SPINAL GUIDES PACS (PACS MEDICAL IMAGING DISPLAY WORKSTATION)
K092427 · Albert Davydov Dds PC Professional · LLZ · Mar 16, 2010 · Radiology
Device Facts
Record ID
K092427
Device Name
SPINAL GUIDES PACS (PACS MEDICAL IMAGING DISPLAY WORKSTATION)
Applicant
Albert Davydov Dds PC Professional
Product Code
LLZ · Radiology
Decision Date
Mar 16, 2010
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.2050
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
Spinal Guides PACS is intended to perform: operations relating to the acceptance of spinal X-ray medical images and patient demographic information, their display, digital processing, review and editing, measurements report generation with respective storage and teleradiology exchange capabilities. They are intended to be used by a physician to view the images and use as an aid in calculation of alteration of motion segment integrity (AOMSI) of human spine. This device is not intended to be used for mammography images and does not require usage of 5 Mega pixel monitors.
Device Story
Spinal Guides PACS is a software-based workstation for viewing and analyzing digital spinal X-ray images. Input consists of lateral flexion/extension X-ray images acquired with a physical metal calibrator plate. A web user uploads images and demographic data; a local operator at a central location performs analysis. The software guides the operator through point placement on vertebral bodies; automatically generates a fourth point to complete geometric quadrangles; calculates relative metric discrepancies, angulation, and shifts; and compares results against norms. Output is a PDF report containing AOMSI calculations, emailed to the web user. The device assists physicians in quantifying spinal impairment and treatment planning. It does not diagnose pathologies. Used in clinical settings by medical practitioners.
Clinical Evidence
Bench testing only. Software verification and validation performed in conformance with specifications and DICOM standard PS3 NEMA 3.0.
Technological Characteristics
Software application installed on standard computers/servers. Connectivity via internet/teleradiology. Programming language: C# (.NET 3.5). Compliant with DICOM PS3 NEMA 3.0. Requires physical metal calibrator plate for image scaling. Does not require 5MP monitors.
Indications for Use
Indicated for physicians to view spinal X-ray images and aid in the calculation of alteration of motion segment integrity (AOMSI) of the human spine. Not indicated for mammography.
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).
{0}------------------------------------------------
MAR ] 3 2010
Page 1 of 11
Traditional 510 (k) Submission
## Submission Date: K092427
3/2/2010
### Revised 510(k) Summary
Spinal Guides PACS (PACS Medical Imaging Display Workstation)
Picture Archiving and communications Common/Classification Name: system (PACS)
LLZ
Classification Product Code
Proprietary Name:
510 (K) Letter Owner
Address
Phone number Fax e-mail
109-33 71st Road, #11B Forest Hills, NY 11375 718-261-4812 718-261-4812 albertydavydov@yahoo.com
Spinal Guides PACS
Albert Davydov, DDS, PC
Albert Davydov, DDS Submitter's Contact person:
August 1, 2009 Date the Summary was prepared:
# A. LEGALLY MARKETED PREDICATE DEVICE
| The predicate device name | Opal-RadTM |
|---------------------------|------------------------------------------------------------|
| Applicant Name | Viztek, Inc.<br>6491 Powers Ave.<br>Jacksonville, FL 32217 |
| 510(K) Number | K063337 |
| Regulation # 21 CFR | 892.2050 |
| | |
{1}------------------------------------------------
#### Page 2 of 11
Traditional 510 (k) Submission
## Submission Date: K092427
3/2/2010
LLZ Classification Product Code
### B. DEVICE DESCRIPTION
The device is represented by a software computer program installed on regular computers.
The device has two types of users: a web and a local user.
The web user submits an image set for processing to the local user via internet to the device's database.
The local user is viewing the images of the image set, process the image set and sends a PDF report with calculations for the web user.
#### Workflow details
Working a mage is transferred to the device database by a web user. An operator (a local user) then uses a workstation to analyze AOMSI and generate a PDF (a look abol ations, which is then available for viewing on the web for the web user.
The local user/operator/server is installed at only one core location and X-ray images from different users are sent to the location for analyses.
The device is primarily intended for viewing digital spinal X-ray images and to prepare analyses of alteration of motion segment integrity (AOMSI).
### Automated part of the reporting process
- 1. Automatic limitation of points placed respective to the number of vertebras
- 2. Automation of 4th point positioning.
- 3. Automatic mathematical calculations
- 3. Automatic notice to calibrate an image upon placement of first point on an image in image editor window
- 5. Automation of notification of an improper order of points
- 6. Automatic user password retrieval
- 7. Automatic submission of PDF report via e-mail to the web user
### What is needed to perform the analysis?
{2}------------------------------------------------
#### Page 3 of 11
#### Traditional 510 (k) Submission
### Submission Date: K092427
3/2/2010
- 1. The analyses are to be performed only by a licensed medical practitioner who is knowledgeable of specific spinal anatomy and specific protocols for image analysis
- 2. Medical Device Spinal Guides PACS
- Spinal pure lateral X-ray views in flexion and extension taken with the calibrator 3. in place
- 4. Computer hardware
- 5. Internet with enough available speed
#### Processing
For all square vertebras the first point (I) is placed on the superior anterior
external line angle of the vertebral body.
For all square vertebras the second point (II) is placed on the superior
posterior external line angle of the vertebral body.
For all square vertebras the third point (III) is placed on the inferior
posterior external line angle of the vertebral body.
For all square vertebras the forth point is computer generated. The 4th
point (IV) is placed to the location to make the inferior side of the figure equal and
parallel to the same of the upper.
For the vertebra without vertebral body (C1) the point locations are as follows:
- The first point is placed on the Superior Anterior External Line 1.
Angle formed by dens of C2 and the most proximal point to it on C1
{3}------------------------------------------------
#### Page 4 of 11
Traditional 510 (k) Submission
## Submission Date: K092427
3/2/2010
The second point is placed on the Superior Posterior Internal Line 2. Angle formed by radiographic laminar-pedicle junction of C1 and the superior border of C1 at the end point of that junction
The third point is placed on the Inferior Posterior Internal Line 3. Angle formed radiographically by laminar-pedicle junction of C1 and the inferior border of C1 at the very end point of that junction. The forth point is computer generated, as described above
For triangular vertebra (C2):
The first point is placed on the Inferior Anterior External Line 4. Angle of the vertebral body.
The second point is placed on the Inferior Posterior External Line 5. Angle of the vertebral body.
The third point is placed on the next Superior Posterior External 6. Line Angle formed between transverse processus of C2 and the dens of C2 vertebrae
> 7. The forth point is computer generated
{4}------------------------------------------------
### Page 5 of 11
### Traditional 510 (k) Submission
## Submission Date: K092427
3/2/2010
Once the third point is placed, the fourth one is generated by a computer.
The fourth point is placed to complete a proper quadrangle to form square, parallelogram or rhombus.
The fourth point is placed by a computer to make the lower side equal and
parallel to the upper side and the opposing internal line angles equal to each other.
Measuring
Before placement of points the local user has to calibrate the image.
Once we have placed the points we can relate them to each other by
calculating degrees of their planes.
After the points are placed and proper geometrical figures are created the
device will measure relative metric discrepancies.
The device measures relative angulation as well as specific metric relationship of shifts in millimeters and in percentages relative specific points.
Then, the data is compared with known norms and abnormalities respective to the specific points and spinal parts.
Significance of the study
In order to treat the patient better, estimate prognosis of the patient's condition and quantify the patient's impairment due to damages to the spine the AMA published certain criteria by which a doctor has to formulate a diagnosis
5 of 11
{5}------------------------------------------------
#### Page 6 of 11
Traditional 510 (k) Submission
### Submission Date: K092427
3/2/2010
and treatment plan, as well as quantify the patient's permanent impairment rating. The last edition, the 6th Edition of AMA published in 2008 specific limitations in norm and abnormalities for spinal evaluations of alteration of motion segment integrity calculations.
Using computerized technology installed within the device a doctor can spend almost no time in completion of otherwise lengthy mathematical calculations and get precise diagnostic report ready to apply for the best patient's care.
Once specific measurements of relationship of one vertebra to another are obtained, they are compared to norms and abnormalities.
The patient will be treated better and treatments will get better outcomes.
The individual and third party payers will save money when treatments are not indicated.
The device does not read pathologies. It is an AOMSI (alteration of motion segment integrity) specific.
#### Quality control functionality
If the order of the points placed are not followed the above protocol (not as 1, 2, 1. 3, but 1, 3, 2) the 4th point will be placed away from the field of the column by the computer making the operator aware of the error made.
6 of 11
{6}------------------------------------------------
### Page 7 of 11
Traditional 510 (k) Submission
2.
3.
# Submission Date: K092427
3/2/2010
The error figure will be seen by the local user immediately during
processing.
No points can be placed on an image without prior calibration
> X-ray images have to be taken with the calibrator, a small quadrangular metal plate with known dimensions. The calibrator will be affixed on the patient's skin in the designated area with the help of special, made out of paper, holder. The holder will position the metal plate vertically. The plate will be shown on an image as a quadrangle. A local user (operator) will be adjusting the image's size according to the calibrator's image and its known dimensions. The image set will be reviewed for quality before the processing can be done. If images sent are not in the appropriate quality, the image set will be rejected by the local user. The web user will see the specific image set rejected and why and will consider for a resubmission a better quality image
4.
7 of 11
{7}------------------------------------------------
### Page 8 of 11
Traditional 510 (k) Submission
న.
# Submission Date: K092427
#### 3/2/2010
Buttons: 1) "Undo"- returns to the previous state,
2) "Zoom In"- increases the image in size,
3) "Zoom Out"- decreases the image in size,
4) "Reset to Original"- returns the image to the
original size,
5) "Trace Image" guides the operator through the
processing of the image
6) "Test Points" retrieves the points from the
database on the processed image from the database
The architecture of the device is represented by the following diagram:
{8}------------------------------------------------
Page 9 of 11
Image /page/8/Figure/2 description: This image shows a diagram of a traditional 510(k) submission process. The submission date is 3/2/2010, and the submission number is K092427. The diagram includes a web browser, a web server, a database server, and a local application. The web browser sends image set data to the web server via HTTP, and the web server generates an image set and MSI report. The web server also gets completed image set calculations from the SQL server via TCP/IP and inserts the image set into the image storage.
{9}------------------------------------------------
#### Page 10 of 11
Traditional 510 (k) Submission
### Submission Date: K092427
3/2/2010
### C. INTENDED USE
ー、
Spinal Guides PACS is intended to perform: operations relating to the acceptance of spinal X-ray medical images and patient demographic information, their display, digital processing, review and editing, measurements report generation with respective storage and teleradiology exchange capabilities.
They are intended to be used by a physician to view the images and use as an aid in calculation of alteration of motion segment integrity (AOMSI) of human spine. This device is not intended to be used for mammography images and does not require usage of 5 Mega pixel monitors.
# D. SUBSTANTIAL EQUIVALENCE SUMMARY
"Spinal Guides" PACS has substantially same indications for use as the legally marketed predicate device Opal-Rad manufactured by Viztek, Inc., K063337 with major differences being:
- 1. It does not process images for mammography and does not require 5M pixel monitors, nor does it display 3D images acquired from CT and MR modalities.
- 2. It was created in C# computer language
- 3. Spinal Guides PACS were specifically made viewing of the images and for calculation of Alteration of Motion Segment Integrity (AOMS) of human spine.
This indication difference does not modify the intended use- to assist users performing quantifications and qualifications common to the general medicine, orthopedic, radiologic, and chiropractic specialty.
The new device has substantially the same control methods and operating principles as the predicate (both are computer systems and software installed in them, both intended for viewing of images) with the following major differences:
- 1. Images for Spinal Guides are to be taken with the calibrator affixed on the patient's skin
- Web users are opening the images and enter all required demographic information 2. and complete an image set for submission to database in "Pending" status
- 3. Local users are able to open image sets and view the images as well as process the images using automatic calculation process and formulate a PDF report turning "In process" and "Waiting for Completion" and "Complete", or turn the image sets into "Reject" to reject the image set.
{10}------------------------------------------------
#### Page 11 of 11
Traditional 510 (k) Submission
### Submission Date: K092427
.3/2/2010
- 4. Once the image set turned to "Complete" by the local user the PDF report is automatically available to the web user
Descriptive characteristics and data provided in this submission are sufficiently precise, to the best of our knowledge, to assure substantial equivalence.
# E. TECHNOLOGICAL CHARACTERISTICS
Both the new device and the predicate are software applications installed on standard computers and servers, and utilize teleradiology via internet.
The technological characteristics are substantially the same in the proposed and predicate devices, with major differences are as follows:
- 1. Visual Studio 3.5.net C# programming language
- 2. The new device does not require usage of 5 megapixel monitors since the application is not intended to use mammography images
#### F. TESTING
Nonclinical tests for Spinal Guides PACS (software verification and validation) have been performed in conformance to specifications and the application is in conformance to DICOM standard PS3 NEMA 3.0 1/1/2008
#### G. CONCLUSIONS
This 510(k) has demonstrated Substantial Equivalence of Spinal Guides PACS and Opal-Rad ™ as defined in the Federal Food, Drug and Cosmetic Act and various guidance documents issued by the Center for Devices and Radiological Health.
{11}------------------------------------------------
Image /page/11/Picture/0 description: The image shows the logo for the Department of Health & Human Services (USA). The logo consists of a circular border with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" arranged around the perimeter. Inside the circle is a stylized emblem featuring a symbol that resembles an abstract bird or a flowing design, composed of three curved lines.
Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Room - WO66-G609 Silver Spring. MD 20993-0002
## MAR 1 3 2010
Albert Davydov, DDS 109-33 7156 Road, #11B FOREST HILLS NY 11375
Re: K092427
Trade/Device Name: Spinal Guides PACS Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: March 2, 2010 Received: March 9, 2010
Dear Dr. Davydov:
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
{12}------------------------------------------------
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 will allow you to begin 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 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.
Donald J. Trump
Donald J. St.Pierre Acting Director Division of Radiological Devices Office of In Vitro Diagnostic Device Evaluation and Safety Center for Devices and Radiological Health
Enclosure
{13}------------------------------------------------
Page 1 of 1
Submission Date:
3/2/2010
# Indications for use Statement
510(k) Number:
K092427
Spinal Guides PACS
Device Name:
Indications For Use:
Spinal Guides PACS is intended to perform: operations relating to the acceptance of spinal Xray medical images and patient demographic information, their display, digital processing, review and editing, measurements report generation with respective storage and teleradiology exchange capabilities. They are intended to be used by a physician to view the images and use as an aid in calculation of
alteration of motion segment integrity (AOMSI) of human spine.
This device is not intended to be used for mammography images and does not require usage of 5 Mega pixel monitors.
Prescription Use AND/OR Over-The-Counter Use No Yes (Part 21 CFR 801 Subpart D) (21 CFR 801 Subpart C) (PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Beview Evaluation Page 1 of
(Division Sign-On)
Division of Radiological Devices
Office of In Vitro Diagnostic Device Evaluation and Safety
510K K092427
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.