The EXCELL™ 22, is an in-vitro diagnostic instrument for use in counting blood cells, classifying white blood cells (WBC) and flagging specimens containing abnormal blood cells in clinical laboratories at diverse sites. Per NCCLS H20A section 4(9), flagging is defined as "identifying a sample or blood film for further attention or review".
Device Story
EXCELL 22 is an in vitro diagnostic hematology analyzer; derived from Danam DATACELL 18MS. Inputs: whole blood samples. Transformation: utilizes laser-excited multi-dimensional flow cytometry for five-part WBC differential and impedance-based counting for other parameters; incorporates hydrodynamic focus sample injection and von Behrens silencer for platelet aperture. Outputs: quantitative blood cell counts (WBC, RBC, Hgb, Hct, MCV, MCH, MCHC, RDW, Plt, MPV) and WBC differential percentages/numbers; flags abnormal specimens. Used in clinical laboratories; operated by laboratory personnel. Output used by clinicians to assess hematological status and identify need for manual review. Benefits: provides automated, accurate, and reproducible blood cell analysis and flagging to support clinical decision-making.
Clinical Evidence
Bench testing and comparative clinical study. Study 1: 390 whole blood samples compared EXCELL 22 against Coulter S+IV and Cell-Dyn 3000; correlation coefficients >0.980 for measured parameters. Study 2: 173 samples evaluated flagging performance; EXCELL 22 reported 0 false negatives and 1 false positive, compared to 0 false negatives and 7 false positives for the Cell-Dyn 3000. Results confirm accuracy and equivalence.
Technological Characteristics
Laser-excited multi-dimensional flow cytometer; impedance-based cell counting; hydrodynamic focus sample injection; von Behrens silencer for platelet aperture. External PC-based control. DC motors. Analyzes whole blood. No specific material standards cited.
Indications for Use
Indicated for use in clinical laboratories for counting blood cells, classifying white blood cells, and flagging abnormal blood cell specimens in patients requiring hematological analysis.
Regulatory Classification
Identification
An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.
Special Controls
*Classification.* Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”
{0}------------------------------------------------
# 510(k) Summary
MWI. Inc.
| Common/Clasification Name: | Counter, Differential Cell<br>Hematology Analyzer |
|----------------------------|-----------------------------------------------------------------------------------------------------------------------------|
| Sponsor: | MWI, Inc.<br>d.b.a. Danam Electronics<br>4230 Shilling Way<br>Dallas, TX 75237<br>Tel (214) 210-4900<br>Fax (214) 210-4949 |
| Contact: | Greg Witherspoon |
| Prepared: | April 29, 1999 |
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.
The assigned 510(k) number is K99639
#### LEGALLY MARKETED PREDICATE DEVICES A
To show that EXCELL 22 Is safe and effective, it is compared to two legally marketed devices. The Cell-Dyn 3000 WBC differential is well respected in the industry as being fundamentally sound in theory and implementation, but because of well known WBC fragile lymphocyte counting problems it is not used for the WBC count for this comparison. The design of the EXCELL 22 is derived from the proven Danam DATACELL 18MS that traces its performance equivalence to the Coulter S+IV. For this reason, the basic hematology parameters are compared to the Coulter S+IV and the white cell differential is compared to the Cell-Dyn 3000. The laser optical WBC differential that was added to the DATACELL 18MS is similar to that of the Cell-Dyn 3000.
The Coulter S+IV reproducibility and linearity is superior to the Cell-Dyn products and makes a better comparison for those parameters which are provided.
{1}------------------------------------------------
The predicate devices are marketed under 510(k) clearance. The Cell-Dyn 3000 is manufactured by Sequoia Turner Corporation, (now Abbott Laboratories) under K890491. The DATACELL 18MS is manufactured by MWI, Inc. d.b.a. Danam Electronics under K945678.
#### B DEVICE DESCRIPTION
The EXCELL 22 is a DATACELL 18MS with an additional optical channel for performing a five-part white cell differential. The five-part optical white cell differential system is substantially equivalent to the Cell-Dyn 3000.
Modifications to the DATACELL 18MS present in the new instrument are:
- Addition of a laser excited multi dimensional flow cytometer .
- . addition of a reagent for the optical flow cell
- provision for collecting data from the optical detectors .
- replacing of AC motors with DC motors to make the product suitable . for international applications
- replacing the internal PC computer and monitor with an external PC to . gain room for the optical detection system
- . provision in the slide valve for the additional dilution for the WBC optical measurement
- . addition of hydrodynamic focus sample injection system for the WBC
- improved dilution logic to speed up the measurement .
- � improved platelet aperture system called the von Behrens silencer.
The operating modes are the same as the DATACELL 18MS.
#### C INTENDED USE
The subject product, EXCELL 22, is an in vitro diagnostic instrument for use in counting blood cells, classifying white blood cells (WBC), and flagging specimens containing abnormal blood cells. The marketed instruments, DATACELL 18MS and Cell-Dyn 3000, have the same intended use.
#### D TECHNOLOGICAL CHARACTERISTICS
The subject product, EXCELL 22, has similar technological characteristics as the predicate devices. The EXCELL 22 is simply the addition of an optical five-part white cell differential to the Danam DATACELL 18MS. The white cell differential is closely related to the technology utilized by the Gell-Dyn 3000. The other changes are refinements of the technology used in the DATACELL 18MS.
{2}------------------------------------------------
#### TESTING E
Evaluation of performance characteristics was done in the Danam OC
are and the contractions formas instruments are routinely maintained for Evaluation of performance characteristics was goutinely maintained for laboratory where the reference institutions and controls. The instruments
monitoring performance of Danam reagents and controls. The instruments monitoring performance of Danam reagents and Streek Laboratories Para
are controlled using Coulter 4C for the S+V and Streck Laboratories Para
Click Street C & L = 0000 Clic are controlled using Coulter 4C for the Services exist for the 12 plus for the Cell-Dyn 3000. Silght callsmands on the line the the the the the different brands of callbrator and control procusion applicians'
evaluation were obtained from various sources including physicians' evaluation were obtained not hospital laboratories.
### Linearity
Linearity is set on all Danam Excell products by a serial dilution
is a set on all products and corporators against hemoglibin. Linearity is set on all Danam LXcoll production in hemoglobin. The
technique plotting all counted parameters against hemoglobin technique ploting all counted purchip to verify hemoglobin
hemoglobin is assayed for each dilution to verify hemoglobin hemogiobilitis assayed for ouch effectificant tochnique since the linearity. This is a particularly useful lochinique envous and cell counts.
The results of the linearity test indicate that the EXCELL 22 meets The results of the infounty toos contained in the Operator's Reference Manual.
### Precision
Studies of instrument precision are used to confirm the Studies of instrument procision are assisted operation. Precision is reproducibility of the initial blood camping material. The precision evaluated by replicate analysos of solicates of high, normal, and studies consist of 10 consocutive repression test indicate that low control material. The rooms of the performance specifications contained in the Operator's Reference Manual.
To evaluate precision of day to day operations, statistics are TO evaluate precision of day to day open aterial when the testing of denved from the daily tooting or alsured are within patient samples was done. All values of variation are less than acceptable fanges and their disoned for the control product when it is the specifical IDSD .......................................................................................................................................................... expected range and indicate satisfactory performance of the EXCELL 22.
{3}------------------------------------------------
### Accuracy
Accuracy is evaluated by comparison of measured and calculated Accuracy is evaluated by companissn of clinical specimens by EXCELL 22 and parameters from testing of cirined opesifierential percential percentages and the reference instruments. The Cell-Dyn 3000. All other parameters were compared with the Coulter S+IV. Because no established were compared with the Oouler oology analyzers, instruments were standardo are avellable calibrator stated to be calibrated to a commorolains and the some parameters.
Comparison of results is made between samples counted by the Companson of roballer forence instruments. Two studies were performed. The first study is of a large number of samples comparing the EXCELL 22 and the reference instruments to companing the EXOLED accuracy of the subject instrument. The delemine correlation of acceration of reference method differential determination to resolve flag differences between the Cell-Dyn 3000 and the EXCELL 22.
### Study 1
Study i
This study consisted of 390 whole blood samples obtained from I nis study consisted as defined in NCCLS H3-A2, intended to be representative of the universe that the EXCELL 22 is intended to serve. The specimens were tested during the period from February 08, 1999 to April 08, 1999.
> Patient samples that gave a white blood cell differential morphological positive result on the Cell-Dyn 3000 reference instrument and the EXCELL 22 were eliminated from the white blood cell differential count portion of the correlation study, as recommended in NCCLS H20-A, resulting in a reduction of the samples for the WBC differential count portion to 268.
> Patient samples giving a PLT/RBC morphological positive result on the reference instrument and instrument under evaluation were eliminated from the PLT, RBC, MCV, RDW, HGB portion of the correlation study, as recommended in NCCLS H20-A, resulting in a reduction of the samples to 326.
All samples were promptly analyzed on the EXCELL 22, Coulter S+IV, Cell-Dyn 3000 and the results recorded.
{4}------------------------------------------------
The correlation coefficient, slope and y-Intercept were determined for each parameter. Measured parameter results (WBC, RBC, Hgb. MCV, Pit) obtained by the EXCELL 22 exhibited coefficients of correlation is greater than 0.980.
Calculated RDW and WBC differential parameter results are considered to be accurate when the slope of the line of correlation is within the range of 0.95 to 1.05 and the coefficient of correlation is greater than 0.900 for all cell types except the basophils. The basophil is an infrequently occurring cell type that is reduced in correlation coefficient due to the very small frequency range and the statistical noise caused by the low number of basophils observed.
The results of this study indicate that the EXCELL 22 is accurate and is substantially equivalent to the legally marketed reference instruments.
#### Study 2
The purpose of this study is to evaluate the flagging characteristics of the EXCELL 22. This study consisted of 173 whole blood samples obtained from various sources, collected as defined in NCCLS H3-A2, and intended to be representative of the universe that the EXCELL 22 is intended to serve. The specimens were tested during the period from March 10, 1999 to April 08, 1999.
All samples were promptly analyzed by the EXCELL 22, Cell-Dyn 3000 and the results recorded. A slide was made of each specimen for further analysis.
The EXCELL 22 and the Cell-Dyn 3000, both report a DIFF flag when they cannot reliably discriminate the cell clusters and produce a meaningful five part white cell differential. This is typically droo to the presence of highly abnormal cell distributions, abnormal cell morphology, or deterioration of sample condition.
On all samples reported with a DIFF flag by the Cell-Dyn 3000 and/or by the EXCELL 22, three different technologists performed a manual differential count. The manual count from each technologist was recorded, and the average result of all three was used in order to minimize the effects of human error and to improve statistical confidence of the observation.
The EXCELL 22 reported no false negative and 1 false positive result; the Cell-Dyn 3000 reported no false negative and 7 false positive results.
{5}------------------------------------------------
The result of the EXCELL 22 flagging study indicated that no unreliable WBC differential results were reported.
#### F CONCLUSIONS
Careful analysis of the results of comparison of the EXCELL 22 with the Careful analysis of the results of companses of the substantial equivalence of the EXCELL 22 with the legally marketed devices. The EXCELL 22 is safe and effective for its intended use.
・
{6}------------------------------------------------
DEPARTMENT OF HEALTH & HUMAN SERVICES
Image /page/6/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo features a stylized caduceus, which is a symbol often associated with healthcare. The words "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" are arranged in a circular pattern around the caduceus. The logo is black and white.
JUL - 1 1999
Mr. Gregory A. Witherspoon Manager, Quality Affairs and Regulatory Affairs MWI, Inc. dba DANAM Electronics 4230 Shilling Way Dallas, Texas 75237
K991539 Re: Trade Name: EXCELL™ 22 Regulatory Class: II Product Codc: GKZ Dated: April 30, 1999 Received: May 3, 1999
Dear Mr. Witherspoon:
We have reviewed your Section 510(k) notification of intent to market the device referenced We have reviewed your Section 510(x) notifications in (for the indications for use indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce stated in the enclosure) to legally manoled processor in Medical Device Amendments, or to devices that prior to May 28, 1770, the chasinent and the provisions of the Federal Food, Drug, and have been reclassified in accordance with the provide device, subject to the general controls Cosmetic Act (Act). You may, morelors, manol isions of the Act include requirements for annual provisions of the Act. "The general obline provise stice, labeling, and prohibitions against misbranding and adulteration.
If your device is classified (see above) into either class II (Special Controls) or class III (Premarket Approval), it may be subject to such additional controls. Existing major regulations (Premarket Apploval), it may of subject to ader as a learners , Title 21, Parts 800 to 895. allecting your device car o determination assumes compliance with the Current Good A suisfantially equirations as set forth in the Quality System Regulation (QS) for Manufacturing Practice requirements (21 CFR Part 820) and that, through periodic QS inspections, the Food and Drug Administration (FDA) will verify such assumptions. Failure to mispections, the rood and Drig reasult in regulatory action. In addition, FDA may publish comply wan and Greaterning your device in the Federal Register. Please note: this response to your premarket notification submission does not affect any obligation you might have under sections 531 through 542 of the Act for devices under the Electronic Product Radiation Control provisions, or other Federal laws or regulations.
Food and Drug Administration 2098 Gaither Road Rockville MD 20850
{7}------------------------------------------------
### Page 2
Under the Clinical Laboratory Improvement Amendments of 1988 (CLIA-88), this device may
out of the may of the since if a leterroing if it does, you should contact the Under the Clinical Laboratory Improvement Anlenements of 1780 ( Under 1977)
require a CLIA complexity categorization. To determine if it does, you should contact the require a CLIA complexity Categorization - FC CC
Centers for Disease Control and Prevention (CDC) at (770) 488-7655.
This letter will allow you to begin marketing your device as described in your 510(k) premarket
s and the supportunity of any for the taskes of your device to a legally mark This letter will allow you to begin marketing your device to a legally marketed
notification. The FDA finding of Substantial equivalence of your device to notification. The FDA finding of substantial equivaled of your device and thus, permits your device to proceed to the market.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and If you desire specific advice for your devices), please contact the Office of Compliance at
additionally 809.10 for in vitro diagnostic devices), presentials and vour device additionally 809.10 for in vitto diagnostions on the promotion and seriesing of your device, (301) 594-4588. Additionally, for questions on the promo. A lso, please note the regulation
please contact the Office of Compliance at (301) 594-4639. Also, please note the please contact the Office of Compliatic at (301) 34-4037. 7200 (FR 807.97). Other general
entitled, "Misbranding by reference to premarket notification"(21 CFR 807.97). Oth entitled, "Misbranding by reference to prematics and reason (and the Division of Small
information on your responsibilities under the Act may be obtained from the Division of information on your responsibilities under (800) 638-2041 or (301) 443-6597, or at its
Manufacturers Assistance at its toll-free number (800) 638-2041 or (301) 443-6597, or a Manufacturers Assistance at to to to to to to to to to to to this.".
Sincerely yours,
Steven Sutman
Steven I. Gutman, M.D, M.B.A. Director Division of Clinical Laboratory Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosure
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the logo for MWI, INC. The logo includes a stylized waveform graphic to the left of the text. Below the company name, it says "dba DANAM3 ELECTRONICS" in a smaller font.
4230 SHILLING WA DALLAS, TEXAS 75237 (214) 210-4900 (800) 433-0945 FAX (214) 210-4949
Page 1 of 2
# 510(k) Number (if known): K991539
# Device Name: EXCELL™ 22
### Indication for Use: The EXCELL™ 22, is an in-vitro diagnostic
instrument for use in counting blood cells, classifying white blood cells (WBC) and flagging specimens containing abnormal blood cells in clinical laboratories at diverse sites. Per NCCLS H20A section 4(9), flagging is defined as "identifying a sample or blood film for further attention or review".
# The EXCELL 22 reports on the following parameters:
- White Blood Cells (Leukocytes) WBC
- Red Blood Cells (Erythrocytes) RBC
- Hemoglobin Concentration Hgb
- Hematocrit (relative volume of erythtocytes) Hct
- Mean Corpuscular (erythrocyte) Volume MCV
- Mean Corpuscular (erythrocyte) Hemoglobin MCH
- Mean Corpuscular (erythrocyte) Hemoglobin Concentration MCHC
- Red Blood Cell (erythrocyte volume) Distribution Width RDW
- Platelet or Thrombocyte Count Pit
- Mean Platelet (thrombocyte) Volume MPV
### Continued on next page
# (PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo for MWI, INC. The logo includes a stylized waveform graphic to the left of the text. Below the company name, it says "dba DANAM® ELECTRONICS" in a smaller font.
4230 SHILLING WA DALLAS, TEXAS (214) 210-
Page 2 of 2
510(k) Number (if known): K991539
Device Name: EXCELL™ 22
# Parameters Continued:
- Lymphocyte (number) LY#
- Lymphocyte (percent of WBC) LY%
- Monocyte (number) MO#
- Monocyte (percent of WBC) MO%
- Basophil (number) BA #
- BA% Basophil (percent of WBC)
- Neutrophil (number) NE#
- Neutrophil (percent of WBC) NE%
- Eosinophil (number) EO#
- Eosinophil (percent of WBC) EO%
(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)
Concurrence of CDRH, Office of Device Evaluation (ODE)
Peter E. Madeni
(Division Sign-Off)
Division of Clinical Laboratory Devices K991539
510(k) Number
Prescription -
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.