FILTERWIRE EZ (2.25 MM - 3.5 MM) EMBOLIC PROTECTION SYSTEM, MODELS 20120-190, 20120-300
Applicant
Boston Scientific Corp
Product Code
NFA · Cardiovascular
Decision Date
Apr 10, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 870.1250
Device Class
Class 2
Attributes
Therapeutic, Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K051984 · Apr 10, 2006
FILTERWIRE EZ (2.25 MM - 3.5 MM) EMBOLIC PROTECTION SYSTEM, MODELS 20120-190, 20120-300
Boston Scientific Corp
FIRE Trial (K023691) clinical study data
The sponsor used a subset of patients from the previously conducted FIRE Trial (K023691) as a historical control group to compare 30-day MACE rates against the BLAZE II registry study for the subject device.
FIRE Trial (K023691); Randomized clinical trial (subset used as historical control); Follow-up/Duration: 30 days
Patients treated with Medtronic GuardWire Plus in saphenous vein grafts with vessel diameter 2.25 mm - 3.5 mm; Sample Size: 169
Not applicable for this study
30-day MACE rate
Indications for Use
The FilterWire EZTM Embolic Protection System is indicated for use as a guide wire and embolic protection system to contain and remove embolic material (thrombus/debris) while performing angioplasty and stenting procedures in coronary saphenous vein bypass grafts. The diameter of the vessel at the site of filter loop placement should be between 2.25 mm and 5.5 mm. - The safety and effectiveness of this device as an embolic protection system has not been established in the cerebral, carotid, or peripheral vasculature. - The safety and effectiveness of the device as an embolic protection system has not been established in treating patients with acute myocardial infarction. - The safety and effectiveness of the device as an embolic protection system has not been established in treating native coronaries.
Device Story
Temporary intra-vascular 0.014" guide wire filtration system; used during coronary saphenous vein bypass graft angioplasty/stenting. System includes Protection Wire, EZ Delivery Sheath, and EZ Retrieval Sheath. Physician places wire distal to lesion; delivery sheath removed to expand filter in artery lumen. After procedure, retrieval sheath captures filter loop containing trapped emboli; system removed. Benefits patient by containing/removing thrombus/debris, reducing embolic complications. Used in clinical interventional settings.
Clinical Evidence
Prospective, multi-center, non-randomized BLAZE II study (N=140). Primary endpoint: 30-day MACE rate. Subject device MACE rate 3.8% vs 12.4% for GuardWire Plus (FIRE trial subset). Adjusted difference -4.4% (95% CI: -11.6%, 2.9%), supporting non-inferiority. Device success 98.5%, clinical success 94.7%, final TIMI 3 flow 100%.
Technological Characteristics
0.014" guide wire system; Nitinol filter/basket; Bionate polyurethane filter membrane; radiopaque markers on filter loop; compatible with 6F guide catheters; 190 cm or 300 cm lengths; single operator exchange delivery.
Indications for Use
Indicated for patients undergoing angioplasty and stenting in coronary saphenous vein bypass grafts requiring embolic protection. Vessel diameter at filter placement site: 2.25 mm to 5.5 mm. Contraindicated for cerebral, carotid, or peripheral vasculature; acute myocardial infarction; and native coronary arteries.
Regulatory Classification
Identification
A percutaneous catheter is a device that is introduced into a vein or artery through the skin using a dilator and a sheath (introducer) or guide wire.
Predicate Devices
FilterWire EZ (3.5 mm - 5.5 mm) Embolic Protection System (K032884)
Medtronic PercuSurge GuardWire Plus Temporary Occlusion and Aspiration System (K013913)
Reference Devices
Boston Scientific Add Wire Extension Wire (K970376)
{0}------------------------------------------------
# APR 1 0 2006
| (This Summary is submitted in accordance with 21 CFR Part 807, Section 807.92) |
|--------------------------------------------------------------------------------|
|--------------------------------------------------------------------------------|
| Submitter's Name: | Boston Scientific Corporation |
|-----------------------------|----------------------------------------------------------------------------------------------------------------------|
| Submitter's Address: | 2011 Stierlin Court<br>Mountain View, CA 94043-4655 |
| Contact Person: | Debbie McIntire<br>Senior Regulatory Affairs Specialist<br>(650) 623-1703<br>(650) 623-1610 FAX<br>mcintird@bsci.com |
| Device Proprietary Name: | FilterWire EZ <sup>TM</sup> (2.25 mm – 3.5 mm) Embolic<br>Protection System |
| Device Common Name: | Embolic Protection Device |
| Device Classification Name: | 21 CFR 870.1250, Percutaneous Catheter |
| Device Class: | Class II |
| Date Prepared: | July 15, 2005 |
## Identification of Predicate Devices:
The Boston Scientific FilterWire EZTM (2.25 mm - 3.5 mm) Embolic Protection System is substantially equivalent in design and intended use to the FilterWire EZ (3.5 mm - 5.5 mm) Embolic Protection System legally marketed under K032884 and to the Medtronic® PercuSurge GuardWire Plus® Temporary Occlusion and Aspiration System (K013913) indicated in 2.5 -- 5.0 mm SVG vessel diameters.
### Device Description:
Section 4
The Boston Scientific FilterWire EZ (2.25 mm - 3.5 mm) Embolic Protection System is a temporary intra-vascular 0.014" guide wire filtration system that is placed distal to the vessel lesion to be treated by interventional procedures. The system consists of a Protection Wire (190 cm or 300 cm length), an EZ Delivery Sheath, an EZ Retrieval Sheath and accessories. The 190 cm long wire is compatible
510(k) Summary
{1}------------------------------------------------
with the Boston Scientific Add Wire® Extension Wire (K970376 cleared June 6, 1997) for over-the-wire catheter exchanges.
The Filter Wire EZ (2.25 mm - 3.5 mm) Protection Wire is delivered via the EZ Delivery Sheath. Once the Protection Wire is across the lesion, the filter bag is expanded in the artery lumen by removing the EZ Delivery Sheath. After treating the lesion, all interventional devices are removed, and the EZ Retrieval Sheath or EZ Bent Tip Retrieval Sheath is advanced to the proximal end of the filter and the filter loop is retracted into the EZ Retrieval Sheath, trapping any emboli caught during the procedure. The EZ Retrieval Sheath and EZ Protection Wire are then removed from the patient simultaneously.
## Indications for Use:
The Filter Wire EZ (2.25 mm - 3.5 mm) Embolic Protection System represents a product line extension to the commercially available FilterWire EZ (3,5 mm - 5,5 mm) Embolic Protection System (K032884), so the indications for use statement is similar to that already cleared under K032884 except the reference to the diameter of the vessel at the site of filter loop placement which covers the range from 2.25 mm to 3.5 mm. Please note the indications statement includes a change in phrasing to emphasize the intended vessel diameter range for filter loop placement, and that range will be inclusive of the predicate and subject devices range. The proposed Indications for Use statement is provided below:
"The FilterWire EZTM Embolic Protection System is indicated for use as a guide wire and embolic protection system to contain and remove embolic material (thrombus/debris) while performing angioplasty and stenting procedures in coronary saphenous vein bypass grafts. The diameter of the vessel at the site of filter loop placement should be between 2.25 mm and 5.5 mm.
- . The safety and effectiveness of this device as an embolic protection system has not been established in the cerebral, carotid, or peripheral vasculature.
- . The safety and effectiveness of the device as an embolic protection system has not been established in treating patients with acute myocardial infarction.
- The safety and effectiveness of the device as an embolic protection system has . not been established in treating native coronaries."
## Summary of Technological Characteristics:
The Filter Wire EZ (2.25 mm - 3.5 mm) Embolic Protection System indicated for use in saphenous vein bypass grafts is equivalent to the Filter Wire EZ (3.5 mm - 5.5 mm) Embolic Protection System cleared under K032884 and the Medtronic® PercuSurge GuardWire Plus® (GuardWire Plus ) cleared under K013913 in that the intended use, principles of operation, design and materials are similar. The
<sup>*</sup> Also referred to as PercuSurge
{2}------------------------------------------------
following design attributes are the same or similar for the subject device and the identified predicate devices:
.
:
:
{3}------------------------------------------------
| Predicate Devices | | Subject Device |
|---------------------------------------------------|------------------------------------------------------|--------------------------------------------|
| FilterWire EZ<br>(3.5 mm - 5.5 mm) System | Medtronic<br>GuardWire Plus | FilterWire EZ<br>(2.25 mm - 3.5 mm) System |
| Single Operator Exchange<br>delivery systems | Same | Same |
| Filter-based technology | Balloon-based technology | Filter-based technology |
| Nitinol® filter/basket<br>component | Elastomeric Occlusion<br>Balloon on Nitinol Hypotube | Nitinol® filter/basket<br>component |
| Polyurethane filter<br>membrane | Elastomeric Occlusion<br>Balloon | Bionate™ polyurethane filter<br>membrane |
| Compatibility with .014"<br>guide wires | Same | Same |
| Compatibility with 6F guide<br>catheters | Same | Same |
| Available in 2 lengths<br>190cm or 300 cm lengths | Same | Same |
| Radiopaque guide wire tips | Same | Same |
| Radiopaque markers on filter<br>loop | Contrast/Heparinized saline<br>mixture in balloon | Radiopaque markers on filter<br>loop |
### Performance Data:
Filter Wire EZ (2.25 mm - 3.5 mm) System in-vitro testing consisted of dimensional testing, tensile/torque testing and functional testing. Biocompatibility, packaging testing, product shelf life testing, functional testing in animal models and a clinical study in saphenous vein graft patients (G020229 - BLAZE II) have also been successfully conducted. In-vitro test results verified that the Filter Wire EZ (2.25 mm - 3.5 mm) Embolic Protection System met all applicable product specifications and is deemed adequate for its intended use.
Results from the BLAZE II study (EmBoLic Protection TrAnsluminally with the Filter Wire EZ DEvice in Saphenous Vein Grafts), designed to assess the Filter Wire EZ (2.25 mm - 3.5 mm) Embolic Protection System during percutaneous treatment of saphenous vein graft stenosis in terms of 30-day MACE rates validated the safety and effectiveness of the FilterWire EZ (2.25 mm -- 3.5 mm) System. These results were compared to the 30-day MACE results of a subset of GuardWire Plus patients from the FIRE Trial (K023691) (treated in the same vessel diameter range of 2.25 mm - 3.5 mm).
The BLAZE II study design was prospective, multi-center, and non-randomized. One-hundred thirty-one (131) registry patients, eight (8) roll-in patients and one (1) compassionate use patient were enrolled at 19 centers in this study. Clinical followup was performed 30 days post-procedure. The cumulative incidence of MACE at 30 days (primary endpoint) was 3.8% for the FilterWire EZ (2.25 mm - 3.5 mm) patients. The 30 day MACE results of the GuardWire Plus subset patients (treated in the same vessel diameter range of 2.25 mm - 3.5 mm) in the FIRE Trial was 12.4%.
{4}------------------------------------------------
The FilterWire EZ (2.25 mm - 3.5 mm) System demonstrated device performance with device success of 98.5%, clinical success of 94.7% and final TIMI 3 flow of 100%. Methods from the BLAZE II registry were analogous to the previously completed Randomized FIRE Trial (FilterWire EX / Medtronic GuardWire Plus) and the BLAZE study (Filter Wire EZ) with respect to enrollment criteria and primary endpoint.
Due to the non-randomized nature of group membership, adjusted one-sided and two-sided confidence intervals of the treatment difference in 30-day MACE rate were also calculated as follows. For each individual, a propensity score for group membership (FilterWire EZ™ (2.25 mm - 3.5 mm), PercuSurge) was calculated using logistic regression, with "group" as the outcome and baseline and predictor variables as independent variables. Patients were then categorized into quintiles based on this propensity score. An estimate of the overall treatment difference (and its confidence interval) across all propensity score quintiles, adjusted for propensity score quintile. was calculated. By this method we obtain an adjusted difference between FilterWire EZTM (2.25 mm - 3.5 mm) and PercuSurge on 30-day MACE rate of -4.4% with adjusted two-sided 95% CI of [-11.6%, 2.9%], and adjusted upper one-sided 95% CI of 1.8%, also supporting non-inferiority.
During conduct of the study, there were 40 BLAZE II patients who had at least one missing CK-MB result with the remaining CK-MB results being <3x normal range; there were 2 BLAZE II patients with missing CK-MB at all three time points (6-8. 12-16, and 18-24 hours post-procedure). To address this issue of missing CK-MB data, additional analysis on MACE was performed. In the primary analysis, these 42 patients were considered as not having non-Q wave MI since the majority of them had missing CK-MB due to being discharged early from the hospital because of no safety concerns. To estimate what the non-Q wave MI rate would have been for these patients had their missing CK-MB(s) been measured, the following analysis was performed. Data from FIRE, BLAZE and BLAZE II patients with non-missing CK-MB at all three time points (6-8, 12-16, and 18-24 hours post procedure) were used to statistically estimate, for each BLAZE II patient with missing CK-MB, the probability that at least one missing CK-MB was abnormal (>3x normal range). The probabilities were then summed to obtain an estimate of the number of missing CK-MB patients who would have had an abnormal CK-MB and hence non Q-wave MI. The resulting estimate was that no more than 1 of these 42 patients would have had non Q-wave MI and, hence, MACE. The following table displays the results of a revised MACE analysis where one additional patient is included in the BLAZE II MACE incidence.
As can be seen, there is no marked change in results from the primary analysis; i.e., non-inferiority to GuardWire Plus is still achieved.
{5}------------------------------------------------
Table 6. Revised MACE analysis imputing 1 additional patient.
| | BLAZE II (N=131) | PercuSurge (N=169)* | Difference [95% C.I.] | Upper one-sided |
|----------------------------------------------------|------------------|---------------------|-----------------------|-----------------|
| MACE (to 30 days) | 4.6% (6/131)** | 12.4% (21/169) | -7.8% [-13.9%,-1.6%] | -2.7% |
| * Control group from FIRE trial with 2.25≤R VD≤3.5 | | | | |
** Included additional MACE based on predicted values for m issing CK-MB.
## Statement of Substantial Equivalence
Based on a comparison of intended use, results of in-vitro testing, in-vivo testing, biocompatibility, packaging, and clinical evaluation, Boston Scientific considers the FilterWire EZ (2.25 mm - 3.5 mm) Embolic Protection System substantially equivalent to the legally marketed FilterWire EZ (3.5 mm - 5.5 mm) Embolic Protection System (K032884) and the Medtronic® PercuSurge GuardWire Plus® Temporary Occlusion and Aspiration System (K013913).
{6}------------------------------------------------
Image /page/6/Picture/2 description: The image shows the logo for the U.S. Department of Health and Human Services. The logo features a stylized eagle with three stripes representing the three levels of government: federal, state, and local. The eagle is encircled by the text "DEPARTMENT OF HEALTH AND HUMAN SERVICES, USA".
Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850
APR 1 0 2006
Boston Scientific Corporation c/o Ms. Debbie McIntire Senior Regulatory Affairs Specialist 2011 Stierlin Court Mountain View, CA 94043-4655
Re: K051984
> Trade/Device Name: FilterWire EZTM Embolic Protection System, sizes 2.25 - 3.5mm Regulation Number: 21 CFR 870.2350 Regulation Name: Distal Embolic Protection Guidewire Regulatory Class: Class II Product Code: NFA Dated: March 10, 2006 Received: March 13. 2006
Dear Ms. McIntire:
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 either class II (Special Controls) or class III (PMA), 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 898. 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
{7}------------------------------------------------
comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050. This letter will allow you to 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 Part 801), please contact the Office of Compliance at (240) 276-0120. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 443-6597 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.
Sincerely yours.
Bran D. Zuckerman, M.D. Director Division of Cardiovascular Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{8}------------------------------------------------
510(k) Number (if known)_KO519184
Device Name: FilterWire EZ™ (2.25 mm - 3.5 mm) Embolic Protection System
Indications for Use:
The FilterWire EZTM Embolic Protection System is indicated for use as a guide wire and embolic protection system to contain and remove embolic material (thrombus/debris) while performing angioplasty and stenting procedures in coronary saphenous vein bypass grafts. The diameter of the vessel at the site of filter loop placement should be between 2.25 mm and 5.5 mm.
- The safety and effectiveness of this device as an embolic protection system has not . been established in the cerebral, carotid, or peripheral vasculature.
- The safety and effectiveness of the device as an embolic protection system has not . been established in treating patients with acute myocardial infarction.
- The safety and effectiveness of the device as an embolic protection system has not . been established in treating native coronaries.
Prescription Use X (Per 21 CFR 801 Subpart D) AND/OR
Over-The-Counter Use (Per 21 CFR 807 Subpart C)
(PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
(Division Sign-Off)
Division of Cardiovascular Devices
510(k) Number *K05/984*
April 2006
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.