K172322 · Siemens Healthcare Diagnostics, Inc. · JHI · Mar 29, 2018 · Clinical Chemistry
Device Facts
Record ID
K172322
Device Name
Atellica IM Total hCG (ThCG)
Applicant
Siemens Healthcare Diagnostics, Inc.
Product Code
JHI · Clinical Chemistry
Decision Date
Mar 29, 2018
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1155
Device Class
Class 2
Indications for Use
The Atellica IM Total hCG (ThCG) assay is for in vitro diagnostic use in the quantitative determination of human gonadotropin (hCG) in human serum using the Atellica IM Analyzer. The Atellica IM ThCG assay is intended as an aid in the early detection of pregnancy.
Device Story
The Atellica IM Total hCG (ThCG) assay is a quantitative chemiluminescent sandwich immunoassay performed on the Atellica IM Analyzer. It utilizes goat polyclonal anti-hCG antibodies labeled with acridinium ester and mouse monoclonal anti-hCG antibodies coupled to paramagnetic particles. The device measures hCG in human serum; the amount of hCG present is directly proportional to the relative light units (RLUs) detected by the analyzer. The assay is intended for use in clinical laboratory settings by trained personnel. Healthcare providers use the quantitative results to aid in the early detection of pregnancy. The device provides a standardized measurement of hCG, facilitating clinical assessment of pregnancy status.
Clinical Evidence
No clinical studies were performed. Evidence is based on analytical bench testing, including precision (n=320), linearity (n=11), dilution recovery, detection limits (LoB, LoD, LoQ), analytical specificity (cross-reactivity and interference), and a method comparison study (n=115) against the predicate device, yielding a correlation coefficient (R) of 0.999.
Technological Characteristics
Sandwich immunoassay; direct chemiluminescent detection. Reagents: goat polyclonal anti-hCG (acridinium ester) and mouse monoclonal anti-hCG (paramagnetic particles). Sample volume: 25 µL. Incubation: 8 minutes at 37°C. Standardized to WHO 4th IS 75/589. Automated platform (Atellica IM Analyzer).
Indications for Use
Indicated for the quantitative determination of hCG in human serum to aid in the early detection of pregnancy. No specific age or gender restrictions are provided, though reference ranges are established for non-pregnant women ages 17-54 and postmenopausal women aged ≥ 41.
Regulatory Classification
Identification
A human chorionic gonadotropin (HCG) test system is a device intended for the early detection of pregnancy is intended to measure HCG, a placental hormone, in plasma or urine. A human chorionic goadotropin (HCG) test system is a device intended for any uses other than early detection of pregnancy (such as an aid in the diagnosis, prognosis, and management of treatment of persons with certain tumors or carcinomas) is intended to measure HCG, a placental hormone, in plasma or urine.
Predicate Devices
ADVIA Centaur® Total hCG assay (k925277)
Submission Summary (Full Text)
{0}
1
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY TEMPLATE
A. 510(k) Number:
k172322
B. Purpose for Submission:
Adding previously cleared assay to the Atellica IM Test System
C. Measurand:
Total beta human chorionic gonadotropin (β-hCG) in human serum
D. Type of Test:
Quantitative, chemiluminescent immunoassay
E. Applicant:
Siemens Healthcare Diagnostics Inc.
F. Proprietary and Established Names:
Atellica IM Total hCG (ThCG)
G. Regulatory Information:
1. Regulation section:
21 CFR 862.1155 Human chorionic gonadotropin test system
2. Classification:
Class II
3. Product code:
JHI
4. Panel:
Clinical Chemistry (75)
{1}
H. Intended Use:
1. Intended use(s):
See indication for use below.
2. Indication(s) for use:
The Atellica IM Total hCG (ThCG) assay is for in vitro diagnostic use in the quantitative determination of human gonadotropin (hCG) in human serum using the Atellica IM Analyzer.
The Atellica IM ThCG assay is intended as an aid in the early detection of pregnancy.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
For use on the Atellica IM Analyzer
I. Device Description:
The Atellica IM Total β-hCG (ThCG) assay is a chemiluminescent immunoassay previously cleared for use on the Ciba-Corning ACS system in k925277. The Atellica IM System instrument was previously cleared as the Trinidad IM instrument under k151792; the new name of the system is the Atellica IM Analyzer.
The Atellica IM Total (ThCG) assay consists of the following reagents:
- Lite Reagent: 5.0 mL reagent pack contains goat polyclonal anti-hCG (~0.1 μg/mL) labeled with acridinium ester in buffered saline, sodium azide (0.1%), and preservatives.
- Solid Phase Reagent: 22.5 mL reagent pack monoclonal anti-hCG antibody (~0.02 mg/ml) covalently linked to paramagenetic particles, buffered saline, sodium azide (0.1%), and preservatives.
- Master Curve card: The master curve values are contained on a card that is provided with each kit.
J. Substantial Equivalence Information:
1. Predicate device name(s):
ADVIA Centaur Total (ThCG) assay
{2}
2. Predicate 510(k) number(s):
k925277
3. Comparison with predicate:
| Similarities and Differences | | |
| --- | --- | --- |
| Item | Candidate Device Atellica IM Total (ThCG) Assay | Predicate Device ADVIA Centaur Total (ThCG) Assay k925277 |
| Intended Use | For in vitro diagnostic use in the quantitative determination of human chorionic gonadotropin (hCG) in serum. This system is intended for use as an aid in the early detection of pregnancy. | Same |
| Detection Antibody | Goat polyclonal anti-hCG antibody labeled with acridinium ester | Same |
| Capture Antibody | Mouse monoclonal anti-hCG antibody coavailently coupled to paramagnetic particles | Same |
| Assay Principle | Chemiluminescence sandwich immunoassay | Same |
| Sample type | Serum | Same |
| Analytical measuring range | 2.6-1000 mIU/mL (IU/L) | 2.0-1000 mIU/mL (IU/L) |
| Analyzer | Atellica IM System | Ciba-Corning ACS System |
| Sample Volume | 25 μL | 50 μL |
| Reagent Volume | 50 μL of Lite Reagent and 225 μL of Solid Phase | 100 μL of Lite Reagent and 450 μL of Solid Phase |
| Incubation Time | 8 minutes at 37°C | 7.5 minutes at 37°C |
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP5-A3 Evaluation of Precision Performance of Quantitative Measurement Methods, Approved Guideline-Third Edition
CLSI EP6-A Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach, Approved Guideline
CLSI EP17-A2 Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures, Approved Guideline-Second Edition
{3}
CLSI EP7-A2 Interference Testing in Clinical Chemistry, Approved Guideline –Second Edition
CLSI EP9-A3 Method Comparison and Bias Estimation Using Patient Samples, Approved Guideline – Third Edition
CLSI EP28-A3c Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory, Approved Guideline – Third Edition
CLSI EP25-A Evaluation of Stability of In Vitro Diagnostic Reagents, Approved Guideline
## L. Test Principle:
The Atellica IM Total (ThCG) assay is a 2-site sandwich immunoassay using direct chemiluminescent technology that employs a goat polyclonal anti-hCG antibody labeled with acridinium ester and a purified mouse monoclonal anti-hCG secondary antibody, which is covalently bound to paramagnetic particles. These 2 antibodies are specific for different epitopes that are present on both the free $\beta$-subunit and the $\beta$-subunit of intact hCG.
A direct relationship exists between the amount of hCG present in the patient sample and the amount of relative light units (RLUs) detected by the system.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision studies were conducted using two lots of Atellica IM Total (ThCG) reagent and two Atellica IM analyzers. Testing was performed two times a day with 2 replicates for 20 non-consecutive days for a total of 80 replicates. This study was performed using 3 spiked human serum samples and 3 human serum based control samples.
Analysis of variance (ANOVA) was used to evaluate the data consistent with the recommendations of CLSI EP5-A2. In addition, an estimate of the repeatability, between-run, between-day, and within-laboratory precision using the restricted maximum likelihood method (REML) method was conducted. Precision results from all reagent lots and all systems (n=320) are shown below:
| Sample | Mean | Repeatability | | Between-run | | Between-day | | Within-lab | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Serum 1 | 2.4 | 0.21 | 8.8 | 0.08 | 3.3 | 0.11 | 4.7 | 0.25 | 10.5 |
| Serum 2 | 12.6 | 0.36 | 2.8 | 0.2 | 1.6 | 0.12 | 1.0 | 0.43 | 3.4 |
| Serum 3 | 782.0 | 14 | 1.8 | 6.89 | 0.9 | 6.73 | 0.9 | 17 | 2.2 |
| Control 1 | 6.8 | 0.31 | 4.5 | 0.02 | 0.3 | 0.2 | 3.0 | 0.37 | 5.5 |
| Control 2 | 23.4 | 0.6 | 2.6 | 0.39 | 1.7 | 0.37 | 1.6 | 0.81 | 3.5 |
| Control 3 | 202.1 | 3.62 | 1.8 | 2.35 | 1.2 | 3.44 | 1.7 | 5.52 | 2.7 |
{4}
b. Linearity/assay reportable range:
Linearity
Linearity was established by preparing eleven sample dilutions at concentrations from 5.6 -1138 mIU/mL by mixing different proportions of a normal human pregnant female hCG serum sample with a normal human serum sample without detectable hCG. The samples were tested with the Atellica IM Total (ThCG) assay on one analyzer in triplicate with two reagent lots. Results from the two reagent lots were similar. The expected values were plotted against the recovered hCG values. Linear regression gave the following equation:
$$
y = 1.037x + 1.619, R^2 = 0.9977
$$
The data support an analytical measuring range of 2.6-1000 mIU/mL.
Dilution Studies
A dilution recovery study was performed using 9 unique human serum samples (1200-14000 mIU/mL) to demonstrate the accuracy of dilution of samples above the reportable range of the candidate device. Dilutions for each sample were made with hCG negative serum pool (1/2, 1/4, 1/8, 1/16 dilutions) resulting in sample concentrations of approximately 185 - 900 mIU/mL.
This study was run on one instrument using one reagent pack lot. Each sample dilution was measured in triplicates. Percent recovery was calculated for each sample as shown below:
| Sample Number | Dilution | Observed Mean (mIU/mL) | Expected Mean (mIU/mL) | % Recovery |
| --- | --- | --- | --- | --- |
| 1 | Neat | - | 1200.0 | - |
| | 1:2 | 543.0 | 600.0 | 91 |
| 2 | Neat | - | 1800.0 | - |
| | 1:2 | 822.0 | 900.0 | 91 |
| | 1:4 | 456.4 | 450.0 | 101 |
| | 1:8 | 232.9 | 225.0 | 104 |
| | Mean | | | 99 |
| 3 | Neat | - | 1600.0 | - |
| | 1:2 | 724.4 | 800.0 | 91 |
| | 1:4 | 412.1 | 400.0 | 103 |
| | Mean | | | 97 |
| 4 | Neat | - | 3000.0 | - |
| | 1:4 | 737.0 | 750.0 | 98 |
| | 1:8 | 403.7 | 375.0 | 108 |
| | 1:16 | 403.7 | 375.0 | 108 |
| | Mean | | | 105 |
{5}
| Sample Number | Dilution | Observed Mean (mIU/mL) | Expected Mean (mIU/mL) | % Recovery |
| --- | --- | --- | --- | --- |
| 1 | Neat | - | 1200.0 | - |
| | 1:2 | 543.0 | 600.0 | 91 |
| 5 | Neat | - | 6000.0 | 0 |
| | 1:8 | 652.1 | 750.0 | 87 |
| | 1:16 | 351.9 | 375.0 | 94 |
| | Mean | | | 90 |
| 6 | Neat | - | 5000.0 | - |
| | 1:8 | 599.3 | 625.0 | 96 |
| 7 | Neat | - | 7000 | - |
| | 1:8 | 830.3 | 875.0 | 95 |
| | 1:16 | 464.3 | 437.5 | 106 |
| | Mean | | | 101 |
| 8 | Neat | - | 10000.0 | - |
| | 1:16 | 606.9 | 625.0 | 97 |
| 9 | Neat | - | 14000.0 | - |
| | 1:16 | 821.0 | 875.0 | 94 |
The recoveries ranged from 87% to 108% with mean recoveries of 91%, 101%, 98% and 100% for dilution factors 1/2, 1/4, 1/8, and 1/16. The Instructions for Use recommends diluting and retesting samples with hCG levels > 1000 mIU/mL to obtain accurate results.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The calibrators for the Atellica IM Total (ThCG) Assay are traceable to the World Health Organization (W.H.O.) 4th International Standard (IS) for hCG (75/589) and were cleared under k920372.
d. Detection limit:
The Limit of Blank (LoB), Limit of Detection (LoD) and Limit of Quantification (LoQ) were evaluated in accordance with CLSI EP17-A2 Guideline using the Atellica IM Total (ThCG) System.
**Limit of blank:**
The limit of blank was determined by testing five blank samples consisting of buffer based diluents and delipidized human serums. The samples were tested with 2 reagent lots on one instrument, once per day, 20 replicates per sample for 3 days yielding a total of 300 blank measurements per reagent lot. The limit of blank was determined non-parametricically. The highest value of the two reagent lots was the limit of blank. The limit of blank was determined to be 1.5 mIU/mL.
{6}
7
# Limit of detection
Low-level hCG samples (1.7 mIU/mL and 2.9 mIU/mL) were prepared from five human serum pools spiked with patient samples with hCG. These samples were tested with 2 reagent lots on one instrument, once per day, 20 replicates per sample for 3 days yielding a total of 300 measurements per reagent lot. The LoD, 1.7 mIU/mL, was determined parametrically using the highest LoD from the two reagent lots.
# Limit of quantitation:
Five low-level hCG samples were prepared from $\beta$-hCG negative human serum samples spiked with WHO $\beta$-hCG stock. These samples were tested with 2 reagent lots on one instrument in 5 replicates per run, 2 runs per day over 5 days (N=50 per sample per lot). The assay LoQ claimed by the sponsor from the worst lot is 2.6 mIU/mL based on a total error goal of bias and precision $\leq 30\%$.
## e. Analytical specificity:
### Cross-Reactivity:
To determine the cross-reactivity of related proteins in the Atellica IM Total (ThCG) assay, four human serum samples with hCG levels of approximately 2.2, 5, 50, and $500\mathrm{mIU / mL}$, were spiked with Thyroid Stimulating Hormone (TSH), Luteinizing Hormone (LH), Follicle Stimulating Hormone (FSH), Prolactin (PRL), and Human Growth Hormone (hGH) and assayed using two reagent lots on one Atellica IM analyzer. Results from these cross-reactant spiked samples were evaluated against that of the serum without potential cross-reactants. No cross-reactivity (defined by the sponsor as $< \pm 10\%$ bias between the test pool and control pool for samples) was observed at the concentrations that were tested for PRL, hGH, TSH, LH, and FSH as shown below.
| Substance | Concentration |
| --- | --- |
| TSH | 1 mIU/mL |
| LH | 500 mIU/mL |
| FSH | 500 mIU/mL |
| PRL | 1000 ng/mL |
| hGH | 500 mg/mL |
## Interference Study:
Two human serum pools spiked with hCG to final concentrations of $5\mathrm{mIU / mL}$ and $500\mathrm{mIU / mL}$ were spiked with various endogenous substances and therapeutic drugs. All samples were tested in triplicate with two reagent lots on one Atellica IM system. Results from these spiked serum samples were compared to results of serum without potential interferences. There was no significant interference (defined by the sponsor as $< \pm 10\%$ between the test pool and the control pool) up to the concentrations summarized below.
{7}
| Potential interfering substances | Highest interferent concentration tested at which no significant interference was observed |
| --- | --- |
| Atropine | 20 mg/dL |
| Bilirubin, conjugated | 40 mg/dL |
| Bilirubin, unconjugated | 40 mg/dL |
| Caffeine | 308 μg/L or 0.0308 mg/dL |
| EDTA | 3.4 μmol/L |
| Ethanol | 100 mg/dL |
| Gentisic acid | 117 μmol/L or 0.0117 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Triglycerides (Intralipid) | 3 g/L |
| Acetaminophen | 20 mg/dL |
| Acetylsalicyclic acid | 65 mg/dL |
| Heparin | 7200 U/dL |
| Albumin | 6 g/L |
| Ibuprofen | 50 mg/dL |
**Hook effect:**
Samples with hCG concentrations up to 1.0 million mIU/mL were prepared by spiking human hCG antigen to a pool of normal human serum, and were tested with the candidate Atellica IM Total (ThCG) assay. No hook effect was observed at hCG concentrations up to 1.0 million mIU/mL.
The sponsor includes the following statement in the labeling regarding hook effect:
“High ThCG concentrations can cause a paradoxical decrease in the RLUs (high-dose hook effect). In this assay, patient samples with hCG concentrations as high as 1,000,000 mIU/mL (IU/L) will report > 1000.0 mIU/mL (IU/L). Results were established using the Atellica IM Analyzer.”
**Human Anti-Mouse Antibodies:**
To determine the susceptibility of the Atellica IM Total (ThCG) assay to potential human anti-mouse antibody (HAMA) interference, three patient samples and two control samples containing HAMA up to 1500 ng/mL were spiked with low and high hCG (6.5 mIU/mL and 501 mIU/mL). No HAMA interference at a concentration up to 1500 ng/mL was observed.
The sponsor includes the following statement in the Limitations section of the labeling:
“Identified sources of interference that have the potential to bind to and interfere with
{8}
any component of the assay include: heterophile and human anti-mouse antibodies (such as anti-mouse (HAMA), anti-rabbit, anti-goat)."
f. Assay cut-off:
Not applicable; this is a quantitative assay.
2. Comparison studies:
a. Method comparison with predicate device:
A total of 107 unaltered and 8 altered serum samples were evaluated in singlet with the candidate Atellica IM Total (ThCG) System and the predicate ADVIA Centaur Total (ThCG) assay (k972525). The sample values ranged from 2.4 – 947.7 mIU/mL on the predicate device, and 2.3 – 897.8 mIU/mL on the candidate device. The results are summarized in the table below.
| Parameter | Deming Regression |
| --- | --- |
| n | 115 |
| Slope | 0.937 |
| Intercept | 0.234 |
| R | 0.999 |
| Sample Range | 2.4-947.7 mIU/mL |
b. Matrix comparison:
Not applicable.
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.
{9}
10
5. Expected values/Reference range:
Serum samples from 192 apparently healthy non-pregnant women ages 17-54 and 174 postmenopausal women aged $\geq 41$ were tested in singlicate with the Atellica IM Total (ThCG) assay. The 2.5 and 97.5 percentiles of the concentration values were considered the expected value range of the Atellica IM Total (ThCG) assay. Results are listed below:
| Reference Population age (years) | N subjects | Median (mIU/mL) | 95% CL of Normal Range (mIU/mL) | 95% CL of Lower Range (mIU/mL) | 95% CL of Upper Range (mIU/mL) |
| --- | --- | --- | --- | --- | --- |
| 17-54 | 192 | 2.0 | 1.5-4.2 | 1.4-1.6 | 3.5-4.8 |
| ≥ 41 | 174 | 3.9 | 1.8-10.1 | 1.5-1.9 | 8.1-13.8 |
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.