DEN060007 · Maine Molecular Quality Controls, Inc. · NZB · Oct 12, 2006 · Microbiology
Device Facts
Record ID
DEN060007
Device Name
INTROL CF PANEL I CONTROL
Applicant
Maine Molecular Quality Controls, Inc.
Product Code
NZB · Microbiology
Decision Date
Oct 12, 2006
Decision
DENG
Submission Type
Post-NSE
Regulation
21 CFR 866.5910
Device Class
Class 2
Indications for Use
INTROL™ CF Panel I Control is intended for in vitro diagnostic use as a quality control to monitor analytical performance of the extraction, amplification and detection steps of diagnostic assays used in the detection of the Cystic Fibrosis Transmembrane Conductance Regulator (CFTR) gene mutations and variants. This product is intended to be extracted and analyzed routinely with each CFTR assay run.
Device Story
INTROL™ CF Panel I Control consists of synthetic CFTR DNA suspended in a matrix of synthetic DNA targets, carrier DNA, preservatives, dye, and stabilizers. The device mimics a human whole blood specimen; it is processed through standard clinical laboratory extraction methods. Following extraction, the released synthetic DNA is used in molecular amplification-based assays to monitor the performance of the extraction, amplification, and detection steps. The control contains 38 specific CFTR mutations, polymorphisms, and variants. It is used by laboratory technicians in clinical settings to ensure assay reliability. Healthcare providers use the resulting quality control data to validate that the diagnostic assay is functioning correctly for each run, thereby ensuring the accuracy of patient test results.
Clinical Evidence
Bench testing only. Performance evaluated at 10 external sites (8 clinical laboratories) using 11 manufacturing lots across 66 runs. Testing demonstrated 100% correct calls (1133/1133) across multiple amplification methods. Stability studies (real-time, stress, freeze/thaw, open vial) confirmed product integrity and signal consistency over 12 months and under various environmental conditions.
Technological Characteristics
Synthetic CFTR DNA in a matrix of synthetic DNA targets, non-human carrier DNA, preservatives, dye, and stabilizers. Contains 27 CFTR gene exons plus intronic borders. Form factor: 5 liquid bottles (versions G106ac or G106de). Storage: 2-8°C. No energy source. Not software-based.
Indications for Use
Indicated for use as a quality control material to monitor the analytical performance of extraction, amplification, and detection steps in diagnostic assays for 38 CFTR gene mutations and variants, including those recommended by ACMG and ACOG, in patients undergoing cystic fibrosis genetic testing.
Regulatory Classification
Identification
Quality control material for cystic fibrosis nucleic acid assays. A quality control material for cystic fibrosis nucleic acid assays is a device intended to help monitor reliability of a test system by detecting analytical deviations such as those that may arise from reagent or instrument variation in genetic testing. This type of device includes recombinant, synthetic, and cell line-based DNA controls.
Special Controls
*Classification.* Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 866.9. The special control is FDA's guidance document entitled “Class II Special Controls Guidance Document: Quality Control Material for Cystic Fibrosis Nucleic Acid Assays.” See § 866.1(e) for the availability of this guidance document.
The device is classified as Class II under regulation 21 CFR 866.5910 with special controls. The special control guidance document "Class II Special Controls Guidance Document: Quality Control Material for Cystic Fibrosis Nucleic Acid Assays" is available at http://www.fda.gov/cdrh/oivd/guidance/1614.html.
Reference Devices
Tag-It™ Cystic Fibrosis (CF) Kit
Submission Summary (Full Text)
{0}------------------------------------------------
### 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
- A. 510(k) Number: k060070
- B. Purpose for Submission: New device
- C. Measurand:
Controls for assays detecting Cystic Fibrosis Transmembrane Conductance Regulator (CFTR) gene mutations and variants
- D. Type of Test: Assayed quality control material
- E. Applicant: Maine Molecular Quality Controls, Inc. (MMQCI)
- F. Proprietary and Established Names: INTROL™ CF Panel I Control
- G. Regulatory Information:
- 1. Regulation section: 866.5910 DNA quality control material for genetic testing
- 2. Classification: De novo, Class II
- 3. Product code: NZB, Quality control material, genetics, DNA
- 4. Panel: Immunology (82)
# H. Intended Use:
- 1. Intended use(s):
INTROL™ CF Panel I Control is intended for in vitro diagnostic use as a quality control to monitor analytical performance of the extraction, amplification and detection steps of diagnostic assays used in the detection of the Cystic Fibrosis Transmembrane Conductance Regulator (CFTR) gene mutations and variants. This product is intended to be extracted and analyzed routinely with each CFTR assay run.
- 2. Indication(s) for use:
INTROL™ CF Panel I Control is intended for in vitro diagnostic use as a quality control to monitor analytical performance of the extraction, amplification and detection steps of diagnostic assays used in the detection of the Cystic Fibrosis Transmembrane Conductance Regulator (CFTR) gene mutations and variants. This product is intended to be extracted and analyzed routinely with each CFTR assay run.
The INTROL™ CF Panel I Control is designed to monitor the detection of 38 CFTR mutations associated with cystic fibrosis, including the 23 mutations recommended for testing by American College of Medical Genetics (ACMG) and American College of Obstetricians and Gynecologists (ACOG). The INTROLTM CF Panel I Control also monitors 3 polymorphisms (1506V, 1507V, F508C) and
{1}------------------------------------------------
the 5/7/9T variants.
- 3. Special conditions for use statement(s): For prescription use only.
The INTROL™ CF Panel I Control is designed to monitor the presence of 38 CFTR mutations associated with cystic fibrosis, including the 23 mutations recommended for testing by American College of Medical Genetics (ACMG) and American College of Obstetricians and Gynecologists (ACOG). The INTROLTM CF Panel I Control also monitors 3 polymorphisms (1506V, 1507V, F508C) and the 5/7/9T variants.
- 4. Special instrument requirements: Not applicable.
## I. Device Description:
INTROL™ CF Panel I Control consists of synthetic CFTR DNA suspended in a matrix of synthetic DNA targets, carrier DNA of a non-human species, preservatives, dye, and stabilizers. The synthetic DNA contains all 27 CFTR gene exons plus intronic borders, and contains specific mutations and polymorphisms which are divided among 5 bottles (bottles a, b, c, d, and e). The 5 bottles exist in two versions: Version G106ac includes bottles (a), (b), and (c), while Version G106de includes bottles (a), (b), (d), and (e). The specific mutations present in each bottle are listed below in Table 1; all other CFTR sequence is wild type. CFTR mutations that are not listed cannot be detected in the INTROL™ CF Panel I Control.
Control sequences include the mutations, wild type alleles, and polymorphisms recommended for testing by the American College of Medical Genetics (ACMG) and American College of Obstetricians and Gynecologists (ACOG). CFTR mutations that are not listed cannot be detected in the INTROL™ CF Panel I Control.
CFTR DNA is stabilized in the matrix and released when processed through common extraction methods as if it were a whole blood specimen. Following extraction, the released DNA can be used in common amplification based molecular assays techniques. Because INTROL™ CF Panel I Control is designed to mimic the whole blood sample, the resulting copy number of the artificial CFTR segment, after extraction, will be similar to that found in a processed human whole blood sample (v/v).
{2}------------------------------------------------
Table 1. Composition of INTROLTM CF Panel I Control includes following combinations of CFTR mutations and polymorphisms (plus wild type sequence covering 27 CFTR exons).
| Allele | Genotype | Allele | Genotype | |
|--------------|----------------------------|------------|--------------------------|-------------------|
| | Bottle a (both versions) | | Bottle b (both versions) | |
| 7T* | 7T / 7T | E60X | Homozygous mutant | |
| (I507V)* | I507V / WT | G85E* | Homozygous mutant | |
| (F508C)* | F508C / WT | I148T | Homozygous mutant | |
| S549N/ S549R | Heterozygous | 621+1G>T* | Homozygous mutant | |
| S1251N | Heterozygous | 711+1G>T* | Homozygous mutant | |
| | | 1078delT | Homozygous mutant | |
| | Bottle c (Version ac only) | R334W* | Homozygous mutant | |
| 394delTT | Heterozygous | R347P* | Homozygous mutant | |
| R117H* | Heterozygous | 9T* | 9T / 9T | |
| R347H | Heterozygous | A455E* | Homozygous mutant | |
| 5T* / 7T* | Heterozygous | del F508* | Homozygous mutant | |
| (I506V)* | I506V / WT | V520F | Homozygous mutant | |
| del 1507* | Heterozygous | 1717-1G>A* | Homozygous mutant | |
| R553X* | Heterozygous | G542X* | Homozygous mutant | |
| 2183AA>G | Heterozygous | G551D* | Homozygous mutant | |
| | | R560T* | Homozygous mutant | |
| | Bottle d (Version de only) | 1898+1G>A* | Homozygous mutant | |
| 394delTT | Homozygous mutant | 2143delT | Homozygous mutant | |
| R117H* | Homozygous mutant | 2184delA* | Homozygous mutant | |
| R347H | Homozygous mutant | 2789+5G>A* | Homozygous mutant | |
| 5T* | 5T / 5T | 3120+1G>A* | Homozygous mutant | |
| del 1507* | Homozygous mutant | 3199del6 | Homozygous mutant | |
| R553X* | Homozygous mutant | D1152H | Homozygous mutant | |
| 2183AA>G | Homozygous mutant | R1162X* | Homozygous mutant | |
| | | 3659delC* | Homozygous mutant | |
| | Bottle e (Version de only) | | 3849+10kbC>T* | Homozygous mutant |
| 7T* | 7T / 7T | 3876delA | Homozygous mutant | |
| (I506V)* | I506V / I506V | 3905insT | Homozygous mutant | |
| | | W1282X* | Homozygous mutant | |
| | | N1303K* | Homozygous mutant | |
*ACMG / ACOG Panel
# J. Substantial Equivalence Information:
- 1. Predicate device name(s): Not applicable.
- 2. Predicate 510(k) number(s): Not applicable.
- 3. Comparison with predicate: Not applicable
K. Standard/Guidance Document Referenced (if applicable): None referenced.
{3}------------------------------------------------
## L. Test Principle:
Not applicable.
### M. Performance Characteristics (if/when applicable):
- 1. Analytical performance:
All INTROL™ CF Panel I Control products are tested by an FDA-cleared CFTR mutation detection method before being released for market distribution. Any mutations not tested by the FDA-cleared method are sequenced bidirectionally before product is released. All mutations must be detected.
- a. Precision/Reproducibility:
The clinical study performed at the external sites evaluated reproducibility of INTROL™ CF Panel I quality control material with respect to within run, between run, between sites, between lots, and between methods. External site evaluations:
The clinical laboratory study performed at the external sites evaluated reproducibility of INTROL™ CF Panel I Control quality control material with respect to within run, between run, between sites, between lots, and between methods.
Evaluation using different extraction methods:
| # extraction<br>methods | #<br>laboratories | # successful laboratory<br>extractions | percent<br>successful |
|-------------------------|-------------------|----------------------------------------|-----------------------|
| 21 | 134 | 129 | 96% * |
* Five laboratories didn't continue after DNA extraction because DNA quantitation method they used indicated that no DNA was extracted/isolated. Considering that the level of synthetic CFTR DNA present in the extracted control may not be detectable with certain quantitation methods, there is a possibility that extractions in these 5 laboratories may have been successful; however this could not be assessed because the assays were not performed.
INTROL™ CF Panel I quality control material has been tested using CFTR assays at 10 external sites. 8 of which were clinical laboratories representing intended user. Samples from 11 different manufacturing lots were tested at minimally 3 external sites in at least 3 separate runs. Results are summarized in the Table 2.
| Method | Site | # of<br>Lots1 | # of<br>Runs | Total<br>Calls | Percent<br>Correct<br>Calls |
|--------------------------------|------|---------------|--------------|----------------|-----------------------------|
| Tag-ItTM | 1 | 10 | 9 | 223 | 100% |
| Tag-ItTM | 2 | 3 | 9 | 138 | 100% |
| Tag-ItTM | 3 | 1 | 1 | 6 | 100% |
| Tag-ItTM | 4 | 1 | 1 | 7 | 100% |
| Tag-ItTM | 5 | 1 | 1 | 4 | 100% |
| eSensor | 6 | 5 | 1 | 30 | 100% |
| eSensor | 7 | 5 | 1 | 38 | 100% |
| Other Amplification<br>methods | 8 | 3 | 1 | 31 | 100% |
| Other Amplification<br>methods | 9 | 1 | 2 | 7 | 100% |
| Other Amplification<br>methods | 10 | 5 | 40 | 649 | 100% |
| 6 methods | | 11 Lots | 66<br>Runs | 1133<br>Calls | 100% |
Table 2. External site evaluations.
Each bottle is processed independently and has its own lot number.
{4}------------------------------------------------
- b. Linearity/assay reportable range: Not applicable.
- Traceability, Stability, Expected values (controls, calibrators, or methods): C. Bidirectional sequencing of INTROL™ CF Panel I DNA is used to validate the presence of mutant or wild type sequence.
Product acceptance criteria and testing: All INTROL™ CF Panel I Control products are tested by an FDA-cleared CFTR mutation detection method before being released for market distribution. Any mutations not tested by the FDA-cleared method are sequenced bidirectionally before product is released. All mutations must be detected.
Upon receipt and after opening, the material should be stored at 2° - 8°C. INTROL™ CF Panel I Control material is shipped with a "Do not freeze" warning in the device labeling.
Unopened INTROLTM CF Panel I Control material is stable through the expiration date printed on each bottle when stored refrigerated (2° - 8°C). Opened material returned to the refrigerator (2° - 8°C) shortly after use is stable for thirty (30) days from the date of opening.
### Real time stability study:
Results of the real time studies are in the tables below. Stability was tested using 4 different methods, including cleared Tag-It™ Cystic Fibrosis (CF) Kit from Tm Bioscience, and bidirectional sequencing. Testing was performed at 1, 2, 3, 4, and 12 months. In addition, real time testing was performed with 5 different lots of quality control material. At 12 months, all mutations and variants were tested using either the FDA cleared assay or bidirectional sequencing. Data from this ongoing study currently supports a shelf-life of 12 months.
| Stability Testing | Number of<br>Lots | Percent<br>Correct Calls |
|---------------------|-------------------|--------------------------|
| Date of Manufacture | 5 | 100% |
| 1 month | 5 | 100% |
| 2 months | 3 | 100% |
| 3 months | 1 | 100% |
| 4 months | 2 | 100% |
| 12 months | 3 | 100% |
#### Stress testing:
Elevated Temperature Studies:
The study goal was to demonstrate product stability during prolonged shipping without refrigeration. A bottle of INTROLTM CF Panel I was removed from storage and mailed across the US and back without wet ice. Testing of the stressed product in the CFTR assay showed no loss of signal.
{5}------------------------------------------------
Two samples of INTROL™ CF Panel were compared after one was incubated at 60°C for 21-24 days, and the other incubated at 4°C, extracted and tested in duplicate in CFTR assay. There was no loss of signal after incubation at 60°C.
### Freeze/Thaw Studies:
A bottle of INTROL™ CF Panel I was placed at -20℃ for 48 hours, thawed and tested in CFTR assay. No loss of signal was detectable after one cycle of freeze/ thaw.
### Open Vial Stability:
Two open vial studies were performed. In the first study, a bottle of INTROLTM CF Panel I was mixed, opened briefly, then stored at 2-8℃ for 49 days. In the second study, a bottle of INTROL™ CF Panel I was mixed and opened with pipette simulation six times over 35 days. Both studies demonstrated no loss of signal when used in CFTR assay at the end of the test period.
#### Expected Results:
Expected results with the INTROLTM CF Panel I Control using two FDAcleared CFTR assays are presented in Table 3.
| Method | Correctly Identified Alleles | No Call or other | Not Tested |
|---------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Tag-It | All wt alleles<br>7T, I507V, F508C, S549R, G85E, I148T, 621+1G>T,<br>1078delT, R334W, R347P, 9T, A455E, delF508,<br>V520F, 1717+1G>A, G542X, G551D, R560T,<br>1898+1G>A, 2184delA, 3120+1G>A, R1162X,<br>3659delC, 3849+10kbC>T, 3876delA, 3905insT,<br>W1282X, N1303K, 394delTT, R117H, R347H, 5T/7T,<br>I506, dell507, R553X, 2183AA>G | S549N MUT1<br>711+1G>T No Call2<br>2789+5G>A No Call3 | S1251N, E60X, 2143delT<br>3199del6, D1152H, |
| eSensor | All wt alleles<br>7T, I148T, 621+1G>T, 1078delT, R334W, R347P, 9T,<br>A455E, delF508, 1717+1G>A, G542X, G551D, R560T,<br>1898+1G>A, 2184delA, 2789+5G>A, 3120+1G>A,<br>R1162X, 3659delC, 3849+10kbC>T, W1282X,<br>N1303K, R117H, 5T/7T, dell507, R553X, | G85E No Amp3<br>711+1G>T No Amp4 | I507V, F508C, S549N,<br>S549R, S1251N, E60X,<br>1078delT V520F,<br>2143delT, 3199del6,<br>D1152H, 3876delA,<br>3905insT, 394delTT,<br>R347H, I506V,<br>2183AA>G, |
Table 3. Results with the INTROL™ CF Panel I using two FDA cleared CFTR assays.
' Detected as homozyqous mutant.
Insufficient control sequence for one of the 711+1G>T amplicon primers.
3 Insufficient control sequence for one of the 2789+5G>A amplicon primers.
4 Mutation E60X interferes with a G85E amplicon primer.
- d. Detection limit: Not applicable
- e. Analytical specificity: Not applicable.
- f. Assay cut-off: Not applicable.
{6}------------------------------------------------
- 2. Comparison studies:
- Method comparison with predicate device: a. Not applicable.
- b. Matrix comparison: Not applicable.
- 3. Clinical studies:
- a. Clinical Sensitivity: Not applicable.
- Clinical specificity: b. 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: Not applicable
# N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
# O. Conclusion:
The petition for Evaluation of Automatic Class III Designation for this device is accepted. The device is classified as Class II under regulation 21 CFR 866.5910 with special controls. The special control guidance document "Class II Special Controls Guidance Document: Quality Control Material for Cystic Fibrosis Nucleic Acid Assays" is available at http://www.fda.gov/cdrh/oivd/guidance/1614.html.
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.