THINKINGNET, THINKINGPACS/RIS - PROPRIETARY NAME FRO THINKINGNET, THINKINGARCHIVE (OR NUPAX) - THE MANAGEMENT AND ARCHIV
Applicant
Thinking Systems Corp.
Product Code
LLZ · Radiology
Decision Date
Jul 9, 2012
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.2050
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
ThinkingNet with its modality specific and remote access applications is intended to be used by trained clinical staff to perform medical image management, communications, archiving and processing and review of medical images. The system can run on dedicated workstation or in a server-client configuration.
Device Story
ThinkingNet is a multi-modality PACS/RIS for medical image management, processing, and review. It ingests DICOM images from various diagnostic modalities. The system operates via local workstations or remote access (Web browser, thick/thin-client, cloud-based). Core functions include image storage, archival, transmission, and display. Advanced modules provide quantitative post-processing, multi-planar reformatting (MPR), 3D visualization, and modality-specific tools (e.g., mammography hanging protocols, orthopedic measurements, cardiac analysis). Clinicians use the system to interpret images and generate reports, facilitating clinical decision-making. Remote access allows collaboration and review by physicians and technologists. The device benefits patients by enabling efficient, accurate, and timely diagnostic review across various clinical settings.
Clinical Evidence
Bench testing only. Performance testing included requirements specification, design specification, hazard/risk analysis, modular testing, verification testing, validation testing, and integration testing to demonstrate substantial equivalence.
Technological Characteristics
Multi-modality PACS/RIS software. Supports DICOM standards. Deployment: local workstation, server-client, or cloud-based. Connectivity: LAN/WAN. Remote access via thick/thin-client or browser. Supports Windows and non-Windows clients (except ThinkingNet.Net). Modality-specific modules for radiology, cardiology, molecular imaging, and mammography. Includes 3D/MPR visualization and quantitative post-processing tools.
Indications for Use
Indicated for acceptance, transmission, storage, archival, reading, interpretation, clinical review, analysis, annotation, distribution, printing, editing, and processing of DICOM-compatible diagnostic images/data. Used by radiologists, cardiologists, physicians, technologists, and clinicians. Includes modules for molecular imaging (nuclear medicine, PET, SPECT), hybrid imaging (PET-CT, PET-MRI), mammography (screening/diagnosis), cardiology (nuclear, PET, echo, X-ray angio, CTA), orthopedics (measurements), 3D/MPR visualization, and quality assurance. Remote access via ThinkingWeb options supported.
Regulatory Classification
Identification
A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.
Special Controls
*Classification.* Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
Predicate Devices
Philips/Stentor iSite PACS 4.x and iSite Radiology (K063267, K013630)
{0}------------------------------------------------
K120305.
9 2012 JUL
## 510(k) Safety and Effectiveness Summary
# ThinkingNet Modality Applications and Web Extensions
## 1.1 Demographic Information
#### 1.1.1 Date Prepared
January 15, 2012 (Last update on July 5, 2012)
#### 1.1.2 Submitter
Thinking Systems Corporation
750 94" Avenue North, Suite 211 St. Petersburg, FL 33705 Phone: 727-217-0909 Fax: 727-217-0938 Email: jb@thinkingsystems.com
## 1.1.3 Contact
JB Wang, Co-CEO and Co-founder 750 94th Avenue North, Suite 211 St. Petersburg, FL 33705 Phone: 727-217-0909 Fax: 727-217-0938 Email: jb@thinkingsystems.com
## 1.2 Device Name
ThinkingNet Modality and Web Applications
## 1.2.1 Trade or Proprietary Names
ThinkingPACS/RIS (same as ThinkingNet), ModalityBroker (when used as a modality PACS), ThinkingArchive (the image archival and management subsystem), MDStation (the image review and processing subsystem), NuGateway (the image connectivity subsystem) and ThinkingWeb (the remote Web access subsystem).
## 1.2.2 Common Name
The common name used by FDA for similar devices is Picture Archive and Communications System (PACS).
## 1.3 Classification(s) of the Device
When the software modules are packaged and marketed as an image storage and communications device, with just NuPAX and NuLink (NuGateway) only for example, the system
{1}------------------------------------------------
falls in the classification of Medical Image Storage (Section 892.2010, product code LMB) and Medical Image Communications (Section 892.2020, product code LMD) devices. They are Class I.
As an integrated product; ThinkingNet with software modules that provide functions for advanced image processing, manipulation, enhancement, compression or quantification, is classified as a Picture Archiving and Communications System (PACS, Section 892.2050). The classification panel is Radiology and the product code is LLZ. It is a Class II device.
## 1.4 Device Description
ThinkingNet is a multi-modality PACS/RIS with applications optimized for each individual imaging modality. The image data and applications can be accessed locally or remotely. ThinkingNet workstation software is designed as diagnostic reading and processing software packages, which may be marketed as software only, as well as packaged with standard off-the-shelf computer hardware.
The base functions include receiving, transmission, storage, archival, display images from all imaging modalities. When enabled, the system allows remote access of image data and applications over a local or wide area network, using a Web browser, thick-client, thin-client or cloud-based remote application deployment method.
Options allow for additional capability, including modality specific applications, quantitative postprocessing, modality specific measurements, multi-planar reformatting and 3D visualization.
ThinkingNet Molecular Imaging modules offer the image processing functionality, through MDStation and ThinkingWeb, that have the same indication as the predicate modality workstations. It delivers image processing and review tools for applications used in functional imaging modalities, such as nuclear medicine, PET, PET/CT, SPECT/CT and PET/MRI.
ThinkingNet Mammo module is a diagnostic softcopy breast imaging workstation with diagnostic print capability.
- It displays and prints regionally approved DICOM DR Digital Mammography Images (MG . SOP class) with a default or user defined mammography hanging protocol.
- . It displays and prints regionally approved DICOM CR Digital Mammography Images (CR SOP class) a default or user defined mammography hanging protocol.
- It displays adjunct breast imaging modality studies (i.e. Breast MR, Breast . PET and Breast gamma camera) for comparison.
ThinkingWeb modules offer comprehensive remote image and application access methods to allow clinicians to review and process images remotely. It has the following modules.
- . ThinkingWebLite: Clientless image distribution via simple Web browser (see NuWEB in K010271). It is primarily a referral physician's portal, not intended for primary reading.
- . ThinkingNet.Net: A thick-client implementation using an existing image review module (NuFILM) with a proprietary image streaming mechanism.
- . ThinkingWeb: Cross-platform thin-client remote application access based the existing MDStation software and off-the-shelf remote computing technology.
- . ThinkingWeb Extreme: A cloud-based remote application deployment implementation based the existing MDStation software and off-the-shelf cloud computing technologies.
Besides ThinkingNet.Net, all ThinkingWeb products support cross-platform client computer devices. Thinking Net uses Windows-based client computer.
{2}------------------------------------------------
#### 1.5 Intended Use
ThinkingNet with its modality specific and remote access applications is intended to be used by trained clinical staff to perform medical image management, communications, archiving and processing and review of medical images.
The system can run on dedicated workstation or in a server-client configuration.
## 1.6 Description of Changes
Since we claim that ThinkingNet is optimized for each individual imaging modality, we feel that is appropriate to make ThinkingNet functionally comparable with modality workstations manufactured by modality vendors. In this application we will compare ThinkingNet imaging modality specific applications in radiology, cardiology, molecular imaging and mammographic imaging modalities with modality specific predicate devices and applications.
As the computer software and IT technologies evolve, a Web-based thin and thick client solution can deliver the same user interface, functionality and speed as a dedicated full diagnostic workstation. The proposed change also involves the expansion of ThinkingWeb (previously cleared as NuWEB in K010271) to include full workstation featured remote viewing and processing functions. The client device is cross-platform except for the ThinkingNet.Net thickclient solution.
These changes have been a part of the natural evolution of ThinkingNet without requiring major design changes. The product remains as safe and effective as the previously cleared ThinkingNet (K010271) and the predicate devices.
## 1.7 Legally Marketed Predicate Devices
Thinking Systems ThinkingNet is substantially equivalent to following primary predicate devices.
| Device Name | FDA Clearance<br>Number | Primary Indications |
|-------------------------------------------------------|-----------------------------------------|----------------------------------------------------------|
| Philips/Stentor iSite PACS 4.x and iSite<br>Radiology | K063267, K013630<br>(primary predicate) | Web-based Multi-modality<br>PACS and PACS<br>Workstation |
| Thinking Systems ThinkingNet | K010271 | All |
Thinking Systems ThinkingNet is substantially equivalent to following additional predicate devices in the respective specific indications.
| Device Name | FDA Clearance<br>Number | Specific Indications |
|-------------|-------------------------|----------------------|
| | | |
×
{3}------------------------------------------------
| GE Xeleris 3 | K093982 | Nuclear medicine, multi-<br>modality image co-<br>registration and fusion, PET-<br>CT, SPECT-CT and CT<br>image processing, integrated<br>third-party post-processing<br>software, such as Cedars<br>QGS/QPS/QBS, Invia 4D<br>MSPECT, Syntermed ECTb<br>and Syntermed NeuroQ |
|------------------------|---------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Agfa/Heartlab Ascentia | K050228 | Cardiology PACS |
| Agfa IMPAX MA3000 | K081976 | Mammography review |
| GE EchoPAC | K101324 | Echocardiography and<br>vascular image review,<br>measurements and<br>calculation |
| GE AW Server | K081985 | RECIST, Quantitative<br>oncology response<br>assessment |
## 1.8 Determination of Substantial Equivalence
ThinkingNet with its Web options and modality specific modules has the same intended use and indications for use, target populations, and technical characteristics as the legally marketed predicate devices in the respective areas tabulated above. Specifically,
- ThinkingNet with ThinkingWeb options is a medical image management, . communications and review device that has the same indications for use, target populations and technical characteristics as the legally marketed predicate device Philips iSite PACS with iSite Radiology client (K063267, K013630) and ThinkingNet (K010271). They are substantially equivalent.
The main difference between ThinkingNet and Philips iSite are the following.
- ThinkingNet contains more inherently built-in modality specific applications. iSite 1. offers many modality specific applications via internal and 30-party integration of plug-ins or add-ons.
- ThinkingWeb Extreme and ThinkingWeb use server-side processing and do not 2. download any patient data. iSite client on the other hand uses an image streaming technology to download image data onto the client device.
- ന് ThinkingWeb Extreme and ThinkingWeb support both Windows and non-Windows client devices. iSite is Windows specific.
- ThinkingNet molecular imaging subsystem is substantially equivalent to GE Xeleris . (K093982). Note: GE Xeleris Suite is also marketed as part of GE Centricity PACS in addition to being a workstation.
{4}------------------------------------------------
- ThinkingNet mammography imaging module is substantially equivalent to Agfa IMPAX . MA3000 (K081976). It can be used for screening and diagnosis (with MG. "For presentation" images only) from FDA approved modalities in softcopy (using FDA cleared displays for mammography) and printed formats.
- . ThinkingNet cardiology subsystem is substantially equivalent to Agfa/Heartlab Ascentia (K050228).
- . ThinkingNet RECIST module for solid tumor treatment response evaluation is substantially equivalent to GE AW Server's OncoQuant subsystem.
- . ThinkingNet NuFILM's echocardiography image review, measurement and calculation module is substantially equivalent to GE EchoPac (K101324). The main difference is that NuFILM is more vendor neutral because it does not rely on proprietary files native to GE echo machines.
The differences between the ThinkingNet software and the predicate devices may affect the safety and effectiveness of the device. Performance testing was conducted to show that ThinkingNet is safe and effective.
ThinkingNet is designed, developed, verified and validated following Thinking Systems' ISO 13485 registered and FDA 21 CFR Part 820 compliant Quality System.
The following quality assurance measures were applied to the development of the system.
- . Requirements Specification
- . Design Specification
- . Hazard and Risk Analysis
- . Modular Testing
- � Verification Testing
- . Validation Testing (Performance Testing)
- . Integration Testing
#### 1.9 Conclusion
Thinking Systems considers ThinkingNet with its Web options and modality specific modules to be as safe, as effective, and performance is substantially equivalent to the predicate device(s) listed in Section 1.7.
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a stylized eagle or bird symbol, with three curved lines representing its wings or feathers. The text "DEPARTMENT OF HEALTH & HUMAN SERVICES USA" is arranged in a circular pattern around the bird symbol.
Food and Drug Administration 10903 New Hampshire Avenue Document Control Room -- WO66-G609 Silver Spring, MD 20993-0002
Mr. JB Wang Co-CEO & Co-founder Thinking Systems Corporation 750 94th Avenue N., Suite 211 ST. PETERSBURG FL 33702
9 2012 JUL
Re: K120305
Trade/Device Name: ThinkingNet Modality and Web Applications Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: May 31, 2012 Received: June 13, 2012
## Dear Mr. Wang:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration.
If your device is classified (see above) into class II (Special Controls), it may be subject to such additional controls. Existing major regulations affecting your device can be found in Title 21, Code of Federal Regulations (CFR), Parts 800 to 895. 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 Parts 801 and 809); medical device reporting (reporting of
{6}------------------------------------------------
medical device-related adverse events) (21 CFR 803); and good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820). This letter requirences as be form arketing 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 Parts 801 and 809), please contact the Office of In Vitro Diagnostic Device Evaluation and Safety at (301) 796-5450. 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 the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.
Sincerely Yours,
Janine M. Morris
Acting Director Division of Radiological Devices Office of In Vitro Diagnostic Device Evaluation and Safety Center for Devices and Radiological Health
Enclosure
{7}------------------------------------------------
## INDICATIONS FOR USE FORM
## 510(k) Number (if known): K120305
## Device Name: ThinkingNet Modality and Web Applications
#### Indications For Use:
The ThinkingNet is a Medical Image Management and Review System, commonly known as PACS. ThinkingNet made by Thinking Systems Corporation, Florida, USA, is indicated for acceptance, transmission, storage, archival, reading, interpretation, clinical review, analysis, annotation, distribution, printing, editing and processing of digital images and data acquired from DICOM compatible diagnostic device, by healthcare professionals, including radiologists, cardiologists, physicians, technologists and clinicians.
- -With a ThinkingWeb option it can be used to access diagnostic information remotely with all workstation functionality or to collaborate with other users. The client device is cross platform for all but the thick-client ThinkingNet.Net option.
- With the molecular imaging option it can be used for processing and interpreting nuclear medicine and other molecular imaging studies.
- With image co-registration and fusion option it can be used for processing and interpreting PET-CT, PET-MRI, SPECT-CT and other hybrid imaging studies.
- With the Mammography option it can be used for screening and diagnosis (with -MG, "For presentation" images only) from FDA approved modalities in softcopy (using FDA cleared displays for mammography) and printed formats.
- With the cardiology option it can be used for reading, interpreting and reporting cardiac studies, such as nuclear cardiac, PET cardiac, echocardiographic, X-ray angiographic and CTA studies.
- With the Orthopedic option it can be used to perform common orthopedic measurements of the hip, knee, spine, etc.
OR
- With the 3D/MPR option it can be used to volumetric image data visualization: -MIP, MPR, VR and triangulation.
- With the Quality Assurance option it can be used by PACS administrators or clinicians to perform quality control activities related to patient and images data.
Prescription Use X (Per 21 CFR 801 Subpart D)
Over-The-Counter User
(21 CFR 801 Subpart C)
(PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of In Vitro Diagnostic Devices (OIVD)
VII
Mmmh D.O.R
Division Sign-Off
Office of In Vitro Diagnostic Device Evaluation and Safety
510(k) K120305
Page 1 of 1
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
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.