Prospective clinical cohort of outpatients presenting with suspected DVT; Routine clinical diagnostic workup (Wells' rules, imaging)
The study evaluated the diagnostic performance (sensitivity, specificity, NPV, PPV) of the INNOVANCE D-Dimer assay on the Sysmex CS-2100i for the exclusion of DVT in patients presenting to emergency or ambulatory settings.
INNOVANCE D-Dimer DVT Exclusion Validation Study; Multicenter, prospective cohort study using frozen specimens; Follow-up/Duration: 3-month follow-up for patients with negative clinical diagnosis
Consecutive outpatients presenting to emergency or ambulatory departments with suspected first event of DVT; Sample Size: 1317 patients (final analysis); Number of Sites: Multicenter (US and OUS sites)
Imaging methods (e.g., ultrasound) and 3-month clinical follow-up
Sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV) for DVT exclusion
Indications for Use
The Sysmex CS-2100i is a fully automated blood coagulation analyzer intended for in vitro diagnostic use using venous blood samples collected in 3.2% sodium citrate tubes to analyze clotting, chromogenic and immunoassay methods in the clinical laboratory. For determination of: - Prothrombin Time (PT) seconds and PT INR with Dade® Innovin® - Activated Partial Thromboplastin Time (APTT) with Dade® Actin® FSL - Fibrinogen (Fbg) with Dade® Thrombin Reagent - Antithrombin (AT) with INNOVANCE® Antithrombin - D-dimer with INNOVANCE® D-Dimer. The performance of this device has not been established in neonate and pediatric patient populations.
Device Story
Sysmex CS-2100i is an automated, random-access blood coagulation analyzer for clinical laboratories. It processes venous plasma samples (3.2% sodium citrate) using clotting, chromogenic, and immunoassay methods. The system performs automated pipetting, dilution, and analysis of samples in normal or micro-sample modes. It utilizes mechanical, hydraulic, and electrical systems to measure coagulation parameters. Results are displayed on an integrated Information Processing Unit (IPU), printable, or transmittable to a host computer. The device aids clinicians in diagnosing coagulation disorders and excluding DVT/PE when used with non-high PTP assessment models. By providing rapid, quantitative D-dimer results, it assists in clinical decision-making regarding the necessity of further imaging, potentially reducing unnecessary diagnostic procedures for patients suspected of DVT or PE.
Clinical Evidence
Multicenter study (n=1317) evaluated INNOVANCE D-Dimer assay on Sysmex CS-2100i for exclusion of first-event DVT. Patients with suspected DVT were categorized by Wells' rules; high PTP patients excluded. Performance compared to imaging/3-month follow-up. Results: Sensitivity 97.5% (95% LCL 91.3%), Specificity 46.1% (95% LCL 43.3%), NPV 99.7% (95% LCL 98.7%).
Technological Characteristics
Automated coagulation analyzer; mechanical, hydraulic, and electrical sensing. Uses 3.2% sodium citrate venous plasma. Halogen lamp light source (660 nm for D-dimer). Random access, cap-piercing capability. Temperature control: 37°C ± 0.5°C (detector). Connectivity: Bidirectional interface (CA, ASTM, CS protocols). Automated calibration and QC (X-Bar, Levey-Jennings).
Indications for Use
Indicated for use in clinical laboratories to analyze venous plasma samples (3.2% sodium citrate) for coagulation parameters including PT, APTT, Fibrinogen, Antithrombin, and D-dimer. D-dimer assay is indicated for use in conjunction with a non-high clinical pre-test probability (PTP) assessment model to exclude deep vein thrombosis (DVT) and pulmonary embolism (PE). Not established for neonate or pediatric populations.
Regulatory Classification
Identification
A multipurpose system for in vitro coagulation studies is a device consisting of one automated or semiautomated instrument and its associated reagents and controls. The system is used to perform a series of coagulation studies and coagulation factor assays.
Special Controls
*Classification.* Class II (special controls). A control intended for use with a multipurpose system for in vitro coagulation studies is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K161312
B. Purpose for Submission:
The purpose of this submission is to extend the use of the previously cleared INNOVANCE® D-dimer assay (K093626) for the exclusion of deep vein thrombosis (DVT) to the Sysmex CS-2100i.
In addition to the INNOVANCE® D-dimer assay for the exclusion of pulmonary embolism (PE), the Sysmex CS-2100i was also cleared for the following assays: Prothrombin Time (PT) seconds and PT INR with Dade® Innovin®, Activated Partial Thromboplastin Time (APTT) with Dade® Actin® FSL, Fibrinogen (Fbg) with Dade® Thrombin Reagent, and Antithrombin (AT) with INNOVANCE® Antithrombin in the premarket notification K151259.
C. Manufacturer and Instrument Name:
Sysmex Corporation; Sysmex CS-2100i
D. Type of Test or Tests Performed:
Quantitative coagulation test: INNOVANCE® D-Dimer with the following intended use:
For the quantitative determination of cross-linked fibrin degradation products (D-dimers) in human plasma on Siemens Healthcare Diagnostics and Sysmex® Coagulation Systems. The INNOVANCE® D-Dimer assay is intended for use in conjunction with a non-high clinical pre-test probability (PTP) assessment model to exclude deep vein thrombosis (DVT) and pulmonary embolism (PE).
E. System Descriptions:
1. Device (Instrument) Description:
The Sysmex CS-2100i is an automated blood coagulation instrument for in vitro diagnostic use in clinical laboratories. The instrument analyzes venous plasma samples collected in 3.2% sodium citrate using clotting, chromogenic and immunoassay methods. Analysis results are displayed on the Information Processing Unit (IPU) screen. Results can be printed on external printers or transmitted to a host computer. The instrument is capable of measuring the assays in a normal mode and a micro-sample mode.
{1}
For the previously cleared assay description refer to K151259 and K093626.
2. Principles of Operation:
The Sysmex CS-2100i is an automated blood coagulation instrument which performs testing analysis using its mechanical, hydraulic, and electrical systems. The instrument uses associated reagents, controls, calibrators, and consumable materials to perform assays for Prothrombin Time (PT) seconds and PT INR, Activated Partial Thromboplastin Time (APTT), Fibrinogen, Antithrombin, and D-dimer.
3. Modes of Operation:
Random access, open tube or capped vials.
Does the applicant’s device contain the ability to transmit data to a computer, webserver, or mobile device?
☐ Yes ☐ X or ☐ No
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission?
☐ Yes ☐ or ☐ No ☐ X
4. Specimen Identification:
Specimens can be identified either manually or by barcode:
5. Specimen Sampling and Handling:
a. Normal mode: Automatic pipetting of a specimen; capped sample tube analysis and re-analysis.
b. Micro mode: Automatic pipetting of a specimen for each analysis through a secondary dispensing sample probe; sample tubes must be uncapped; no automatic re-analysis.
6. Calibration:
Calibration is an automated function of the Sysmex CS-2100i coagulation analyzer. A calibration curve is performed for each calibrated application.
7. Quality Control:
The analyzer has two types of control methods: X-Bar control and Levey-Jennings control.
{2}
8. Software:
FDA has reviewed applicant’s Hazard Analysis and Software Development processes for this line of product types:
Yes ☐ X or No ☐
F. Regulatory Information:
1. Regulation section:
21 CFR 864.5425, Multipurpose system for in vitro coagulation studies
2. Classification:
Class II
3. Product code:
JPA, System, multipurpose for in vitro coagulation studies
4. Panel:
Hematology (81)
G. Intended Use:
1. Indication(s) for Use:
The Sysmex CS-2100i is a fully automated blood coagulation analyzer intended for in vitro diagnostic use using venous blood samples collected in 3.2% sodium citrate tubes to analyze clotting, chromogenic and immunoassay methods in the clinical laboratory.
For determination of:
- Prothrombin Time (PT) seconds and PT INR with Dade® Innovin®
- Activated Partial Thromboplastin Time (APTT) with Dade® Actin® FSL
- Fibrinogen (Fbg) with Dade® Thrombin Reagent
- Antithrombin (AT) with INNOVANCE® Antithrombin
- D-dimer with INNOVANCE® D-Dimer.
The performance of this device has not been established in neonate and pediatric patient populations.
2. Special Conditions for Use Statement(s):
{3}
For prescription use only.
## H. Substantial Equivalence Information:
1. Predicate Device Name(s) and 510(k) numbers:
Sysmex® CA-1500 (K011235)
2. Comparison with Predicate Device:
The predicate system is the INNOVANCE D-dimer assay DVT exclusion claim using the Sysmex CA®-1500.
| Similarities | | |
| --- | --- | --- |
| Item | Device Sysmex CS-2100i | Predicate Sysmex CA®-1500 |
| Intended Use | The Sysmex® CS-2100i is a fully automated blood coagulation analyzer intended for in vitro diagnostic use using plasma collected from venous blood samples in 3.2% sodium citrate tubes to analyze clotting, chromogenic and immunoassay methods in the clinical laboratory. For determination of:
• Prothrombin Time (PT) seconds and PT INR with Dade® Innovin®
• Activated Partial Thromboplastin Time (APTT) with Dade® Actin® FSL
• Fibrinogen (Fbg) with Dade® Thrombin Reagent
• Antithrombin (AT) with INNOVANCE® Antithrombin
• D-dimer with INNOVANCE® D-Dimer
The performance of this device has not been established in neonate and pediatric patient populations. | The intended use of the Sysmex CA®-1500 is as a fully automated, computerized blood plasma coagulation analyzer for in vitro diagnostic use in clinical laboratories. The instrument uses citrated human plasma to perform the following parameters and calculated parameters:
Clotting Analysis
Prameters: Prothrombin Time (PT); Activated Partial Thromboplastin Time (APTT); Fibrinogen (Clauss); Batroxobin Time; Extrinsic Factors (II, V, VII, X); Intrinsic Factors (VIII, IX, XI, XII); Protein C.
Chromogenic Analysis
Parameters: Antithrombin III; Factor VIII; Plasminogen; Heparin; Protein C; α2-Antiplasmin.
Immunologic Analysis
Parameters: D-dimer.
Calculated Parameters: PT |
{4}
| Similarities | | |
| --- | --- | --- |
| Item | Device Sysmex CS-2100i | Predicate Sysmex CA®-1500 |
| | | Ratio; PT INR; PT %; Derived Fibrinogen; Factor Assays % Activity |
| Application | Immuno-chemical Application: D-dimer with INNOVANCE® D-Dimer | Same |
| Sample Type | 3.2% sodium citrate venous plasma | Same |
| Clinical Reportable Range | 0.19 to 35.2 mg/L FEU | Same |
| Specimen Processing | Automatic Pipetting and Dilution | Same |
| Sampling Mode | Normal and Micro Mode | Same |
| Sample Volumes in Normal Mode | 13 μL | Same |
| Temperature Control | Sample incubation well: 37°C ± 1.0°C | Same |
| Random Access | Yes | Same |
| Liquid Level Sensing | Yes – reagent and sample | Same |
| Bar Code Reader | Sample + reagent | Same |
| Rinse & Buffer Solutions - On-board - External | CA-CLEAN I; CA-CLEAN II; Dade Owren’s Buffer Water | Same Same |
| STAT Testing | Yes | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device Sysmex CS-2100i | Predicate Sysmex CA®-1500 |
| Operating Principle: Immuno-chemical | D-dimer at 660 nm | D-dimer at 800 nm |
| Light Source: | Halogen Lamp | Light Emitting Diode |
| Cap Piercing | Cap piercer | Cap piercer and No cap piercer |
| Pipetting Capabilities - Reagent probe - Sample probe | 20 – 200 μL 4 – 270 μL | 3 – 200 μL 5 – 450 μL |
| Temperature Control | -Detector: 37°C ± 0.5°C -Reagent incubation probe: 37.5 °C ± 0.5 °C | -Detector: 37°C ± 1.0°C -Reagent incubation probe: 37°C ± 1.0°C |
{5}
| Differences | | |
| --- | --- | --- |
| Item | Device Sysmex CS-2100i | Predicate Sysmex CA®-1500 |
| Reagent Cooling | 10°C ± 2°C, when ambient temperature is 20°C – 28°C. During operation 4°C - 15°C, when ambient temperature is 15°C – 30°C | 15°C ± 2°C, when ambient temperature is 15°C – 30°C |
| Sample Volumes in Micro Mode | 15 μL | 13 μL |
| Bidirectional Interface Communication Protocols | CA-, ASTM-, CS- Protocol | CA-, ASTM-Protocol |
I. Special Control/Guidance Document Referenced (if applicable):
CLSI H59-A Quantitative D-dimer for the Exclusion of Venous Thromboembolic Disease
J. Performance Characteristics:
1. Analytical Performance:
Applicable analytical performance studies using the INNOVANCE® D-Dimer assay on the Sysmex CS-2100i are documented in K151259. The following studies were performed and were not necessary to reproduce for this submission because the performance remains unchanged: method comparison with predicate device, clinical cut-off validation for pulmonary embolism (PE), precision/reproducibility, linearity, detection limit, carryover, interfering substances, on-board stability for reagent and control material, ambient temperature tolerance testing, expected values/reference range, dilution options comparison, and normal mode vs. micro mode comparison.
2. Other Supportive Instrument Performance Data Not Covered Above:
Clinical cut-off: Validation for deep vein thrombosis (DVT)
The INNOVANCE® D-Dimer assay was evaluated on the Sysmex CS-2100i analyzer in a multi-center study at U.S. and foreign (European) sites to validate the exclusion of a first event of deep vein thrombosis (DVT). These sites were emergency or ambulatory departments.
All potentially eligible patients who were suspected of having a first event DVT were evaluated using the Wells' rules to estimate their pre-test probability (PTP), and then categorized into likely or unlikely, or alternatively as high, intermediate or low PTP. Patients with a high PTP score were excluded from enrollment. Patients with no or a positive D-dimer result with the D-dimer assay used at each study center were
{6}
evaluated by imaging methods. Patients with a negative D-dimer result with the D-dimer assay used at each study center underwent imaging at the physician's discretion.
All patients with a negative clinical diagnosis of DVT at presentation were followed up after three months to evaluate potential development of DVT.
Specimens were collected prospectively from 1907 consecutive outpatients and stored frozen. Of these 1907 patients, 368 were excluded from analysis based on the preanalytical and post-analytical exclusion criteria (including 213 patients reported to have a previously documented or chronic DVT), resulting in a total of 1539 patients. In addition, patients with unobtainable follow-up data were excluded from analysis resulting in 1317 patients available for final analysis. The overall prevalence of DVT in the 1317 patients was 6.1% (80 of 1317) with 7.0% in the U.S. patients and 4.7% in the European patients.
The specimens collected in clinical sites were tested with the INNOVANCE® D-Dimer assay on the Sysmex CS-2100i analyzer and results were compared to a cut-off value of 0.50 mg/L FEU. A D-dimer result < 0.50 mg/L FEU was considered negative and a D-dimer result ≥ 0.50 mg/L FEU was considered positive. Instrument-specific sensitivity, specificity, negative predictive value (NPV) and positive predictive value (PPV) with lower bound (LCL) of a two-sided 95% confidence interval were calculated. Results obtained for each study population are detailed below:
Clinical Sensitivity and Specificity; U.S. Results
| U.S. sites DVT | Reference (Imaging and 3-month follow-up) | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| INNOVANCE® D-Dimer on Sysmex CS-2100i System | Positive | 55 | 450 | 505 |
| | Negative | 1 | 297 | 298 |
| | Total | 56 | 747 | 803 |
Sensitivity % = 98.2 95% LCL = 90.4
Specificity % = 39.8 95% LCL = 36.2
NPV % = 99.7 95% LCL = 98.1
NPV* % = 99.2 95% LCL = 95.7
PPV % = 10.9 95% LCL = 8.5
PPV* % = 22.3 95% LCL = 17.9
U.S. prevalence = 56/803 = 0.070 = 7.0%
*standardized to a prevalence of 15%
{7}
Clinical Sensitivity and Specificity; Outside U.S. Results (OUS)
| OUS sites DVT | Reference (Imaging and 3-month follow-up) | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| INNOVANCE® D-Dimer on Sysmex CS-2100i System | Positive | 23 | 217 | 240 |
| | Negative | 1 | 273 | 274 |
| | Total | 24 | 490 | 514 |
Sensitivity % = 95.8 95% LCL = 78.9
Specificity % = 55.7 95% LCL = 51.2
NPV % = 99.6 95% LCL = 98.0
NPV* % = 98.7 95% LCL = 93.0
PPV % = 9.6 95% LCL = 6.5
PPV* % = 27.6 95% LCL = 20.0
OUS prevalence = 24/514 = 0.047 = 4.7 %
*standardized to a prevalence of 15%
Clinical Sensitivity and Specificity; Overall Results
| U.S. and OUS sites DVT | Reference (Imaging and 3-month follow-up) | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| INNOVANCE® D-Dimer on Sysmex CS-2100i System | Positive | 78 | 667 | 745 |
| | Negative | 2 | 570 | 572 |
| | Total | 80 | 1237 | 1317 |
Sensitivity % = 97.5 95% LCL = 91.3
Specificity % = 46.1 95% LCL = 43.3
NPV % = 99.7 95% LCL = 98.7
NPV* % = 99.1 95% LCL = 96.6
PPV % = 10.5 95% LCL = 8.5
PPV* % = 24.2 95% LCL = 20.2
U.S. + OUS prevalence = 80/1317 = 0.061 = 6.1 %
*standardized to a prevalence of 15%
K. Proposed Labeling:
The labeling is sufficient and does satisfy the requirements of 21 CFR Part 809.10.
{8}
L. Conclusion:
The submitted information in this premarket notification is complete and does support a substantial equivalence decision.
9
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.