MONEBO AUTOMATED ECG ANALYSIS AND INTERPRETATION SOFTWARE LIBRARY, VERSION 3.0
K062282 · Monebo Technologies, Inc. · DPS · Mar 22, 2007 · Cardiovascular
Device Facts
Record ID
K062282
Device Name
MONEBO AUTOMATED ECG ANALYSIS AND INTERPRETATION SOFTWARE LIBRARY, VERSION 3.0
Applicant
Monebo Technologies, Inc.
Product Code
DPS · Cardiovascular
Decision Date
Mar 22, 2007
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 870.2340
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
The Automatic Analysis and Interpretation Software Library is intended for use by qualified medical professionals for the assessment of arrhythmias using historic ambulatory ECG data. The product supports downloading and analyzing data recorded in compatible formats from any device used for the arrhythmia diagnostics such as Hotter, Event Monitor, 12 lead ambulatory or resting ECG devices, or other similar devices when assessment of the rhythm is necessary. The Automatic Analysis and Interpretation Software Library can also be electronically interfaced, and perform analysis with data transferred from other computer based ECG systems, such as an ECG management system. The Automatic Analysis and Interpretation Software Library provides ECG signal processing and analysis on a beat by beat basis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, interval measurement, heart rate measurement, and rhythm analysis for up to sixteen(16) leads of captured data. The library is not for use in life supporting or sustaining systems or ECG monitoring and Alarm devices. The product can be integrated into computerized ECG monitoring devices. In this case the medical device manufacturer will identify the indication for use depending on the application of their device.
Device Story
Monebo Automated ECG Analysis and Interpretation Software Library (v3.0) is an object library (callable functions) integrated into ECG management software or ECG devices. Input: captured ECG data (up to 16 leads). Processing: signal processing, QRS detection, feature extraction, interval measurement (PR, QT), heart rate calculation, and rhythm classification. Output: annotated ECG analysis and interpretation. Used by trained medical professionals to review data and render diagnostic/treatment decisions. Benefits: assists clinicians in identifying arrhythmias from historic ambulatory recordings. Not for real-time monitoring or life-support.
Clinical Evidence
Bench testing only. Performance validated using AHA, MIT-BIH, and CSE databases per ANSI/AAMI EC 57 and IEC 60601-2-51. Results: QRS sensitivity 99.45-99.56%, VEB sensitivity 81.79-87.03%. Arrhythmia detection sensitivity 96%, specificity 97%. Overall rhythm classification performance: 90.23% sensitivity, 96.42% specificity, 82.19% positive predictivity.
Technological Characteristics
Object library (callable functions) compiled into machine/IDL code. Operates on Microsoft .Net framework. Provides signal processing, QRS detection, feature extraction, and rhythm analysis for up to 16 leads. Software-only device; no physical materials. Algorithm class: automated signal processing and classification.
Indications for Use
Indicated for use by qualified medical professionals for assessment of arrhythmias in adult patients using historic ambulatory ECG data from Holter, event monitors, 12-lead ambulatory, or resting ECG devices. Not for use in life-supporting/sustaining systems or real-time monitoring/alarm devices.
Regulatory Classification
Identification
An electrocardiograph is a device used to process the electrical signal transmitted through two or more electrocardiograph electrodes and to produce a visual display of the electrical signal produced by the heart.
{0}------------------------------------------------
K0622282
pg 1 of 4
#### 510(k) Summary of Safety and Effectiveness
510(k) Notification Date: August 4, 2006 January 3, 2007 Revised March 6, 2007 Revised
MAR 2 2 2007
Submitter: Monebo Technologies, Inc. 1800 Barton Creek Blvd Austin, Texas 78735-1606
Contact Person: Dale J. Misczvnski Phone: 512-732-0235 512-732-0285 Fax: Email: dale.misczynski@monebo.com
Trade/Device Name: Monebo Automated ECG Analysis and Interpretation Software Library, Version 3.0 Regulation Number: 21 CFR 870.2340 Regulation Name: Electrocardiograph Regulatory Class: Class II (two) Product Code: DPS
### Level of Concern Statement
The Monebo Automated ECG Analysis and Interpretation Software Library is a Moderate Level of Concern Software Device.
The library is intended for use with ECG management software which is a Moderate Level of Concern software device.
The library is not for use in life supporting or sustaining systems or ECG monitoring and Alarm devices.
A latent design flaw, failure or malfunction of the software, which were not revealed during the validation, verification and testing process, is possible over the life of the product. The results could result in a delayed response of appropriate medical care that would lead to injury or further diagnostic evaluations. The intended end users of the ECG analysis information are trained medical professional who are responsible for reviewing the device output and rendering the final diagnostic or treatment decision.
{1}------------------------------------------------
K062282
Pg 2 of 4
### Predicate Devices:
The Monebo Automatic Arrhythmia Detection Software Library, Agilent and Brentwood predicates are software only devices that monitor cardiac function. Table 1 compares the features of the Monebo Automated ECG Analysis and Interpretation Software Library to predicate devices.
| Feature | Monebo<br>Automated<br>ECG<br>Analysis and<br>Interpretation<br>Software<br>Library | Monebo<br>Automatic<br>Arrhythmia<br>Detection<br>Software<br>Library<br>510(k)<br>K043380 | Agilent<br>510(k)<br>K003621 | Brentwood<br>510(k)<br>K013717 |
|-----------------------------------------------------------------|-------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------|-----------------------------------|--------------------------------|
| Heart rate determination for<br>non-paced adult | YES | NO | YES | YES |
| QRS Detection | YES | YES | YES | YES |
| Non-paced arrhythmia<br>interpretation for adult<br>patients | YES | NO | YES | YES |
| Non-paced ventricular<br>arrhythmia calls for adult<br>patients | YES | YES | YES | YES |
| Intervals measurement | YES | NO | YES | YES |
| Ventricular ectopic beat<br>detection | YES | YES | YES | YES |
| Patient Populations | Adult | Adult | Adults,<br>Pediatric,<br>Neonatal | Adult |
## Test Results
The bench test results of the software using AHA and MIT-BIH databases per ANSI/AAMI EC 57 are shown in the table below:
| Summary results of AHA and MIT testing | | | | |
|----------------------------------------|--------|--------|--------|--------|
| Database | QRS Se | QRS +P | VEB Se | VEB +P |
| AHA | 99.56 | 99.9 | 82.49 | 95.65 |
| MIT-BIH | 99.45 | 99.45 | 87.03 | 87.76 |
| NST | 91.56 | 85.66 | 81.79 | 53.19 |
The bench test results of the software using CSE database per IEC 60601-2-51 are shown in the tables below:
| Summary results of CSE DB testing | | | | |
|-----------------------------------|-------------------------------|-------------------------------------|---------------------------|------------------------------|
| Measurement | Acceptable<br>Mean difference | Acceptable<br>standard<br>deviation | Monebo mean<br>difference | Monebo standard<br>deviation |
{2}------------------------------------------------
K062282
pg 3 of 4
| MARKER BELL B OR E E BLE<br>interval | A + There and the state of the state of the state of the state of the state of the state of the state of the state of the state of the state of the state of the state of the<br>t<br>47.00<br>and and the before and would would and | And and the first of the first of the first and the first and<br>Madhentures and | ----------<br>Carmer Land<br>1 | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------<br>1 |
|--------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| duration<br>ﻟ<br>State Access All And And And And And And All And All All Propert Material Property And Pro- | 1<br>------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------<br>1<br>------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | A<br>0 |
| ntervai<br> | 185<br>1<br>1<br>I<br>A CALLERY - LETTER THE LEAST THE LEAST THE LEAST THE LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST LEAST L<br>---------- | ALL ALL ARRETH AND THE CHANGE OF CHEARTH AND THE CHANGE OF CHEARTH AND THE CHART THE CHART THE LEAST CHEAR FOR THE FOR THE FOR THE FOR THE FOR THE FORM FOR THE FORM FOR THE F<br>------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | .<br>1<br>------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------<br>A MINING AND AND AND OF A<br>00<br>Change |
| | | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | Acres A |
## Summary results of MIT DB arrhythmia statement testing:
| Accuracy of Arrhythmia Detection | | | |
|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------|---------------------------------|---------------------------------|
| Sensitivity | Specificity | Positive Predictive<br>Accuracy | Negative Predictive<br>Accuracy |
| 96 | 97 | 73 | 97 |
| Arrhythmias: Normal sinus rhythm, Sinus Bradycardia, Sinus Tachycardia, PVC, APC, Atrial Fibrillation,<br>Ventricular Tachycardia, Ventricular Flutter, Sinus Tachycardia, Pause (Asystole), AV block, BBB,<br>Ventricular trigeminy, Ventricular Bigeminy, AIVR | | | |
| Accuracy of Arrhythmia Statements | | | | |
|------------------------------------------------------------------------------------------------------------|-------------------|-------------------|------------------------------------|------------------------------------|
| Arrhythmias | Sensitivity | Specificity | Positive<br>Predictive<br>Accuracy | Negative<br>Predictive<br>Accuracy |
| MIT DB | | | | |
| Normal sinus<br>rhythm | 100 | 100 | 95 | 100 |
| PVC | 100 | 100 | 86 | 100 |
| APC | 96 | 66 | 70 | 66 |
| Atrial Fibrillation | 100 | 100 | 77 | 100 |
| Ventricular<br>Tachycardia | 75 | 89 | 60 | 89 |
| Bradycardia | Insufficient data | 96 | Insufficient data | 96 |
| Tachycardia | Insufficient data | 100 | Insufficient data | 100 |
| AV block | 57 | 87 | 26 | 87 |
| BBB | 77 | 88 | 25 | 88 |
| Ventricular<br>Trigeminy | 50 | 84 | 100 | 84 |
| Ventricular<br>Bigeminy | 81 | 93 | 81 | 93 |
| AIVR | 100 | 100 | 15 | 100 |
| Pause | Insufficient data | Insufficient data | Insufficient data | Insufficient data |
| CU DB | | | | |
| Ventricular<br>Flutter* | 100 | 94 | * | * |
| * Positive Predictive and Negative Predictive Accuracy cannot be calculated because all records contain VF | | | | |
The results covering Sensitivity, Positive Predictivity, Specificity, False Positive Rate, and Negative Predictivity and which are based on a database of 250 annotated ECG strips, renorded by various event recorders are in the table below.
{3}------------------------------------------------
| Rhythm | Sensitivity | Positive<br>Predictivity | Specificity | False<br>Positive<br>Rate | Negative<br>Predictivity |
|-----------------------------------|-------------|--------------------------|-------------|---------------------------|--------------------------|
| | Se | +P | Sp | FPR | -P |
| Normal sinus rhythm | 91.18 | 100.00 | 100.00 | 0.00 | 96.81 |
| Atrial fibrillation | 90.91 | 80.00 | 95.15 | 4.85 | 98.00 |
| Nodal rhythm | 76.47 | 46.43 | 93.56 | 6.44 | 98.20 |
| SVTA | 100.00 | 61.90 | 92.86 | 7.14 | 100.00 |
| Ventricular tachycardia | 100.00 | 85.71 | 99.59 | 0.41 | 100.00 |
| BBB | 82.14 | 79.31 | 97.30 | 2.73 | 97.74 |
| 1st degree AV block | 88.46 | 74.19 | 96.43 | 3.57 | 98.63 |
| 2nd degree AV block<br>(Mobitz 1) | 96.77 | 100.00 | 100.00 | 0.00 | 99.55 |
| 2nd degree AV block<br>(Mobitz 2) | 100.00 | 100.00 | 100.00 | 0.00 | 100.00 |
| Complete AV block | 96.77 | 100.00 | 100.00 | 0.00 | 99.55 |
| Idioventricular rhythm | 72.73 | 88.89 | 99.58 | 0.42 | 98.76 |
| Sinus bradycardia | 91.67 | 100.00 | 100.00 | 0.00 | 98.62 |
| Sinus tachycardia | 77.78 | 100.00 | 100.00 | 0.00 | 98.31 |
| APC | 77.50 | 65.26 | 80.59 | 19.41 | 88.39 |
| PVC | 89.55 | 73.17 | 87.98 | 12.02 | 95.83 |
| Pause | 96.88 | 73.81 | 94.95 | 5.05 | 99.52 |
| Overall Performance | 90.23 | 82.19 | 96.42 | 3.58 | 98.23 |
### Device Description:
The Monebo Automated ECG Analysis and Interpretation Software Library is an "object library". An object library is a collection of callable functions that have been complied (or assembled) into machine code or IDL code of the computer on which they execute. The Monebo Automated ECG Analysis and Interpretation Software Library consists of a basic application for viewing, analyzing and annotating ECG data, and a callable object library built on the Microsoft™ .Net framework. An application software program can be written to invoke some or all of the functions in an object library.
The Monebo Automated ECG Analysis and Interpretation Software Library provides ECG signal processing, QRS detection and measurement of duration, QRS feature extraction, classification of Normal and Ventricular Ectopic beats, heart rate measurement, measurement of PR and QT intervals, and rhythm interpretation for up to 16 leads of captured ECG data.
The library can be accessed through an Application Program Interface (API) as a callable function. This allows the library to be used as an accessory to an ECG management application or as a stand-alone product.
Monebo will compile the Monebo Automated ECG Analysis and Interpretation Software Library specified by an ECG device manufacturer. An object library will be created and delivered to the device manufacturer, who can then integrate it into application software for their ECG analysis.
{4}------------------------------------------------
Image /page/4/Picture/2 description: The image shows the logo for the U.S. Department of Health and Human Services. The logo features a stylized eagle with three human profiles incorporated into its design. The text "DEPARTMENT OF HEALTH AND HUMAN SERVICES, USA" is arranged in a circular pattern around the eagle.
APR 2 0 2007
Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850
Monebo Technologies Inc. c/o Mr. Dale Misczynski 1800 Barton Creek Blvd Austin, TX 78735
Re: K062282
Trade/Device Name: Monebo Automated ECG Analysis and Interpretation Software Library Regulation Number: 21 CFR 870.2340 Regulation Name: Electrocardiograph Regulatory Class: Class II (two) Product Code: DPS Dated: March 6, 2007 Received: March 7, 2007
Dear Mr. Misczynski:
This letter corrects our substantially equivalent letter of March 22, 2007.
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 (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.
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.
{5}------------------------------------------------
Page 2 - Mr. Misczynski
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); 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.
This letter will allow you to continue marketing your device as described in your Section 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Office of Compliance at (240) 276-0120. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). 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 (240) 276-3150 or at its Internet address http://www.fda.gov/cdrh/dsma/dsmamain.html
Sincerely yours,
B.J. Zimmerman fa
Bram D. Zuckerman, M.D. Director Division of Cardiovascular Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{6}------------------------------------------------
# Indications for Use
### 510(k) Number: K062282
### Device Name: Monebo Automatic ECG Analysis and Interpretation Software Library
Indications for Use:
The Automatic Analysis and Interpretation Software Library is intended for use by qualified medical professionals for the assessment of arrhythmias using historic ambulatory ECG data. The product supports downloading and analyzing data recorded in compatible formats from any device used for the arrhythmia diagnostics such as Hotter, Event Monitor, 12 lead ambulatory or resting ECG devices, or other similar devices when assessment of the rhythm is necessary. The Automatic Analysis and Interpretation Software Library can also be electronically interfaced, and perform analysis with data transferred from other computer based ECG systems, such as an ECG management system. The Automatic Analysis and Interpretation Software Library provides ECG signal processing and analysis on a beat by beat basis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, interval measurement, heart rate measurement, and rhythm analysis for up to sixteen(16) leads of captured data. The library is not for use in life supporting or sustaining systems or ECG monitoring and Alarm devices
The product can be integrated into computerized ECG monitoring devices. In this case the medical device manufacturer will identify the indication for use depending on the application of their device.
Prescription Use V
AND/OR
1000 1000 Over-The-Counter Use
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
Bhumimmo
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.