K223679 · Beckman Coulter, Inc. · PQO · Feb 3, 2023 · Clinical Chemistry
Device Facts
Record ID
K223679
Device Name
Access AMH
Applicant
Beckman Coulter, Inc.
Product Code
PQO · Clinical Chemistry
Decision Date
Feb 3, 2023
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1092
Device Class
Class 2
Indications for Use
The Access AMH assay is a paramagnetic particle chemiluminescent immunoassay for the quantitative determination of anti-Müllerian hormone (AMH) levels in human serum and lithium heparin plasma using the Access Immunoassay Systems as an aid in the assessment of ovarian reserve in women presenting to fertility clinics. This system is intended to distinguish between women presenting with AFC (antral follicle count) values > 15 (high ovarian reserve) and women with AFC values ≤ 15 (normal or diminished ovarian reserve). The Access AMH is intended to be used in conjunction with other clinical and laboratory findings such as antral follicle count, before starting fertility therapy. The Access AMH is not intended to be used for monitoring of women undergoing controlled ovarian stimulation in an Assisted Reproduction Technology program.
Device Story
Access AMH is a quantitative chemiluminescent immunoassay for measuring anti-Müllerian hormone (AMH) in human serum or lithium heparin plasma. The device uses a simultaneous one-step sandwich immunoenzymatic principle; samples are incubated with mouse monoclonal anti-AMH antibodies conjugated to alkaline phosphatase and paramagnetic particles coated with mouse monoclonal anti-AMH antibodies. After incubation, a magnetic field separates bound materials from unbound components. A chemiluminescent substrate is added; light emission, measured by a luminometer, is directly proportional to AMH concentration. The system determines analyte levels via a stored multi-point calibration curve. Used in clinical laboratories on Access Immunoassay Systems (specifically DxI 9000), the output provides clinicians with quantitative AMH values. These results, used alongside antral follicle count (AFC) and other clinical findings, assist in assessing ovarian reserve prior to fertility therapy. The device helps categorize patients by ovarian reserve status, aiding clinical decision-making regarding fertility treatment planning.
Clinical Evidence
Bench testing only. Performance established via analytical studies including precision (repeatability/reproducibility), linearity (0.08–24 ng/mL), and method comparison (N=126 samples) against the predicate. Clinical sensitivity, specificity, and reference ranges were established in the predicate submission (K170524).
Indicated for women presenting to fertility clinics to assess ovarian reserve by distinguishing between high (>15) and normal/diminished (≤15) antral follicle count (AFC) values. Not for monitoring women undergoing controlled ovarian stimulation in Assisted Reproduction Technology programs.
Regulatory Classification
Identification
An anti-mullerian hormone test system is an in vitro diagnostic device intended to measure anti-mullerian hormone in human serum and plasma. An anti-mullerian hormone test system is intended to be used for assessing ovarian reserve in women.
Special Controls
An anti-mullerian hormone test system must comply with the following special controls: 1) Premarket notification submissions must include the following information: i. An adequate traceability plan to minimize the risk of drift in anti-mullerian hormone test system results over time. ii. Detailed documentation of a prospective clinical study to demonstrate clinical performance or, if appropriate, results from an equivalent sample set. This detailed documentation must include the following information: a. Results must demonstrate adequate clinical performance relative to a well-accepted comparator. b. Clinical sample results must demonstrate consistency of device output throughout the device measuring range that is appropriate for the intended use population. c. Clinical study documentation must include the original study protocol (including predefined statistical analysis plan), study report documenting support for the proposed indications for use(s), and results of all statistical analyses. iii. Reference intervals generated by testing an adequate number of samples from apparently healthy normal individuals in the intended use population. 2) Your 809.10(b) compliant labeling must include a warning statement that the device is intended to be used for assessing the ovarian reserve in conjunction with other clinical and laboratory findings before starting any fertility therapy, and that the device should be used in conjunction with the Antral Follicle Count.
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) An adequate traceability plan to minimize the risk of drift in anti-mullerian hormone test system results over time.
(ii) Detailed documentation of a prospective clinical study to demonstrate clinical performance or, if appropriate, results from an equivalent sample set. This detailed documentation must include the following information:
(A) Results must demonstrate adequate clinical performance relative to a well-accepted comparator.
(B) Clinical sample results must demonstrate consistency of device output throughout the device measuring range that is appropriate for the intended use population.
(C) Clinical study documentation must include the original study protocol (including predefined statistical analysis plan), study report documenting support for the proposed indications for use(s), and results of all statistical analyses.
(iii) Reference intervals generated by testing an adequate number of samples from apparently healthy normal individuals in the intended use population.
(2) The labeling required under § 809.10(b) of this chapter must include a warning statement that the device is intended to be used for assessing the ovarian reserve in conjunction with other clinical and laboratory findings before starting any fertility therapy, and that the device should be used in conjunction with the antral follicle count.
Predicate Devices
Access AMH (k170524)
Submission Summary (Full Text)
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K223679
B Applicant
Beckman Coulter Inc
C Proprietary and Established Names
Access AMH
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| PQO | Class II | 21 CFR 862.1092 - Anti-Mullerian Hormone Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Modification to a previously cleared device
B Measurand:
Anti-Müllerian hormone (AMH)
C Type of Test:
Quantitative chemiluminescent immunoassay
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The Access AMH assay is a paramagnetic particle chemiluminescent immunoassay for the quantitative determination of anti-Müllerian hormone (AMH) levels in human serum and lithium heparin plasma using the Access Immunoassay Systems as an aid in the assessment of ovarian reserve in women presenting to fertility clinics. This system is intended to distinguish between women presenting with AFC (antral follicle count) values > 15 (high ovarian reserve) and women with AFC values ≤ 15 (normal or diminished ovarian reserve). The Access AMH is intended to be used in conjunction with other clinical and laboratory findings such as antral follicle count, before starting fertility therapy. The Access AMH is not intended to be used for monitoring of women undergoing controlled ovarian stimulation in an Assisted Reproduction Technology program.
C Special Conditions for Use Statement(s):
- Rx - For Prescription Use Only
- Samples for AMH levels should be drawn on days 2-4 of the menstrual cycle.
- The Access AMH assay is intended to be used for assessing the ovarian reserve in conjunction with other clinical and laboratory findings before starting any fertility therapy (including pre-treatment such GnRH agonist down-regulation therapy) and should be used in conjunction with AFC.
- The Access AMH assay is not intended to be used for monitoring of women undergoing controlled ovarian stimulation in an Assisted Reproduction Technology program.
D Special Instrument Requirements:
Performance data shown below was collected on the DxI 9000 Access Immunoassay analyzer.
IV Device/System Characteristics:
A Device Description:
The Access AMH assay reagent pack consists of the following components:
- R1a: Paramagnetic particles coated with mouse monoclonal anti-AMH in TRIS buffer with surfactant, protein (bovine), <0.1% sodium azide, 0.1% ProClin 300
- R1b: Mouse anti-AMH alkaline phosphatase conjugate in MES buffer, surfactant, protein (bovine, recombinant), <0.1% sodium azide, 0.1% ProClin 300
K223679 - Page 2 of 8
{2}
- R1c: TRIS buffer with surfactant, protein (murine, bovine), <0.1% sodium azide, 0.1% ProClin 300
## B Principle of Operation:
The Access AMH assay is a simultaneous one-step immunoenzymatic ("sandwich") assay. A sample is added to a reaction vessel, along with a mouse monoclonal anti-AMH antibody conjugated to alkaline phosphatase in MES buffer, TRIS buffered saline with proteins, and paramagnetic particles coated with a mouse monoclonal anti-AMH antibody in TRIS buffer.
After incubation in a reaction vessel, materials bound to the solid phase are held in a magnetic field while unbound materials are washed away. Then, the chemiluminescent substrate is added to the vessel and light generated by this reaction is measured with a luminometer. The light production is directly proportional to the concentration of AMH in the sample. The amount of analyte in the sample is determined from a stored, multi-point calibration curve.
## V Substantial Equivalence Information:
### A Predicate Device Name(s):
Access AMH
### B Predicate 510(k) Number(s):
K170524
### C Comparison with Predicate(s):
| Device & Predicate Device(s): | K223679 | K170524 |
| --- | --- | --- |
| Device Trade Name | Access AMH | Access AMH |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | A paramagnetic particle chemiluminescent immunoassay for the quantitative determination of anti-Müllerian hormone (AMH) levels in human serum and lithium heparin plasma using the Access Immunoassay Systems as an aid in the assessment of ovarian reserve in women presenting to fertility | Same |
K223679 - Page 3 of 8
{3}
VI Standards/Guidance Documents Referenced:
- CLSI EP17- A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline – Second Edition.
- CLSI EP05-A3, Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline-Third Edition.
- CLSI EP06-Ed2, Evaluation of the Linearity of Quantitative Measurement Procedures; Approved Guideline.
- CLSI EP09c-A3, Method Procedure Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Third Edition.
K223679 - Page 4 of 8
{4}
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Precision studies were performed based on CLSI EP05-A3 to estimate repeatability and within-laboratory precision. The study was run on three DxI 9000 Immunoassay analyzers and three reagent pack lots. Six serum samples and 3 value assigned quality control samples spanning the claimed measuring range were used in the determination of imprecision. Each sample was assayed in duplicate with two runs per day, over 22 days for a total of 44 runs and 88 replicates per sample on each instrument and reagent lot combination. Each instrument was evaluated with one reagent lot. The within-run, between-run, between-day, and total imprecision was calculated. Results from multiple lots were similar. Results from one representative lot are provided in the table below:
| AMH (ng/mL) | | | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | N | Mean | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Sample 1 | 88 | 0.29 | 0.010 | 3.6 | 0.006 | 2.0 | 0.006 | 2.0 | 0.013 | 4.6 |
| Sample 2 | 88 | 0.80 | 0.030 | 3.7 | 0.000 | 0.0 | 0.000 | 0.0 | 0.030 | 3.7 |
| QC Sample 1 | 88 | 1.0 | 0.03 | 3.0 | 0.02 | 2.1 | 0.03 | 3.0 | 0.05 | 4.8 |
| Sample 3 | 88 | 2.4 | 0.11 | 4.5 | 0.00 | 0.0 | 0.05 | 2.0 | 0.12 | 5.0 |
| QC Sample 2 | 88 | 5.1 | 0.18 | 3.4 | 0.03 | 0.7 | 0.09 | 1.7 | 0.20 | 3.9 |
| Sample 4 | 88 | 6.9 | 0.19 | 2.8 | 0.00 | 0.0 | 0.16 | 2.3 | 0.25 | 3.6 |
| Sample 5 | 88 | 13 | 0.4 | 3.1 | 0.3 | 1.9 | 0.3 | 2.6 | 0.6 | 4.5 |
| QC Sample 3 | 88 | 16 | 0.7 | 4.4 | 0.0 | 0.0 | 0.5 | 3.1 | 0.8 | 5.4 |
| Sample 6 | 88 | 19 | 0.5 | 2.6 | 0.3 | 1.8 | 0.3 | 1.4 | 0.6 | 3.4 |
A reproducibility study was conducted based on CLSI EP05-A3 to assess instrument-to-instrument variability. Seven serum samples with different AMH concentrations were run on three DxI 9000 Immunoassay analyzers. The samples were tested across three reagent lots and one calibrator lot on each instrument with five replicates per run and one run per day over five days. The within-run, between-day, between-instrument, and reproducibility was calculated for each reagent lot. Results from multiple lots were similar. Results from one representative lot are provided below:
K223679 - Page 5 of 8
{5}
| Concentration (ng/mL) | | | Repeatability (Within-run) | | Between-day | | Between - instrument | | Reproducibility | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | N | Mean | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Sample1 | 75 | 0.013 | 0.000 | 3.5 | 0.000 | 1.3 | 0.000 | 2.2 | 0.001 | 4.3 |
| Sample2 | 75 | 0.28 | 0.008 | 2.8 | 0.003 | 1.0 | 0.002 | 0.7 | 0.009 | 3.1 |
| Sample3 | 75 | 0.79 | 0.017 | 2.2 | 0.000 | 0.0 | 0.008 | 1.0 | 0.019 | 2.4 |
| Sample4 | 75 | 2.4 | 0.09 | 3.7 | 0.02 | 1.0 | 0.00 | 0.0 | 0.09 | 3.8 |
| Sample5 | 75 | 7.0 | 0.19 | 2.7 | 0.06 | 0.9 | 0.09 | 1.3 | 0.22 | 3.1 |
| Sample6 | 75 | 13 | 0.3 | 2.3 | 0.2 | 1.7 | 0.2 | 1.7 | 0.4 | 3.3 |
| Sample7 | 75 | 19 | 0.5 | 2.8 | 0.1 | 0.8 | 0.4 | 2.3 | 0.7 | 3.7 |
2. Linearity:
Linearity was evaluated based on CLSI EP06-Ed2. A native sample containing a concentration of AMH at the low end of the measuring interval was obtained. Two serum samples were mixed to create a sample at the high end of the measuring interval. In addition to the high and low AMH concentration samples, seven (7) mixtures were tested in this study. These samples were prepared independently by using incrementally larger proportions of the high sample diluted with the low sample, in order to achieve AMH concentrations that covered the range of the assay. The low sample was run in replicates of eight, and all other samples were run in replicates of four (4). This study was run on three DxI 9000 Immunoassay analyzers, using three reagent lots. The data was analyzed using a weighted linear regression model as described in the guideline. Results for a representative linear data fit are shown below:
$$
y = 0.9935x + 0.0001
$$
The results support the claimed measuring range of 0.08 to 24 ng/mL.
3. Analytical Specificity/Interference:
Potential cross-reactivity, interference, and high dose effect were evaluated in K170524. No cross reactivity, interference, or high dose effect was observed.
HAMA/Heterophile interference
HAMA/heterophile interference has not been evaluated for this device. The labeling contains the following limitation:
"For assays employing antibodies, the possibility exists for interference by heterophile antibodies in the patient sample. Patients who have been regularly exposed to animals or have received immunotherapy or diagnostic procedures utilizing immunoglobulins or immunoglobulin fragments may produce antibodies, e.g., HAMA, that interfere with immunoassays. Additionally, other heterophile antibodies such as human anti-goat antibodies may be present in patient samples. Such interfering antibodies may cause erroneous results. In rare cases, interference due to extremely high titers of antibodies to analyte-specific antibodies can occur. Carefully evaluate the applicability of this assay in patients suspected of having HAMA/heterophile antibodies."
K223679 - Page 6 of 8
{6}
4. Assay Reportable Range:
The assay reportable range is 0.08 to 24 ng/mL.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The Access AMH assay traceability remains unchanged since the clearance of K170524. The assay is traceable to internal reference standards (primary reference calibrators), which consist of recombinant AMH in a BSA matrix. A detailed traceability plan was reviewed and found acceptable in K170524.
6. Detection Limit:
The Limit of Blank, Limit of Detection, and Limit of Quantitation were determined in accordance with CLSI EP17-A2.
Limit of Blank (LoB): The sponsor defined the Limit of Blank (LoB) as the non-parametric 95th percentile value from 75 measurements of five different blank samples obtained on three DxI 9000 Immunoassay analyzers with three reagent pack lots. The sponsor claims a LoB of 0.001 ng/mL.
Limit of Detection (LoD): The maximum observed LoD is taken as the reported value for the measurement. The LoD estimate for the AMH assay is 0.002 ng/mL on the DxI 9000 Immunoassay analyzer.
Limit of Quantitation (LoQ): To calculate the LoQ, three DxI 9000 Immunoassay analyzers were used with three reagent pack lots and three calibrator lots. Eleven native serum samples containing low levels of AMH analyte were prepared. Each of the samples were run in replicates of nine, in one run per day, for five days on three reagent pack lots (45 replicates of each sample on each reagent lot). The sponsor defined the LoQ as the lowest concentration of analyte that can be quantified with a total precision of ≤ 20% CV. The results provided demonstrate the 20% CV LoQ estimate for the Access AMH assay is 0.003 ng/mL. The claimed LoQ is 0.08 ng/mL.
7. Assay Cut-Off:
To predict an antral follicle count of > 15, the corresponding AMH cutoff is 1.77 ng/mL.
B Comparison Studies:
1. Method Comparison with Predicate Device:
A method comparison study was performed comparing the candidate Access AMH assay on the DxI 9000 Access Immunoassay analyzer to the comparator device, the predicate Access AMH assay run on the Access 2 Immunoassay system using a protocol based on CLSI EP09c-A3. A total of one hundred twenty-six (126) native serum samples were run on three DxI 9000 instruments and three Access 2 instruments with three reagent pack lots and three calibrator lots. Results analyzed using Passing-Bablok linear regression are shown below:
K223679 - Page 7 of 8
{7}
| N | Slope | Intercept | Correlation Coefficient R |
| --- | --- | --- | --- |
| 126 | 1.02 (1.00- 1.03) | 0.011 | 1.00 |
2. Matrix Comparison:
A matrix comparison study was conducted in K170524 and demonstrates equivalent performance between serum and lithium heparin plasma.
C Clinical Studies:
1. Clinical Sensitivity:
Clinical sensitivity was established in K170524.
2. Clinical Specificity:
Clinical specificity was established in K170524.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not Applicable.
D Clinical Cut-Off:
The clinical cutoff validated in the clinical study is 1.77 ng/mL to distinguish women with an AFC >15 or ≤ 15. This cutoff is the same as for the predicate device.
E Expected Values/Reference Range:
The reference range information was established in K170524.
VIII Proposed Labeling:
The labeling is sufficient, and it satisfies the requirements of 21 CFR Parts 801 and 809, as applicable and the special controls for this device type under 21 CFR 862.1092.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K223679 - Page 8 of 8
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.
