Archived clinical NSCLC tissue specimens; Routine clinical manual FISH analysis records
Retrospective clinical archive data was used to perform a method comparison between the automated GenASIs ScanView System and manual FISH analysis to establish analytical performance.
Method Comparison of GenASIs ScanView vs. Manual Method; Retrospective method comparison study; Study Period: Archived slides from the 6 months prior to the study
Patients with non-small cell lung cancer (NSCLC); Sample Size: 179 slides; Number of Sites: 4
Manual FISH analysis
Percent agreement (overall, negative, and positive) between automated and manual methods
Indications for Use
The GenASIs ScanView System is an automated scanning microscope and image analysis system. It is intended for in vitro diagnostic use as an aiding tool to the pathologist or cytogeneticist in the detection, classification and enumeration of cells of interest based on color, intensity, size, pattern; and shape. The GenASIs ScanView System is indicated as an accessory to the following FDA cleared/approved devices to detect the following cell types: 1. CEP® X Spectrum Orange™/CEP® Y Spectrum Green™ DNA Probe Kit and is limited to the analysis of CEP XY probes via high magnification capture and analysis of interphase nuclei. CEP XY is indicated for use to assess the effectiveness of bone marrow transplantation in opposite-sex transplants. 2. Human breast cancer containing the HER-2/neu gene labeled in Red and the centromere of chromosome 17 labeled in Green via fluorescence in situ hybridization (FISH) in interphase nuclei from formalin-fixed, paraffin embedded human breast cancer tissue specimens with Vysis® PathVysion™ HER-2 DNA Probe kit. Results from the PathVysion™ Kit are intended for use as an adjunct to existing clinical and pathologic information used as prognostic factors in stage II, node-positive breast cancer patients. The PathVysion™ kit is further indicated as an aid to predict disease-free and overall survival in patients with stage II, node positive breast cancer, treated with adjuvant cyclophosphamide, doxorubicin, and 5-fluorouracil (CAF) chemotherapy. 3. Cells in urine specimens, stained by fluorescence in situ hybridization (FISH) using Vysis UroVysion™ Bladder Cancer Kit to detect aneuploidy for chromosomes 3, 7, 17, and loss of the 9p21 locus, from persons with hematuria suspected of having bladder cancer. The results are intended for use, in conjunction with and not in lieu of current standard diagnostic procedures, as an aid for initial diagnosis of bladder carcinoma in patients with hematuria and subsequent monitoring for tumor recurrence in patients previously diagnosed with bladder cancer. 4. Gene rearrangements involving the ALK gene (2p23) via fluorescence in situ hybridization (FISH) in formalin-fixed paraffin-embedded (FFPE) non-small cell lung cancer (NSCLC) tissue specimens, using Vysis® ALK (Anaplastic Lymphoma Kinase) Break Apart FISH Probe kit. The GenASIs ALK System is indicated to aid in identifying those patients eligible for treatment with XALKORI® (crizotinib). The GenASIs ScanView System is to be used as an adjunctive automated enumeration tool in conjunction with manual visualization.
Device Story
GenASIs ScanView is an automated digital imaging system comprising a microscope, motorized stage, camera, and workstation. It processes FFPE NSCLC tissue slides hybridized with Vysis ALK Break Apart FISH probes. The system captures images of cells; identifies regions of interest; and enumerates orange, green, and fused (yellow) signals. Pathologists review a gallery of captured cells to approve, modify, or reject automated calls. The system calculates the percentage of positive cells for gene rearrangement to aid in identifying patients eligible for XALKORI (crizotinib) therapy. It functions as an adjunctive tool to manual visualization in clinical laboratory settings.
Clinical Evidence
Bench testing only. Method comparison study across four clinical sites using 179 FFPE NSCLC slides (including 9 equivocal cases) compared GenASIs ScanView to manual counting. Results showed 100% overall agreement (95% CI: 98%-100%), 100% negative percent agreement, and 100% positive percent agreement. Reproducibility and repeatability studies (within-day, between-day, between-system) showed 100% concordance for positive/negative diagnoses.
Technological Characteristics
Integrated digital imaging system: microscope, motorized X-Y stage, CCD camera, workstation. Software: GenASIs ScanView Version 7.0. Connectivity: Barcode reader for specimen ID. Sterilization: N/A. Energy: Electrical. Form factor: Benchtop workstation.
Indications for Use
Indicated for use as an aid to pathologists/cytogeneticists for detection, classification, and enumeration of cells in FISH assays, specifically: CEP XY probes for bone marrow transplant assessment; HER-2/neu in breast cancer for prognosis/treatment prediction; UroVysion for bladder cancer diagnosis/monitoring; and ALK gene rearrangements in FFPE NSCLC tissue to identify patients eligible for XALKORI (crizotinib) therapy.
Regulatory Classification
Identification
An automated FISH enumeration system is a device that consists of an automated scanning microscope, image analysis system, and customized software applications for FISH assays. This device is intended for in vitro diagnostic use with FISH assays as an aid in the detection, counting and classification of cells based on recognition of cellular color, size, and shape, and in the detection and enumeration of FISH signals in interphase nuclei of formalin-fixed, paraffin-embedded human tissue specimens.
Special Controls
The device is classified as Class II under regulation 21 CFR 866.4700 with special controls. The special control guidance document " Class II Special Controls Guidance Document: Automated Fluorescence in situ Hybridization (FISH) Enumeration Systems" is available at www.fda.gov/cdrh/oivd/guidance/1550.pdf.
*Classification.* Class II (special controls). The special control is FDA's guidance document entitled “Class II Special Controls Guidance Document: Automated Fluorescence*in situ* Hybridization (FISH) Enumeration Systems.” See § 866.1(e) for the availability of this guidance document.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k122554
B. Purpose for Submission:
Addition of the GenASI ALK System Application to the GenASI ScanView System for fluorescence *in situ* hybridization (FISH) of gene rearrangements involving the Anaplastic Lymphoma Kinase (ALK) gene (2p23)
C. Manufacturer and Instrument Name:
Applied Spectral Imaging Ltd.
GenASIs ScanView System
GenASI ALK System
D. Type of Test or Tests Performed:
Automated fluorescence *in situ* hybridization (FISH) detection and enumeration of rearrangements involving the ALK gene (2p23) in formalin-fixed paraffin embedded (FFPE) human non-small cell lung cancer (NSCLC) tissue specimens treated with the Vysis® ALK Break Apart FISH Probe Kit
E. System Descriptions:
1. Device Description:
The GenASIs ScanView is an integrated digital imaging system constructed of a microscope, motorized multi-slide stage, camera, and a workstation. It is designed to acquire images of cells and enables identification and examination of cells of interest. Pathologists can view and scan cells and record the image, using both bright field and fluorescent illumination. The acquired images can be enhanced, archived, retrieved and printed. The automated microscope enables Z motion of the slide and the motorized stage enables its X-Y motions. The microscope also includes motorized filter turret containing fluorescence filters. The Gen ASIs ALK System software application evaluates FISH in human NSCLC tissue specimens hybridized with the Vysis® ALK Break Apart FISH Probe Kit.
{1}
2
2. Principles of Operation:
The Gen ASIs ScanView System works with the Gen ASIs ALK System software application to evaluate FISH stained human NSCLC tissue specimens by the Vysis® ALK Break Apart FISH Probe Kit. The probe kit contains a mixture of two probes that are on opposite sides flanking the breakpoint of the ALK gene. The 3'-ALK probe hybridizes telomerically at the breakpoint and is labeled with Spectrum Orange and the 5'-ALK probe hybridizes centromerically at the breakpoint and is labeled with Spectrum Green. After hybridization with the ALK Probe, the 2p23 ALK region in its native state will be seen as two immediately adjacent or fused orange/green (yellow) signals (2F). However, if a t(2;5) or other chromosome rearrangement at the 2p23 ALK breakpoint region has occurred, one orange and one green signal will be seen, while the native ALK region will remain as an orange/green fusion signal. The user defines the regions containing tumor cells and manually captures cells from these regions. The system automatically defines the cells of interest and the pathologist then either chooses specific cells for analysis or the system analyzes all of the cells from the selected regions. At least 100 cells should be counted. The GenASIs ALK System application reports the counts of the orange, green and fused (yellow) signals in each cell and classifies it according to predefined cell categories. After the scanning, each cell is presented in a gallery and the pathologist can approve, modify or reject the call for each cell. The overall statistics are updated accordingly. Only after the pathologist confirms the final score is the calculated percent positive cells for the gene rearrangement printed out in a final report.
3. Modes of Operation:
Semi-automated; manual capture of selected regions with computer-assisted interpretation
4. Specimen Identification:
Barcode Reader
5. Specimen Sampling and Handling:
Specimens are FFPENSCLC tissue specimens on glass slides hybridized with the Vysis® ALK Break Apart FISH Probe kit.
Scanning more than one slide requires a specialized stage that supports a tray holding up to nine slides for automatic scanning
{2}
6. Calibration:
Calibration is performed by GenASI personnel at installation. Routine calibration by the user is not required.
7. Quality Control:
The accuracy of the GenASIs ScanView System depends on the laboratory following the quality control instructions for the Vysis® ALK FISH Probe Kit.
8. Software:
FDA has reviewed applicant’s Hazard Analysis and Software Development processes for this line of product types:
Yes ☐ X or No ☐
F. Regulatory Information:
1. Regulation section:
21 CFR §866.4700 – Automated fluorescence *in situ* hybridization (FISH) enumeration systems
2. Classification:
Class II
3. Product code:
NTH – system, automated scanning microscope and image analysis for fluorescence *in situ* hybridization (FISH) assays
4. Panel:
Immunology (82)
G. Intended Use:
1. Indication(s) for Use:
The GenASIs ScanView System is an automated scanning microscope and image analysis system. It is intended for *in vitro* diagnostic use as an aiding tool to the pathologist or cytogeneticist in the detection, classification and enumeration of cells of interest based on color, intensity, size, pattern; and shape. The GenASIs
3
{3}
ScanView System is indicated as an accessory to the following FDA cleared/approved devices to detect the following cell types:
1. CEP® X Spectrum Orange™/CEP® Y Spectrum Green™ DNA Probe Kit and is limited to the analysis of CEP XY probes via high magnification capture and analysis of interphase nuclei. CEP XY is indicated for use to assess the effectiveness of bone marrow transplantation in opposite-sex transplants.
2. Human breast cancer containing the HER-2/neu gene labeled in Red and the centromere of chromosome 17 labeled in Green via fluorescence *in situ* hybridization (FISH) in interphase nuclei from formalin-fixed, paraffin embedded human breast cancer tissue specimens with Vysis® PathVysion™ HER-2 DNA Probe kit. Results from the PathVysion™ Kit are intended for use as an adjunct to existing clinical and pathologic information used as prognostic factors in stage II, node-positive breast cancer patients. The PathVysion™ kit is further indicated as an aid to predict disease-free and overall survival in patients with stage II, node positive breast cancer, treated with adjuvant cyclophosphamide, doxorubicin, and 5-fluorouracil (CAF) chemotherapy.
3. Cells in urine specimens, stained by fluorescence *in situ* hybridization (FISH) using Vysis UroVysion™ Bladder Cancer Kit to detect aneuploidy for chromosomes 3, 7, 17, and loss of the 9p21 locus, from persons with hematuria suspected of having bladder cancer. The results are intended for use, in conjunction with and not in lieu of current standard diagnostic procedures, as an aid for initial diagnosis of bladder carcinoma in patients with hematuria and subsequent monitoring for tumor recurrence in patients previously diagnosed with bladder cancer.
4. Gene rearrangements involving the ALK gene (2p23) via fluorescence *in situ* hybridization (FISH) in formalin-fixed paraffin-embedded (FFPE) non-small cell lung cancer (NSCLC) tissue specimens, using Vysis® ALK (Anaplastic Lymphoma Kinase) Break Apart FISH Probe kit. The GenASIs ALK System is indicated to aid in identifying those patients eligible for treatment with XALKORI® (crizotinib).
The GenASIs ScanView System is to be used as an adjunctive automated enumeration tool in conjunction with manual visualization.
2. Special Conditions for Use Statement(s):
For prescription use only.
4
{4}
5
# H. Substantial Equivalence Information:
1. Predicate Device Name(s) and 510(k) numbers:
Applied Spectral Imaging, ScanView System, k110345
2. Comparison with Predicate Device:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Methodology | Fluorescence in situ hybridization (FISH) | same |
| Device components | Microscope, PC, keyboard, control panel, color monitor, CCD camera, motorized stage | same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Probe Kit | Vysis ALK Break Apart FISH Probe Kit | Vysis UroVysion™ Bladder Cancer Kit |
| Specimen type | Lung Cancer Tissue | Urine |
| Software version | GenASIx ScanView Version 7.0 | ScanView Version 6.0 |
# I. Special Control/Guidance Document Referenced (if applicable):
Class II Special Controls Guidance Document: Automated Fluorescence in situ Hybridization (FISH) Enumeration Systems, 23 May 2005.
Guidance for Industry and FDA Staff: Statistical Guidance on Reporting Results from Studies Evaluating Diagnostic Tests”; March 2007.
Guidance for the Content of Premarket Submission for Software Contained in Medical Device, CDRH, May 2005.
# J. Performance Characteristics:
1. Analytical Performance:
a. Accuracy:
Slides containing formalin-fixed paraffin-embedded (FFPE) tissue specimens from patients with non-small cell lung cancer (NSCLC) were hybridized with
{5}
the FDA approved Vysis ALK Break Apart FISH Probe Kit according to the manufacturer's instructions.
At each clinical site, archived slides from NSCLC tissue specimens, previously counted and analyzed manually in the last 6 months, were used for the test. Negative cases were selected sequentially from a known bank of negative samples. All positive and equivocal slides that were available during the period of the comparison studies were used for the analysis in order to have an adequate number of slides in each of the categories.
Patients with NSCLC that were negative for the EGFR test were included in the study. At four clinical sites, a total of 179 slides including 9 cases in the equivocal zone (10-50%) were analyzed. The GenASIs ScanView operator had no prior knowledge of the manual counting results. Method comparison results for all four sites combined are presented below in Table 1:
Table 1: Method Comparison of GenASIs ScanView vs. Manual Method - All sites combined
| | Manual Method | | | |
| --- | --- | --- | --- | --- |
| | | Negative | Positive | Total |
| GenASIs ScanView Method | Negative | 147 | 0 | 147 |
| | Positive | 0 | 32 | 32 |
| | Total | 147 | 32 | 179 |
Overall agreement: $100\%$ (95% CI: 98%-100%)
Negative percent agreement: $100\%$ (95% CI: 97.5%-100%)
Positive percent agreement: $100\%$ (95% CI: 89.1%-100%)
# b. Precision/Reproducibility:
A panel of 10 slides chosen by the manual counting results, 4 of which were negative (<10%), 3 equivocal (10-50%) and 6 positive (>50%) were evaluated for repeatability and reproducibility of diagnosis (positive/negative) for the following:
- Within-day/within system: each one of the slides was evaluated three times on the same system on the same day.
- Between days: slides were assessed on three separate days on the same system (interval between assessments was at least five days).
- Between systems: three GenASIs ScanView ALK Systems were used at three different sites by three different operators.
Diagnoses over different days and systems were $100\%$ concordant for positive vs. negative results, as were within-day results. Both repeatability and reproducibility in the study were $100\%$ .
{6}
Mean percent positive cells, standard deviation and % coefficient of variation for each study are presented in Table 2 below. For the negative specimens %CV values are not applicable as a higher degree of variance is to be expected in negative or low positive specimens due to the fewer signals.
Table 2: Repeatability and reproducibility analysis by panel member
| Panel Member | % Positive Cells Counted Manually | Within-day/Within-System | | | Between-Day | | | Between-System | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | Mean % Positive Cells | SD | % CV | Mean % Positive Cells | SD | % CV | Mean % Positive Cells | SD | % CV |
| 1 | 61 | 56.9 | 4.6 | 8.0 | 56.4 | 3.7 | 6.7 | 56.2 | 3.1 | 5.5 |
| 2 | 52 | 46.9 | 5.9 | 12.6 | 47.5 | 4.3 | 9.1 | 46.1 | 4.4 | 9.5 |
| 3 | 85 | 79.6 | 5.2 | 6.5 | 80.0 | 3.8 | 4.8 | 79.4 | 3.5 | 4.5 |
| 4 | 0 | 0.9 | 1.0 | N/A | 1.2 | 0.8 | N/A | 1.1 | 0.7 | N/A |
| 5 | 0 | 1.3 | 1.3 | N/A | 0.8 | 1.1 | N/A | 1.1 | 1.1 | N/A |
| 6 | 0 | 0.6 | 0.7 | N/A | 0.5 | 0.5 | N/A | 0.7 | 0.7 | N/A |
| 7 | 0 | 0.6 | 1.0 | N/A | 0.9 | 0.8 | N/A | 0.8 | 0.8 | N/A |
| 8 | 18 | 22.2 | 2.9 | 13.2 | 25.2 | 4.8 | 19.1 | 24.4 | 5.0 | 20.5 |
| 9 | 27 | 26.7 | 4.2 | 15.9 | 27.8 | 3.8 | 13.6 | 28.3 | 4.1 | 14.4 |
| 10 | 31 | 29.6 | 5.7 | 19.2 | 32.6 | 6.4 | 19.6 | 32.2 | 5.9 | 18.2 |
An additional panel of 5 equivocal specimens around the cutoff (10-25%) were tested for repeatability within-day/within-system. Results are presented in Table 3 below:
Table 3: Within-day/Within Repeatability for specimens around the cutoff
| Panel Member | % Positive Cells Counted Manually | Mean% Positive Cells | SD | %CV |
| --- | --- | --- | --- | --- |
| 1 | 12 | 11.6 | 1.62 | 13.9 |
| 2 | 19 | 18.6 | 1.13 | 6.0 |
| 3 | 22 | 19.7 | 0.6 | 3.1 |
| 4 | 18 | 17.6 | 0.98 | 5.6 |
| 5 | 19 | 19.6 | 1.32 | 6.7 |
c. Linearity:
Not applicable.
d. Carryover:
Not applicable.
{7}
e. Interfering Substances:
Not applicable.
2. Other Supportive Instrument Performance Data Not Covered Above:
Not applicable.
K. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
L. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
8
{8}
9
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.