XN CHECK BF is used for control and calibration verification of Sysmex XN series (XN-10, XN-11, XN-20, XN-21) analyzers. It is not. however, intended for actual calibration of these analyzers. Assayed parameters include: WBC-BF (10^3/μl), RBC-BF (10^6/ μl), ΜΝ# (10^3/μl), ΜΝ% (%), ΡΜΝ% (%), ΡΜΝ% (%), ΤC-ΒΓ# (10°3/μl)
Device Story
XN CHECK BF is an in-vitro diagnostic hematology control; consists of stabilized red and white blood cell components in preservative medium. Packaged in 3ml polypropylene vials. Used in clinical laboratories to verify calibration and monitor performance of Sysmex XN series analyzers (XN-10, XN-11, XN-20, XN-21). Device provides assayed values for WBC-BF, RBC-BF, MN#, PMN#, MN%, PMN%, and TC-BF#. Laboratory personnel process the control through the analyzer; results are compared against expected values to ensure system accuracy and reproducibility. Benefits include reliable quality control for body fluid analysis, ensuring clinical diagnostic accuracy.
Clinical Evidence
Bench testing only. Studies included open-vial stability (30 days), closed-vial stability (84 days), and precision performance. Data demonstrated consistent reproducibility and stability for the entire product dating, confirming substantial equivalence to the predicate.
Technological Characteristics
Stabilized red and white blood cell components in preservative medium. Packaged in 3ml polypropylene vials. Storage at 2-8°C. No electronic or software components; purely a chemical/biological control mixture.
Indications for Use
Indicated for use as an in-vitro diagnostic control material for monitoring the accuracy and precision of Sysmex XN-10, XN-11, XN-20, and XN-21 hematology analyzers in clinical laboratory settings.
Regulatory Classification
Identification
A hematology quality control mixture is a device used to ascertain the accuracy and precision of manual, semiautomated, and automated determinations of cell parameters such as white cell count (WBC), red cell count (RBC), platelet count (PLT), hemoglobin, hematocrit (HCT), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and mean corpuscular hemoglobin concentration (MCHC).
Special Controls
*Classification.* Class II (special controls). Except when intended for use in blood components, the device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
Predicate Devices
XN CHECK™ BF (k120744)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k141957
B. Purpose for Submission:
Expanded indications for use of previously cleared control material (k120744) with the modified Sysmex XN series (XN-11 and XN-21) hematology analyzers
C. Measurand:
Assayed hematology parameters: WBC-BF (10³/μL), RBC-BF (10⁶/μL), MN# (10³/μL), PMN# (10³/μL), MN% (%), PMN% (%), TC-BF# (10³/μL)
D. Type of Test:
Quantitative
E. Applicant:
Streck, Inc.
F. Proprietary and Established Names:
XN CHECK™ BF
G. Regulatory Information:
1. Regulation section:
21 CFR § 864.8625, Hematology quality control mixture
2. Classification:
Class II
3. Product code:
JPK, mixture, hematology quality control
4. Panel:
{1}
Hematology (81)
## H. Intended Use:
1. Intended use(s):
XN CHECK BF is used for control and calibration verification of Sysmex XN series (XN-10, XN-11, XN-20, XN-21) analyzers. It is not, however, intended for actual calibration of these analyzers. Assayed parameters include:
WBC-BF (10³/μL), RBC-BF (10⁶/μL), MN# (10³/μL), PMN# (10³/μL), MN(%), PMN(%), TC-BF# (10³/μL)
2. Indication(s) for use:
Same as intended use
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
Sysmex XN (XN-10, XN-11, XN-20, XN-21) hematology analyzers
## I. Device Description:
XN CHECK™ BF body fluid control is an in-vitro diagnostic product that contains the following: stabilized red blood cell component(s) and stabilized white blood cell component(s) in a preservative medium. The control includes two levels (i.e., low and medium) which are packaged separately in polypropylene plastic vials with screw caps containing 3 mL. The vials will be packaged in (4) welded vacuum formed clamshell container with the Instructions for Use / assay sheet. The product storage conditions are at 2-8°C.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
XN CHECK™ BF
2. Predicate 510(k) number(s):
k120744
3. Comparison with predicate:
{2}
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | XN CHECK BF is used for control and calibration verification of Sysmex XN series (XN-10, XN-11, XN-20, XN-21) analyzers. It is not, however, intended for actual calibration of these analyzers. Assayed parameters include: WBC-BF (10^{3}/μL), RBC-BF (10^{6}/μL), MN# (10^{3}/μL), PMN# (10^{3}/μL), MN% (%), PMN% (%), TC-BF# (10^{3}/μL) | XN CHECK BF is used for control and calibration verification of Sysmex XN (XN-10, XN-20) analyzers. It is not, however, intended for actual calibration of these analyzers. Assayed parameters are: WBC- BF (10^{3}/μL), RBC-BF (10^{6}/μL), MN# (10^{3}/μL), PMN# (10^{3}/μL), MN% (%), PMN% (%), TC-BF# (10^{3}/μL) |
| Open-vial stability | 30 days | Same |
| Closed-vial stability | 84 days | Same |
| Reagents | XN CHECK BF contains the following: stabilized red blood cell component(s) and stabilized white blood cell component(s) in a preservative medium. | Same |
| Storage conditions | 2 - 8°C | Same |
## K. Standard/Guidance Document Referenced (if applicable):
CLSI H26-A2, Validation, Verification, and Quality Assurance of Automated Hematology Analyzers; Approved Standard-Second Edition
CLSI EP05-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition
## L. Test Principle:
Bi-level XN CHECK™ BF was designed to evaluate the accuracy and precision of the Sysmex XN series (XN-10, XN-11, XN-20, XN-21) instruments.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision performance studies were conducted at 2 different sites. Data were collected across 3 different Sysmex XN-21 analyzers throughout the product dating claim, with 3 separately manufactured lots of two levels of XN CHECK BF control material. Three operators performed 10 consecutive runs on each analyzer with
{3}
separate vials of control from each lot at the beginning and end of the product dating claim. The datasets collected across the 3 lots of XN CHECK BF illustrate consistent recovery across multiple instruments at multiple sites with the resulting data sets recovering within the parameter specific assay assignment ranges set forth for each measurand.
The acceptance criteria for the XN CHECK BF assayed parameters were based on a compilation of the CV% for each measurand over the data collected on 3 XN-21 instruments at 2 sites throughout the product dating claim, with the 3 separately manufactured lots of XN CHECK BF. The acceptance criteria was based on the data collected internally at Streck and external sites which takes into account interoperator, inter-laboratory, and inter-instrument variability. The reported CV% for each measurand per level, per lot was deemed acceptable if less than the threshold value as reported in the XN CHECK BF CV% Summary Table.
Results show that the CV% values collected were within acceptable threshold values.
## XN-CHECK BF CV% Summary Table
| XN-CHECK BF Level 1 | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Lot # | Measurand (%CV) | | | | | | |
| | WBC-BF | RBC-BF | MN# | PMN# | MN% | PMN% | TC-BF# |
| 3280 | 4.4807 | 3.9460 | 5.9163 | 5.6166 | 4.402 | 2.895 | 4.4807 |
| 3322 | 3.6548 | 4.4597 | 6.7422 | 5.3493 | 5.674 | 3.915 | 3.6548 |
| 3336 | 3.7443 | 5.0878 | 6.6383 | 5.2739 | 5.417 | 3.735 | 3.7443 |
| CV% Acceptance Criteria | 10.0 | 10.0 | 10.0 | 10.0 | 15.0 | 10.0 | 10.0 |
| XN-CHECK BF Level 2 | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Lot # | Measurand (%CV) | | | | | | |
| | WBC-BF | RBC-BF | MN# | PMN# | MN% | PMN% | TC-BF# |
| 3280 | 2.2505 | 2.4603 | 3.7223 | 3.3590 | 3.241 | 2.229 | 2.2505 |
| 3322 | 3.1141 | 4.2985 | 4.3791 | 4.0480 | 3.356 | 2.406 | 3.1141 |
| 3336 | 2.8845 | 3.8881 | 4.7677 | 4.3441 | 4.122 | 2.960 | 2.8845 |
| CV% Acceptance Criteria | 15.0 | 5.0 | 10.0 | 10.0 | 15.0 | 15.0 | 10.0 |
To illustrate the variance component estimates, an Analysis of Variance (ANOVA) method was used in data analysis as shown in tables below.
{4}
| Module XN-21 | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Level 1 | | | Within-run | | Between-run | | Between-instrument | | Between-lot | | Between-site | | Total | |
| Sample | N | Mean | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| WBC-BF | 180 | 0.077 | 0.003 | 3.86 | 0.001 | 0.95 | 0.001 | 0.85 | 0.001 | 0.79 | 0.000 | 0.00 | 0.003 | 4.14 |
| RBC-BF | 180 | 0.026 | 0.001 | 2.95 | 0.001 | 2.19 | 0.001 | 1.94 | 0.000 | 0.00 | 0.001 | 3.35 | 0.001 | 5.34 |
| MN# | 180 | 0.031 | 0.002 | 6.36 | 0.000 | 0.00 | 0.000 | 0.00 | 0.000 | 0.00 | 0.001 | 1.89 | 0.002 | 6.64 |
| PMN# | 180 | 0.046 | 0.002 | 4.83 | 0.001 | 2.32 | 0.000 | 0.93 | 0.001 | 1.76 | 0.001 | 1.44 | 0.003 | 5.89 |
| MN% | 180 | 40.44 | 1.921 | 4.75 | 0.731 | 1.81 | 0.000 | 0.00 | 0.534 | 1.32 | 0.884 | 2.19 | 2.300 | 5.69 |
| PMN% | 180 | 59.56 | 1.921 | 3.22 | 0.731 | 1.23 | 0.000 | 0.00 | 0.534 | 0.90 | 0.884 | 1.48 | 2.300 | 3.86 |
| TC-BF | 180 | 0.077 | 0.003 | 3.86 | 0.001 | 0.95 | 0.001 | 0.85 | 0.001 | 0.79 | 0.000 | 0.00 | 0.003 | 4.14 |
| Module XN-21 | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Level 2 | | | Within-run | | Between-run | | Between-instrument | | Between-lot | | Between-site | | Total | |
| Sample | N | Mean | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| WBC-BF | 180 | 0.307 | 0.007 | 2.26 | 0.005 | 1.69 | 0.000 | 0.15 | 0.004 | 1.32 | 0.002 | 0.52 | 0.010 | 3.16 |
| RBC-BF | 180 | 0.078 | 0.001 | 1.68 | 0.001 | 1.91 | 0.002 | 2.80 | 0.001 | 1.60 | 0.002 | 2.17 | 0.004 | 4.65 |
| MN# | 180 | 0.127 | 0.005 | 4.04 | 0.002 | 1.65 | 0.000 | 0.00 | 0.002 | 1.38 | 0.001 | 0.97 | 0.006 | 4.68 |
| PMN# | 180 | 0.180 | 0.006 | 3.07 | 0.004 | 2.24 | 0.000 | 0.19 | 0.003 | 1.89 | 0.004 | 1.97 | 0.008 | 4.68 |
| MN% | 180 | 41.43 | 1.319 | 3.18 | 0.552 | 1.33 | 0.000 | 0.00 | 0.522 | 1.26 | 0.769 | 1.86 | 1.705 | 4.12 |
| PMN% | 180 | 58.57 | 1.319 | 2.25 | 0.552 | 0.94 | 0.000 | 0.00 | 0.522 | 0.89 | 0.769 | 1.31 | 1.705 | 2.91 |
| TC-BF | 180 | 0.307 | 0.007 | 2.26 | 0.005 | 1.69 | 0.000 | 0.15 | 0.004 | 1.32 | 0.002 | 0.52 | 0.010 | 3.16 |
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Value assignment:
Value assignment for XN-CHECK™ BF was based on data collected across 3 XN-21 instruments. Data was collected across three separately manufactured lots. A 10-run reproducibility study was executed for the bi-level control on each lot at the beginning and end of the product dating claim (n=60 per level). Three operators conducted the value assignment study.
Assay values were assigned to the parameters assayed on the XN-11/XN 21 based on a statistical analysis of the data collected externally and at Streck. The assay ranges assigned to each parameter were based on the data collected and the acceptance criteria takes into account inter-operator, inter-laboratory, and inter-instrument variability.
Open-vial stability:
The open-vial stability claim was verified on the XN-21 instrument. Open-vial stability testing was performed real-time for the 30-day open-vial stability claim throughout the stated product life.
{5}
Two vials of control per level from each lot were analyzed in duplicate over a period of 30 days (i.e., analysis performed on days 1, 31 and four intermediate testing days (days 7, 14, 21 and 28); (n=24)). All of the data for this study was collected internally at Streck utilizing one operator. Four data points were collected at each testing event. Throughout the collection of the open-vial stability data each vial of control was stored between 2° to 8°C and removed from the refrigerator for testing. After testing, the vial was returned to the refrigerator until the next testing event. CV% was used to generate acceptance criteria of the open-vial stability study. The CV% selected was based on a compilation of the CV% shown in the precision performance studies as well as the performance specifications of the XN-11/XN-21 instruments. Selection of the acceptance criteria was based on the data collected internally at Streck and external sites. It takes into account inter-operator, inter-laboratory, and inter-instrument variability. The reported CV% for each measurand per level, per lot was deemed acceptable if less than the threshold value as reported in the XN CHECK BF CV% Summary Table (above).
Results show that the CV% values collected were within acceptable threshold values.
## Closed-vial stability:
The 84-day Closed-Vial Stability claim was verified on the XN-21 with all three lots of control material. Two vials of control per level from each reference lot were used at each testing interval for the study. A minimum of four data points were collected at each testing event over the 84-day closed-vial stability claim. Data was collected internally with one operator. All data were collected and analysis of the assayed parameters on the XN-11/21 analyzers was performed using CLSI EP5-A2 methods. For each measurand, on each lot, using one instrument, imprecision estimates were calculated for each level of the 3 separately manufactured lots.
CV% was used to generate acceptance criteria of the closed-vial stability study. The CV% selected was based on a compilation of the CV% shown in the precision performance studies. Selection of the acceptance criteria was based on the data collected internally at Streck and external sites. It takes into account inter-operator, inter-laboratory, and inter-instrument variability. The reported CV% for each measurand per level, per lot was deemed acceptable if less than the threshold value as reported in the XN CHECK BF CV% Summary Table above.
Results show that the CV% values collected were within acceptable threshold values.
Open- and closed-vial stability of XN-CHECK™ BF was assessed in terms of the measurand drift as suggested in the CLSI EP-25 Guideline. Scatter plots were provided with fitted linear regression lines and corresponding 95% confidence intervals. The acceptance criteria were based on a specific percentage of change from mean level at time 0. All parameters were within the draft acceptance limits for the target time durations for both open- and closed-vial stability.
6
{6}
| Maximum Allowable Change for Stability | | |
| --- | --- | --- |
| Parameter | Level 1 or 2 | Drift Acceptance Limit (% Change from Baseline) |
| WBC-BF | L1 | ± 20% |
| | L2 | ± 30% |
| RBC-BF | L1 | ± 20% |
| | L2 | ± 10% |
| MN# | L1 | ± 20% |
| | L2 | ± 20% |
| PMN# | L1 | ± 20% |
| | L2 | ± 20% |
| MN% | L1 | ± 30% |
| | L2 | ± 30% |
| PMN% | L1 | ± 20% |
| | L2 | ± 30% |
| TC-BF | L1 | ± 20% |
| | L2 | ± 20% |
d. Detection limit:
Not applicable
e. Analytical specificity:
Not applicable
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
Not applicable
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
{7}
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
The end-user is instructed to refer to the product assay sheet accompanying the product information sheet.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
8
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.