The Synermed Glucose Reagent is for the in vitro quantitative measurement of glucose in serum on the Synermed IR-1200. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and of pancreatic islet cell carcinoma. The Synermed IR-1200 analyzer is intended for in vitro diagnostic use as a multiparameter chemistry instrument that quantitates the levels of constituents in serum. The analyzer is an automated, random access, computer controlled, clinical chemistry analyzer for clinical chemistry tests. The instrument provides in vitro quantitative measurements for glucose in serum. The device is intended for use only in clinical laboratories.
Device Story
The Synermed IR-1200 is an automated, random-access, computer-controlled clinical chemistry analyzer for use in clinical laboratories by trained personnel. It processes serum samples using spectrophotometric measurement across 12 wavelengths (340-800 nm). The system utilizes liquid-stable reagents (e.g., Glucose Oxidase) to perform endpoint or kinetic assays. The analyzer automates sample/reagent pipetting, mixing, pre-heating, reaction monitoring, and cuvette washing/drying. An externalized computer manages the operating system, calculations, and results display. By automating manual laboratory functions, the device aims to improve efficiency, reduce errors, and enhance the accuracy and precision of quantitative test results, aiding clinicians in diagnosing and monitoring metabolic disorders.
Clinical Evidence
Bench testing only. Performance validated per CLSI guidelines: precision (EP05-A3), linearity (EP06-A6), interference (EP07-A2), and detection limits (EP17-A). Method comparison (EP09-A3) against the Hitachi 717 using 115 serum samples showed high correlation (r=0.9994, slope=0.988). Interference studies identified significant bias (>10%) from ascorbic acid, methyldopa, and uric acid at specific concentrations.
Technological Characteristics
Automated photometric chemistry analyzer. Uses glucose oxidase enzymatic reaction; detection at 650-660 nm. Reagents: glucose oxidase, peroxidase, ampyrone, N-sulfopropyl-N-ethyl-3,5-dimethylaniline. Dimensions: 51in x 34in x 44in; weight 750 lbs. Reusable PMMA cuvettes. Semiconductor cooling for reagents; 37°C incubation. Connectivity: Data transmission to computer/server (no wireless). Power: 220 VAC. Software-controlled.
Indications for Use
Indicated for in vitro quantitative measurement of glucose in serum for patients requiring diagnosis or treatment of carbohydrate metabolism disorders, including diabetes mellitus, neonatal hypoglycemia, and pancreatic islet cell carcinoma.
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:
k153692
B. Purpose for Submission:
Adding previously cleared test on a new instrument platform
C. Measurand:
Glucose
D. Type of Test:
Quantitative, photometric
E. Applicant:
Infrared Laboratory Systems, LLC (DBA Synermed)
F. Proprietary and Established Names:
Synermed Glucose Reagent
Synermed IR-1200 Chemistry Analyzer
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CGA | II | 862.1345, Glucose Test System | Chemistry (75) |
| JJE | I, exempt | 862.2160, analyzer, chemistry (photometric, discrete) for clinical use | Chemistry (75) |
H. Intended Use:
1. Intended use(s):
{1}
The Synermed Glucose Reagent is for the in vitro quantitative measurement of glucose in serum on the Synermed IR-1200. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and of pancreatic islet cell carcinoma.
The Synermed IR-1200 analyzer is intended for in vitro diagnostic use as a multiparameter chemistry instrument that quantitates the levels of constituents in serum. The analyzer is an automated, random access, computer controlled, clinical chemistry analyzer for clinical chemistry tests. The instrument provides in vitro quantitative measurements for glucose in serum. The device is intended for use only in clinical laboratories.
2. Indication(s) for use:
See intended use above.
3. Special conditions for use statement(s):
For prescription use only.
4. Special instrument requirements:
Synermed IR-1200 Chemistry Analyzer
I. Device Description:
Clinical laboratories can use the Synermed IR-1200 chemistry analyzer for in vitro diagnostic testing. The analyzer consists of a carousel system for reagents and samples, an internal cooling unit, a sampling/dispensing arm assembly, an incubation assembly, and a wash station. The analyzer is controlled by software using a Windows operating system and dedicated applications software. The Synermed IR-1200 analyzer includes a heater to provide 37 degree reaction temperatures. The IR-1200 also keeps reagents cold during storage using a semiconductor. The IR-1200 chemistry analyzer measures 51in × 34in × 44 in (L×W×H) and weighs 750 lbs.
The Infrared Laboratory Systems' Synermed IR-1200 Chemistry Analyzer uses the previously-cleared Synermed Glucose Reagent kit for spectrophotometric analysis of glucose in serum. The analyzer automatically combines the sample with the reagent(s), mixes, incubates the mixture, measures the absorbance of the chromophore, and calculates the concentration of the analyte. After analysis, the cuvettes are automatically washed and dried prior to the next use.
The Synermed Glucose reagent include liquid ready to use reagents, R1 and R2. The reagent composition consists of the glucose chromogen, 280 umol/L N-sulfopropyl-N-ethyl-3,5-dimethylaniline, and the glucose reagent, 280 umol/L ampyrose, 1400 U/L peroxidase
2
{2}
(horseradish) and 18,000 U/L glucose oxidase (microbial) in the final reaction mixture. The glucose reagents were previously cleared in k903063.
# J. Substantial Equivalence Information:
1. Predicate device name(s):
Hitachi 717 Chemistry Analyzer
Synermed Glucose Test System
2. Predicate 510(k) number(s):
k872494
k903063
3. Comparison with predicate:
Analyzer:
| Similarities and Differences | | |
| --- | --- | --- |
| Item | Candidate Device: Synermed IR-1200 Chemistry Analyzer | Predicate Device: Hitachi 717 Chemistry Analyzer (k872494) |
| Intended Use | An automated clinical analyzer for in vitro diagnostic use only in clinical laboratories. | Same |
| Setting | Clinical laboratory use only | Same |
| Specimen type | Human serum | Same |
| Power | 220 VAC, 50/60 Hz | 115 VAC, 60 Hz |
| Analytical Methods | Endpoint, kinetic | Same |
| Mode of detection | Photometric | Same |
| Calibration Methods | Linear and Nonlinear calibration | Same |
| Throughput (Max) | 800 photometric tests/hour | 600 photometric tests/hour |
| Calibration/QC | Programmable Cal/ QC, will repeat automatically if out of range | Same |
| Photometer wavelength | 340-800 (12 wavelengths) | Same |
| Linear absorbance range | 0-3.3 absorbance | 0-3.2 absorbance |
| Reaction Cuvettes | Reusable PMMA (polymethylmethacrylate) | Same |
| Lightpath | 0.5 cm | 0.6 cm |
| Sample Volume | 1.5-35 μL | 1-20 μL |
| Reagent Volume | 15-350 μL | 50-350 μL |
| Reaction Volume | 120-450 μL | 250-400 μL |
{3}
Glucose reagent:
| Similarities and Differences | | |
| --- | --- | --- |
| Item | Candidate Device: Synermed Glucose Test System | Predicate Device: Synermed Glucose Test System (k903063) |
| Intended Use | For the quantitative measurement of glucose in serum | Same |
| Test Principle or Method | Glucose oxidase | Same |
| Sample Type | Serum | Serum, plasma |
| Measuring Range | 8-885 mg/dL | 0-900 mg/dL |
| Instrument use for | Synermed IR-1200 analyzer | Hitachi 717 analyzer |
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP6-A Evaluatoin of the Linearity of Quantitative Measurement Procedures: A Statistical Approach
CLSI EP07-A2 Interference Testing in Clinical Chemistry
CLSI EP09-A3 Measurement Procedure Comparison and Bias Estimation Using Patient Samples
CLSI EP10-A3-AMD Preliminary Evaluation of Quantitative Clinical Laboratory Measurement Procedures
CLSI EP15-A3 User Verifications of Precision and Estimation of Bias
CLSI EP17-A2 Evaluation of Detection Capability for Clinical Laboratory Measurement
L. Test Principle:
The glucose measurement is based on the enzymatic reaction of glucose with glucose oxidase. Glucose oxidase catalyzes the conversion of glucose to gluconolactone, which then forms gluconic acid and hydrogen peroxide. The hydrogen peroxide reacts with N-sulfopropyl-N-ethyl-3, 5-dimethylaniline and ampyrone in the presence of peroxidase to form a blue azo dye, which is quantitated at 650-660 nm.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
{4}
A precision study was conducted on the Synermed IR-1200 by measuring five levels of human serum pools for glucose (45, 120, 180, 375, and 625 mg/dL). Each sample was run in duplicate twice a day for twenty days for a total of 80 measurements for each analyte. The mean, standard deviation and coefficient of variation were determined for glucose at all control levels. Precision results are summarized in the table below.
| | Within Run Precision | | Total Precision | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL glucose) | S.D. (mg/dL) | C.V. (%) | S.D. (mg/dL) | C.V. (%) |
| 44.6 | 0.25 | 0.5% | 0.5 | 1.2% |
| 120.7 | 1.35 | 1.1% | 1.7 | 1.4% |
| 180.8 | 1.74 | 0.9% | 2.1 | 1.1% |
| 375.2 | 0.6 | 0.1% | 0.8 | 0.2% |
| 626.03 | 0.6 | 0.09% | 0.8 | 0.1% |
b. Linearity/assay reportable range:
Linearity studies for glucose were performed on the Synermed IR-1200 chemistry analyzer using eleven different levels of glucose and four replicates at each level. The measurement for the four replicates were averaged and plotted against the expected value. The samples were prepared by mixing high and low pools of human serum. The tested values in the linearity study for glucose were (in mg/dL) 6.5, 24, 33, 45, 120, 180, 275, 375, 476, 576, 672, 780, and 900. Results from the linear regression are summarized in the table below.
Linearity Results
| Measurand | Slope | Intercept | R² | Sample Range Tested | Claimed Measuring Range |
| --- | --- | --- | --- | --- | --- |
| Glucose (mg/dL) | 0.9928 | 1.3499 | 0.9999 | 6.5 – 900 | 8 – 885 |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
The Synermed Glucose Reagent is traceable to NIST 917b.
Stability claims for the SYNERMED GLUCOSE REAGENT is established in the predicate device k903063.
Calibrators:
The sponsor recommends the use of Synermed IR Cal II calibrator for the Synermed Glucose Reagent. The Synermed IR Cal II Calibrator was previously cleared in k940571.
{5}
6
d. Detection limit:
The Synermed Glucose measurement procedure was evaluated for detection limits according to CLSI document EP17-A2. The Limit of Blank (LoB) study was performed using blank pools prepared from 5 human serum samples treated with glucose oxidase. Two different pools were measured 30 times over two days on the IR-122 Chemistry Analyzer using two lots of reagent, resulting in 120 samples. LoB was determined to be 2.8 mg/dL.
The Limit of Detection (LoD) study was performed using a pool of serum samples with an expected concentration of 4.5 mg/dL. The pool of serum samples were measured 30 times in over two days on the IR-122 Chemistry Analyzer using one two lots of reagent, resulting in 120 samples in two separate studies (n=60 in each study). LoD was determined to be 3.65 mg/dL.
The Limit of Quantitation (LoQ) study was performed using a pool of 5 human serum samples containing a low concentration of glucose greater than the LoD but not greater than 4x the LoB. The serum pool was measured 30 times in over two days on the IR-122 Chemistry Analyzer using one two lots of reagent, resulting in 120 samples in two separate studies (n=60 in each study). The LoQ was determined to be 6.5 mg/dL.
The claimed measuring range of the glucose assay is 8 to 885 mg/dL.
e. Analytical specificity:
The Synermed Glucose measurement procedure was evaluated for interference according to CLSI document EP07-A2. Effects of common endogenous substances including conjugated bilirubin (0.76 and 20 mg/dL), unconjugated bilirubin (0.76 and 20 mg/dL), hemoglobin (100 and 500 mg/dL), triglycerides (176.99 and 3274.34 mg/dL) and uric acid (11.77 and 23.54 mg/dL) were evaluated at two different glucose concentrations (80 mg/dL and 120 mg/dL) for interference. Furthermore, the following exogenous substances: ascorbic acid (1.22 and 6.02 mg/dL), acetaminophen (20.11 and 200.18 µg/mL), genatmicin (7.51 and 10.05 µg/mL), ibuprofen (40.08 and 500.21 µg/mL), L-dopa (0.41 and 1.24 µg/mL), methyldopa (4.24 and 14.99 µg/mL), N-acetylcysteine (0.08 and 0.25 mg/dL), ofloxacin (8.78 and 17.5 mg/L), salicyluric acid 0.2 and 0.6 µg/mL), tetracycline (3.78 and 16.27 µg/mL) were evaluated at two different glucose concentrations (80 mg/dL and 120 mg/dL) for interference. The sponsor defined non-significant interference when the bias between the tested and control samples are within ±9.99%.
No interference was seen when testing conjugated and unconjugated bilirubin, hemoglobin, triglycerides, acetaminophen, gentamicin, ibuprofen, L-dopa, N-acetylcysteine, and tetracycline at either level of interferent concentration.
{6}
However, significant interference was observed and additional dose response study was performed to determine the level and bias of the significant interference substance. The following substances had significant interference with the assay and results for the non-significant concentration and significant concentration are summarized in the tables below.
| Interfering Substance | Highest Tested Concentration of Substance without Significant Interference at Glucose Concentration = 80 mg/dL | Highest Tested Concentration of Substance without Significant Interference at Glucose Concentration = 1200 mg/dL |
| --- | --- | --- |
| Ascorbic Acid | 4.82 mg/dL | 4.82 mg/dL |
| Methyldopa | 12.31 ug/mL | 12.31 ug/mL |
| Ofloxacin | 8.78 mg/L | 8.78 mg/L |
| Salicyluric Acid | 0.5 ug/mL | 0.6 ug/mL |
| Uric Acid | 20.6 mg/dL | 20.6 mg/dL |
| Interferent | Interferent Concentration | % Bias seen at Glucose 80mg/dL | % Bias seen at Glucose 120mg/dL |
| --- | --- | --- | --- |
| Ascorbic Acid | 6.02mg/dL | -11.7 | -13.0 |
| Methyldopa | 14.99ug/mL | -10 | -11.1 |
| Salicyluric Acid | 0.6ug/mL | -13.7 | -8.7 *not significant |
| Uric Acid | 23.54mg/dL | -10.7 | -11.5 |
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
Method comparison was performed according to CLSI EP9-A3, 115 samples for glucose were tested using the candidate device on the Synermed IR-1200 and Hitachi 717 chemistry analyzers. Some altered samples were included in this study to cover the range of the assay. The study results are summarized in the table below:
| Analyte | Units | Sample Type | Concentration Range Tested | N | Slope | Intercept | R2 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Glucose | mg/dL | Serum | 15 – 885 | 115 | 0.988 | -0.178 | 0.9994 |
{7}
b. Matrix comparison:
Not applicable.
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):
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Reference Values are provided in the labeling according to literature as follows:
Glucose: 74 – 106 mg/dL
Tietz, N.W. editor, Fundamentals of Clinical Chemistry, 6th edition, W.B. Saunders Co., Philadelphia, 2008.
N. Instrument Name:
Synermed IR-1200 Chemistry Analyzer
O. System Descriptions:
1. Modes of Operation:
Does the applicant’s device contain the ability to transmit data to a computer, webserver,
8
{8}
or mobile device?
Yes ☐ X ☐ or No ☐
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission?
Yes ☐ or No ☐ X ☐
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:
Barcode identification of patient samples.
4. Specimen Sampling and Handling:
Samples are manually placed on in the sample disk rack. Once the samples are tested, they can be manually removed.
5. Calibration:
The recommended calibrator for glucose is the IR Cal II Calibrator, previously cleared in K940571. Calibration should be performed every 30 days or if quality control material is outside of range. Assay the reference material according to the procedure used for patient samples.
6. Quality Control:
The sponsor recommends the following in their labeling: “A generally recognized Quality Control program using both high and low control material must be used.” This statement is found in the limitations, warnings and disclaimers. The sponsor recommends that the QC material be run daily with the batch runs. The sample carosel has spaces dedicated to calibration and control materials.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The “Performance Characteristics” Section above:
A carry-over study has been performed and found to be acceptable.
An operating temperature study was performed and demonstrated that the acceptable ambient
9
{9}
operating temperature is between 16 °C – 30 °C.
EMC and Electrical Safety Testing were performed and found to be acceptable.
**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.
10
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.