HemosIL Homocysteine is an automated latex enhanced immunoassay for the quantitative determination of total L-homocysteine in human citrated plasma on IL Coagulation Systems. Homocysteine values can assist in the diagnosis and treatment of patients suspected of having hyperhomocysteinemia or homocystinuria. HemosIL Homocysteine Controls are assayed quality controls intended to monitor the accuracy and precision of HemosIL Homocysteine on IL Coagulation Systems. For in vitro diagnostic use.
Device Story
HemosIL Homocysteine is an automated latex-enhanced immunoassay used on IL Coagulation Systems (e.g., ACL TOP, ACL Futura) to measure total L-homocysteine in citrated plasma. The process involves three stages: reduction of protein-bound/disulfide homocysteine to free homocysteine; enzymatic conversion to S-adenosyl-L-homocysteine (SAH) using SAH hydrolase and excess adenosine; and competitive agglutination between anti-SAH monoclonal antibody-coated latex particles and the generated SAH. The degree of agglutination is inversely proportional to homocysteine concentration, measured via light transmission decrease. The device is used in clinical laboratory settings by trained personnel. Results assist clinicians in diagnosing and managing hyperhomocysteinemia and homocystinuria. The system provides automated dilution for samples exceeding the linear range, improving workflow efficiency and diagnostic accuracy.
Clinical Evidence
Method comparison study of 76 paired sodium citrate and EDTA patient plasma samples (range 4.2–56.7 µmol/L) showed correlation (r=0.9915, slope 0.8292) against predicate. Precision assessed across multiple IL Coagulation Systems (ACL Advance, ACL TOP, ACL ELITE/ELITE PRO) using two control levels and plasma samples; total CV% ranged from 3.5% to 6.2%.
Technological Characteristics
Latex-enhanced immunoturbidimetric assay. Reagents include PBS buffer, TCEP reductant, SAH hydrolase enzyme, and polystyrene latex particles coated with anti-SAH monoclonal antibody. Operates on IL Coagulation Systems (ACL TOP, ACL Futura, ACL 9000). Quantitative measurement via light transmission. Calibrated using SAH in PBS. Standardized per CLSI guidelines (EP5-A, EP7-A, H21-A4).
Indications for Use
Indicated for the quantitative determination of total L-homocysteine in human citrated plasma to assist in the diagnosis and treatment of patients suspected of having hyperhomocysteinemia or homocystinuria.
Regulatory Classification
Identification
A urinary homocystine (nonquantitative) test system is a device intended to identify homocystine (an analogue of the amino acid cystine) in urine. The identification of urinary homocystine is used in the diagnosis and treatment of homocystinuria (homosystine in urine), a heritable metabolic disorder which may cause mental retardation.
Predicate Devices
Abbott IMx Homocysteine (k992858)
Submission Summary (Full Text)
{0}
1
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY TEMPLATE
A. 510(k) Number:
k061598
B. Purpose for Submission:
New device
C. Measurand:
Homocysteine
D. Type of Test:
Quantitative, turbidimetric assay
E. Applicant:
Instrumentation Laboratory Corporation
F. Proprietary and Established Names:
HemosIL Homocysteine
HemosIL Homocysteine controls (sold separately)
G. Regulatory Information:
1. Regulation section:
21 CFR 862.1377
21 CFR 862.1660
2. Classification:
Class II and Class I
{1}
3. Product code:
LPS (kit) and JJX (controls)
4. Panel:
75 (Chemistry)
H. Intended Use:
1. Intended use(s):
See Indication(s) for use below.
2. Indication(s) for use:
HemosIL Homocysteine is an automated latex enhanced immunoassay for the quantitative determination of total L-homocysteine in human citrated plasma on IL Coagulation Systems. Homocysteine values can assist in the diagnosis and treatment of patients suspected of having hyperhomocysteinemia or homocystinuria.
HemosIL Homocysteine Controls are assayed quality controls intended to monitor the accuracy and precision of HemosIL Homocysteine on IL Coagulation Systems.
For in vitro diagnostic use.
3. Special conditions for use statement(s):
Prescription use only
4. Special instrument requirements:
For use with IL Coagulation Systems (ACL TOP, ACL ELITE/ELITE PRO/8/9/10000, ACL Futura/ACL Advance).
I. Device Description:
HemosIL Homocysteine reagent kit includes the following reagents and calibrator material:
1. Buffer (Cat. No. 0020007810): 2 vials x 9 mL of PBS (phosphate buffer solution) with preservative.
2. Reductant (Cat. No. 0020007820): 2 vials x 2 mL of adenosine and Tris (2-carboxyethyl) phosphine (TCEP) solution in Bis-Tris buffer with
2
{2}
preservative.
3. Enzyme (Cat. No. 0020007830): 2 vials x 2 mL of recombinant S-adenosyl-L-homocysteine-hydrolase (SAHH) solution in phosphate buffer with stabilizer and preservative.
4. Conjugate (Cat. No. 0020007840): 2 vials x 2.5 mL of conjugate solution in PBS (phosphate buffer solution) with stabilizer and preservative.
5. a-SAH Latex Reagent (Cat. No. 0020007850): 2 vials x 2 mL of a lyophilized suspension of polystyrene latex particles coated with an anti S-adenosyl-L-homocysteine (SAH) monoclonal antibody in buffer containing bovine serum albumin and 0.02% Bronidox™ as a preservative.
6. Calibrator (Cat. No. 0020007860): 2 vials x 1 mL of S-adenosyl-L-homocysteine (SAH) in PBS (phosphate buffer solution) with preservative.
HemosIL Homocysteine Controls kit consists of:
1. Hcy Control level 1 (Cat. No. 00200007910): 3 vials x 1 mL of a lyophilized solution of diluted L-homocysteine and a preservative.
2. Hcy Control level 2 (Cat. No. 00200007920): 3 vials x 1 mL of a lyophilized solution of diluted L-homocysteine and a preservative.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Abbott IMx Homocysteine
2. Predicate 510(k) number(s):
k992858
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | Quantitative in vitro diagnostic determination of total L-homocysteine for diagnosis and treatment of hyperhomocysteinemia and homocystinuria. | Quantitative in vitro diagnostic determination of total L-homocysteine for diagnosis and treatment of hyperhomocysteinemia and homocystinuria. |
| Methodology | Particle Enhanced Immunoturbidimetry | Fluorescence Polarization Immunoassay |
| Calibrator Material | One level: S-adenosyl-L-homocysteine (SAH) in PBS (phosphate buffer solution) with preservative. | Two levels: 1) A: Phosphate buffer 2) B: Gravimetrically prepared S-adenosyl-L-homocysteine |
{3}
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | | (SAH) in phosphate buffer at defined concentrations. |
| Control Materials | Two levels: Lyophilized solution of diluted L-homocysteine and a preservative. | Three levels: L-homocysteine in processed human serum with sodium azide as preservative. |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Sample types | Citrated plasma only | Serum and EDTA or Lithium Heparin Plasma |
| Detection Limits | 2.4 μmol/L | 0.50 μmol/L |
| Functional sensitivity | 4.5 μmol/L | NA |
| Reportable range | 4.5 to 30 μmol/L without rerun 4.5 to 60 μmol/L with rerun, automatic dilutions. | 0.5 to 50 μmol/L |
| Normal range | For U.S. populations: 3.5-9.3 μmol/L For Spain populations: ACL Futura/ACL Advance is 4.1-10.6 μmol/L ACL ELITE/ELITE PRO/8/9/10000 is 4.0-11.2 μmol/L ACL TOP is 4.3-11.1 μmol/L | 4.5-12.4 μmol/L |
# K. Standard/Guidance Document Referenced (if applicable):
# STANDARDS
# Title and Reference Number
CSLI Guideline, EP5-A Evaluation of Precision Performance of Clinical Chemistry Devices.
CSLI Guideline, EP7-A Interference Testing in Clinical Chemistry; Approved Guideline.
CLSI/NCCLS. Collection, Transport, and Processing of Blood Specimens for Testing Plasma-Based Coagulation Assays, Fourth Edition, CLSI/NCCLS Document H21-A4; Vol. 23 No. 35.
{4}
5
L. Test Principle:
Homocysteine levels in patient plasma are measured automatically on IL Coagulation Systems in three stages:
1. Reduction of mixed disulfides and protein-bound forms of Hcy present in the plasma samples to free Hcy.
2. Enzymatic conversion of free Hcy to S-adenosyl-L-homocysteine (SAH) by the SAH hydrolase (SAHH) in the presence of an excess of adenosine.
3. Competitive agglutination reaction between anti-SAH and SAH/conjugate.
The degree of agglutination is inversely proportional to the concentration of total Hcy in the sample and is determined by measuring the decrease of transmitted light caused by the aggregates.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A precision study was performed using a plasma sample and controls. Samples were run in duplicate twice a day for 20 days on three different instruments following the CSLI EP5-A Guidelines. Mean, SD, and CVs were calculated and all samples had CV less than 10 % for within run, between day and total precision. The acceptance criteria are ≤ 10 % for within run, between day and total precision.
| ACL TOP | Mean (μmol/L) | CV% (Within run) | CV% (Total) |
| --- | --- | --- | --- |
| Hcy Control Level 1 | 11.4 | 2.0 | 4.8 |
| Hcy Control Level 2 | 22.4 | 1.5 | 3.5 |
| Hcy plasma sample | 8.1 | 2.9 | 5.5 |
| ACL 9000 | Mean (μmol/L) | CV% (Within run) | CV% (Total) |
| --- | --- | --- | --- |
| Hcy Control Level 1 | 12.3 | 2.3 | 5.1 |
| Hcy Control Level 2 | 22.8 | 4.3 | 6.2 |
| Hcy plasma sample | 8.4 | 2.6 | 5.9 |
{5}
| ACL Futura | Mean (μmol/L) | CV% (Within run) | CV% (Total) |
| --- | --- | --- | --- |
| Hcy Control Level 1 | 10.5 | 3.5 | 6.0 |
| Hcy Control Level 2 | 21.1 | 2.6 | 3.5 |
| Hcy plasma sample | 7.9 | 3.5 | 5.6 |
b. Linearity/assay reportable range:
i) Regular test (Without Rerun)
A linear study was performed using three different instruments, ACL Futura, ACL 9000, and ACL TOP. The Homocysteine calibrator was diluted and analyzed in replicates of five with two different lots of HCY kits. The test was considered linear if the $\mathrm{CV} < 20\%$ and the recovery within $\pm 20\%$ of the target value and the following acceptance criteria were met:
Slope of 0.9-1.1; $\mathrm{R}^2 \geq 0.96$ ; and Intercept of $0.0 \pm$ Detection Limit
This test has a linear range of $4.5 - 30\mu \mathrm{mol} / \mathrm{L}$ without rerun.
ii) Regular test (With Rerun)
A linear study was performed using three different instruments, ACL Futura, ACL 9000, and ACL TOP to verify that the Hcy level in citrated plasma samples can be accurately recovered when the samples are diluted. A plasma sample containing approximately $60~\mu \mathrm{mol} / \mathrm{L}$ of Hcy was diluted to different dilution with both the kit Buffer and with a human plasma sample with low Hcy concentration. Each dilution was analyzed in quadruplicate using two different lots of Hcy kits with and without rerun. Samples above $30~\mu \mathrm{mol} / \mathrm{L}$ were automatically diluted by the rerun capability of the instrument. The test was considered linear if the $\mathrm{CV} < 20\%$ and the recovery within $\pm 20\%$ of the target value and the following acceptance criteria were met:
Slope of 0.9-1.1; $\mathrm{R}^2 \geq 0.96$ ; and Intercept of $0.0 \pm$ Detection Limit
This test has a linear range of $4.5 - 60\mu \mathrm{mol} / \mathrm{L}$ with rerun.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The HemosIL Homocysteine calibrator is traceable to an Internal Reference Standard that was prepared gravimetrically with S-adenosyl-L-homocysteine (SAH) in phosphate buffer. A $5000\mu \mathrm{mol} / \mathrm{L}$ Homocysteine Reference Stock concentrate was prepared by gravimetrically adding S-adenosyl-L-homocysteine (SAH) to Calibrator Diluent. The Homocysteine assay is calibrated using the Calibrator included as a component of the kit.
The reconstituted controls stability testing was performed at several intervals and for temperature stored at $15 - 25^{\circ}\mathrm{C}$ , $2 - 8^{\circ}\mathrm{C}$ , and $-20^{\circ}\mathrm{C}$ . The data supported
{6}
the reconstituted controls stability of 7 days at 15-25°C, 2 months at 2-8 °C, and 1 month at -20°C.
d. Detection limit:
The detection limits were established by running twenty replicates of the Buffer with two different lots of Hcy kits on three different instruments, ACL Futura, ACL 9000 and ACL TOP. For each reagent lot on each instrument platform, the mean, SD, and mean + 3SD were calculated. The highest calculated value for all the instrument platforms was used to establish the detection limit claims of 2.4 μmol/L.
e. Analytical specificity:
An interference study was performed by spiking two citrated plasma samples containing approximately 8 and 15 μmol/L of Hcy with the kit buffer and the other with 20 times more concentrated interfering substance. Study was performed on ACL Futura, ACL 9000, and ACL TOP. No significant interference if the % recovery was within ± 15% of the expected control result.
There was no significant interference by the following interferents:
- Hemoglobin up to 490 mg/dL
- Bilirubin up to 19 mg/dL
- Triglycerides up to 1325 mg/dL
- Rheumatoid Factor up to 480 IU/mL
- Sodium Fluoride up to 4.0 g/L
A cross-reactivity study was performed using normal plasma samples spiked with the following concentrations and results were summarized in the following table:
| Compound | Assayed concentration | % cross reactivity |
| --- | --- | --- |
| L-Cysteine | 5 mmol/L | 0.0 % |
| Adenosine | 1 mmol/L | 0.2 % |
| L-Methionine | 0.4 mmol/L | -0.2 % |
| L-Cystathionine | 2 mmol/L | 0.1 % |
| S-Adenosyl-L-methionine | 0.5 mmol/L | 2.6 % |
| DL-Homocysteine-thiolactone | 0.1 mmol/L | 4.7 % |
| Glutathione | 100 mmol/L | 0.0% |
As limitations, the applicant stated the followings in the package insert:
{7}
1. Specimens from patients who are on drug therapy involving S-adenosymethionine may show falsely elevated levels of homocysteine. Patients who are taking methotrexate, carbamazepine, phenytoin, nitrous oxide, anticonvulsants, or 6-azuridine triacetate, may have elevated levels of homocysteine due to their effect on the pathway.
2. Specimens from patients who have received preparation of mouse monoclonal antibody for diagnosis or therapy may contain human antimouse antibody (HAMA). HAMA present in serum or plasma specimens may interfere in immunoassays that utilize mouse monoclonal antibodies. These specimens should not be assayed in the Hcy assay.
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study was conducted in Italy, using 76 paired sodium citrate and EDTA patient plasma samples analyzed in duplicate using HemosIL Homocysteine on an ACL 9000(sodium citrate plasma) verses IMx Homocysteine (EDTA plasma). Samples ranged in Homocysteine values from 4.3 to 56.7 µmol/L.
The slope and intercept were calculated by Passing & Bablock and the correlation coefficient by Pearson. Correlation regression yielded: y = 0.829x + 0.350, r = 0.9915. Y = ACL 9000(sodium citrate plasma), X = IMx (EDTA plasma). All criteria met the applicant's acceptable criteria of: Slope = 0.80-1.20, R² ≥ 0.950, Intercept = 0.0± Detection limit.
b. Matrix comparison between the Citrated and EDTA plasma on the ACL TOP:
A correlation study was conducted using 139 paired sodium citrate and EDTA patient plasma samples analyzed in duplicate on an ACL TOP using HemosIL Homocysteine. Samples ranged in Homocysteine values from 5.5 to 34.4 µmol/L.
The slope and intercept were calculated by Passing & Bablock and the correlation coefficient by Pearson. The performance of citrated versus EDTA plasma is substantially equivalent, although there was an average bias of 15.2% between the sample types. Correlation regression yielded: y = 0.799x + 0.406, r = 0.9939. Y = Citrate plasma, X = EDTA plasma.
c. Instruments equivalent studies between ACL 9000 verses ACL Futura and ACL TOP:
A method comparison study was performed to compare the performance of HemosIL Homocysteine on the representative instrument platforms. 117
{8}
citrated plasma samples were tested on an ACL 9000, ACL Futura, and ACL TOP. Samples tested ranged from 7.9 to 69.9 μmol/L. The statistical analysis by Passing & Bablok regression yielded the following results.
1. ACL 9000 vs ACL Futura, y=0.9458 x + 0.0149, r = 0.99. x = ACL 9000, y = ACL Futura
2. ACL 9000 vs ACL TOP, y=0.9780 x + 0.2943, r = 0.99. x = ACL 9000, y=ACL TOP
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:
One hundred forty (140) citrated plasma samples, 50 males and 90 females, were from apparently healthy blood bank donors in Barcelona, Spain were tested in duplicate using HemosIL Homocysteine on an ACL Futura, ACL 9000, and ACL TOP. One (4) sample was removed as a far outlier (criteria: 3 inter-quartile ranges above the mean) and was not used in the final calculations, bringing the final total to n=136. The distribution was normal (parametric) and therefore, parametric statistics were applied. The 95% reference interval limit with a confidence interval of 90% for each instrument platform is listed as below:
ACL Futura/ACL Advance: 4.1-10.6 μmol/L
ACL ELITE/ELITE PRO/8/9/10000: 4.0-11.2 μmol/L
ACL TOP: 4.3-11.1 μmol/L
ACL Advance is in the same family as the ACL Futura. ACL ELITE, ELITE PRO, ACL 8000 and ACL 10000 are in the same family as the ACL 9000.
9
{9}
One hundred twenty-six (126) citrated plasma samples from apparently healthy blood bank donors in U.S. were tested at Instrumentation Laboratory Co. using HemosIL Homocysteine on an ACL TOP. One (1) sample was removed as a far outlier (criteria: 3 inter-quartile ranges above the mean) and was not used in the final calculations, bringing the final total to $n = 125$ . The distribution was normal (parametric) as shown in the frequency distribution plots below.

The table below shows the $95\%$ reference interval limit with a confidence interval of $90\%$ :
| | 95% Limit | 90% CI |
| --- | --- | --- |
| Lower | 3.48 | 3.10 – 3.85 |
| Upper | 9.31 | 8.94 – 9.69 |
Therefore, the normal range for citrated plasma for the U.S. population is 3.5-9.3 $\mu \mathrm{mol} / \mathrm{L}$ .
# 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.
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.