SPOTCHEM II INOGANIC PHOSPHORUS, CPK AND URIC ACID TESTS
K051648 · Arkray, Inc. · CGS · Jan 31, 2006 · Clinical Chemistry
Device Facts
Record ID
K051648
Device Name
SPOTCHEM II INOGANIC PHOSPHORUS, CPK AND URIC ACID TESTS
Applicant
Arkray, Inc.
Product Code
CGS · Clinical Chemistry
Decision Date
Jan 31, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1215
Device Class
Class 2
Indications for Use
The SPOTCHEM II Inorganic Phosphorus test is intended to measure inorganic phosphorous in serum, plasma, and whole blood. Measurements of inorganic phosphorous are used in the diagnosis and treatment of various disorders, including parathyroid gland and kidney disease, and vitamin D imbalance. The SPOTCHEM II CPK test is intended to measure the activity of the enzyme creatine phosphokinase in serum, plasma, and whole blood. Measurements of creatine phosphokinase and isoenzymes are used in the diagnosis and treatment of myocardial infarction and muscle diseases such as progressive, Duchenne-type muscular dystrophy. The SPOTCHEM II Uric Acid test is intended to measure uric acid in serum, plasma, and whole blood. Measurements of uric acid are used in the diagnosis and treatment of numerous renal and metabolic disorders, including renal failure, gout, leukemia, psoriasis, starvation or other wasting conditions, and of patients receiving cytotoxic drugs.
Device Story
SPOTCHEM II assays (Inorganic Phosphorus, CPK, Uric Acid) are in vitro diagnostic tests for use on the SPOTCHEM EZ analyzer. Device consists of a multi-layered plastic reagent strip; user applies serum, plasma, or whole blood sample to the strip. Analyzer uses reflectance spectroscopy to measure colorimetric reaction rates at specific wavelengths (610 nm for Phosphorus; 550 nm for CPK and Uric Acid). Instrument software calculates analyte concentration based on a two-point calibration curve stored on a lot-specific magnetic card. Results are displayed to the healthcare provider to aid in diagnosing conditions like kidney disease, myocardial infarction, gout, and metabolic disorders. Intended for professional use.
Clinical Evidence
Bench testing only. Precision assessed via intra-assay (n=20) and inter-assay (n=20) studies; CVs generally <5%. Linearity confirmed up to 18.7 mg/dL (phosphorus), 993 IU/L (CPK), and 12.8 mg/dL (uric acid). Method comparison against predicate (n=41) showed strong correlation (r=0.997, 0.992, 0.996 respectively). Matrix comparison (serum vs. whole blood) showed high correlation (r=0.981-0.999).
Technological Characteristics
Plastic reagent strips with multi-layered test fields. Reflectance spectroscopy (550 nm/610 nm). Quantitative colorimetric/enzymatic assays. Calibration via lot-specific magnetic card. Analyzed on SpotChem EZ analyzer. No specific material standards cited.
Indications for Use
Indicated for patients requiring quantitative measurement of inorganic phosphorus, creatine phosphokinase (CPK), or uric acid in serum, plasma, or whole blood to assist in the diagnosis and treatment of renal, metabolic, and muscular disorders.
Regulatory Classification
Identification
A creatine phosphokinase/creatine kinase or isoenzymes test system is a device intended to measure the activity of the enzyme creatine phosphokinase or its isoenzymes (a group of enzymes with similar biological activity) in plasma and serum. Measurements of creatine phosphokinase and its isoenzymes are used in the diagnosis and treatment of myocardial infarction and muscle diseases such as progressive, Duchenne-type muscular dystrophy.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k051648
B. Purpose for Submission:
Notification of intent to market three assays – SpotChem II Inorganic Phosphorous, SpotChem II CPK, SpotChem II Uric Acid - on an existing device.
C. Measurand:
Phosphorus (Inorganic)
Creatine phosphokinase
Uric Acid
D. Type of Test:
Quantitative, colorimetric
E. Applicant:
Arkray, Inc.
F. Proprietary and Established Names:
SPOTCHEM II Inorganic Phosphorus
SPOTCHEM II CPK
SPOTCHEM II Uric Acid
G. Regulatory Information:
1. Regulation section:
21CFR 862.1580: Phosphorus (inorganic) test system
21CFR 862.1215: Creatine phosphokinase/creatine kinase
21CFR 862.1775: Uric acid test system
2. Classification:
Phosphorus (Inorganic) – Class I(reserved)
Creatine phosphokinase/creatine kinase – Class II
Uric Acid – Class I(reserved)
{1}
3. Product code:
CEO - Phosphorus (inorganic)
CGS - Creatine phosphokinase/creatine kinase
KNK - Uric acid test system
4. Panel:
Chemistry (75)
H. Intended Use:
1. Intended use(s):
See indications for use.
2. Indication(s) for use:
The SPOTCHEM II Inorganic Phosphorus test is intended to measure inorganic phosphorous in serum, plasma, and whole blood. Measurements of inorganic phosphorous are used in the diagnosis and treatment of various disorders, including parathyroid gland and kidney disease, and vitamin D imbalance.
The SPOTCHEM II CPK test is intended to measure the activity of the enzyme creatine phosphokinase in serum, plasma, and whole blood. Measurements of creatine phosphokinase and isoenzymes are used in the diagnosis and treatment of myocardial infarction and muscle diseases such as progressive, Duchenne-type muscular dystrophy.
The SPOTCHEM II Uric Acid test is intended to measure uric acid in serum, plasma, and whole blood. Measurements of uric acid are used in the diagnosis and treatment of numerous renal and metabolic disorders, including renal failure, gout, leukemia, psoriasis, starvation or other wasting conditions, and of patients receiving cytotoxic drugs.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
SPOTCHEM EZ analyzer
{2}
I. Device Description:
The SpotChem II Inorganic Phosphorus, CPK, and Uric assays are in vitro diagnostic procedures intended to measure inorganic phosphorus, CPK, and uric acid quantitatively in human serum and plasma on the SpotChem EZ Analyzer. The device is composed of a plastic strip to which a multi-layered test field is affixed. The layers consist of a sample-retention layer, a layer containing the reagent and a support layer. A fixed amount of serum or plasma is placed on the test field of the reagent strip. The serum or plasma spreads in a uniform fashion across the entire surface of the sample retention layer. The serum or plasma then permeates into the reagent layer where the reaction is initiated.
J. Substantial Equivalence Information:
1. Predicate device name(s):
PolyChem Inorganic Phosphorus, PHO500
PolyChem CK, TCK500
PolyChem Uric Acid, URA500
2. Predicate 510(k) number(s):
PolyChem Inorganic Phosphorus: K020852/A002
PolyChem CK: K020852/A007
PolyChem Uric Acid: K020852/A025
{3}
3. Comparison with predicate:
| | Inorganic Phosphorus | CPK | Uric Acid |
| --- | --- | --- | --- |
| Predicate Methodology | Colorimetric | Colorimetric enzyme-based | Colorimetric |
| Submitted Methodology | Colorimetric | Colorimetric enzyme-based | Colorimetric enzyme-based |
| Predicate Storage Temperature | 2-8 °C | 2-8 °C | 2-8 °C |
| Submitted Storage Temperature | 2-8 °C | 2-8 °C | 2-8 °C |
| Predicate Sample Matrix | Serum/Urine | Serum/Plasma, Urine | Serum/Plasma, Urine |
| Submitted Sample Matrix | Serum/Plasma, Whole blood | Serum/Plasma, Whole blood | Serum/Plasma, Whole blood |
| Predicate Controls | Recommended | Recommended | Recommended |
| Submitted Test Controls | Recommended | Recommended | Recommended |
| Correlation with Predicate device | N = 41. Samples spanned from 1.8 - 12.6 mg/dL. The regression equation was y = 0.912x-0.187 and r =0.997 | N = 41. Samples spanned from 57 - 774 IU/L. The regression equation was y = 0.948x-1.056 and r =0.992 | N = 41. Samples spanned from 1.7 -11.9 mg/dL. The regression equation was y = 0.991x-0.239 and r =0.996 |
K. Standard/Guidance Document Referenced (if applicable):
None referenced.
L. Test Principle:
Phosphorus in the sample is combined with molybdate to form a phosphomolybdate complex. In the presence of ascorbic acid, a reducing agent, this complex forms a strongly colored "molybdenum blue". The rate at which the blue color is generated, as measured at $610~\mathrm{nm}$ by reflectance spectroscopy, is directly proportional to the concentration of inorganic phosphorous in the patient sample.
In the presence of CPK, creatine phosphate reacts with ADP to form creatine and ATP. ATP is utilized in a subsequent reaction involving glucose and hexokinase to generate glucose-6-phosphate. Glucose-6-phosphate reacts with NADP in the presence of G6PDH to form NADPH. NADPH reacts with the dye tetrazolium violet to form the strongly colored purple chromogen complex. The rate at which the purple chromogen complex is formed, measured at $550~\mathrm{nm}$ , is proportional the amount of CPK originally in the sample.
{4}
In the presence of uricase, uric acid reacts with oxygen and generates hydrogen peroxide. This generated hydrogen peroxide subsequently reacts with 4-aminoantpyrine and N-Ethyl-N-(2-hydroxy-3-sulfopropyl)-m-toluidine to form a red-purple reaction product. The absorbance of this product, measured at $550~\mathrm{nm}$ , is proportional the concentration of uric acid in the sample. Ascorbic acid, a reducing agent that would interfere with this assay by reacting with the hydrogen peroxide, is removed from the sample by a comparatively fast reaction with Ascorbate oxidase.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Intra-assay precision was assessed by assaying three levels of control samples twenty times in one run. The company used an acceptance criterion of $5\%$ CV. The results:
| | | Level 1 | Level 2 | Level 3 |
| --- | --- | --- | --- | --- |
| Number of Samples | | 20 | 20 | 20 |
| Inorganic Phosphorus | Mean (mg/dL) | 2.07 | 4.26 | 8.25 |
| | SD (mg/dL) | 0.080 | 0.106 | 0.150 |
| | %CV | 3.9% | 2.5% | 1.8% |
| CPK | Mean (IU/L) | 64.9 | 158.9 | 505.1 |
| | SD (IU/L) | 2.78 | 6.96 | 20.95 |
| | %CV | 4.3% | 4.4% | 4.2% |
| Uric Acid | Mean (mg/dL) | 3.34 | 6.04 | 9.46 |
| | SD (mg/dL) | 0.067 | 0.088 | 0.139 |
| | %CV | 2.0% | 1.5% | 1.5% |
The company determined the intra-assay precision of their devices using whole blood. They performed 10 replicate measurements of one pooled blood sample in one day. The company used an acceptance criterion of $5\%$ CV. The results:
| | | Whole Blood |
| --- | --- | --- |
| Inorganic Phosphorus | Mean (mg/dL) | 8.58 |
| | SD (mg/dL) | 0.204 |
| | %CV | 2.4% |
| CPK | Mean (IU/L) | 265.9 |
| | SD (IU/L) | 12.31 |
| | %CV | 4.6% |
| Uric Acid | Mean (mg/dL) | 7.89 |
| | SD (mg/dL) | 0.152 |
| | %CV | 1.9% |
{5}
Inter-assay precision was assessed by assaying three levels of samples in duplicate in ten runs over 5 days. The company's acceptance criteria was a $\mathrm{CV} < 10\%$ . The results:
| | | Level 1 | Level 2 | Level 3 |
| --- | --- | --- | --- | --- |
| Number of Samples | | 20 | 20 | 20 |
| Inorganic Phosphorus | Mean (mg/dL) | 1.99 | 4.22 | 7.99 |
| | SD (mg/dL) | 0.075 | 0.088 | 0.184 |
| | %CV | 3.8% | 2.1% | 2.3% |
| CPK | Mean (IU/L) | 76.4 | 183.5 | 393.2 |
| | SD (IU/L) | 3.44 | 6.22 | 12.96 |
| | %CV | 4.5% | 3.4% | 3.3% |
| Uric Acid | Mean (mg/dL) | 3.38 | 6.04 | 10.14 |
| | SD (mg/dL) | 0.079 | 0.088 | 0.223 |
| | %CV | 2.3% | 1.5% | 1.5% |
# b. Linearity/assay reportable range:
The linearity was assessed by assaying serial dilutions covering the concentration range of the assay. Serial dilutions sets were prepared using $7\%$ BSA. The linearity claim is based on a percent deviation of $< 5\%$ at the two highest analyte concentrations. The inorganic phosphorous assay was shown to be linear up to $18.7~\mathrm{mg / dL}$ . The CPK assay was found to be linear up to $993~\mathrm{IU / L}$ . The uric acid assay was found to be linear up to $12.8~\mathrm{mg / dL}$ .
# c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The calibration set points are fixed by the manufacturer and are unique with each reagent lot and stored on the magnetic card provided with each kit. The principle of the calibration is to fix a two-point calibration curve for a given lot into the memory of the instrument. The sample absorbencies are then read off this fixed curve by the instrument, the concentration is calculated, and the results are provided by the software. The magnetic card has values of the basic calibration curve (Cal-Low (a) and Cal-High (b)) and its own measured value (Cal-Low (A) and Cal-High (B)). During calibration, the SpotChem EZ reads these 4 values from magnetic card, and calculates the calibration to be A->a, B->b. The values of A and B are determined by the manufacture based on the average of 18 measurements each of the high and low calibrator. The value of the calibrator is assigned by the manufacturer by assessing the mean value of 3 lots measured 6 times a day for 5 days on 2 instruments for each level of calibrator.
Real time studies of the assay strips confirm a shelf life in excess of $25\%$ of the shelf life claimed on the package insert when stored at $2 - 8^{\circ}\mathrm{C}$ .
{6}
Control values are determined using previously cleared control material (k0942458). Values for the control material are obtained by sampling a minimum of five vials from a lot across 3 instruments and measured 10 times per instrument and vial. Each instrument is calibrated daily during the value assignment.
d. Detection limit:
Functional sensitivity was assessed by diluting a pool to 10 different concentrations below the lower limit of the normal analyte range. Each dilution was assayed in replicates of ten. The mean, standard deviation and percent coefficient of variation were calculated for the ten replicates of each dilution. The functional sensitivity of the test was defined at the value of the dilution where the CV is approximately 20% (taking into consideration that the actual mean was within +10% of the expected target). The company determined that the functional sensitivity of the inorganic phosphorous was 0.64 mg/dL with a CV of 10.9%. The functional sensitivity of the CPK assay was 48.7 IU/L with a CV of 1.9%. The uric acid assay had a functional sensitivity of 1.63 mg/dL with a CV of 5.1%.
e. Analytical specificity:
Studies were performed to assess common or known substances that could interfere with the method. A summary of the data for know interferents appears in the table below:
| | Inorganic Phosphorus | CPK | Uric Acid |
| --- | --- | --- | --- |
| Interference | | | |
| Hemoglobin | 50 mg/dL | 150 mg/dL | 200 mg/dL |
| Bilirubin | 8.76 mg/dL | 6.54 mg/dL | 2.18 mg/dL |
| Triglycerides | 354.5 mg/dL | 280.8 mg/dL | 396.8 mg/dL |
f. Assay cut-off:
Not applicable for a device of this type
2. Comparison studies:
a. Method comparison with predicate device:
Clinical correlation studies were performed comparing the SpotChem II Inorganic Phosphorus, CPK, and Uric acid results generated on the SpotChem EZ analyzer against the results from the PolyChem analyzer using serum and plasma samples. The correlations were as follows:
Inorganic Phosphorus: y = 0.912x-0.187, r = 0.9967, n = 41, range: 1.8 - 12.6 mg/dL
CPK: y = 0.948x-1.056, r = 0.9921, n = 41, range: 57-774 IU/L
Uric Acid: y = 0.964x-0.297, r = 0.983, n = 41, range 0.7-5.3 mg/dL
{7}
b. Matrix comparison:
Clinical correlation studies were performed comparing the inorganic phosphorus, CPK, and uric results generated with serum and whole blood samples when performed on the SpotChem EZ analyzer. The correlations were as follows:
Inorganic Phosphorus: y = 0.994x - 0.019, r=0.9814, n=21
CPK: y = 1.098x - 1.843, r=9991, n=20
Uric Acid: y= 1.004x - 0.099, r= 9969, n = 20
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable for a device of this type
b. Clinical specificity:
Not applicable for a device of this type
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable for a device of this type
4. Clinical cut-off:
Not applicable for a device of this type
5. Expected values/Reference range:
Inorganic Phosphorus⁽¹⁾: 2.5-4.5 mg/dL
Uric acid⁽¹⁾: 3.5 - 7.2 mg/dL (male)
2.6 - 6.0 mg/dL (female)
CPK⁽²⁾: 10-80 IU/L male
10-70 IU/L female
⁽¹⁾ Tietz, N.W., “Textbook of Clinical Chemistry 2ⁿᵈ ed.”, W.B. Saunders Co.,
Philadelphia (1994)
⁽²⁾ Szasz, G., Gruger, W., Bernt, E., Clin. Chem, 22(5): 650-656 (1976)
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}
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.