K010322 · Orthodyne, Inc. · HSB · May 2, 2001 · Orthopedic
Device Facts
Record ID
K010322
Device Name
ISKD (INTRAMEDULLARY SKELETAL KINETIC DISTRACTOR)
Applicant
Orthodyne, Inc.
Product Code
HSB · Orthopedic
Decision Date
May 2, 2001
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 888.3020
Device Class
Class 2
Attributes
Therapeutic
Indications for Use
The ISKD is indicated for limb lengthening of the tibia and femur.
Device Story
ISKD is an intramedullary limb lengthening system for tibia and femur. Device consists of a telescoping titanium rod, locking screws, and an external handheld monitor. Patient performs rotational oscillations of the limb during ambulation; internal one-way clutch and threaded rod mechanism convert rotation into gradual distraction. A sealed internal magnet rotates with the device; external monitor tracks magnet pole changes to measure daily progress. Used in clinical settings by physicians; patient performs daily ambulation to drive distraction. Output provides objective tracking of lengthening progress for clinician review. Benefits include controlled osteogenic distraction for limb lengthening without external fixation frames.
Clinical Evidence
Clinical experience with 19 patients (9 pilot, 10 feasibility). Pilot study included complex cases (poly-trauma, soft tissue defects). Feasibility study (n=10) mean age 40.8, mean discrepancy 57.6mm. 8/10 patients achieved target length. Mean distraction rate 0.78mm/day. Adverse events included 2 device-related (loose/broken screw) and 6 unrelated. Bench testing included static 4-point bend, torsional, and fatigue testing (1 million cycles). Animal study (ovine model) confirmed bone regeneration and device function.
Technological Characteristics
Materials: Ti6A14V ELI (ASTM F136). Design: Telescoping intramedullary nail with one-way clutch and threaded rod. Fixation: 4.0mm titanium locking screws. Energy: Mechanical (patient ambulation). Connectivity: External handheld monitor uses magnetic sensing to track internal magnet position. Sterilization: Gamma radiation (device) and steam (instruments).
Indications for Use
Indicated for limb lengthening of the tibia and femur in patients requiring surgical correction of limb length discrepancy.
Regulatory Classification
Identification
An intramedullary fixation rod is a device intended to be implanted that consists of a rod made of alloys such as cobalt-chromium-molybdenum and stainless steel. It is inserted into the medullary (bone marrow) canal of long bones for the fixation of fractures.
{0}------------------------------------------------
**MAY - 2 2001**
K0/0322
# SUMMARY OF SAFETY AND EFFECTIVENESS ORTHODYNE ISKD SYSTEM
#### GENERAL INFORMATION 1.
Classification Names:
Common Name:
Device Trade Name:
Intramedullary fixation rod & Smooth or threaded metallic bone fixation fastener
Internal Limb Lengthener
"ISKD": (Intramedullary Skeletal Kinetic Distractor)
21 CFR Parts 888.3020 and 888.3040
Classification Code(s):
Submitter's Name & Address:
Orthodyne Inc. 1118 So. Orange Avenue, Suite 204 Orlando, FL 32804 (407)316-8098
pending Establishment Registration No: Contact Person:
Carl Knobloch
Summary Preparation Date:
January 17, 2001
#### II. PREDICATE DEVICE
System is substantially equivalent to two The Orthodyne ISKD commercially available devices. The Orthodyne ISKD System is substantially equivalent in design and function to the Grosse and Kempf Locking Nail System manufactured by Howmedica Corp. of Rutherford, New Jersey. The Gross Kempf (i.e., GK Nail) device was originally cleared by FDA under K813371 on March 1, 1982, and most recently under The Orthodyne ISKD System is K983358 on November 18, 1998. substantially equivalent in intended use to the Orthofix Dynamic Axial Fixation System cleared by FDA under 510(k) K955848 on March 20, 1996
{1}------------------------------------------------
### Device Description III.
The ISKD System is an intramedullary limb lengthening system that provides gradual, controlled osteogenic distraction of the tibia and femur. The ISKD System consists of the telescoping internal limb lengthening device, titanium locking screws, instrumentation and an external handheld Monitor. As the patient performs rotational oscillations of the affected limb during normal ambulation, the ISKD distracts as the distal section of the implant gradually telescopes out of the proximal section. The the implant is controlled by a one-way clutch mechanism and a threaded and. A small magnet sealed within the ISKD implant rotates simultaneously as the implant distracts. The hand-held external Monitor is similar to an electronic compass and communicates with the magnet by detecting and tracking changes in the magnet poles. The external Monitor enables both trationing and physicians to monitor the daily limb lengthening progress. Titanium locking screws (2 proximal and 2 distal) secure the device in place in the intramedullary canal.
#### IV. INDICATIONS FOR USE
The ISKD System intended for limb lengthening of the femur and tibia.
### BIOMECHANICAL TESTING V.
In order to demonstrate that the ISKD Internal Limb Lengthener has the mechanical properties necessary to perform its intended use, and that the ISKD Internal Limb Lengthener performs as well as or better than the predicate device, Orthodyne has conducted mechanical and functional testing of the ISKD System.
Static 4-point bend testing, torsional testing, nail fatigue testing, 3-point bend testing of the locking screw and functional testing was performed on the ISKD System. In general, the ISKD internal limb lengthener was more rigid in 4-point bending than the predicate nails. Also, the ISKD internal limb lengthener was stiffer in torsion than the predicate nails. In all nail fatigue testing, all nails ultimately completed the necessary one million cycles. In the 3-point bend testing of the locking screws, the statistical analysis showed the ISKD screws significantly greater in yield strength, ultimate strength and fatigue life than a commercially available bone screw. The stiffness was slightly higher but was not statistically significant. All samples passed the functional testing of the clutches, magnet and interface with the locking screws.
{2}------------------------------------------------
#### VI. Animal Testing
ANMAL TESTING
A 10mm ISKD Internal Limb Lengthener was implanted in the left femur of A Tonin ISKD internal Limb Longthonor was grin of the ISKD was 15cm.
a 20-month old female sheep. The start length of the ISKD was 15cm. After the desired distraction, the device was designed to lock both linearly And torsionally to function, the assume intramedullary (IM) nail until bone regenerate formation was complete.
The sheep was allowed to immediately bear full weight on the implant without the use of any external device constraining movement. without "the "use" of " any "Oxtornal " "Unes a week for the first 3 weeks. Radiographs of the threaded rod within the ISKD is easily identifiable on By design, the threads Tour was is 1mm per rotation of the rod. (Note: the external monitoring device was not available at the time of this study). the external monitoring downer of threads seen between the clutches on each consecutive radiograph. ISKD distraction was determined within 0.5 mm
consecutive radiograph. ISKD distraction was determined what wasn't be consecutive radiograph: Torte alone of threads seen between the clutches on each consecutive radiograph.
During the first 10 days following surgery, the animal walked with a slight Dunny the first 10 days following our the limb with the implant. By the limp, gradually increasing the freatment was given to any limb, second week, no notioouble proferential was not and the animal walked normariy. Altis time, the ISKD distracted at a manipulated of consistent 1.3mm each day. After 27mm of distraction, on Day felatively consistent 1.5mm Saon uxyl stopped lengthening. (The cause 24, this protoxpe implant promatinely of the ISKD stopped lengthening, the was addressed in a readolight) ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... to any limb.
The usual physiologic formation of regenerate bone tissue continued normally. Callus formation was visible on radiograph at 19 days. An normally. Oallus Tormation was evident at 35 days. At no time did the sheep show signs of infection or unusual pain. On Day 40 the sheep was show 'Signs' of Throotion' of 'arrantallawed to roam a 70-acre field with other transported to a shoop family steogenic callus formation was verified at 78 Sheep. I ull circumic evaluation of both the undisturbed bone and the days. Radiographic evaluation of both a remodeling of the femoral lengthened - bone - on was surgically removed from the diaphysis. On day 100 the 10.0 inn first femur shows complete cortical bone Sheep. A radiograph of the hartstripped from the femur and the bone was formation. The penostedinal axis with a band saw. The regenerate bone blisected down its fongitualifial allus. In summary, the results of is comparable to that of the and the ISKD lengthening device performed as inis animal Study materially lengthened the femur in an ovine model without untoward effects.
{3}------------------------------------------------
#### BIOCOMPATIBILITY VII.
The ISKD Internal Limb Lengthening device and locking screws are made from titanium alloy, Ti6A14V ELI conforming to ASTM F136.
### CLINICAL TESTING VIII.
Orthodyne has clinical experience with 19 patients implanted with an ISKD Internal Limb Lengthener. Upon IRB approval, nine patients participated in a pilot study followed a 10 patient feasibility study.
The nine patients participating in the pilot study were considered "compassionate use" as these patients presented with complicated histories, numerous risk factors including unresolved poly-trauma, severe soft tissue defect, severe contractures, poor bone quality, previous and recurring infections, multiple illnesses, etc. These patients required limb lengthening of the femur or the tibia ranging from 31-105mm. And in most cases, the ISKD was a last stage option as these patient's deformities were so extreme and/or previous lengthening procedures had failed.
Despite their complicated histories, eight of the nine patients were able to achieve the limb length they needed. One patient received 75mm out of the 105mm of length needed, but was not able to lengthen further due to the severe soft tissue contractures resulting from the pre-existing soft tissue deficit.) Certain design improvements were made to the ISKD system based upon this clinical experience.
Ten patients are enrolled to date into the feasibility study. The feasibility study patients presented with fewer complications and risk factors than those in the pilot study. Of the 10 patients, seven were males and three were females; age at surgery ranged from 18-63 with a mean age of 40.8 years. The cause of limb discrepancy was trauma for nime patients and post-polio infection for one patient. Eleven lengthening procedures were performed with these 10 patients (one patient required 2 procedures to reach his goal length). The discrepancy range was 30-120mm, with a mean discrepancy of 57.6mm. The goal length range was 30-80mm with a mean of 48.1mm. The distraction period range (implant to end of distraction) was 22-169 days, with a mean of 83 days. The length attained was 23-80mm, with a mean range of 45.0mm. The distraction rate range was 0.40-1.79mm/day, with a mean range of 0.78mm/day. Of these 10, eight patients achieved the length needed.
Two of the patients were noncompliant - one exceeded the recommended level of daily physical activity and one failed to meet the recommended level of daily physical activity. Six patients achieved complete healing (4/4 with intact cortices); and four patients achieved partial healing (3/4 intact cortices) as of the last completed radiographic follow-up.
{4}------------------------------------------------
Of the four patients who achieve partial healing, two patients were lost to follow-up, and one patient had a second ISKD implanted and healed afterwards. The fourth patient is still being followed and has since been noted as healed by the physician. Of those who completely healed, the consolidation period range was 219-505 days.
Four patients experienced a total of eight adverse events. Two events (a loose screw and a broken screw) were device related. These events occurred after distraction was complete and did not affect outcome. Six events were determined to be unrelated to the device (two related to the lengthening procedure, one due to a pre-existing condition, one due to surgical error, one as a complication of surgery and one non-compliance).
Though the feasibility study patients presented with fewer complications and risk factors, it was determined that patients presenting with severe soft tissue defects and/or contractures should be excluded as this complicates limb lengthening process and can prevent proper functioning of the ISKD.
#### IX. STERILIZATION
| ISKD Intramedullary Lengthening device | |
|----------------------------------------|---------------------------------|
| Method | Gamma Radiation |
| Radiation Dose | 25 Mrad |
| Sterility Assurance Level | 10-6 |
| Sterility Validation Method | ANSI/AAMI ST32-1991; Method I |
| Packaging | PETG tray with double Tyvek lid |
| Pyrogenicity | Not labeled pyrogen free |
| | ISKD Instrument Set |
|---------------------------------|-----------------------------------------------------------------------------|
| Method | Steam Sterilization |
| Cycle | Pre-Vacuum |
| Temperature | 132° - 135° C [270° - 275°F] |
| Exposure Time | Minimum of 10 minutes |
| Sterility Assurance Level (SAL) | 10-6 |
| Sterility Validation Method | ANSI/AAMI ST46-1993-<br>Prevacuum Steam Sterilization of<br>Medical Devices |
{5}------------------------------------------------
# X.
SUBSTANTIAL EQUIVALENCE
ISKD is claimed to be substantially equivalent in design and function to
| FEATURES | ISKD | GROSSE & KEMPF<br>INTRAMEDULLARY<br>LOCKING NAIL | ORTHOFIX DYNAMIC<br>AXIAL FIXATION SYSTEM |
|------------------------------|----------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| INTENDED USE | "Limb lengthening of<br>the tibia and femur" | "Temporary stabilization<br>of various types of<br>fractures, osteotomies,<br>malunions and nonunions<br>of the femur and tibia.<br>Other types of<br>procedures include<br>reconstrunction, bone<br>lengthening/shortening,<br>prophylactic nailing of<br>impending fractures and<br>fusions. | Intended for use in the<br>treatment of bone<br>conditions including leg<br>lengthening, osteotomies,<br>arthrodesis, fracture<br>fixation and other bone<br>conditions amendable to<br>treatment by use of the<br>external fixation modality. |
| MATERIAL | Ti6A14V ELI | 316 LVM Stainless Steel | 316 LVM stainless steel<br>bone pins |
| DESIGN FEATURES | Intramedullary nail | Intramedullary nail | Unilateral external fixator |
| | Telescoping sections | NA | Telescoping sections |
| | One way clutch design | NA | Both compression and<br>distraction |
| METHOD OF<br>FIXATION | 4.0 mm diameter<br>smooth shaft Locking<br>screws<br>(proximal and distal) | Tibial: 4.6mm threaded<br>Locking Screws (proximal<br>and distal)Femoral:<br>6.28mm threaded<br>Locking Screws<br>Proximal and distal) | Bone pins |
| NUMBER OF<br>FIXATION POINTS | 2 proximal/2 distal | Tibial - 2 proximal/2 distal<br>Femoral - 1 proximal/2<br>distal | 2-3 proximal/ 2-3 distal |
| DESIGN OF ENDS | Blunt | Blunt | NA |
| LONGITUDINAL<br>CURVATURE | Tibial Device - 15°±1°<br>bend; femoral - none | Tibial- 17.5°; femoral -<br>none | None |
| CROSS<br>SECTIONAL SHAPE | Circular | Tibial: Slotted<br>Cloverleaf<br>Femoral: Partially<br>slotted Cloverleaf | NA |
・ .
{6}------------------------------------------------
## XI. Conclusion
Based upon the results of animal, biomechanical and clinical testing the ISKD System has the mechanical properties to perform its intended use of limb lengthening of the tibia and femur and is considered to be substantially equivalent to the predicate devices in design, material and intended use.
> Orthodyne Inc. Premarket Notification: ISKD Internal Limb Lengthening System Submitted: January 22, 2001
{7}------------------------------------------------
Image /page/7/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a stylized eagle with three tail feathers, representing the department's commitment to health, human services, and well-being. The eagle is encircled by the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" in a circular arrangement.
Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850
MAY - 2 2001
Mr. Carl Knobloch Vice President and General Manager Orthodyne Inc. 1118 South Orange Avenue, Suite 204 Orlando, Florida 32806
Re: K010322
Trade Name: ISKD Intramedullary Skeletal Kinetic Distractor Regulation Number: 888.3020 Regulatory Class: II Product Code: HSB Dated: January 22, 2001 Received: February 2, 2000
Dear Mr. Knobloch:
We have reviewed your Section 510(k) notification of intent to market the device referenced wo have have determined the device is substantially equivalent (for the indications for use above and 10 have assnowned in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in encerhen actor of 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 II (Special Controls) or class III (Premarket Approval), it may be subject to such additional controls. Existing major regulations (1 remancer ripproval), in may of the Code of Federal Regulations, Title 21, Parts 800 to 895. A substantially equivalent determination assumes compliance with the current Good Manufacturing Practice requirement, 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 regulation may result 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.
{8}------------------------------------------------
# Page 2 - Mr. Carl Knobloch
If you desire specific advice for your device on our labeling regulation (21 CFF Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4659. Additionally, for questions on the promotion and advertising of your device, (201) 594-4637. Radhiance 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 mormation on your responsionates and in the mumber (800) 638-2041 or at (301) 443-6597, or at its Internet address "http://www.fda.gov/cdrh/dsmamain.html".
Sincerely yours,
Miriam C. Provost
for Celia M. Witten, Ph.D., M.D. Director Division of General, Restorative and Neurological Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{9}------------------------------------------------
# INDICATION FOR USE STATEMENT
Page **_ of _**
510(k) Number (if known):
Kolosar
Device Name:
"ISKD" Intramedullary Skeletal Kinetic Distractor
Indications for Use:
The ISKD is indicated for limb lengthening of the tibia and femur.
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
Prescription Use:
(Per 21 CFR 801.109)
96)
Or
Over-The-Counter_No
(Optional Format 1-2-
Muriam C. Provost
(Division Sign-Off) Division of (veneral, Restorative and Neurol gical Devices
510(k) Number K010322
Orthodyne Inc. Premarket Notification: ISKD Internal Limb Lengthening System Submitted: January 22, 2001
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.