N ANTISERA TO HUMAN IMMUNOGLOBULINS (IGG, IGA AND IGM)
K042735 · Dade Behring, Inc. · CFN · Feb 15, 2005 · Immunology
Device Facts
Record ID
K042735
Device Name
N ANTISERA TO HUMAN IMMUNOGLOBULINS (IGG, IGA AND IGM)
Applicant
Dade Behring, Inc.
Product Code
CFN · Immunology
Decision Date
Feb 15, 2005
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5510
Device Class
Class 2
Indications for Use
In vitro diagnostic reagents for the quantitative determination of immunoglobulins (IgG, lgA and IgM) in human serum, heparinized and EDTA plasma as well as IgG in human cerebrospinal fluid (CSF) using the BN™ Systems.
Device Story
In vitro diagnostic reagents for quantitative measurement of immunoglobulins (IgG, IgA, IgM) in human serum, plasma, and CSF. Operates via immunonephelometry on BN™ Systems; proteins in sample form immune complexes with specific antibodies; complexes scatter light; scattered light intensity proportional to protein concentration. Results compared against known standards. Used in clinical laboratory settings by trained personnel. Output provides quantitative protein levels to assist clinicians in diagnosing abnormal protein metabolism and immune resistance deficiencies.
Clinical Evidence
Bench testing only. Performance evaluated by comparing results across different sample matrices (heparinized plasma, EDTA plasma) against serum. Study included 49 heparinized and 20 EDTA samples. Results showed high correlation (r-values 0.920–1.003) and minimal bias, confirming substantial equivalence to the predicate.
Indicated for the quantitative determination of IgG, IgA, and IgM in human serum, heparinized plasma, and EDTA plasma, and IgG in human cerebrospinal fluid (CSF). Aids in the diagnosis of abnormal protein metabolism and immune deficiency states.
Regulatory Classification
Identification
An immunoglobulins A, G, M, D, and E immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the immunoglobulins A, G, M, D, an E (serum antibodies) in serum. Measurement of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
Predicate Devices
N Antisera to Human Immunoglobulins (IgG, IgA, and IgM) Assay (K860894)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
DEVICE ONLY TEMPLATE
A. 510(k) Number:
K042735
B. Purpose for Submission:
Modified device
C. Analyte:
IgG, IgA, IgM
D. Type of Test:
IgG, IgA, IgM: serum, heparinized (sodium heparin, ammonium heparin, and lithium heparin) and EDTA plasma
IgG: CSF
E. Applicant:
Dade Behring Inc.
F. Proprietary and Established Names:
N Antisera to Immunoglobulins (IgG, IgA, and IgM) Assay
G. Regulatory Information:
1. Regulation section:
21 CFR 866.5510 Immunoglobulins A,G,M,D,E immunological test system
2. Classification:
Class II
3. Product Code:
CFN, Method, Nephelometric, Immunoglobulins (G,A,M)
4. Panel:
Immunology
H. Intended Use:
1. Intended use(s):
In vitro diagnostic reagents for the quantitative determination of immunoglobulins (IgG, IgA and IgM) in human serum, heparinized and EDTA plasma as well as IgG in human cerebrospinal fluid (CSF) by means of immunonephelometry on the BN™ Systems.
2. Indication(s) for use:
In vitro diagnostic reagents for the quantitative determination of immunoglobulins (IgG, IgA and IgM) in human serum, heparinized and EDTA plasma as well as IgG in human cerebrospinal fluid (CSF) using the
{1}
$\mathrm{BN}^{\mathrm{TM}}$ Systems. Measurements of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
3. Special condition for use statement(s):
For prescription use only
4. Special instrument Requirements:
$\mathrm{BN}^{\mathrm{TM}}$ Systems including $\mathrm{BN}^{\mathrm{TM}}$ 100, $\mathrm{BN}^{\mathrm{TM}}$ II System, and $\mathrm{BN}^{\mathrm{TM}}$ ProSpec System.
| Feature | BN™ 100 | BN™ II System | BN™ ProSpec |
| --- | --- | --- | --- |
| 1. Intended Use | The BN™ 100 allows fully automatic determination of proteins in various body liquids. Precipitation as well as agglutination reactions (latex) can be performed quantitatively and quickly | The BN™ II is a system for the quantitative determination of proteins in serum, plasma, urine, and CSF. | The BN™ ProSpec is a system for the quantitative determination of proteins in serum, plasma, urine, and CSF |
| 2. Measuring Methods | Nephelometry | Nephelometry | Nephelometry |
| 3. Measuring Principles | End-point measurement; Fixed-time kinetic measurement | End-point measurement; Fixed-time kinetic measurement; VLinIntegral | End-point measurement; Fixed-time kinetic measurement; VLinIntegral |
| 4. Physical characteristics: | | | |
| a. Light Sources | LED | LED | LED |
| b. Wavelengths | 840 nm | 840 nm | 840 nm |
| c. Pipetting | Yes | Yes | Yes |
| d. Interfacing | Bi-directional | Bi-directional | Bi-directional, host query, ASTM |
| e. Data Input/Output | Computer & Printer | Computer & Printer | Computer & Printer |
| f. Barcode Identification | Yes | Yes | Yes |
| g. Dimensions | 47.3 x 94 x5 1 cm (h x w x d) | 71.5 x 124 x 63 cm (h x w x d) | 66 x 110 x 66 cm (h x w x d) |
| h. Dilutor Volume | 500 μL | Left 1000 μL (Variable) Middle 2500 μL (Variable) Right 250 μL (Variable) | 500 μL (Variable) |
| i. Transfer Arm | 1 | 2 | 1 |
| j. Transfer Arm | 1 | 2 | 1 |
| k. Transfer Arm | 1 | 2 | 1 |
| l. Transfer Arm | 1 | 2 | 1 |
{2}
# I. Device Description:
The device consists of N antiserum to human IgG; N antiserum to human IgA, N antihuman IgM. One vial each containing $5\mathrm{mL}$ or $2\mathrm{mL}$ .
# J. Substantial Equivalence Information:
1. Predicate device name(s):
N Antisera to Human Immunoglobulins (IgG, IgA, and IgM) Assay
2. Predicate K number(s):
K860894
3. Comparison with predicate:
| Similarities | | | |
| --- | --- | --- | --- |
| Item | Device | Predicate | |
| Reagents | Modified N Antisera to Human Immunoglobulins | N Antisera to Human Immunoglobulins | |
| Instrument | N Antiserum to human IgG,A,M | Same | |
| | BN™ Systems | Same | |
| Instruments | N Antisera to Human Immunoglobulins | N Antisera to Human Immunoglobulins | |
| Instruments | N Antisera to Human IgA | N Antisera to Human IgA | |
| Instruments | N Antisera to Human IgA | N Antisera to Human IgA | |
{3}
Page 4 of 10
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Sample Type | IgG,A,M: serum, heparinized and EDTA plasma.
IgG: CSF | IgG,A,M: serum
IgG: CSF |
K. Standard/Guidance Document Referenced (if applicable):
Not referenced
L. Test Principle:
Proteins contained in human body fluids from immune complexes in an immunochemical reaction with specific antibodies. These complexes scatter a beam of light passes through the sample. The intensity of the scattered light is proportional to the concentration to the concentration of the relevant protein in the sample. The result is evaluated by comparison with a standard of known concentration.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
The intra-assay precision
The intra-assay precision was determined by using three concentration levels of specimen over five days, testing two independent runs per day (am/pm), assaying four replicates (e.g. 5 x 2 x 4 = 40 replicates).
IgG
5.0g/L 3.0% CV
8.4g/L 1.8% CV
12.1 g/L 2.6% CV
IgA
1.0 g/L 1.6% CV
1.7g/L 3.3% CV
2.5 g/L 2.5% CV
IgM
0.27 g/L 3.8% CV
0.69g/L 3.2% CV
0.90 g/L 2.6% CV
{4}
Page 5 of 10
## The inter-assay precision
The inter-assay precision was determined by using three levels of concentration specimen. The samples were assayed in two independent run with 4 replicates in 5 days (n=40)
IgG
5.0g/L 2.1% CV
8.4g/L 1.4% CV
12.1 g/L 1.5% CV
IgA
1.0 g/L 3.7% CV
1.7g/L 2.7% CV
2.5 g/L 2.1% CV
IgM
0.27 g/L 4.0% CV
0.69g/L 1.9% CV
0.90 g/L 1.7% CV
Total precision
IgG
5.0g/L 3.4% CV
8.4g/L 2.7% CV
12.1 g/L 2.1% CV
IgA
1.0 g/L 4.1% CV
1.7g/L 4.0% CV
2.5 g/L 3.1% CV
IgM
0.27 g/L 5.3% CV
0.69g/L 3.4% CV
0.90 g/L 2.8% CV
## b. Linearity/assay reportable range:
The assay ranges for serum or plasma specimens of the N Antisera to human Immunoglobulins G,A,M are approximately:
IgG 1.4 to 46 g/L (1:400 dilution)
IgA 0.25 to 8.0 g/L (1:20 dilution)
IgAs 0.06 to 2.0 g/L (1:5 dilution)
IgM 0.2 to 6.4 g/L (1:20 dilution)
IgMs 0.05 to 1.6 g/ (1:5 dilution)
{5}
Page 6 of 10
The assay ranges for CSF specimens of the N Antisera to human Immunoglobulins G is approximately: CSF IgG 3.6 to 115 mg/L.
**(Methods and acceptance criteria undisclosed)**
c. Traceability (controls, calibrators, or method):
The device does not contain controls and calibrators.
d. Detection limit:
Typical lower limit of the detection are:
Serum or plasma IgG 0.19 g/L,
CSF IgG 0.5 mg/L
Serum or plasma IgA 0.016 g/L
Serum or plasma IgM 0.043 g/L
The analytical sensitivity of the assay is established by the lower limit of the reference curve, and depend upon the concentrations of the proteins in N Protein Standard SL.
e. Analytical specificity:
The specificity of the N Antisera Human Immunoglobulins (IgG, IgA, and IgM) assay were tested against normal human serum and plasma pool, antigens to human, and preparations of human IgG, IgA, IgM and Bence-Jonse proteins, type Kappa and Lambda in different analytical methods. There are no known cross-reactivities of the antisera.
f. Assay cut-off:
IgG 7.0 to 16.0 g/L
IgA 0.7 to 4.0 g/L
IgM 0.4 to 2.3 g/L
2. Comparison studies:
a. Method comparison with predicate device:
One hundred (100) serum samples were assayed with N Antisera to humanimmunoglobulins on a BN System ii (y) and a radial immunodiffusion (RID) method (x). Correlation of the results yielded following data:
| Protein | Coefficient of correlation |
| --- | --- |
| IgG y(BN) = 1.09X (RID) - 0.12 g/L | 0.97 |
| IgA y(BN) = 0.99X (RID) + 0.06 g/L | 0.99 |
| IgM y(BN) = 1.08X (RID) - 0.06 g/L | 0.99 |
b. Matrix comparison:
Serum/Heparin Plasma Comparison-BN II
IgG (n=67)
{6}
Page 7 of 10
Heparin plasma sample = 0.973 serum sample + 0.068 g/L
95% Confidence Interval
Slope (0.953, 0.997)
Intercept (-0.068, 0.263)
Pearson correlation coefficient (r = 0.989; r² = 0.978)
NOTE: Recovery study showed deviation of heparinized plasma for IgG assay (lithium Heparin vs. Sodium Heparin -1.158%; lithium Heparin vs. Ammonium Heparin -0.153%; Ammonium Heparin vs. Sodium Heparin -1.007%)
IgA (n=65)
Heparin plasma sample = 0.988 serum sample - 0.008 g/L
95% Confidence Interval
Slope (0.973, 1.005)
Intercept (-0.026, 0.012)
Pearson correlation coefficient (r = 0.998; r² = 0.997)
NOTE: Recovery study showed deviation of heparinized plasma for IgA assay (lithium Heparin vs. Sodium Heparin -2.94%; lithium Heparin vs. Ammonium Heparin -4.08%; Ammonium Heparin vs. Sodium Heparin -1.19%)
IgM (n=64)
Heparin plasma sample = 0.981 serum sample + 0.006 g/L
95% Confidence Interval
Slope (0.953, 1.011)
Intercept (-0.018, 0.024)
Pearson correlation coefficient (r = 0.991; r² = 0.982)
NOTE: Recovery study showed deviation of heparinized plasma for IgM assay (lithium Heparin vs. Sodium Heparin 0.6%; lithium Heparin vs. Ammonium Heparin -0.151%; Ammonium Heparin vs. Sodium Heparin 0.752%)
Serum/EDTA Plasma Comparison-BN II
IgG (n=37)
EDTA plasma sample = 1.012 serum sample - 0.274 g/L
95% Confidence Interval
Slope (0.967, 1.051)
Intercept (-0.557, 0.003)
Pearson correlation coefficient (r = 0.988; r² = 0.976)
IgA (n=36)
EDTA plasma sample = 0.961 serum sample - 0.011 g/L
95% Confidence Interval
Slope (0.933, 0.998)
{7}
Page 8 of 10
Intercept (-0.041, 0.024)
Pearson correlation coefficient (r = 0.994; r² = 0.989)
IgM (n=36)
EDTA plasma sample = 0.939 serum sample + 0.004 g/L
95% Confidence Interval
Slope (0.892, 0.982)
Intercept (-0.014, 0.031)
Pearson correlation coefficient (r = 0.980; r² = 0.961)
3. Clinical studies:
a. Clinical sensitivity:
n/a
b. Clinical specificity:
n/a
c. Other clinical supportive data (when a and b are not applicable):
n/a
4. Clinical cut-off:
Refer to 1/f
5. Expected values/Reference range:
The reference intervals for serum or plasma were derived from a consensus document of a group of professional societies and diagnostic companies on guidelines for interim reference ranges for 14 proteins in serum based on the standardization against the IFCC/BCR/CAP Reference material (CRM 470).
IgG 7.0 to 16.0 g/L
IgA 0.7 to 4.0 g/L
IgM 0.4 to 2.3 g/L
(Reference: Dati F Schumann G., Thomas L., et al. Consensus of a Group of Professional Societies and Diagnostics Companies on guidelines for Interim Reference Ranges for 14 proteins in Serum Based on the Standardization against the IFCC/BCR/CAP Reference Material (CRM 470). International Federation of Clinical Chemistry. Community Bureau of Reference of the Commission of the European Communities. College of American Pathologists. Eur J Clin Chem Clin Biochem 1996; 34:517-520).
Reference interval for IgG in CSF sample is less than 34 mg/L.
(References: 1. Felgenhauer K. Laboratory Diagnosis of Neurological Disease. In: Thomas L ed. Clinical Laboratory Diagnostics. Frankfurt TH Books Verlagsgesellschaft, 1998:1308-26. 2. Reiber H, Peter JB, Cerebrospinal Fluid Analysis: Disease-related Data Patterns and Evaluation Programs. J Neurol Sci. 2001; 184:101-122).
{8}
Page 9 of 10
References range (2.5th-97.5th percentile) for childhood and aldolescence:
IgG
| Age (years) | Male (g/L) | Female (g/L) |
| --- | --- | --- |
| 1 | 3.5-8.6 | 4.0-9.8 |
| 4 | 5.1-12.6 | 5.3-13.0 |
| 7 | 6.0-14.7 | 5.9-14.6 |
| 10 | 6.6-6.2 | 6.4-15.9 |
| 14 | 6.6-16.2 | 6.8-16.7 |
| 18 | 6.5-16.0 | 6.9-17.0 |
IgA
| Age (years) | Male (g/L) | Female (g/L) |
| --- | --- | --- |
| 1 | 0.17-0.96 | 0.17-0.94 |
| 4 | 0.36-1.98 | 0.33-1.85 |
| 7 | 0.48-2.66 | 0.44-2.44 |
| 10 | 0.57-3.18 | 0.52-2.90 |
| 14 | 0.64-3.52 | 0.62-3.43 |
| 18 | 0.68-3.79 | 0.69-3.80 |
IgM
| Age (years) | Male (g/L) | Female (g/L) |
| --- | --- | --- |
| 1 | 0.30-1.83 | 0.34-2.06 |
| 4 | 0.35-2.13 | 0.42-2.55 |
| 7 | 0.37-2.26 | 0.45-2.78 |
| 10 | 0.38-2.35 | 0.48-2.94 |
| 14 | 0.40-2.44 | 0.50-3.09 |
| 18 | 0.41-2.51 | 0.52-3.22 |
(Reference: Richie RF, Palomaki GE, Neveux LM et al. Reference Distributions for Immunoglobulins A, G, and M: a practical, simple, and clinical relevant approach in a large cohort. J Clin Lab Anal. 1998; 12:263-270).
N. Conclusion:
The submitted material in this premarket notification is complete and supports a substantial equivalence decision.
{9}
Page 10 of 10
O. Other Supportive Information:
n/a
P. Administrative Information:
1. Applicant contact information:
a. Name of applicant:
Dade Behring Inc.
b. Mailing address:
Glasgow Business Community
P.O. Box 6101, M.S. 514
Newark, DE 19714-6101
c. Phone #:
781-826-4551
d. Fax #:
781-826-2497
e. E-mail address (optional):
kathleen-dray-lyons@dadebehring.com
f. Contact:
2. Review documentation:
Q. Reviewer Name and Signature:
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.