The Fujirebio Diagnostics CA 19-9™ RIA, an in vitro diagnostic test for the quantitative measurement of the CA 19-9 tumor associated antigen, in human serum or plasma, is indicated for the serial measurement of CA 19-9 to aid in the management of patients diagnosed with cancers of the exocrine pancreas. The test is useful as an aid in: Monitoring of disease status in those patients having confirmed pancreatic cancer who have levels of serum or plasma CA 19-9 above the cutoff, at the time of diagnosis. CA 19-9 values must be interpreted in conjunction with all other available clinical and laboratory data before a medical decision is determined.
Device Story
Solid-phase radioimmunoassay (RIA) for quantitative measurement of CA 19-9 tumor-associated antigen in human serum or plasma; utilizes forward sandwich principle. Polystyrene beads coated with mouse monoclonal anti-CA 19-9 antibody incubated with patient specimen; CA 19-9 antigen binds to solid support. Unbound material removed via aspiration/washing. Second mouse monoclonal anti-CA 19-9 antibody labeled with 125I added; binds to captured antigen. Unbound labeled antibody removed via aspiration/washing. Bound radioactivity measured in gamma counter. Standard curve generated by plotting antigen concentration versus radioactivity; patient concentrations interpolated from curve. Used in clinical laboratory settings by trained personnel. Results aid clinicians in monitoring disease status in confirmed pancreatic cancer patients. Interpretation requires integration with other clinical/laboratory data.
Clinical Evidence
Clinical performance evaluated in 61 patients with pancreatic cancer (234 observations). Effectiveness assessed by correlating serial CA 19-9 marker changes (≥20% increase/decrease or stable) with disease status (progressive, stable, responding). 57% of positive serum sets correlated with disease progression; 71% of sets with no significant marker change correlated with stable disease. Analytical performance included sensitivity (0.9 U/mL), linearity (slope 0.96), and reproducibility (intra-assay CV 12.5% at 8 U/mL).
Indicated for serial measurement of CA 19-9 in human serum or plasma to aid management of patients diagnosed with exocrine pancreatic cancer, specifically for monitoring disease status in patients with baseline CA 19-9 levels above the cutoff (37 U/mL).
Regulatory Classification
Identification
A tumor-associated antigen immunological test system is a device that consists of reagents used to qualitatively or quantitatively measure, by immunochemical techniques, tumor-associated antigens in serum, plasma, urine, or other body fluids. This device is intended as an aid in monitoring patients for disease progress or response to therapy or for the detection of recurrent or residual disease.
Special Controls
*Classification.* Class II (special controls). Tumor markers must comply with the following special controls: (1) A guidance document entitled “Guidance Document for the Submission of Tumor Associated Antigen Premarket Notifications (510(k)s) to FDA,” and (2) voluntary assay performance standards issued by the National Committee on Clinical Laboratory Standards.
Predicate Devices
Abbott Laboratories AxSYM® CEA MEIA
Submission Summary (Full Text)
{0}------------------------------------------------
MAY 0 9 2002
Image /page/0/Picture/1 description: The image shows the logo for "FUJIREBIO DIAGNOSTICS, INC." The logo consists of a stylized graphic to the left of the text. To the right of the text is a handwritten number, "K020566".
## 510(k) SUMMARY
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.
The assigned 510(k) number is: K020566.
### Submitter Information
| Address: | Fujirebio Diagnostics, Inc.<br>201 Great Valley Parkway<br>Malvern, PA 19355 |
|---------------------------|---------------------------------------------------------------------------------|
| Contact person: | Daniel J. O'Shannessy, Ph.D., (610) 240-3811 |
| Summary preparation date: | February 15, 2002 |
| Name of Device | |
| Trade/Proprietary Name: | Fujirebio Diagnostics CA 19-9TM RIA |
| Common/Usual Name: | Immunological test for 1116NS19-9 Antibody Defined Antigen<br>(CA 19-9) |
| Classification Name: | 21CFR 866.6010, Class II, Tumor Associated Antigen<br>Immunological Test System |
| Predicate Device | |
Abbott Laboratories AxSYM® CEA MEIA
### Device Description
The Fujirebio Diagnostics CA 19-9™ RIA is a solid-phase radioimmunoassay based on the forward sandwich principle. Polystyrene beads coated with a mouse monoclonal antibody against CA 19-9 are incubated with a serum or plasma specimen, or the appropriate standards or controls. During the incubation, the CA 19-9 antigen present in the specimen is specifically bound to the solid support by the mouse monoclonal antibody. Unbound material present in the specimen is removed by aspiration and washing of the beads. The same mouse monoclonal anti-CA 19-9 labeled with 1281 is then incubated with the beads and binds
{1}------------------------------------------------
to the CA 19-9 antigen already bound to the beads. Unbound labeled antibody is removed by aspiration and washing. The bound radioactivity is determined by counting the beads in a gamma counter. A standard curve is obtained by plotting the CA 19-9 antigen concentration of the standards versus bound radioactivity. The CA 19-9 antigen concentrations of unknown patient specimens are determined from the standard curve and are directly proportional to the concentration of the bound tracer molecules.
#### Intended Use
The Fujirebio Diagnostics CA 19-9™ RIA, an in vitro diagnostic test for the quantitative measurement of the CA 19-9 tumor associated antigen, in human serum or plasma, is indicated for the serial measurement of CA 19-9 to aid in the management of patients diagnosed with cancers of the exocrine pancreas. The test is useful as an aid in:
Monitoring of disease status in those patients having confirmed pancreatic cancer who have levels of serum or plasma CA 19-9 above the cutoff, at the time of diagnosis.
CA 19-9 values must be interpreted in conjunction with all other available clinical and laboratory data before a medical decision is determined.
#### Summary of Performance characteristics
#### Analytical Sensitivity (Minimal Detectable Dose)
The analytical sensitivity was determined to be 0.9 U/mL. This level of analytical sensitivity is well below the established "cut-off" of 37 U/mL.
#### Interfering Substances
The appropriate NCCLS guideline was followed to determine possible sources of interference with the Fujirebio Diagnostics CA 19-9™ RIA kit. Only human anti-mouse antibodies (HAMA), at a titer of 16,636, showed potential interference with the assay. This concentration of human anti-mouse antibody is extremely high. HAMA was also tested at a lower titer of 1664 and showed no effect on the assay. All other substances that were tested with the Fujirebio Diagnostics CA 19-9™ RIA kit showed no interference at the levels tested.
#### Recoverv Studies
Ten (10) patient samples were spiked with purified CA 19-9 antigen at three (3) different levels. Results were reported as percent recoveries (% Recovery) and compared to the acceptable percent Recovery Limits calculated using the precision of the assay diluent buffer (which was run as samples, both spiked and unspiked).
For the Low spike samples, where the values of added antigen were approximately 8 U/mL, acceptable limits of % Recovery were calculated as being 87.9 - 112.1%. For the Mid spike samples, where the values of added antigen were approximately 29 U/mL, acceptable limits of % Recovery were calculated to be 81.9 - 118%. For the High spike samples, where the values of added antigen were approximately 90 U/mL, acceptable limits of % Recovery were calculated to be 93.0 - 107.0%. These data are listed in the table below.
{2}------------------------------------------------
| Patient<br>Number | Low Spike<br>Percent Recovery | Mid - Spike<br>Percent Recovery | High Spike<br>Percent Recovery |
|-------------------|-------------------------------|---------------------------------|--------------------------------|
| 1 | 110.23% | 103.42% | 111.58% |
| 2 | 112.12% | 101.87% | 96.49% |
| 3 | 114.08% | 102.35% | 99.07% |
| 4 | 121.37% | 102.30% | 107.50% |
| 5 | 112.41% | 102.89% | 100.45% |
| 6 | 92.31% | 102.18% | 99.99% |
| 7 | 117.43% | 100.93% | 98.81% |
| 8 | 101.98% | 97.75% | 99.10% |
| 9 | 99.64% | 102.43% | 98.49% |
| 10 | 101.78% | 102.96% | 99.78% |
| Mean | 108.34% | 101.91% | 101.13% |
#### Linearity
The linearity of the Fujirebio Diagnostics CA 19-9 RIA was tested with serial dilutions of 12 individuals with elevated CA 19-9 assay values. Dilutions were prepared in CA 19-9 0 Standard/Diluent Regression analysis comparing observed and expected CA 19-9 assay values yielded a mean slope for the twelve samples of 0.96 ± 0.031 and a mean y-intercept of 5.97 ± 7.65.
#### Reproducibility:
Each of three (3) sites performed one (1) run per day for thirteen (13) acceptable days with three (3) different lots of product. Test materials were assayed in random order for each run. but were tested identically across each lot of reagent under evaluation.
The total average variability ranged from 6.7% (44 U/mL) to 15.4% (8 U/mL). Day-to-day variation across sample-site-lot combinations peaked at 14.9 % CV with a nadir of 0%. The maximum intra-assay variation was 18 % at a CA 19-9 concentration of 8 U/mL, a concentration below the first non-zero calibrator and well under the clinical cut-off of 37 U/mL. The average intra-assay variation across all sites and lots for that 8 U/mL sample was 12.5 % CV. For all other concentrations tested, the average intra-assay variation did not exceed 6.5% CV.
### Clinical Data
#### Apparently Healthy Subjects:
To determine the distribution of CA 19-9 values in apparently normal healthy individuals, and to confirm the cutoff of 37 U/mL, a sample of 200 women and 200 men who were apparently disease free were assessed.
{3}------------------------------------------------
## Fujirebio Diagnostics CA 19-9™ RIA Distribution of
| Group | Total | <37<br>U/mL | 37 - 49.9<br>U/mL | 50 - 69.9<br>U/mL | 70 - 99.9<br>U/mL | >100<br>U/mL |
|---------|-------|-------------|-------------------|-------------------|-------------------|--------------|
| Males | 200 | 189 (94.5%) | 4 (2.0%) | 5 (2.5%) | 0 (0.0%) | 2 (1.0%) |
| Females | 200 | 186 (93.0%) | 7 (3.5%) | 4 (2.0%) | 2 (1.0%) | 1 (0.5%) |
## Values of Apparently Healthy Subjects
### Benign Disease Cohorts:
Three hundred and ninety-nine (399) benign disease patient cohorts were assembled to determine the distribution of serum CA 19-9 values in benign diseases that may be coexistent in patients with confirmed pancreatic cancer.
| Diagnostic Group | Total | <37<br>U/mL | 37 - 49.9<br>U/mL | 50 - 69.9<br>U/mL | 70 - 99.9<br>U/mL | ≥100<br>U/mL |
|--------------------------------------------------|-------|-------------|-------------------|-------------------|-------------------|--------------|
| Benign Diseases of the<br>Genitourinary Tract | 99 | 90 (90.9%) | 6 (6.1%) | 2 (2.0%) | 1 (1.0%) | 0 (0.0%) |
| Benign Diseases of the<br>Gastrointestinal Tract | 100 | 88 (88.0%) | 7 (7.0%) | 3 (3.0%) | 2 (2.0%) | 0 (0.0%) |
| Benign Diseases of the<br>Pancreas/Pancreatitis | 100 | 94 (94.0%) | 1 (1.0%) | 4 (4.0%) | 1 (1.0%) | 0 (0.0%) |
| Chronic Heart Disease/<br>Hypertension | 100 | 80 (80.0%) | 10 (10.0%) | 5 (5.0%) | 5 (5.0%) | 0 (0.0%) |
### Fujirebio Diagnostics CA 19-9™ RIA Distribution of Values Benign Diseases
#### Monitoring of Disease Status in Patients Diagnosed with Pancreatic Cancer:
The effectiveness of CA 19-9 as an aid in monitoring of disease status in patients diagnosed with pancreatic cancer was determined by assessing changes in CA 19-9 levels in serial serum sets with changes in disease status. Samples from 61 patients with a total of 234 observations were analyzed. The average number of observations per patient was 3.84. Fifty-seven percent (57%) of the positive serum sets correlated with disease progression while seventy-one (71%) of serum sets showing no significant change in the marker correlated with no progression. The Table below presents the data in a 3x3 classification scheme.
The disease states are:
- Progression from one collection to the next collection (Progressing). .
- No Change in disease status (Stable). .
- Reduction in the signs and symptoms of the disease from one collection to the next . (Responding).
Marker changes are classified as:
{4}------------------------------------------------
- A 20% or greater increase in the marker from one collection to the next (INC) .
- No significant change in the marker (|Delta CA 19-9|<20%) (NC) .
- A 20% or greater decrease in the marker value from one collection to the next (DEC) .
## Expanded Distribution
| Marker<br>Change | Disease Status | | | Total |
|------------------|----------------|--------------|--------------|-------|
| | Progressive | Stable | Responding | |
| INC | 31 | 30 | 4 | 65 |
| | 56.4% (1.29) | 32.3% (.477) | 16.0% (.190) | 37.6% |
| NC | 12 | 41 | 7 | 60 |
| | 21.8% (.279) | 44.1% (.789) | 28.0% (.389) | 34.7% |
| DEC | 12 | 22 | 14 | 48 |
| | 21.8% (.279) | 23.7% (.310) | 56.0% (1.27) | 27.7% |
| Total | 55 | 93 | 25 | 173 |
{5}------------------------------------------------
Image /page/5/Picture/1 description: The image is a black and white logo for the U.S. Department of Health & Human Services. The logo features a stylized image of an eagle with three heads, representing the department's mission to protect the health of all Americans and provide essential human services. The words "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" are arranged in a circular pattern around the eagle image.
MAY 0 9 2002
Food and Drug Administration 2098 Gaither Road Rockville MD 20850
Daniel J. O'Shannessy, Ph.D. Chief Scientific Officer Fujirebio Diagnostics, Inc. 201 Great Valley Parkway Malvern, Pennsylvania 19355-1307
Re: k020566
> Trade/Device Name: Fujirebio Diagnostics CA 19-9TM RIA Regulation Number: 21 CFR § 866.6010 Regulation Name: Tumor Associated antigen Immunological Test System Regulatory Class: II Product Code: NIG Dated: April 19, 2002 Received: April 23, 2002
Dear Dr. O'Shannessy:
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 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.
{6}------------------------------------------------
Page 2
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 nvellicate device results in a classification for your device and thus, permits your device to proceed to the market.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4588. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR 807.97). Other general information on your responsibilities under the Act may be obtained 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/dsma/dsmamain.html".
Sincerely yours,
Steven Butman
Steven I. Gutman, M.D., M.B.A. Director Division of Clinical Laboratory Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{7}------------------------------------------------
## INDICATIONS FOR USE STATEMENT
Page 1 of
510(k) Number (if known): K020566
# Device Name: Fujirebio Diagnostics CA 19-9™ RIA
The Fujirebio Diagnostics CA 19-9™ RIA, an in vitro diagnostic test for the quantitative The Tullion Diagnootio Cr. To associated antigen, in human serum or plasma, is indicated measurement of the OF 10 Claims. 18-9 to aid in the management of patients diagnosed with cancers of the exocrine pancreas. The test is useful as an aid in:
Monitoring of disease status in those patients having confirmed pancreatic cancer who have levels of serum or plasma CA 19-9 above the cutoff, at the time of diagnosis.
CA 19-9 values must be interpreted in conjunction with all other available clinical and laboratory data before a medical decision is determined.
Sousan S. Altaie
(Division Sign-Off) Division of Clinical Laboratory Devices
510(k) Number K020566
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE OF NEEDED)
Concurence of CDRH, Office of Device Evaulation (ODE)
(Optional Format 3-10-98)
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.