K965232 · Caltag Laboratories, Inc. · GKZ · May 14, 1997 · Hematology
Device Facts
Record ID
K965232
Device Name
CALTAG CAL-LYSE
Applicant
Caltag Laboratories, Inc.
Product Code
GKZ · Hematology
Decision Date
May 14, 1997
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.5220
Device Class
Class 2
Indications for Use
Caltag Cal-Lyse is a lysis solution to enable the lysis of erythrocytes in samples of anticoagulated human peripheral blood. Cal-Lyse lysing solution is intended as an aid in the enumeration of leukocytes that have been stained with Caltag monoclonal antibodies for analysis by flow cytometric methods.
Device Story
Caltag Cal-Lyse is a chemical lysing solution used in flow cytometric procedures. It is added to anticoagulated human peripheral blood samples previously incubated with fluorochrome-conjugated monoclonal antibodies. The solution lyses red blood cells and fixes leukocytes simultaneously, eliminating red cell debris and unbound antibodies. The resulting sample is analyzed via flow cytometry. The device is used in clinical laboratory settings by trained technicians or laboratory personnel. By removing red blood cells, the solution enables clear identification and enumeration of leukocyte subsets (e.g., B lymphocytes) stained with monoclonal antibodies, facilitating clinical immunophenotyping and diagnostic assessment of blood cell populations.
Clinical Evidence
Clinical performance evaluated using 175 samples (155 normal, 20 abnormal) across three independent laboratories. Comparison of Caltag CD19 antibodies (R-PE, TRI-COLOR) against Coulter predicates (RD1, FITC) showed high correlation (r² range 0.963–0.977; slopes 0.92–0.94). Leukocyte recovery and red blood cell lysis efficiency were validated in 5 normal donors, showing mean 90.8% leukocyte recovery and 91.8% red cell lysis. Specificity data across diverse ethnic groups confirmed minimal non-specific binding.
Technological Characteristics
Chemical lysing solution containing paraformaldehyde as a fixative. Designed for use with fluorochrome-conjugated monoclonal antibodies (R-PE, TRI-COLOR) in whole blood flow cytometry. Operates via chemical lysis of erythrocytes and simultaneous fixation of leukocytes. No electronic or software components; standalone chemical reagent.
Indications for Use
Indicated for use in the lysis of erythrocytes in anticoagulated human peripheral blood samples to aid in the enumeration of leukocytes stained with Caltag monoclonal antibodies for flow cytometric analysis. No pediatric or adolescent indications established.
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.”
Predicate Devices
Coulter CD19 RD1 monoclonal antibody
Coulter CD19 FITC monoclonal antibody
Reference Devices
Ortho-mune Lysing Reagent
Submission Summary (Full Text)
{0}
CALTAG LABORATORIES
K965232 MAY 14 1997
510(K) SUMMARY
SUMMARY OF SAFETY AND EFFECTIVENESS DATA
Caltag Cal-Lyse™ Lysing Solution For Use With Caltag Monoclonal Antibodies
In Flow Cytometric Procedures
NAME AND LOCATION OF MANUFACTURER:
Caltag Laboratories, Inc.
1849 Old Bayshore Highway
Suite 200
Burlingame, CA 94010
(800) 874-4007
NAME OF CONTACT PERSON:
Robert C. Johnson
Executive Vice President
Caltag Laboratories, Inc.
DATE OF PREPARATION OF SUMMARY:
December 24, 1996
Caltag Laboratories Inc. • 1849 Bayshore Blvd., Suite #200 • Burlingame, CA 94010
Telephone (415) 652-0468 • (800) 874-4007 • FAX (415) 652-9030
{1}
-2-
## TRADE NAME OF THE DEVICE:
Caltag Cal-Lyse Lysing Solution For Use With Caltag Monoclonal Antibodies In Flow Cytometric Procedures
## COMMON NAME:
Caltag Cal-Lyse Lysing Solution
## CLASSIFICATION NAME:
Automated Differential Cell Coulter (21 CFR 864.5220)
## LEGALLY MARKETED DEVICE (PREDICATE DEVICE) TO WHICH THE MANUFACTURER IS CLAIMING SUBSTANTIAL EQUIVALENCE:
The Caltag CD19 R-PE monoclonal antibody is substantially equivalent to the Coulter CD19 RD1 monoclonal antibody when red blood are lysed with the Cal-Lyse lysing solution in flow cytometric procedures.
The Caltag CD19 TRI-COLOR monoclonal antibody is substantially equivalent to the Coulter CD19 FITC monoclonal antibody when red blood are lysed with the Cal-Lyse lysing solution in flow cytometric procedures.
The Caltag CD19 R-PE monoclonal antibody is substantially equivalent to the Coulter CD19 FITC monoclonal antibody when red blood are lysed with the Cal-Lyse lysing solution in flow cytometric procedures.
The Caltag CD19 TRI-COLOR monoclonal antibody is substantially equivalent to the Coulter CD19 RD1 monoclonal antibody when red blood are lysed with the Cal-Lyse lysing solution in flow cytometric procedures.
The Caltag CD19 R-PE monoclonal antibody is substantially equivalent to the Caltag CD19 TRI-COLOR monoclonal antibody when red blood are lysed with the Cal-Lyse lysing solution in flow cytometric procedures.
## DESCRIPTION OF THE DEVICE:
Caltag monoclonal antibodies bind to the surfaces of viable blood cells that express the corresponding antigens. To identify cells bearing these antigenic determinants, peripheral blood samples are incubated with fluorochrome-conjugated monoclonal antibodies. Cells are subsequently washed to remove unbound antibody. Prior to the removal of unbound antibody, Cal-Lyse lysing solution is added to lyse red blood cells. Cells may subsequently be washed, resulting in the elimination of red cell debris as well as unbound antibody.
{2}
-3-
Cal-Lyse lysing solution contains paraformaldehyde as fixative, and no additional fixation is required. Antibody-stained and fixed leukocytes are subsequently analyzed by flow cytometric methods.
INTENDED USE OF THE DEVICE:
Caltag Cal-Lyse is a lysis solution to enable the lysis of erythrocytes in samples of anticoagulated human peripheral blood. Cal-Lyse lysing solution is intended as an aid in the enumeration of leukocytes that have been stained with Caltag monoclonal antibodies for analysis by flow cytometric methods.
SUMMARY OF THE TECHNICAL CHARACTERISTICS OF THE MANUFACTURER'S DEVICE COMPARED TO THE PREDICATE DEVICE:
Comparisons of Caltag CD19 and Coulter CD19 Monoclonal Antibodies In Samples In Which Red Blood Cells Are Lysed With Caltag Cal-Lyse Lysing Solution
| No. | Item | Caltag Antibodies | Coulter Antibodies | Comparison |
| --- | --- | --- | --- | --- |
| 1. | Intended Use | Flow Cytometry | Flow Cytometry Immunofluorescence | Substantially equivalent |
| 2. | Specificity | CD19 | CD19 | Substantially equivalent |
| 3. | Target cell | B lymphocyte | B lymphocyte | Substantially equivalent |
| 4. | Chemical form | Monoclonal antibody | Monoclonal antibody | Substantially equivalent |
| 5. | Fluorochromes | R-PE, TRI-COLOR | FITC, RD1 | Substantially equivalent |
| 6. | Available forms | | | |
| | FITC | liquid, PBS | lyophilized | Substantially |
| | PE | liquid, PBS | liquid, PBS | equivalent |
| | TRI-COLOR | liquid, PBS | not available | |
| 7. | Sample prep. methods | whole blood | whole blood | Substantially equivalent |
| 8. | Expected values from this study (n=155) | | | |
| | R-PE | 5-21% | 4-21% (RD1) | Substantially |
| | TRI-COLOR | 4-24% | 3-23% (FITC) | equivalent |
{3}
-4-
# NON CLINICAL TESTS SUPPORTING A DETERMINATION OF SUBSTANTIAL EQUIVALENCE:
## EXPECTED VALUE DATA
Blood samples were collected from a total of 155 apparently healthy adult normal donors in an age range of 16 to 72, and a mean age of 41.
Samples were stained with Caltag monoclonal antibodies and red blood cells were lysed with Caltag Cal-Lyse lysing solution. Samples were collected and analyzed in each of three independent laboratories. An approximately equal number of males and females were collected and analyzed in each laboratory.
The normal donor population included members of differing ethnic origins, including adult Caucasian, Black, Oriental and Hispanic. Donors in geographically diverse areas of the United States, including the Western, Eastern and South Central regions, participated in this study.
Summary of expected values for the CALTAG T and B cell monoclonal antibodies, CD3 FITC and CD19 R-PE, for all normal donors:
| procedure | mean % positive | S.D. | Range ±2 S.D. | n |
| --- | --- | --- | --- | --- |
| CD3 FITC | 71.0 | 7.4 | 58-86 | 155 |
| CD19 R-PE | 13.0 | 4.2 | 5-21 | 155 |
Expected values for pediatrics and adolescents have not been established.
The values obtained from normal individuals may vary from laboratory to laboratory; therefore, it is recommended that each laboratory establish its own normal range.
## SPECIFICITY DATA
Blood samples were obtained from healthy normal donors of Caucasian, Black, Hispanic and Oriental ethnic origins. Samples of each donor were stained with Caltag monoclonal antibodies and red blood cells were lysed with Caltag Cal-Lyse lysing solution. Cells contained in the lymphocyte, monocyte and granulocyte regions were selected for analysis. Separate samples from the same donors were prepared for analysis of red blood cells and platelets and stained with each of the Caltag monoclonal antibodies.
The following specificity data were obtained with the Caltag T and B cell monoclonal antibodies, CD3 FITC and CD19 R-PE, following the lysis of red blood cells with Caltag Cal-Lyse lysing solution:
| CD3 FITC
Ethnic
Origin | Percent of Stained Cells | | | | |
| --- | --- | --- | --- | --- | --- |
| | Lymph. | Mono. | Gran. | Plt. | RBC |
| Caucasian | 65.2 | 1.7 | 1.5 | 0.3 | 0.6 |
| Caucasian | 81.4 | 1.4 | 0.5 | 0.4 | 0.3 |
| Hispanic | 79.2 | 1.9 | 0.6 | 0.3 | 0.4 |
| Oriental | 81.2 | 1.3 | 0.9 | 0.2 | 0.4 |
| Black | 84.9 | 0.9 | 0.6 | 0.4 | 0.4 |
| Mean | 78.4 | 1.4 | 0.8 | 0.3 | 0.4 |
| ±1 S.D. | 7.6 | 0.4 | 0.4 | 0.1 | 0.1 |
{4}
-5-
| CD19 R-PE | | | | | |
| --- | --- | --- | --- | --- | --- |
| Ethnic Origin | Percent of Stained Cells | | | | |
| | Lymph. | Mono. | Gran. | Plt. | RBC |
| Caucasian | 18.0 | 0.6 | 0.9 | 0.5 | 0.5 |
| Caucasian | 13.3 | 1.1 | 0.8 | 0.3 | 0.7 |
| Hispanic | 12.2 | 0.7 | 0.8 | 0.4 | 1.0 |
| Oriental | 11.2 | 1.6 | 1.3 | 0.4 | 0.5 |
| Black | 14.6 | 0.0 | 0.5 | 0.6 | 0.9 |
| Mean | 13.9 | 0.8 | 0.9 | 0.4 | 0.7 |
| ±1 S.D. | 2.6 | 0.6 | 0.3 | 0.1 | 0.2 |
Specific and/or nonspecific antibody Fc binding to monocytes in a patient sample can be excluded by proper gating on lymphocytes on the flow cytometer.
## LEUKOCYTE RECOVERY DATA
This study was conducted on blood samples obtained from 5 normal donors consisting of representatives from Caucasian, Black, Hispanic and Oriental ethnic origins. An appropriate hematology analyzer was used to enumerate leukocytes prior to, and immediately following the lysis of red blood cells with Caltag Cal-Lyse lysing solution and with the Ortho-mune™ Lysing Reagent. Leukocyte recovery from members of differing ethnic origins was comparable. Leukocyte recovery following lysis with Cal-Lyse and Ortho-mune lysing reagents was comparable.
It should be noted that washing of cells alone, in the absence of a lysis procedure may result in a modest loss of cells.
In the following table describing leukocyte recovery, leukocyte counts are expressed as cells per cu. mm.
| Donor No. | Race | Leukocyte Count | | |
| --- | --- | --- | --- | --- |
| | | Prior to Lysis | Following Lysis | Percent Recovered |
| 1 | Caucasian | 8300 | 7200 | 86.7 |
| 2 | Caucasian | 8100 | 7200 | 88.9 |
| 3 | Black | 5700 | 4800 | 84.2 |
| 4 | Hispanic | 6200 | 6000 | 96.8 |
| 5 | Oriental | 7400 | 7200 | 97.3 |
| Mean | | 7140 | 6480 | 90.8 |
| ± 1 SD | | 1150 | 1073 | 6.0 |
## RED BLOOD CELL LYSIS DATA
This study was conducted on blood samples obtained from 5 normal donors, to determine whether essentially all red cells were lysed by the lysing solution. Red cells were lysed in a sample of blood from each donor with Caltag Cal-Lyse lysis solution. An appropriate hematology analyzer was used to enumerate red blood cells prior to and immediately following lysis. The differing orders of magnitude of red cells counted prior to and following lysis should be noted in the following table.
{5}
-6-
# Red Blood Cell Count
| Donor No. | Prior to Lysis cells/cu.mm. x 10^{6} | Following Lysis cells/cu.mm x 10^{5} | Percent Lysed |
| --- | --- | --- | --- |
| 1 | 5.1 | 3.0 | 94.1 |
| 2 | 5.1 | 5.0 | 90.2 |
| 3 | 4.3 | 3.0 | 93.0 |
| 4 | 3.7 | 3.0 | 91.8 |
| 5 | 4.9 | 5.0 | 89.7 |
| Mean | 4.6 | 3.8 | 91.8 |
| ±1 S.D. | 0.6 | 1.1 | 1.9 |
## CLINICAL TESTS SUPPORTING A DETERMINATION OF SUBSTANTIAL EQUIVALENCE:
### CORRELATION DATA
The correlation for the Caltag Cal-Lyse lysing solution was based on the performance of the Caltag B cell monoclonal antibodies CD19 R-PE and CD19 TRI-COLOR. The percent, as well as the mean fluorescence, of B lymphocytes is substantially lower than is observed for T lymphocytes in normal peripheral blood. The resulting analysis of B lymphocytes by flow cytometric methods may be more susceptible to uncontrolled variations in the staining and lysis methods employed.
Samples obtained from normal and abnormal donors were stained with Caltag and comparable Coulter B cell monoclonal antibodies. Red blood cells were lysed with Caltag Cal-Lyse lysing solution in samples that had been stained with both Caltag and Coulter monoclonal antibodies.
A total of 155 normal donor samples were collected and analyzed in each of three independent laboratories, and analyzed on either the FACscan or Profile flow cytometers.
The normal donor population included members of differing ethnic origins, including adult Caucasian, Black, Oriental and Hispanic. Donors in geographically diverse areas of the United States, including the Western, Eastern and South Central regions, participated in this study. Males and females were represented in approximately equal numbers.
A total of 20 abnormal donors were analyzed on both the FACscan and Profile flow cytometers at a single site. Correlations were obtained for the Caltag and Coulter B cell monoclonal antibodies for all normal and abnormal donors (n=175). Red blood cells from all samples were lysed with Cal-Lyse lysing solution.
Comparison of the Caltag CD19 R-PE conjugated monoclonal antibody with the Coulter CD19 RD1 conjugated monoclonal antibody:
| procedure | mean % positive | r^{2} value | slope | Y intercept | n |
| --- | --- | --- | --- | --- | --- |
| CD19 R-PE | 16.4 | 97.7 | 0.92 | 1.30 | 175 |
| CD19 RD1 | 16.2 | | | | |
{6}
-7-
# CD19 R-PE
Linear regression $y = 1.30 + 0.92x$
Comparison of the CALTAG CD19 R-PE conjugated monoclonal antibody with the Coulter CD19 FITC conjugated monoclonal antibody:
| procedure | mean % positive | r² value | slope | Y intercept | n |
| --- | --- | --- | --- | --- | --- |
| CD19 R-PE | 16.4 | 96.3 | 0.93 | 0.69 | 175 |
| CD19 FITC | 16.7 | | | | |
# CD19 R-PE
Linear regression $y = 0.69 + 0.93x$
Comparison of the CALTAG CD19 TRI-COLOR conjugated monoclonal antibody with the Coulter CD19 RD1 conjugated monoclonal antibody:
| procedure | mean % positive | r² value | slope | Y intercept | n |
| --- | --- | --- | --- | --- | --- |
| CD19 TRI-COLOR | 17.1 | 96.7 | 0.92 | 2.14 | 175 |
| CD19 RD1 | 16.2 | | | | |
# CD19 TRI-COLOR
Linear regression $y = 2.14 + 0.92x$
Comparison of the CALTAG CD19 TRI-COLOR conjugated monoclonal antibody with the Coulter CD19 FITC conjugated monoclonal antibody:
| procedure | mean % positive | r² value | slope | Y intercept | n |
| --- | --- | --- | --- | --- | --- |
| CD19 TRI-COLOR | 17.1 | 97.4 | 0.94 | 1.36 | 175 |
| CD19 FITC | 16.7 | | | | |
# CD19 TRI-COLOR
Linear regression $y = 1.36 + 0.94x$
Comparison of the CALTAG CD19 TRI-COLOR conjugated monoclonal antibody with the CALTAG CD19 R-PE conjugated monoclonal antibody:
| procedure | mean % positive | r² value | slope | Y intercept | n |
| --- | --- | --- | --- | --- | --- |
| CD19 TRI-COLOR | 17.1 | 97.6 | 0.99 | -0.56 | 175 |
| CD19 R-PE | 16.4 | | | | |
# CD19 TRI-COLOR
Linear regression $y = -0.56 + 0.99x$
# BIBLIOGRAPHY
1. Mishell B.B., Shilgi A.M., Selected methods in cellular immunology, W.H. Freeman and Company, 1980.
2. Transport and diffusion of red blood cells, Whittam R. editor, Williams and Wilkins, Baltimore, 1984.
3. Gorgi, J.V., Cheng H., Margolick J. et al, Quality control in the flow cytometric measurement of T-lymphocyte subsets: the multicenter AIDS cohort study experience, Clin. Immunol. Immunopathol. 55:173, 1990.
4. NCCLS Document H42-T, Clinical applications of flow cytometry: Quality Assurance and immunophenotyping of peripheral blood lymphocytes, Tentative Guideline, May, 1992.
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.