The Clever Chek TD-3213 Blood Glucose and Blood Pressure Measurement System is intended for in vitro diagnostic use. The system is intended to be used for the quantitative measurement of glucose in capillary whole blood from the fingertip. It is intended for use by healthcare professionals and people with diabetes mellitus at home as an aid in monitoring the effectiveness of diabetes control program. It is not intended for the diagnosis of or screening for diabetes mellitus, and not intended for use on neonates. The system is also intended to be used to measure non-invasively the systolic and diastolic blood pressure and pulse rate of an adult individual, over age 16, at home by using a technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 5.25"~7.75".
Device Story
System combines blood glucose meter and wrist-cuff blood pressure monitor. Glucose testing: electrochemical method using dry reagent biosensor test strips; current proportional to glucose concentration in fresh capillary whole blood. Blood pressure testing: oscillometric method; pressure sensor detects cuff pressure alterations; converts to electrical signals to calculate systolic/diastolic pressure and pulse rate. Used at home by patients or in clinical settings by professionals. Output displayed on meter screen for patient monitoring of diabetes and cardiovascular health; aids in diabetes control program management.
Clinical Evidence
Performance evaluated in laboratory and clinical settings by healthcare professionals and lay users. Studies demonstrated the system is suitable for its intended use. No specific sensitivity/specificity metrics provided in summary.
Technological Characteristics
Integrated meter with wrist cuff and dry reagent biosensor test strips. Glucose sensing: electrochemical. Blood pressure sensing: oscillometric (pressure sensor). Wrist cuff circumference: 5.25"-7.75".
Indications for Use
Indicated for quantitative glucose measurement in capillary whole blood (fingertip) for diabetes monitoring by healthcare professionals or patients at home; not for neonates or diabetes diagnosis. Also indicated for non-invasive systolic/diastolic blood pressure and pulse rate measurement in adults >16 years with wrist circumference 5.25"-7.75".
Regulatory Classification
Identification
A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.
Special Controls
*Classification.* Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k042795
B. Purpose for Submission:
New Device
C. Measurand:
Glucose and Blood Pressure
D. Type of Test:
Glucose - Quantitative Amperometric (Glucose Oxidase)
Blood Pressure - Non-invasive Oscillimetric
E. Applicant:
TaiDoc Technology Corporation
F. Proprietary and Established Names:
Taidoc Clever Chek TD-3213 Blood Glucose and Blood Pressure Measurement System
G. Regulatory Information:
1. Regulation sections:
21 CFR § 862.1345, Glucose Test System
21 CFR § 862.1660, Quality Control Material, Assayed and Unassayed
21 CFR § 870.1130, Noninvasive blood pressure measurement system.
{1}
2. Classification:
Class II (Glucose Test System)
Class I -reserved (Quality Control Material)
Class II (Blood Pressure Measurement System)
3. Product code:
NBW, CGA (Glucose Test System)
JJX (Quality Control Material)
DXN (Blood Pressure Measurement System)
4. Panel:
75 (Clinical Chemistry) - Glucose Test System and Quality Control Material
74 (Cardiovascular) - Blood Pressure Measurement System
H. Intended Use:
1. Intended use/ Indications for Use:
The Clever Chek TD-3213 Blood Glucose and Blood Pressure Measurement System is intended for in vitro diagnostic use. The system is intended to be used for the quantitative measurement of capillary whole blood from the fingertip. It is intended for use by healthcare professionals and people with diabetes mellitus at home as an aid in monitoring the effectiveness of a diabetes control program. It is not intended for the diagnosis of or screening for diabetes mellitus, and is not intended for use on neonates.
The system is also intended to be used to measure non-invasively the systolic and diastolic blood pressure and pulse rate of an adult individual, over age 16, at home by using a technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 5.25 inches to ~ 7.75 inches.
2. Special conditions for use statement(s):
This device is not intended to diagnose or screen for diabetes mellitus, and is not to be used on neonates. For in vitro diagnostic use only.
3. Special instrument requirements:
{2}
Not applicable
I. Device Description:
This device combines the functions of a blood glucose meter and a blood pressure measurement system in one unit. Supplied with the meter are the test strips, code strip, lancets, lancet holder, storage case, and control solutions. To measure blood glucose, the user inserts the code strip that is included with each bottle of test strips. A numerical code appears in the display when the code strip is inserted. Once the user confirms that the numerical code on the display, code strip, and strip bottle all match, a test strip is inserted into the meter and glucose testing can proceed. The sponsor has provided instructions and illustrations explaining that the blood drop will be pulled into the strip sample entry by capillary action and that the confirmation window must be completely filled with blood to get an accurate result. Results are stored in the meter's memory for tracking purposes. The lancet supplied with this device was previously cleared under k833344. The two control solutions supplied with this device were previously cleared under k041107.
To measure blood pressure, the user is instructed to wrap the cuff around the wrist approximately ¼ to ½ inch below the ball of the thumb. Users should sit or lie down for 5 - 10 minutes before taking a reading, and are instructed not to move or talk during the measurement. The sponsor has also provided instructions and illustrations explaining that the user must be sitting and the blood pressure cuff must be at the same level as the user's heart to obtain an accurate reading. Results are stored in the meter's memory for tracking purposes.
Blood glucose and blood pressure cannot be measured simultaneously. The device's software will produce an error code if this is attempted.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Bayer Diagnostics Glucometer Elite Diabetes Care System
APM Blood Pressure Monitoring System, BP108A
2. Predicate 510(k) number(s):
k020208
k0401593. Comparison with predicate:
{3}
| Similarities - Glucose Meter | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Specimen | Same | Capillary Whole Blood |
| Methodology | Same | Electrochemical, Glucose Oxidase |
| Measuring Range | Same | 20 - 600 mg/dL |
| Display | Same | Direct Readout; no calculation required |
| Strip Coding | Same | Required |
| Differences - Glucose Meter | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Alternate Site Testing | Specimen may be taken from fingertip only | Can be used for sites other than finger |
| Power Source | Two 1.5 V AAA batteries | Two 3V batteries |
| Number of Readings Stored in Memory | 352 | 20 |
| Similarities - Blood Pressure Monitoring System | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Type of Reading | Same | Non-invasive, diastolic and systolic blood pressure, pulse rate |
| Location of Reading | Same | Wrist |
| Cuff Circumference | Same | 5.25 - 7.75 inches |
| Stethoscope | Not Required | Not Required |
| Power Source | Same | Two 1.5 V AAA batteries |
| Differences - Blood Pressure Monitoring System | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Measuring Range | 30 - 280 mm Hg | 20 - 280 mm Hg |
| Pulse Rate | 40 - 199 beats / min | 40 - 200 beats / min |
| Number of Readings Stored in Memory | 352 | 128 |
K. Standard/Guidance Document Referenced (if applicable): see C.1.9
{4}
NCCLS EP5-A: Evaluation of Precision Performance of Clinical Chemistry Devices; Approved Guideline
NCCLS EP6-P; Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Proposed Guideline
NCCLS EP7-P; Interference Testing in Clinical Chemistry; Proposed Guideline
IEC 61000-4-2 / 1995; Electromagnetic Compatibility (EMC) - Part 4-2: Testing and Measurement Techniques - Electrostatic Discharge Immunity Test-Edition 1.2; Edition 1:1995 Consolidated with Amendments 1:1998 and 2:2000
IEC 61000-4-3 / 2002; Electromagnetic Compatibility (EMC) - Part 4-3: Testing and Measurement Techniques - Radiated, Radio-Frequency, Electromagnetic Field Immunity Test-Edition 2.1; Edition 2:2002 Consolidated with Amendment 1:2002
EN 60601-1:1990; Medical electrical equipment - Part 1: general requirements for safety including amendments A1, A2, A11, A12, and A13
EN 61010-1-2 / 2001; Safety requirements for electrical equipment for measurement, control and laboratory use - Part 1: general requirements
EN 61326; Electrical Equipment for Measurement, Control and Laboratory Use - EMC Requirements-Includes Amendment A1: 1998 and A2:2001; IEC 61326:1997 + A1:1998 + A2:2000
Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, May 1998
L. Test Principle:
Glucose: the glucose oxidase in the strip reacts with the glucose in the sample to produce an electrical current proportional to the glucose concentration. The meter measures the current and converts it to the corresponding glucose concentration in $\mathrm{mg/dL}$ or $\mathrm{mmol/L}$.
Blood pressure: the pressure sensor in the cuff detects small changes in pressure and converts them to electrical signals. The meter analyzes the signals and converts them to standard measurements of pulse rate and systolic and diastolic blood pressure.
{5}
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility of the glucose meter:
The sponsor evaluated precision of the device by using venous whole blood samples spiked with glucose (for within-day precision) and glucose control solutions (for day-to-day precision).
The venous whole blood samples had concentrations of approximately 44, 99, and 143, 228, and 325 mg/dL. The protocol was conducted at three different sites and testing for each concentration, which consisted of 20 measurements, was completed within 30 minutes to minimize the effects of glycolysis. The results for the venous whole blood samples were as follows:
| Within-day precision | | | | |
| --- | --- | --- | --- | --- |
| | | Site 1 | Site 2 | Site 3 |
| Sample 1 (mg/dL) | mean | 44.0 | 44.3 | 43.9 |
| | SD | 1.5 | 1.7 | 1.4 |
| | CV* | 3.3% | 3.8% | 3.1% |
| Sample 2 (mg/dL) | mean | 99.4 | 100.5 | 99.1 |
| | SD | 3.0 | 2.8 | 2.3 |
| | CV | 3.0% | 2.8% | 2.3% |
| Sample 3 (mg/dL) | mean | 142.7 | 134.8 | 141.7 |
| | SD | 4.1 | 5.0 | 4.3 |
| | CV | 2.9% | 3.7% | 3.0% |
| Sample 4 (mg/dL) | mean | 227.5 | 228.5 | 226.0 |
| | SD | 7.0 | 7.9 | 7.6 |
| | CV | 3.1% | 3.4% | 3.4% |
| Sample 5 (mg/dL) | mean | 325.1 | 324.4 | 326.5 |
| | SD | 8.1 | 8.0 | 8.2 |
| | CV | 2.5% | 2.5% | 2.5% |
*Coefficient of variation = (total imprecision SD/mean) X 100
{6}
The glucose control solutions had concentrations of approximately 70, 128, and 315 mg/dL. The protocol was conducted at three sites using two meters. For each concentration, four measurements were taken over 20 days. The results for the control solutions were as follows:
| Day-to-day precision | | | | |
| --- | --- | --- | --- | --- |
| | | site 1 | site 2 | site 3 |
| Control solution 1 (mg/dL) | mean | 69.7 | 70.0 | 69.5 |
| | SD | 2.5 | 2.2 | 2.1 |
| | CV* | 3.6% | 3.2% | 3.1% |
| Control solution 2 (mg/dL) | mean | 127.6 | 127.2 | 126.5 |
| | SD | 2.8 | 3.9 | 2.8 |
| | CV | 2.2% | 3.1% | 2.2% |
| Control solution 3 (mg/dL) | mean | 314.9 | 314.2 | 320.6 |
| | SD | 8.5 | 9.8 | 9.6 |
| | CV | 2.7% | 3.1% | 3.0% |
*Coefficient of variation = (total imprecision SD/mean) X 100
b. Linearity/assay reportable range:
The linearity of the glucose measurements was demonstrated by comparing eleven prepared whole blood samples on the Taidoc meter and a glucose reference method. The eleven samples ranged in concentration from a low of approximately 20 mg/dL to a high of approximately 560 mg/dL. Linear regression of the comparison data yielded the following relationship:
$$
\text{Taidoc} = (1.07 \times \text{Reference Method}) + 13 \, \text{mg/dL} \times r^2 = 0.9985
$$
The reportable range of glucose measurements is 20 - 600 mg/dL
c. Traceability, Stability, Expected values (controls, calibrators, or methods): The controls supplied with this device were previously cleared under k041107. The sponsor has shown traceability of the Taidoc glucose meter to a laboratory analyzer.
{7}
d. Detection limit: $20\mathrm{mg / dL}$
# e. Analytical specificity:
Specificity of the glucose meter was assessed by spiking various endogenous and exogenous compounds into prepared whole blood samples. The sponsor first prepared a low whole blood control at approximately $80\mathrm{mg / dL}$ glucose and a high whole blood control at approximately $300\mathrm{mg / dL}$ glucose and confirmed these concentrations prior to the addition of the interferents. The sponsor then added increasing amounts of potential interferents to both control solutions and again measured the glucose using the Taidoc meter. If the change in glucose measurement from the control solution was less than $10\%$ , this was considered no interference. Results of this testing were as follows:
| Interferent | Highest Concentration Where No Interference Seen |
| --- | --- |
| Acetaminophen | Low Control - 5 mg/dL High Control - 5 mg/dL |
| Ascorbic Acid | Low Control - 1.25 mg/dL High Control - 3 mg/dL |
| Dopamine | Low Control - 2 mg/dL High Control - 2 mg/dL |
| L-dopa | Low Control - 3 mg/dL High Control - 3 mg/dL |
| Methyldopa | Low Control - 0.5 mg/dL High Control - 0.75 mg/dL |
| Tolbutamide | Low Control - 200 mg/dL High Control - 200 mg/dL |
| Uric Acid | Low Control - 10 mg/dL High Control - 10 mg/dL |
| Triglycerides | Low Control - 2000 mg/dL High Control - 2000 mg/dL |
f. Assay cut-off:
{8}
Not Applicable.
2. Comparison studies:
a. Method comparison with predicate device:
The sponsor performed a consumer study to demonstrate that the glucose meter can be used properly by consumers with the directions provided. This study included 40 paired whole blood and plasma samples at three different sites, for a total of 120 comparisons and 120 consumers. Each site compared the Taidoc meter to a different laboratory analyzer. Results were as follows:
Site 1
Taidoc = (0.9952 X laboratory analyzer) + 2 mg/dL
r² = 0.9734
Site 2
Taidoc = (0.9812 X laboratory analyzer) + 4 mg/dL
r² = 0.9728
Site 3
Taidoc = (0.8647 X laboratory analyzer) + 15 mg/dL
r² = 0.9575
b. Matrix comparison:
Not Applicable. The glucose meter is intended to be used with capillary whole blood from the finger only.
3. Clinical studies:
a. Clinical Sensitivity:
Not Applicable.
b. Clinical specificity:
Not Applicable.
c. Other clinical supportive data (when a. and b. are not applicable):
{9}
4. Clinical cut-off:
Not Applicable.
5. Expected values/Reference range:
The sponsor has included in their labeling a fasting reference range of 70-100 mg/dL (3.9-6.1 mmol/L)
N. Instrument Name:
Taidoc Clever Chek TD-3213 Blood Glucose and Blood Pressure Measurement System
O. System Descriptions:
1. Modes of Operation:
Each test strip is single use and must be replaced with a new strip for additional readings. There are no disposable components used to measure blood pressure.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ X or No ☐
3. Specimen Identification:
There is no sample identification function with this device. Samples are applied directly to the test strip as they are collected.
4. Specimen Sampling and Handling:
This device is intended to be used with capillary whole blood from the finger only. Since the whole blood sample is applied directly to the test strip there are no special handling or storage issues.
5. Calibration:
A Code Strip is provided with each batch of test strips to calibrate the meter for that batch. No further calibrations are required of the user.
6. Quality Control:
{10}
The sponsor is providing a high and low glucose control solution with this device. When a test strip is inserted into the meter and the M (Memory) button is pressed, "CtL" is displayed and the control mode is activated. This prevents control results from being stored in the internal memory. An acceptable range for each control level is printed on the test strip vial label. If control results fall outside these ranges, the user is referred to a list of troubleshooting steps and the customer care line.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Note: the following comments are based on a Division of Cardiovascular Device consult review, and apply to the blood pressure portion of this device only.
The device is said to be in compliance with EN 60601-1, General Requirements for Safety. The manufacturer also indicates that the device was tested and met requirements of EN 60601-1-2 for EMC.
The manufacturer has provided software validation test protocols and results of testing which indicate how well the software handled problems such as cuff overpressure, pressure transducer failure, too long to inflate (indicating a leaking hose, etc.), and other mechanical problems. Also, they have provided reliability testing to 10,000 cycles as well as tables indicating applicable conformance to the ANSI/AAMI SP10 standard.
Comparison to Predicate
Both the Taidoc device and the predicate use the well known oscillometric method within the software algorithm to determine the systolic and diastolic blood pressure and pulse rate. A wrist cuff is inflated automatically. The manufacturer's device appears to differ from the predicate device in the tolerance for the pulse rate at $+/- 1\%$ cuff. The tolerance, for both devices, falls within what is called for in the ANSI/AAMI SP10 standard.
Software
The 510(k) submission contains a description of the software, labeling and system error messages related to software hazard testing plans and test results, software requirement specifications, software design specifications, and information about development. Also, the manufacturer has provided a software analysis that includes the result documents, approval test results, product testing description, and a hazard analysis. The software report was prepared in accordance with the FDA guidance document "Guide for the Content of Premarket Submission for Software Contained in Medical Devices."
11
{11}
12
## Biocompatibility
The manufacturer has provided a signed statement that indicates that the arm/wrists cuffs, have been previously supplied under four different previously cleared 510(k)s – K020897, K012310, K021225, and K012796. Also, it is indicated that they are manufactured in the same manner (as the ones related to this device). Therefore, no statement appears to be necessary regarding the International Organization for Standardization document ISO 10993: Biological Evaluation of Medical Devices for biocompatibility testing (cuffs).
## Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
## R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.