br>of a physician). The Kardia Band<br>System is intended for use by<br>healthcare professionals, adult patients<br>with known or suspected heart<br>conditions, and health conscious<br>individuals. | The Study Watch is intended to record,<br>store, transfer, and display single-<br>channel electrocardiogram (ECG)<br>rhythms. The Study Watch is intended<br>for use by healthcare professionals,<br>adult patients (22 years or older) with<br>known or suspected heart conditions,<br>and health conscious individuals. |
| Product Code | DXH, DPS | DXH, DPS |
| Mechanism of<br>Action | User completes circuit with skin contact<br>and hardware transmits audio signal to<br>MCP to convert and display ECG<br>waveform | User completes circuit with skin contact<br>and hardware measures ECG<br>waveform, which is stored and securely<br>transferred to the cloud via the<br>proprietary Study Hub |
| Where Used | Mobile/active users at rest (ambulatory) | Same |
| Anatomical Sites | Left hand fingers to right wrist or vice<br>versa | Same |
| Data Acquisition:<br>Frequency<br>Response | 0.5 Hz - 40 Hz | 0.16 Hz - 40 Hz |
| ECG Channels | Single Channel | Same |
| Resolution | 16 bit | Same |
| Sample Rate | 300 Samples/Second | 240 Samples/Second |
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the word "verily" in red font. The font is sans-serif and has a modern, clean look. The letters are evenly spaced and the word is easy to read. There is a red line under the "ve" in the word.
| Memory Capacity | Essentially unlimited due to real-time<br>transmission to MCP memory (size of<br>ECG file is miniscule - kilobytes<br>compared to device memory capacity –<br>gigabytes) | 512 MB |
|--------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------|
| Number of ECG<br>Leads | Single lead, 2 sensing electrodes | Single lead, 2 sensing electrodes and 1<br>right-leg drive (RLD) electrode |
| Power Supply:<br>Battery | 1 Lithium Manganese Dioxide Coin Cells | 1 Lithium Polymer Rechargeable<br>Battery |
| Battery Life | 100 hours operational | 112 Hours Per Full Charge |
| User Interface: | Lead I, Left to Right | Same |
| Primary Lead | Ultrasonic acoustics | USB |
| Data Acquisition | Apple Watch Band and Sensor | Study Watch |
| Hardware<br>Software<br>Interface | Apple iOS based software and Apple<br>WatchOS based software | Study Watch Graphical User Interface,<br>Web Portal |
| Physical Specs:<br>Dimensions | 24.5 x 24.5 x 6.5 mm | 42.6 x 42.3 x 11 mm |
| Weight | 9 grams | 22 grams (without watch band) |
| Prescribed | Prescription and OTC | Prescription |
| Environmental:<br>Operating Temp<br>Storage Temp | 10 to 40 degrees C<br>-20 to 60 degrees C | -5 to 40 degrees C<br>-25 to 70 degrees C |
| Communications | Ultrasonic Acoustics acquired by watch | USB via Study Hub |
The major differences between the Study Watch and the AliveCor Kardia Band are as follows:
- > Indications for Use: The Indications for Use statement for Study Watch is not identical to that of the predicate device. The intended use of the predicate device includes detection of atrial fibrillation and normal sinus rhythm based on a system analysis of the collected ECG waveform. These analysis features are not present in the Study Watch, and the proposed device is solely intended to record, store, transfer and display ECG waveforms. The Study Watch patient uses the device to record and transfer ECG waveforms to the healthcare provider, but does not have direct access to independently view these data. Accordingly, the Study Watch is only intended for prescription use.
{6}------------------------------------------------
K182456
Image /page/6/Picture/1 description: The image shows the word "verily" in red font. The word is lowercase and has a line underneath the "ve" portion of the word. The font is sans-serif and the letters are evenly spaced. The background is white.
- Δ Data Collection: The Study Watch features a band and proprietary watch that incorporates two dedicated sensing electrodes to enable single-channel ECG measurement. The first of the sensing electrodes is positioned on the top of the watch, and the other sensing electrode is at the bottom of the watch contacting the user's wrist. When the user wears the watch on one wrist and contacts the top of the watch with the other hand, an acquisition loop is created and an ECG measurement is generated. The watch also includes a third electrode known as a right-leq drive (RLD) electrode which functions to reduce electrical interference from the environment to improve signal quality. The predicate device functions similarly to acquire ECG data from two sensing electrodes on a proprietary watch band, but does not incorporate the RLD electrode. The addition of the RLD electrode does not affect the stated intended use or fundamental scientific technology of the proposed device.
- A Data Transmission: The Study Watch uses a system whereby ECG data is collected by the wearable watch and is then transferred to Verily's Study Hub device via a USB connection to the included charging dock (Cradle). The data are then transferred from the Study Hub to Verily's cloud server for storage using the Study Hub and are then viewed by the HCP using a web portal. The predicate device uses a system that transfers the ECG signal from its electrodes to mobile medical application on the Apple Watch to be analyzed and presented directly to the user.
- A User Access: For the Study Watch, the ECG data is collected by the patient, but is only viewable in its final form by an HCP using the web portal. The predicate device enables viewing of the ECG waveform data by the patient using a dedicated mobile medical application.
The differences in technological characteristics have been evaluated through performance testing and do not raise any new questions of safety and effectiveness, and therefore the proposed device is substantially equivalent to the predicate device.
### Non-Clinical Performance Data
Design validation and verification activities were performed for the Study Watch as a result of the risk analysis assessment and product requirements. Testing included validation of specifications related to software development, sensor performance, stability and material properties. All tests confirmed that the product met the predetermined acceptance criteria. In particular, non-clinical performance testing demonstrated that the Study Watch is substantially equivalent to the predicate device when taking into account its intended use.
The Study Watch was designed and tested in accordance with the applicable requirements in relevant FDA guidance documents and international standards including:
- ISO 14971 (2012): Medical Devices - Application of Risk Managementto Medical Devices.
- . IEC 60601-1-2:2014 Medical electrical equipment - Part 1-2: General requirements for basic safety and essential performance - Collateral Standard: Electromagnetic disturbances - Requirements and tests
- . IEC 60601-1:2005 Medical electrical equipment - Part 1: General requirements for basic safety and essential performance
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the word "verily" in red font. The font is sans-serif and the letters are closely spaced together. There is a horizontal line underneath the "ve" in "verily". The word is likely a logo or brand name.
- . IEC 60601-2-47:2012/ (R)2016 Medical electrical equipment - Part 2-47:Particular requirements for the basic safety and essential performance of ambulatory electrocardiographic systems.
- IEC 62133 Battery Safety Testing
- . IEC 62304:2006 Medical device software -- Software life cycle processes
- . ISO 10993-1:2009 Biological evaluation of medical devices -- Part 1: Evaluation and testing within a risk management process
- . ISTA 2A (2011): Partial Simulation Performance Tests (Packaging). Packaged-Products 150 lb (68 kg) Or Less.
#### Clinical Performance Data
Clinical performance testing was conducted to demonstrate that the Study Watch generates data that meets the clinical quality requirements for an accurate ECG waveform display. The presented data shows qualitative clinical equivalence and inter-beat interval Bland-Altman analysis with Bias of 1.2ms and 95% limits-of-agreement <20ms when compared to industry-standard 12-lead ECG device. The study is sufficient to draw a conclusion of substantial equivalence based on meeting qualitative and quantitative acceptance criteria. In addition, a human factors assessment was conducted to identify errors associated with the use of the Study Watch that could lead to patient harm and to assess the effectiveness of specific risk management measures. This study demonstrated that the Study Watch is safe and effective for the specified intended use.
#### Conclusion
The information in this submission demonstrates that the Study Watch is substantially equivalent to the cited predicate device. The non-clinical and clinical data support the safety and effectiveness of the device and demonstrate that Study Watch should perform as intended in the specified use conditions.
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.