K181823 · AliveCor, Inc. · DQK · Mar 11, 2019 · Cardiovascular
Device Facts
Record ID
K181823
Device Name
KardiaAI
Applicant
AliveCor, Inc.
Product Code
DQK · Cardiovascular
Decision Date
Mar 11, 2019
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 870.1425
Device Class
Class 2
Attributes
Software as a Medical Device
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Atrial Fibrillation Detection
—
—
—
—
—
—
—
Normal Sinus Rhythm Detection
—
—
—
—
—
—
—
Bradycardia Detection
—
—
—
—
—
—
—
Tachycardia Detection
—
—
—
—
—
—
—
Indications for Use
The KardiaAI is a software analysis library intended to assess ambulatory electrocardiogram (ECG) rhythms from adult subjects. The device supports analyzing data recorded in compatible formats from any ambulatory ECG devices such as event recorders, or other similar devices. The library is intended to be integrated into other device software. The library is not intended for use in life supporting, or sustaining systems, or ECG monitors, or cardiac alarm, or OTC use only devices. The KardiaAI provides the following capabilities: - ECG noise filtering, - heart rate measurement from ECGs, - detection of noisy ECGs, and - ECG rhythm analysis for detecting the presence of normal sinus rhythm, atrial fibrillation, bradycardia, and tachycardia (when prescribed or used under the care of a physician).
Device Story
KardiaAI is a software library (SaMD) providing an API for integration into third-party ambulatory ECG devices. It processes 30-second ECG inputs to perform noise filtering, heart rate measurement, and rhythm analysis. The library identifies normal sinus rhythm, atrial fibrillation, bradycardia, and tachycardia. It is intended for non-urgent clinical decision support; output is displayed on the host device for physician review. By automating rhythm analysis, it assists clinicians in diagnosing arrhythmias, potentially improving patient management and diagnostic efficiency.
Clinical Evidence
Bench testing only. Algorithm performance verified using ECG databases compliant with ANSI/AAMI EC57:2012 and proprietary AliveCor databases. Overlapping algorithms (AF, NSR, noise) met performance criteria established for the predicate Kardia Band System.
Technological Characteristics
Software-only library (SaMD) providing an API for integration into host ECG devices. Implements proprietary ECG processing and analysis algorithms. Supports multi-lead ambulatory ECG input. No hardware components. Connectivity via API integration into target device software.
Indications for Use
Indicated for adult subjects (over 18) for assessment of ambulatory ECG rhythms. Supports analysis of data from event recorders or similar ambulatory ECG devices. Not for life-supporting/sustaining systems, ECG monitors, cardiac alarms, or OTC-only devices. Use must be prescribed or under physician care.
Regulatory Classification
Identification
A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
March 11, 2019
AliveCor, Inc. Prabhu Raghavan Vice President of Regulatory and Quality 444 Castro Street, Suite 600 Mountain View. California 94041
Re: K181823
Trade/Device Name: KardiaAI Regulation Number: 21 CFR 870.1425 Regulation Name: Programmable Diagnostic Computer Regulatory Class: Class II Product Code: DOK, DPS Dated: February 8, 2019 Received: February 11, 2019
Dear Prabhu Raghavan:
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 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for
{1}------------------------------------------------
devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.html; 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 medical devices and radiation-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) K181823
Device Name KardiaAI
Indications for Use (Describe)
The KardiaAI is a software analysis library intended to assess ambulatory electrocardiogram (ECG) rhythms from adult subjects. The device supports analyzing data recorded in compatible formats from any ambulatory ECG devices such as event recorders, or other similar devices. The library is intended to be integrated into other device software. The library is not intended for use in life supporting, or sustaining systems, or cardiac alarm, or OTC use only devices.
The KardiaAI library provides the following capabilities:
- · ECG noise filtering.
- · heart rate measurement from ECGs,
- · detection of noisy ECGs, and
· ECG rhythm analysis for detecting the presence of normal sinus rhythm, atrial fibrillation, bradycardia (when prescribed or used under the care of a physician).
Type of Use (Select one or both, as applicable)
> Prescription Use (Part 21 CFR 801 Subpart D)
X Over-The-Counter Use (21 CFR 801 Subpart C)
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
## 510(k) Notification K181823
## GENERAL INFORMATION [807.92(a)(1)]
#### Applicant:
AliveCor, Inc. 444 Castro Street, Suite 600 Mountain View, CA 94041 USA Phone: 650-396-8553 Fax: 650-282-7932
## Applicant Contact Person:
Prabhu Raghavan Vice President of Regulatory and Quality AliveCor, Inc. 444 Castro Street, Suite 600 Mountain View, CA 94041 USA Phone: 650-396-8553 Fax: 650-282-7932 Email: prabhu@alivecor.com
## Assisted by:
Anna Libman Regulatory Consultant to AliveCor, Inc. Consultant, Regulatory Affairs Experien Group, LLC 224 Airport Parkway, Suite 250 San Jose, CA 95110 USA
Date Prepared: March 06, 2019
## DEVICE INFORMATION [807.92(a)(2)]
### Trade Name:
KardiaAI
## Generic/Common Name:
Programmable diagnostic computer
### Classification:
21 CFR§870.1425, Programmable diagnostic computer, Class II
## Product Code:
DQK, DPS
{4}------------------------------------------------
## PREDICATE DEVICE(S) [807.92(a)(3)]
- . Primary predicate: AliveCor, Inc., Kardia Band System, K171816
- Secondary predicate: CardioLogs Technologies, CardioLogs ECG Analysis . Platform, K170568
## DEVICE DESCRIPTION [807.92(a)(4)]
KardiaAI is a software library that implements various ECG processing and analysis algorithms. This Software as a Medical Device (SaMD) computes various physiologic parameters from a 30-second ECG and provides these capabilities in the form of an Application Program Interface (API) library. ECG devices can incorporate the API library into ECG device ("target device") software to enable algorithmic analysis of ECGs to provide analytical capabilities. The device provides ECG noise filtering and detection of noisy ECGs as well as identifies normal sinus rhythm, atrial fibrillation, bradycardia, and tachycardia.
## INDICATIONS FOR USE [807.92(a)(5)]
KardiaAI is a software analysis library intended to assess ambulatory electrocardiogram (ECG) rhythms from adult subjects. The device supports analyzing data recorded in compatible formats from any ambulatory ECG devices such as event recorders, or other similar devices. The library is intended to be integrated into other device software. The library is not intended for use in life supporting, or sustaining systems, or ECG monitors, or cardiac alarm, or OTC use only devices.
The KardiaAI provides the following capabilities:
- ECG noise filtering,
- heart rate measurement from ECGs,
- detection of noisy ECGs, and
- ECG rhythm analysis for detecting the presence of normal sinus rhythm, atrial fibrillation, bradycardia, and tachycardia (when prescribed or used under the care of a physician).
## SUBSTANTIAL EQUIVALENCE
KardiaAI has the same intended use as the predicate devices for the purpose of analyzing ambulatory ECG recordings. All three devices analyze ECGs for non-active patient monitoring or non-urgent clinical decision making. KardiaAI and the predicate devices all condition and analyze ECG signals from ambulatory Lead I ECG devices and provide data for display on the ECG target devices. KardiaAI shares the atrial fibrillation (AF), normal sinus rhythm (NSR), and noise algorithm with the Kardia Band System predicate device and contains the additional classifiers for bradycardia and tachycardia. Further, like the CardioLogs predicate device, KardiaAI is a SaMD with API for connecting with ECG devices and sending algorithm output for display. As such, the device has the same intended use as the predicate devices and similar technological characteristics. Differences between the subject device and the predicates have been tested to ensure that the device meets its intended use. Therefore, KardiaAI is substantially equivalent to the predicate devices.
{5}------------------------------------------------
| Feature | AliveCor KardiaAI | AliveCor Kardia Band System<br>(K171816) | CardioLogs Technologies CardioLogs ECG<br>Analysis Platform<br>(K170568) |
|---------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Product Code | DQK, Computer, Diagnostic, Programmable<br>DPS, Electrocardiograph | DPS, Electrocardiograph<br>DXH, Transmitters And Receivers,<br>Electrocardiograph, Telephone | DQK, Computer, Diagnostic, Programmable<br>DPS, Electrocardiograph |
| Regulation | 870.1425, Programmable diagnostic computer | 870.2920, Telephone electrocardiograph<br>transmitter and receiver | 870.1425, Programmable diagnostic computer |
| Indications for use | KardiaAI is a software analysis library intended<br>to assess ambulatory electrocardiogram (ECG)<br>rhythms from adult subjects.<br>The device supports analyzing data recorded in<br>compatible formats from any ambulatory ECG<br>devices such as event recorders, or other similar<br>devices. The library is intended to be integrated<br>into other device software.<br>The library is not intended for use in life<br>supporting, or sustaining systems, or ECG<br>monitors, or cardiac alarm, or OTC use only<br>devices.<br>KardiaAI provides the following capabilities:<br>• ECG noise filtering,<br>• heart rate measurement from ECGs,<br>• detection of noisy ECGs, and<br>• ECG rhythm analysis for detecting the<br>presence of normal sinus rhythm, atrial<br>fibrillation, bradycardia, and tachycardia | The Kardia Band System is intended to<br>record, store and transfer single-channel<br>electrocardiogram (ECG) rhythms.<br>The Kardia Band System also displays ECG<br>rhythms and detects the presence of atrial<br>fibrillation and normal sinus rhythm (when<br>prescribed or used under the care of a<br>physician).<br>The Kardia Band System is intended for use<br>by healthcare professionals, adult patients<br>with known or suspected heart conditions<br>and health conscious individuals. | The CardioLogs ECG Analysis Platform is intended for<br>use by qualified healthcare professionals for the<br>assessment of arrhythmias using ECG data in subjects<br>over 18 years of age.<br>The product supports downloading and analyzing data<br>recorded in compatible formats from any device used<br>for the arrhythmia diagnostics such as Holter, event<br>recorder, 12 lead ambulatory ECG devices, or other<br>similar devices when assessment of the rhythm is<br>necessary. The CardioLogs ECG Analysis Platform can<br>also be electronically interfaced and perform analysis<br>with data transferred from other computer based ECG<br>systems, such as an ECG management system.<br>The CardioLogs ECG Analysis Platform provides ECG<br>signal processing and analysis, QRS and Ventricular<br>Ectopic Beat detection, QRS feature extraction,<br>interval measurement, heart rate measurement, and<br>rhythm analysis. |
| Feature | AliveCor KardiaAI | AliveCor Kardia Band System<br>(K171816) | CardioLogs Technologies CardioLogs ECG<br>Analysis Platform<br>(K170568) |
| | (when prescribed or used under the care of a<br>physician). | | The CardioLogs ECG Analysis Platform is not for use<br>in life supporting or sustaining systems or ECG<br>monitor and Alarm devices. |
| | | | The product can be integrated into computerized ECG<br>monitoring devices. In this case, the medical device<br>manufacturer will identify the indication for use<br>depending on the application of their device. |
| | | | CardioLogs ECG Analysis Platform interpretation<br>results are not intended to be the sole means of<br>diagnosis. It is offered to physicians and clinicians on<br>an advisory basis only in conjunction with the<br>physician's knowledge of ECG patterns, patient<br>background, clinical history, symptoms, and other<br>diagnostic information. |
| Target population | Adults (over 18) | Adults (over 18) | Adults (over 18) |
| Components | Software only | Software and ECG recording device | Software only |
# Comparison of Technological Characteristics with the Predicate Devices
{6}------------------------------------------------
{7}------------------------------------------------
| Feature | AliveCor KardiaAI | AliveCor Kardia Band System<br>(K171816) | CardioLogs Technologies CardioLogs ECG<br>Analysis Platform<br>(K170568) |
|------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Software Functional<br>Comparisons | - An interface that provides tools to process and<br>analyze ECGs through various algorithms<br>- The automated proprietary ECG algorithms<br>provide supportive information for ECG<br>diagnosis. The library can be accessed by<br>directly connecting to the KardiaAI's<br>Application Programming Interface | - Kardia watch app software used to<br>analyze and display ECG signals<br>received from the Kardia Band hardware<br>- Kardia phone app used to create Kardia<br>account, onboard users, store, re-display<br>and transfer ECGs received from the<br>Kardia watch app | - An interface which provides tools to measure,<br>analyze and review numerous ECGs coded in java<br>language under the Angular and D3.js frameworks;<br>- An automated proprietary ECG interpretation<br>support algorithm which measures and analyzes<br>ECGs to provide supportive information for ECG<br>diagnosis,<br>This application can be accessed through an Internet<br>connection and a web browser, or is directly connected<br>to the CardioLogs' Application Programming Interface<br>(API) |
{8}------------------------------------------------
## PERFORMANCE DATA [807.92(b)]
All necessary testing was conducted on the KardiaAI to support a determination of substantial equivalence to the predicate device.
## Nonclinical Testing Summary [807.92(b)(1)]
Non-clinical testing was conducted to assess algorithm performance and to verify that KardiaAI performs as intended. Algorithm performance testing was assessed using ECG databases from the ANSI/AAMI EC57:2012 standard as well as AliveCor proprietary databases. The overlapping algorithms between KardiaAI and the Kardia Band System met the same performance acceptance criteria. The results of the testing demonstrate that KardiaAI performs to its specifications and meets its intended use, which is substantially equivalent to that of the predicate devices.
## CONCLUSIONS [807.92(b)(3)]
The results of nonclinical testing demonstrate that the KardiaAI meets its intended use which is equivalent to that of the predicate devices. The overlapping AF, NSR, and noise algorithms for KardiaAI and Kardia Band System met the same performance criteria. Testing also ensured that differences in technological characteristics between the KardiaAI and the Kardia Band System (primary predicate) (i.e., bradycardia and tachycardia algorithms as well as multilead ambulatory ECG input) perform as intended and do not raise different questions of safety or effectiveness.
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.