LIAISON TESTOSTERONE; LIAISON TESTOSTERONE CONTROL SET
K122793 · DiaSorin, Inc. · CDZ · Jan 25, 2013 · Clinical Chemistry
Device Facts
Record ID
K122793
Device Name
LIAISON TESTOSTERONE; LIAISON TESTOSTERONE CONTROL SET
Applicant
DiaSorin, Inc.
Product Code
CDZ · Clinical Chemistry
Decision Date
Jan 25, 2013
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1680
Device Class
Class 1
Indications for Use
The DiaSorin LIAISON® Testosterone is a direct, competitive, chemiluminescence immunoassay (CLIA) intended for the quantitative determination of testosterone in human serum and plasma on the LIAISON® Analyzer. The assay is intended for in vitro diagnostic use. Measurement of testosterone is used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in male subjects and, in female subjects hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes. The DiaSorin LIAISON® Testosterone Control Set is intended for use as assayed quality control samples to monitor the accuracy and precision of the DiaSorin LIAISON® Testosterone immunoassav.
Device Story
LIAISON® Testosterone is a direct, competitive chemiluminescence immunoassay (CLIA) for quantitative testosterone measurement in human serum/plasma. Device uses mouse monoclonal antibodies bound to magnetic particles; testosterone in sample competes with isoluminol-labeled testosterone for antibody binding sites. After incubation and wash, starter reagents initiate flash chemiluminescent reaction. Photomultiplier measures light signal (RLU), inversely proportional to testosterone concentration. Performed on LIAISON® Analyzer; fully automated. Used in clinical laboratories for diagnostic assessment of androgen disorders. Results assist clinicians in diagnosing hypogonadism, puberty disorders, impotence, hirsutism, and virilization. Control set monitors assay accuracy/precision.
Clinical Evidence
No clinical trials performed. Evidence consists of analytical bench testing: precision (N=480 per sample, total CV 7.1-14.0%), linearity (16-1500 ng/dL), LoB (3.1 ng/dL), LoD (9.8 ng/dL), and LoQ (16 ng/dL). Interference and cross-reactivity studies conducted per CLSI EP7-A2. Method comparison against predicate (N=162) yielded Passing-Bablok regression Y = 0.9458x - 1.49, R² = 0.9809. Reference ranges established using 622 healthy adults.
Technological Characteristics
Competitive chemiluminescence immunoassay (CLIA). Mouse monoclonal antibodies on magnetic particles. Photomultiplier detection. Sample matrix: serum and EDTA plasma. Measuring range: 16.0 - 1500 ng/dL. Automated processing on LIAISON® Analyzer. Reagent storage: 2-8°C.
Indications for Use
Indicated for quantitative determination of testosterone in human serum and plasma to aid in diagnosis and treatment of androgen-related disorders, including primary/secondary hypogonadism, delayed/precocious puberty, and impotence in males; and hirsutism and virilization in females due to tumors, polycystic ovaries, or adrenogenital syndromes.
Regulatory Classification
Identification
A testosterone test system is a device intended to measure testosterone (a male sex hormone) in serum, plasma, and urine. Measurement of testosterone are used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in males and, in females hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
Predicate Devices
Roche Cobas® Testosterone II Test (k093421)
Roche PreciControl Universal 1 and 2 (k090541)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k122793
B. Purpose for Submission:
New Device
C. Measurand:
Testosterone
D. Type of Test:
Quantitative Chemiluminescent Immunoassay
E. Applicant:
DiaSorin Inc.
F. Proprietary and Established Names:
LIAISON® Testosterone
LIAISON® Testosterone Control Set
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CDZ | Class I, reserved | 21 CFR 862.1680
Testosterone Test System | Clinical Chemistry (75) |
| JJX | Class I, reserved | 21 CFR 862.1660
Quality Control Material | Clinical Chemistry (75) |
H. Intended Use:
1. Intended use(s):
The DiaSorin LIAISON® Testosterone is a direct, competitive,
{1}
chemiluminescence immunoassay (CLIA) intended for the quantitative determination of testosterone in human serum and EDTA plasma on the LIAISON® Analyzer. The assay is intended for in vitro diagnostic use. Measurement of testosterone is used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in male subjects and, in female subjects hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes.
The DiaSorin LIAISON® Testosterone Control Set is intended for use as assayed quality control samples to monitor the accuracy and precision of the DiaSorin LIAISON® Testosterone immunoassay.
2. Indication(s) for use:
Same as intended use.
3. Special conditions for use statement(s):
For in vitro diagnostic use only
For prescription use only
4. Special instrument requirements:
For use on the DiaSorin LIAISON® Analyzer
I. Device Description:
1. Reagent Integral contains: Magnetic particles - coated with monoclonal antibody, stabilizers and preservatives; 2.4 mL
Conjugate - Testosterone conjugated to an isoluminol derivative, with PBS, BSA and preservatives; 12 mL
Assay Buffer - containing BSA, surfactant, and preservatives, 12 mL
2. Levels calibrators containing steroid free human serum, Testosterone at 2 different concentrations, stabilizers and preservatives; 2 vials each level, 2 mL. Calibrators are provided ready to use and provided with the reagent kit (not to be sold separately).
2. Control set contains: 2 levels controls containing steroid free human serum, spiked with testosterone, stabilizers and preservatives; 2 vials each level, 3.5 mL. Controls are provided ready to use.
Each serum/plasma donor unit used in the preparation of this product has been tested by an U.S. FDA approved method and found non-reactive for the presence of the
{2}
antibody to Human Immunodeficiency Virus 1 and 2 (HIV 1/2), the Hepatitis B surface antigen (HBV), and the antibody to Hepatitis C (HCV).
# J. Substantial Equivalence Information:
1. Predicate device name(s):
Roche Cobas® Testosterone II Test
Roche PreciControl Universal 1 and 2
2. Predicate $510(\mathrm{k})$ number(s):
k093421, k090541
3. Comparison with predicate:
| Reagent Similarities and Differences | | |
| --- | --- | --- |
| Item | New Device LIAISON® Testosterone | Predicate Device Roche Cobas® Testosterone II |
| Intended Use/Indications for Use | For the quantitative determination of testosterone in human serum and plasma. Measurement of testosterone is used in the diagnosis and treatment of disorders involving the male sex hormones (androgens), including primary and secondary hypogonadism, delayed or precocious puberty, impotence in male subjects and, in female subjects hirsutism (excessive hair) and virilization (masculinization) due to tumors, polycystic ovaries, and adrenogenital syndromes. | Same |
| Sample size | 100 uL | 20 uL |
| Capture Antibody | Mouse monoclonal antibodies to testosterone | Biotinylated sheep monoclonal antibodies to testosterone |
{3}
Control similarity and differences table:
| Item | The DiaSorin LIAISON® Testosterone Control Set | Roche PreciControl Universal |
| --- | --- | --- |
| Intended Use | It is intended for use as assayed quality control samples to monitor the accuracy and precision of the DiaSorin LIAISON® Testosterone immunoassay. | Intended for use as quality control of Elecsys® immunoassays on the Elecsys® and Cobas® immunoassay analyzers |
| Matrix | Human Serum | Human Serum |
| Levels | Two concentrations: High and Low | Two concentrations: High and Low |
| Reagent Format | Liquid, ready to use | Lyophilized |
| Storage conditions | 2-8°C | 2-8°C |
# K. Standard/Guidance Document Referenced (if applicable):
- CLSI Guideline EP5-A2, Vol.24, No.25; Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline - Second Edition 2004
- CLSI Guideline EP6-A, Vol.23, No.16; Evaluation of Linearity of Quantitative Analytical Methods; Approved Guideline 2003
- CLSI Guideline EP7-A2, Vol.25, No.27; Interference Testing in Clinical Chemistry; 2005 Approved Guideline - Second Edition
- CLSI Guideline EP9-A2-IR, Vol.30, No.17; Method Comparison and Bias Estimation Using Patient Samples; 2010 Approved Guideline Approved Guideline - Second Edition
- CLSI Guideline EP17-A, Vol.24, No.34; Protocols for Determination of Limits of Detection and Limits of Quantitation; 2004 Approved Guideline
- CLSI Guideline C28-A3, Vol.28, No.30; How to Define and Determine Ref.
{4}
Intervals in the Clinical Laboratory; 2008 Approved Guideline
## L. Test Principle:
The method for quantitative determination of the LIAISON® Testosterone assay is a direct, competitive, chemiluminescence immunoassay (CLIA). Specific antibody to testosterone is bound to magnetic particles (solid phase) and testosterone is linked to an isoluminol derivative. During the incubation, testosterone is dissociated from its binding protein and competes with labeled testosterone for binding sites on the antibody. After the incubation, the unbound material is removed with a wash cycle. Subsequently, the starter reagents are added and a flash chemiluminescent reaction is initiated. The light signal is measured by a photomultiplier as relative light units (RLU) and is inversely proportional to the concentration of testosterone present in calibrators, controls, or samples.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Following CLSI document EP5-A2, the sponsor evaluated the precision using 8 samples (2 serum controls and 6 patient serum samples) with concentrations spanning the working range of the assay. The samples were run at several test sites, using multiple LIAISON® Testosterone kit lots, and 2 runs per day for 20 days (N=480 measurements per sample). Results of within-run and total precision are summarized in the table below.
| Sample ID# | N | Mean ng/dL | Within Run | | Total/Across Lots/Across Sites | |
| --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV |
| QC Level 1 | 480 | 219 | 8.0 | 3.4% | 20.0 | 9.1% |
| QC Level 2 | 480 | 781 | 22.0 | 2.8% | 55.0 | 7.1% |
| Sample 1 | 480 | 37.0 | 3.0 | 7.3% | 5.0 | 14.0% |
| Sample 2 | 480 | 83.0 | 5.0 | 5.5% | 9.0 | 10.5% |
| Sample 3 | 480 | 237 | 11.0 | 4.5% | 20.0 | 8.6% |
| Sample 4 | 480 | 418 | 18.0 | 4.3% | 38.0 | 9.2% |
| Sample 5 | 480 | 1048 | 37.0 | 3.5% | 94.0 | 9.0% |
| Sample 6 | 480 | 1325 | 42.0 | 3.2% | 105 | 7.9% |
{5}
b. Linearity/assay reportable range:
The sponsor performed linearity studies in accordance with CLSI EP6-A guidelines using three high samples of each tube type (serum, SST serum, and EDTA plasma). High endogenous or spiked samples were diluted to span the working range of the assay. A total of 9 samples (1 high and 8 diluted) for each linearity sample set were tested in duplicate on the LIAISON® analyzer. Samples tested ranged from 15 to 1528 ng/dL. The observed values were plotted against the expected values and linear regression was performed. All three samples tested with each tube type yielded similar linear regressions. A representative of each tube types are summarized below.
Serum: y = 0.9944x - 16.12, R² = 0.9959,
SST Serum: y = 1.0189x - 14.59, R² = 0.9965
EDTA Plasma: y = 1.0057x - 13.19, R² = 0.9913.
The data support the claimed measuring range of this device, 16 to 1500 ng/dL.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability: The LIAISON® Testosterone Calibrators and Controls are traceable to testosterone USP reference material.
Stability: Shelf life stability studies were performed with assay reagents, calibrators, and controls and demonstrated that they are stable until the expiration date shown on the product labeling when stored as instructed. Calibrators and controls are stable until the expiration date printed on the label when stored as directed and for 28 days once opened when stored as instructed.
Calibration curve stability and reagent open vial stability were performed by the sponsor and demonstrated that the calibration curve is stable for 7 days and open reagent vials are stable for 28 days when stored at 2-8°C.
Value assignment: Kit calibrators and controls concentrations are assigned through an internal procedure. Master calibrators are prepared from a stock solution made from reference material whose concentration is determined spectrophotometrically by the sponsor. The master calibrators are then used to assign values to the kit calibrators and controls using multiple LIASON analyzers with several kit calibrator and control vials over several run and the mean results are used to determine the target values. The mean of the results + 2SD are used for establishing the control ranges.
{6}
Testosterone Calibrators have the following target values:
Level 1 = 30 - 50 ng/dL
Level 2 = 680 - 920 ng/dL
Testosterone Controls have the following target ranges:
Level 1 = 150 - 250 ng/dL
Level 2 = 560 - 840 ng/dL
d. Detection limit:
The Limit of Blank (LoB), Limit of Detection (LoD), and Limit of Quantitation (LoQ) were determined in accordance with CLSI document EP17-A. LoB was calculated using 5 blank samples tested on 2 LIAISON® analyzers over three days using 6 runs with two reagent lots. LoD was calculated using 4 low concentration samples, at and above the mean LoB, tested on 2 LIAISON® analyzers over 3 days using 6 runs and 2 reagent lots. LoQ was calculated using 8 samples tested on 2 LIAISON® analyzers over 3 days using 6 runs and 2 reagent lots.
The LoB was determined to be 3.1 ng/dL and the LoD was determined to be 9.8 ng/dL. The LoQ, which was defined as the lowest concentration for which the CV is less than 20%, was calculated to be 16 ng/dL.
The claimed measuring range of the device is 16 to 1500 ng/dL.
e. Analytical specificity:
Interference:
Following CLSI guidance document EP7-A2, interference studies were performed using two different concentrations of testosterone samples spiked with a single concentration of 5 different endogenous substances (see below chart) and compared to unspiked control samples. The two sets of matched spiked and control samples containing each interferent were tested in the LIAISON® Testosterone assay using multiple replicates (24 replicates for 80 ng/mL testosterone and 15 replicates for 200 ng/dL testosterone) with 1 reagent lot. HAMA (Human anti-mouse antibodies) interference was performed using 5 HAMA samples with testosterone concentrations ranging from 15 to 795 ng/dL. The sponsor defines non-significant interference as bias within 10% between the spiked and the control samples. Results of non-significant interference are summarized in the table below.
7
{7}
| Substance | Concentration Tested |
| --- | --- |
| Hemoglobin | 600 mg/dL |
| Bilirubin (unconjugated) | 20 mg/dL |
| Triglycerides | 1000 mg/dL |
| Cholesterol | 500 mg/dL |
| HAMA | 1753 ng/mL |
In addition, common pharmaceutical compounds were spiked into native human serum samples and tested with the LIAISON® Testosterone assay. Two serum samples pools containing approximately 80 ng/dL and 200 ng/dL testosterone were spiked with potential interferents. The reference sample (control) without interferent was spiked with the respective amount of solvent. Based on the sponsor's definition of non-significant interference (greater than ±10% of control value), the sponsor claims no interference for the compounds and concentrations listed in the table below:
| Compounds tested | Concentration |
| --- | --- |
| Acetylcystein | 150 mg/L |
| Ampicillin | 1000 mg/L |
| Ascorbic acid | 300 mg/L |
| Ca-Dobesilate | 200 mg/L |
| Cyclosporine | 5 mg/L |
| Cefoxitin | 2500 mg/L |
| Heparin | 5000 U |
| Levodopa | 20 mg/L |
| Methyldopa | 20 mg/L |
| Metronidazole | 200 mg/L |
| Phenylbutazone | 400 mg/L |
| Doxycyclin | 50 mg/L |
| Acetylsalicylic Acid | 1000 mg/L |
| Rifampicin | 60 mg/L |
| Acetaminophen | 200 mg/L |
| Ibuprofen | 50 mg/L |
| Theophilline | 100 mg/L |
| Heparin Clexane | 5000 U |
| Dexamethasone | 20 mg/L |
# Cross Reactivity:
A cross-reactivity study was performed using pooled human serum samples, representing 3 testosterone concentrations, each spiked with various testosterone metabolites or similar compounds. Spiked and non-spiked
{8}
samples were tested in triplicate using 1 lot of LIAISON® Testosterone assay and 1 LIAISON® analyzer.
The highest observed cross reactivity is summarized below:
| Cross reactant | Concentration ng/mL | % Cross reactivity |
| --- | --- | --- |
| Androstenedione | 100 | ≤4.27 |
| Cortisol | 1000 | ≤0.03 |
| Cortisone | 2000 | ≤0.01 |
| Danazol | 1000 | ≤0.02 |
| Dexamethasone | 2000 | ≤0.01 |
| DHEA | 1000 | ≤0.02 |
| DHEA-S | 50000 | ≤0.01 |
| D-5-Androstene-3B-17B-diol | 1000 | ≤0.06 |
| Estrone | 1000 | ≤0.03 |
| Ethisterone | 1000 | ≤0.43 |
| Nandrolone | 100 | ≤3.33 |
| Norgesterel | 1000 | ≤0.02 |
| Testosterone propionate | 50 | ≤7.48 |
| 5-a-Androstane-3B,17B-diol | 500 | ≤0.81 |
| 5-a-Dihydrotestosterone | 500 | ≤2.37 |
| 11-B-Hydroxytestosterone | 50 | ≤15.28 |
| 11-Keto-testosterone | 10 | <37.70 |
| Prednisone | 1000 | <0.03 |
| Prednisolone | 1000 | <0.04 |
| Progesterone | 1000 | <0.12 |
| 17-a-Estradiol | 1000 | <0.02 |
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
Following the CLSI EP9-A2 guidance document, the sponsor performed a method comparison study of the LIAISON® Testosterone assay versus the predicate device. A total of 162 serum samples (66 females and 89 males) and 8 testosterone spiked samples were compared across methods, following the manufacturers' instructions (samples ranged from 17 ng/dL to 1393 ng/dL).
{9}
Singlicate results were used for the linear regression analysis. Passing-Bablock linear regression analysis resulted the following: $Y = 0.9458x - 1.49$; $R^2 = 0.9809$ (95% CI for the slope is 0.92 to 0.96 and CI for the intercept is -2 to 2 ng/dL).
b. Matrix comparison:
The sponsor performed a matrix comparison using 51 matched patient sets of serum, SST serum, and EDTA plasma samples. Samples ranging from 16 to $1500\mathrm{ng / dL}$ were analyzed in singlicate using one lot of LIAISON® Testosterone reagents.
Passing-Bablok linear regression analysis reported the following results:
1. SST-Serum (Y) to Serum (X): $y = 1.02x + 1.6$, $R^2 = 1$
2. EDTA Plasma (Y) to Serum (X): $y = 1.04x + 1.6$, $R^2 = 1$
3. Clinical studies:
a. Clinical Sensitivity:
Not Applicable
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:
Human serum samples from 622 apparently healthy adults were tested to determine the reference range for the LIAISON® Testosterone assay. The observed central $95\%$ reference intervals for males and females are listed below.
10
{10}
| Population | N | Median (ng/dL) | Central 95% Interval (ng/dL) |
| --- | --- | --- | --- |
| Males 18-49 years | 161 | 439 | 120 - 1019 |
| Males ≥ 50 years | 132 | 453 | 195 - 895 |
| Females 18-49 years | 202 | 24.0 | <16.0 - 73.0 |
| Females ≥ 50 years | 127 | 22.0 | <16.0 - 51.0 |
# 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.
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.