The NORMA 10 is a Magnetic Resonance Diagnostic Device intended to produce transverse, sagittal, coronal, and oblique 2D and 3D images of the extremities and selected sections of the head. The images produced by the NORMA 10 reflect the spatial distribution of protons (Hydrogen Nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and T2*. When interpreted by trained physicians, these images provide information that can be useful in determining a diagnosis.
Device Story
NORMA 10 is a fixed, open-design MRI system using a 0.12 Tesla permanent magnet. It acquires 2D/3D images of extremities and head sections. Input: H-1 nuclei magnetic resonance signals; processed via pulse sequences (spin echo, gradient echo, fast spin echo, steady state free precession). Output: transverse, sagittal, coronal, and oblique images. Operated by trained clinicians in a clinical setting. Patient positioned between lateral poles; open design reduces claustrophobia. Images interpreted by physicians to assist in diagnosis. System includes C-arm gantry, water-cooled gradients, and computer workstation for image reconstruction.
Clinical Evidence
Bench testing only. Performance evaluated at Odin premises (Oct 1998–Feb 1999) on normal anatomy. Testing confirmed compliance with NEMA standards for SNR, geometric distortion, image uniformity, slice thickness, and spatial resolution. Safety testing confirmed SAR, acoustic noise, and time-varying gradient fields (dB/dt) were below levels of significant risk per FDA guidance.
Technological Characteristics
Permanent magnet MRI (0.12T); C-arm gantry with lateral/longitudinal adjustable poles. Water-cooled gradient subsystem (25 mT/m). Pentium 586 CPU, 64MB RAM, 4xDSP C44 TI array processor. Connectivity: magnetic/floppy disk storage. Pulse sequences: SE, FSE, GE. Open-bore design (24.5x39 cm).
Indications for Use
Indicated for patients requiring diagnostic imaging of extremities and selected sections of the head. Uses H-1 nuclei excitation for T1, T2, T2*, and density-weighted imaging. For prescription use only.
Regulatory Classification
Identification
A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).
Special Controls
*Classification.* Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.
{0}------------------------------------------------
JUN 18 1999
:
KQ9/243
# ATTACHMENT 1
# 510(k) Summary of Safety and Effectiveness
{1}------------------------------------------------
# ODIN Technologies Ltd.
P.O. Box 248, Yokneam Elit 20698, Israel. Tel. 972-4-9591010, Fax. 972-4-9591011
# 510(k) Summary of Safety and Effectiveness
The Following 510(k) Summary of Safety and Effectiveness has been prepared pursuant to requirements for 510(k) summaries specified in 21 CFR § 807.92(a).
### 807.92(a)(1) - Submitter Details:
| Submitter name: | Adi Ickowicz – Regulatory Affairs / Quality Assurance<br>Director |
|-----------------|-------------------------------------------------------------------|
| Address: | P.O. Box 248, Yokneam Elit 20698, Israel |
| Phone: | +972-4-959-1010 |
| Fax: | +972-4-959-1011 |
| E-mail: | adi@odin.co.il |
| Contact Person: | Adi Ickowicz – Regulatory Affairs / Quality Assurance<br>Director |
| Date: | March 15, 1999 |
{2}------------------------------------------------
## 807.92(a)(2) - Device Details:
| Trade Name and Common Name: | NORMA 10 - Magnetic Resonance<br>Diagnostic Device |
|-----------------------------|-----------------------------------------------------------------------------------------------|
| Classification: | 21 CRF 892.1000 Magnetic Resonance<br>Diagnostic Device. |
| Class: | II<br>MRDD were reclassified by FDA from<br>Class III to Class II effective July 28,<br>1998. |
| Product Code: | LNH - Magnetic Resonance Imaging<br>System |
## 807.92(a)(3) - Predicate Devices:
| Medical Device<br>Name | Applicant<br>Name | 510(k) Number | Classification |
|------------------------|-------------------|---------------|-----------------|
| Ortho 8000 | Inner Vision | K963186 | Class II device |
| MRP-5000 | Hitachi | K911642 | Class II device |
Additional Substantial Equivalence Information is provided in the attached Substantial Equivalence Comparison Table.
{3}------------------------------------------------
### 807.92(a)(4) - Device Description:
#### Device Functions:
The NORMA 10 utilizes a permanent magnet to acquire 2D single-slice, multi slice, and 3d volume images. A wide variety of pulse sequences are provided to the operator, including spin echo, gradient echo, fast spin echo, and steady state free precession acquisitions. The NORMA 10 is a fixed system.
#### Scientific Concepts:
Magnetic Resonance (MR) is based on the fact that certain anatomic nuclei have electromagnetic properties, which cause them to act as small spinning bar magnets. The most ubiquitous of these nuclei is hydrogen, which makes it the primary nucleus used in current imaging experiments in magnetic resonance. When placed in a magnetic field, there is a slight net orientation or alignment of these atomic nuclei with the magnetic field. The introduction of a short burst of Radiofrequency (RF) excitation of wavelength specific to the magnetic field strength and to the atomic nuclei under consideration can cause a reorientation of the proton's magnetization vector. When the RF excitation is removed, the proton relaxes and returns to its original orientation. The rate of relaxation is exponential, and varies with the character of the proton and its adjacent molecular environment. This reorientation process is characterized by two exponential relaxation times called TI and T2, which can be measured.
These relaxation events are accompanied by an RF emission or echo which can be measured and used to develop a representation of these emissions on a three dimensional matrix. Spatial localization is encoded into the echo by varying the RF excitation and by appropriately applying magnetic field gradients in x, y, and z directions, and changing the direction and strength of these gradients. Images depicting the spatial distribution of NMR characteristics of the nuclei under
{4}------------------------------------------------
consideration can he constructed by using image processing techniques similar to those used in CT.
For magnetic fields up to 1.5T, the RF frequencies commonly used range up to 65MHz. The RF fields have pulsed power from several watts to greater than 2 kilowatts, and repeat at rates from once every few seconds to greater than fifty per second. The time-varying magnetic gradient fields have a typical duration of sub-millisecond to several milliseconds.
#### Physical and Performance Characteristics:
ODIN Technologies Ltd., has developed an open MRI system based on an innovatively designed permanent magnet of 0.12 Tesla. The system is compact, displaceable, inexpensive and widely open.
The magnetic probe consists of two lateral permanent-magnet poles that can be adjusted laterally and longitudinally, mounted on a C-arm gantry. The anatomic region to be scanned is positioned between the poles. Except for the anatomic region been scanned, the patient is positioned outside of the gantry, thus enhancing patient comfort and reducing the possibility of a claustrophobic reaction.
### 807.92(a)(5) — Device Intended Use:
The NORMA 10 is a Magnetic Resonance Diagnostic Device intended to produce transverse, sagittal, coronal, and oblique 2D and 3D images of the extremities and selected sections of the head. The images produced by the NORMA 10 reflect the special distribution of protons (Hydrogen Nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and T2*.
{5}------------------------------------------------
When interpreted by trained physicians, these images provide information that can be useful in determining a diagnosis.
- Anatomical regions: extremities and selected sections of the . head.
- H-1 Nuclei excited: .
- Diagnostic uses: T1, T2, T2* and density weighted . imaging.
# 807.92(a)(6) - Substantial Equivalence Comparison Table:
| Model | Odin | Hitachi | Innervision |
|-------------------------------------------|----------------------------------------------------------|-----------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------|
| parameter | NORMA 10 | MRP-5000 | Ortho 8000 |
| Clinical application | Extremities and<br>selected sections of<br>the head | Whole body | Extremities |
| Magnet type | Permanent | Permanent | Permanent |
| Field strength | 0.12T | 0.2T | 0.17T |
| 5 gauss fringe field<br>(radial/axial, m) | 1.5 | <2.1 | 0.3 |
| Shimming | Passive, active | Passive | Passive, active |
| Gradient subsystem | | | |
| - Strength mT/m | 25 | 8 | 15 |
| - Rise time to 10mT/m | <1 | <1 | <1 |
| msec | | | |
| Model | Odin | Hitachi | Innervision |
| parameter | NORMA 10 | MRP-5000 | Ortho 8000 |
| Computer system | | | |
| - CPU: | Pentium 586 | Motorola 32 bit | IBM PC |
| - Memory size [MB] | 64 | 4 | 32 |
| array processor | 4xDSP C44 TI | Hitachi | TI |
| - Memory size [MB] | 4000 | 68 | Not specified |
| storage media | magnetic disk,<br>floppy disk | magnetic disk,<br>optical disk | optical disk, tape,<br>CD-R, floppy disk |
| number of images stored | 5000 | 2000 magnetic disk<br>4300 optical disk | 5000 |
| Imaging modes: | | | |
| - single | Yes | Yes | Yes |
| - multislice | Yes | Yes | Yes |
| - volume study | Yes | Yes | Optional |
| - other | FSE, Multislice | Multislab,<br>multiangle, FS, dual<br>slice, MRA, cardiac<br>gated,<br>multislice/multiple<br>angle | Dynamic scan |
| Reconstruction time: | | | |
| - single slice, sec | <3/slice | <4/slice | <3/slice |
| - multislice, sec | <3/slice | <4/slice | <3/slice |
| - volume sec | <20/slice, ave. | <4/slice | <20/slice, ave. |
| model | Odin | Hitachi | Innervision |
| parameter | NORMA 10 | MRP-5000 | Ortho 8000 |
| Cardiac gating<br>(ECG/peripheral) | No | Yes/yes | NA |
| Respiratory gating | No | No | NA |
| Angiography | Optional | Optional | NA |
| Spectroscopy | No | No | NA |
| Imaging; | | | |
| - pulse sequence | Spin Echo, Fast<br>Spin Echo,<br>Gradient Echo, 2D<br>3D | SE, multiple SE,<br>GE, IR, STIR,<br>FSE,dual slice,<br>MRA | SE, FE, IR,<br>multiecho, dynamic |
| - repetition time, msec | 50-5000 increments<br>of 1 | 50-4000 | 50-5000 increments<br>of 1 |
| - echo time, msec | 5-150 | 10-150 | 7-100 increments of<br>1 |
| - inversion time, msec | N/A | 100-800 | 15-5000 incr. of 1 |
| - slice thickness, mm | 4-10 | 3,4,5,6,7,8,10,12.5,<br>15,17.5,20,30,50<br>(2D) 1-5 (3D) | 3-10 incr. of 1 |
| - FOV, cm | 5-18 | 12-40 | 8-16 increments of<br>0.1 |
| model | Odin | Hitachi | Innervision |
| parameter | NORMA 10 | MRP-5000 | Ortho 8000 |
| - scan orientation | Transverse,<br>coronal, sagittal,<br>oblique | Transverse,<br>coronal, sagittal,<br>dual axis, oblique | Orthogonal, oblique |
| - measuring matrix | 64x64 to 256x256<br>steps of 1 in phase<br>encoding | 128x256, 160x256<br>192x256, 256x256,<br>half scan, rectang. | 64x256 to 256x256<br>steps of 1 in phase<br>encoding |
| - display matrix | 1024x768 | 512x512 | Up to 512x512 |
| - pixel intensity | 0-4095 | -2000 to +4000 | 0-255 |
| Surface coils: | | | |
| - spine | No | Yes | NA |
| - knee | Yes | Yes | Yes |
| - neck | No | Yes | NA |
| - TMJ | No | Bilateral | NA |
| - extremity | Yes | Oval Solenoid | Yes |
| - head | Yes | Solenoid quad. | NA |
| - breast | No | Optional bilateral | NA |
| - shoulder | No | Yes | NA |
| - others | No | Flexible | Small dynamic<br>(12cm) large<br>dynamic (18cm) |
| Bore diameter or WxH, cm | 24.5x39 | 100x48 rectangle | 20x75 |
| model | Odin | Hitachi | Innervision |
| parameter | NORMA 10 | MRP-5000 | Ortho 8000 |
| Bore features | Open access to<br>patient | Wide bore short<br>depth, intercom,<br>soft sound<br>gradients | Open access to<br>patient, quiet<br>gradient system<br>built in CD sound<br>sys. |
| Cooling system type | Water cooling<br>(Gradients only) | None, room<br>air-conditioning | Thermal insulation |
| Cryogen use | NA | NA | NA |
| Magnet weight, kg | 380 | 12200 | 500 |
| HxWxD, cm | 135x86x80 | 175x228x157 | 118x51x52 |
| Dicom 3.0 interface | No | Optional | From 3rd party |
| Power requirements: | | | |
| - line voltage, V | 3x208 (3 phase) | 200-240 single<br>phase | 110/240 |
| - Kva | 16 | 6 | <3 |
| - A/C, BTU/hr | <10000 | <10000 | 10000 |
{6}------------------------------------------------
{7}------------------------------------------------
{8}------------------------------------------------
{9}------------------------------------------------
## Clinical Data:
Testing of the system was performed at the Odin premises, during the period of October 1998 through February 1999. The scans were performed on normal anatomy including extremities and selected sections of the head.
{10}------------------------------------------------
# Conclusions from Testing:
Safety and magnetic resonance performance tests were performed on the NORMA 10 in accordance with the NEMA standards.
The results obtained from the safety tests including acoustic noise, Specific Absorption Rate (SAR) and Time-Varying Gradient Fields (dB/dt) were found to be below the levels of significant risk as described in the FDA Guidance for the Submission Of Premarket Notification for Magnetic Resonance Diagnostic Device, dated November 14, 1998. The performance results obtained including Signal-to-Noise Ratio (SNR), Geometric Distortion, Image Uniformity, Slice Thickness, Characterization of Special Purpose Coils and spatial resolution meets the performance specifications claimed.
{11}------------------------------------------------
#### DEPARTMENT OF HEALTH & HUMAN SERVICES
Public Health Service
DEPARTMENT OF HEALTH
Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850
JUN 1 8 1999
Adi Ickowicz Odin Technologies, Ltd. P.O. Box 248 Yokneam, Elet 20698 ISRAEL
RE:
K991243 Norma 10 MR Diagnostic Device Dated: April 10, 1999 Received: April 12, 1999 Regulatory Class: II 21 CFR 892.1000/Procode: 90 LNH
Dear Mr. Ickowicz:
We have reviewed your Section 510(k) notification of intent to market the device referenced above and we 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). 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 III (Special Controls) or dass III (Premarket Approval), it may be subject to such additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 895. A substantially equivalent determination assumes compliance with the Current Good Manufacturing Practice requirements, as set forth in the Quality System Regulation (QS) for Medical Devices: General regulation (21 CFR Part 820) and that, through periodic QS inspections, the Food and Drug Administration (FDA) will verify such assumptions. Failure to comply with the GMP regult in regulatory action. In addition, FDA may publish further announcements concerning your device in the Federal Register. Please note: this response to your premarket notification submission does not affect any obligation you might have under sections 531 through 542 of the Act for devices under the Electronic Product Radiation Control provisions, or other Federal laws or regulations.
This letter will allow you to begin marketing your device as described in your 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 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4613. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding by reference to premarket notification"(21 CFR 807.97). Other general information on your responsibilities under the Act may be obtained from the Division of Small Manufacturers Assistance at its toll-free number (800) 638-2041 or (301) 443-6597, or at its internet address "http://www.fda.gov/cdrh/dsma/dsmamain.html".
Sincerely yours,
CAPT Daniel G. Schultz, M.D. Acting Director, Division of Reproductive, Abdominal, Ear, Nose and Throat, and Radiological Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{12}------------------------------------------------
510(k) Number (if known):
Device Name: NORMA 10
Indication For Use:
The NORMA 10 is a Magnetic Resonance Diagnostic Device intended to produce transverse, sagittal, coronal, and oblique 2D and 3D images of the extremities and selected sections of the head. The images produced by the NORMA 10 reflect the spatial distribution of protons (Hydrogen Nucle) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and T2*. When interpreted by trained physicians, the MR images provide information that can be useful in determining a diagnosis.
- Anatomical regions: extremities and selected sections of the head. ●
- Nuclei excited: H-1 .
- T1, T2, T2* and density weighted imaging. Diagnostic uses: .
(PLEASE DO NOT WRITE BELOW THE LINE – CONTINUE ON ANOTHER PAGE IF NECESSARY)
Concurrence of CDRH. Office of Device Evaluation (ODE)
Ovid A. Seymore
(Division Sign-Off)
(Division Sign-Off) Division of Reproductive, Abdominal, E. and Radiological D 510(k) Number
Prescription Use
(Per 21 CFR 801.109)
OR
Over-The-Counter Use
(Optional Format 1-2-96)
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.