The Piccolo Lactate Dehydrogenase Test System (presently contained on the Chemotherapy Evaluation Panel Reagent Disc) used with the Piccolo Point-of-Care Chemistry Analyzer is intended to be used for the in vitro quantitative determination of lactate dehydrogenase activity in heparinized plasma or serum in a clinical laboratory setting or point-of-care location. Lactate dehydrogenase measurements are used in the diagnosis and treatment of liver diseases such as acute viral hepatitis and cirrhosis; cardiac diseases such as myocardial infarction; and tissue alterations of the heart, kidney, liver, and muscle.
Device Story
Piccolo Lactate Dehydrogenase Test System utilizes reagent discs containing dry reagent beads and liquid diluent; analyzer meters sample (heparinized plasma/serum) and diluent; mixes reagents; performs enzymatic rate reaction at 37°C. Analyzer monitors chemical reactions via optical detection. System provides quantitative LDH activity results (50-1,000 U/L). Used in clinical labs or point-of-care settings by healthcare professionals. Output assists clinicians in diagnosing/treating liver, cardiac, and muscle tissue conditions. Factory-calibrated via barcode on disc.
Clinical Evidence
No clinical trials were performed. Evidence consists of bench testing, including precision (n=80, total CV 2.0-5.0%), linearity (R2=0.998), and method comparison against the predicate (n=60, slope 0.989, correlation 0.994). Interference testing was conducted for endogenous substances and drugs. Reference intervals were established via regression analysis against the predicate.
Technological Characteristics
Single-use 8 cm reagent disc containing lyophilized microspheres (Lactate, NAD+, Diaphorase, INT). Enzymatic reaction monitored bichromatically at 500 nm and 630 nm at 37°C. Standalone point-of-care analyzer platform. Calibration via bar-coded lot-specific data. Complies with NCCLS standards EP9-A2, EP5-A2, EP18-A, EP6-A, EP7-A, and C28-A2.
Indications for Use
Indicated for in vitro quantitative determination of lactate dehydrogenase activity in heparinized plasma or serum for patients requiring diagnosis or treatment monitoring of liver disease, cardiac disease, or tissue alterations of heart, kidney, liver, or muscle. For prescription use only.
Regulatory Classification
Identification
A lactate dehydrogenase test system is a device intended to measure the activity of the enzyme lactate dehydrogenase in serum. Lactate dehydrogenase measurements are used in the diagnosis and treatment of liver diseases such as acute viral hepatitis, cirrhosis, and metastatic carcinoma of the liver, cardiac diseases such as myocardial infarction, and tumors of the lung or kidneys.
Special Controls
*Classification.* Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 862.9.
Predicate Devices
Lactate Dehydrogenase Synchron LX20 (k011213)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
DEVICE ONLY TEMPLATE
A. 510(k) Number:
k051108
B. Purpose for Submission:
New Device
C. Analyte:
Lactate Dehydrogenase
D. Type of Test:
Quantitative
E. Applicant:
Abaxis, Inc.
F. Proprietary and Established Names:
Piccolo® Lactate Dehydrogenase Test System
G. Regulatory Information:
1. Regulation section:
21 CFR 862.1440
2. Classification:
Class II
3. Product Code:
CFJ
4. Panel:
75 (Chemistry)
H. Intended Use:
1. Intended use(s):
See indications for use below
{1}
Page 2 of 9
2. **Indication(s) for use:**
The Piccolo Lactate Dehydrogenase Test System (presently contained on the Chemotherapy Evaluation Panel Reagent Disc) used with the Piccolo Point-of-Care Chemistry Analyzer is intended to be used for the *in vitro* quantitative determination of lactate dehydrogenase activity in heparinized plasma or serum in a clinical laboratory setting or point-of-care location.
Lactate dehydrogenase measurements are used in the diagnosis and treatment of liver diseases such as acute viral hepatitis and cirrhosis; cardiac diseases such as myocardial infarction; and tissue alterations of the heart, kidney, liver, and muscle.
3. **Special condition for use statement(s):**
For prescription use only
4. **Special instrument Requirements:**
Piccolo Point-of-Care Chemistry Analyzer
I. **Device Description:**
According to the sponsor the Piccolo Chemotherapy Evaluation Panel Reagent Disc which contains the Piccolo Lactate Dehydrogenase Test System is designed for heparinized plasma and serum use only. The disc meters the required quantity of sample and diluent, mixes the sample with the diluent, and delivers the mixture to the reaction cuvettes along the disc perimeter. The diluted sample then mixes with the reagent beads, initiating the chemical reactions that are then monitored by the analyzer. The disc is an 8 cm. diameter single-use device. Upon completion of the analysis, the disc, containing the diluted heparinized plasma or serum, is discarded.
J. **Substantial Equivalence Information:**
1. **Predicate device name(s):**
Lactate Dehydrogenase Synchron LX20
2. **Predicate K number(s):**
k011213
{2}
Page 3 of 9
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Piccolo Point-of-Care Chemistry Analyzer | Synchron LX20 Chemistry System |
| Intended Use | Quantitative analysis of Lactate Dehydrogenase | Quantitative analysis of Lactate Dehydrogenase |
| Methodology | Enzymatic | Enzymatic |
| Sample Type | Heparinized Plasma and Serum | Heparinized Plasma and Serum |
| Sensitivity | 50 U/L | 5 U/L |
| Reagents | Dry test-specific reagent beads and liquid diluent; reconstitution performed by analyzer
Active ingredients: Lactate Nicotinamide adenine dinucleotide (NAD+)
Diaphorase p-Iod Nitrotetrazolium Violet (INT) | Liquid reagents
Active ingredients: Lactate Nicotinamide adenine dinucleotide (NAD+) |
| Temperature of Reaction | 37°C | 37°C |
| Calibration | Bar code with factory calibrated lot specific data | Calibration not required |
| Assay Range | 50-1,000 U/L | 5-750 U/L (600-2,700 U/L ORDAC*) |
| Testing Environment | Professional Use | Professional Use |
| Sample Size | ~ Approximately 100 mL | 13 mL |
K. Standard/Guidance Document Referenced (if applicable):
In Vitro Diagnostic Devices: Guidance for the Preparation of 510 (k) Submissions. HHS Publication FDA 97-4224, January, 1997.
Method comparison and bias estimation using patient samples. 2nd ed. NCCLS Document EP9-A2, 2002.
Evaluation of precision performance of clinical chemistry devices. 2nd ed. NCCLS Document EP5-A2, 2004.
Quality Management for unit-use testing. NCCLS Document EP18-A, 2002.
Evaluation of the linearity of quantitative analytical methods. NCCLS Document EP6-A, 2003.
Interference testing in clinical chemistry. NCCLS Document EP7-A, 2002.
How to define and determine reference intervals in the clinical laboratory. 2nd ed. NCCLS Document C28-A2, 2000.
{3}
Page 4 of 9
L. Test Principle:
Reagents are formed into lyophilized microspheres and placed in reaction cuvettes along the periphery of the reagent disc. In the first step, L-Lactate and Nicotinamide adenine dinucleotide (NAD+) is oxidized to pyruvate and nicotinamide adenine dinucleotide (NADH) by lactate dehydrogenase. The resulting NADH is then used to reduce p-Iodo Nitrotetrazolium Violet (INT) to formazan through the catalysis of diaphorase. The highly colored formazan is measured at 500 nm and 630 nm bi chromatically and is directly proportional to the lactate dehydrogenase activity of the sample.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
According to the sponsor, precision studies were conducted using 2 levels of a commercially available human serum-based control. The controls were run in duplicate on the Chemotherapy Evaluation Reagent Disc containing Lactate Dehydrogenase. The sponsor used a total of 4 separate Piccolo Point-of-Care Chemistry Analyzers, 2 at the clinical trial site and 2 at Abaxis. Each level of control was assayed twice a day, once in the morning and once in the afternoon for 5 days for a total of 80 data points. A summary of the within-run and total precision of Lactate Dehydrogenase (LD) assayed on the Piccolo Point-of-care Chemistry Analyzer is shown in the table below.
| Lactate Dehydrogenase (U/L) | Within-Run Precision (n=80) | Total Precision (n=80) |
| --- | --- | --- |
| Control Level 1 | | |
| Mean | 87.2 | 87.2 |
| SD | 3.0 | 4.4 |
| %CV | 3.4 | 5.0 |
| Control Level 2 | | |
| Mean | 350.0 | 350.0 |
| SD | 3.8 | 7.0 |
| %CV | 1.1 | 2.0 |
b. Linearity/assay reportable range:
According to the sponsor a human serum pool containing a low concentration of LD (48 U/L) was spiked with LD to a concentration of 1,143 U/L. Dilutions of this high LD sample were made into the low LD serum pool according to NCCLS EP6-A.
{4}
Pools containing the 5 levels of LD were assayed in replicates of 4 on 4 Piccolo Point-of-Care Chemistry Analyzers. Four analyzers were used to ensure that recoveries were not instrument-specific. The results for Lactate Dehydrogenase were plotted and the graphic representation is summarized in the table below.
| Pool | Linearity Equation | R2 |
| --- | --- | --- |
| 1 | y=0.972x + 0.942 | 0.998 |
| 2 | y=1.053x - 6.766 | 0.999 |
| 3 | y=0.983x + 6.031 | 0.998 |
| 4 | y=1.040x + 1.447 | 0.998 |
| Averaged | y=1.012x + 0.253 | 0.995 |
# Summary of Linearity Results
| Slope | 1.012 |
| --- | --- |
| Intercept | +0.253 |
| Corr. Coefficient | 0.998 |
# c. Traceability (controls, calibrators, or method):
The sponsor calibrated the LD assay to match the LD assay with an internationally used commercial assay.
Stability was determined by real-time stability at 0, 1, 3, 6, 9, 12, 15, 18 and 21 months at $2 - 8^{\circ}\mathrm{C}$ . Accelerated stability testing at $25^{\circ}\mathrm{C}$ at 0, 14, 21 and 28 days and at $35^{\circ}\mathrm{C}$ at 0, 3 and 10 days. The sponsor recommends storage for the Lactate Dehydrogenase assay at $2 - 8^{\circ}\mathrm{C}$ for 6 months after manufactured disc date.
# d. Detection limit:
According to the sponsor the concentration of Lactate Dehydrogenase that could be differentiated above $0\mathrm{mg / dL}$ by the Piccolo Lactate Dehydrogenase Test system with $95\%$ confidence (twice the standard deviation was $8\mathrm{U} / \mathrm{L}$ ) Abaxis decided to take a conservative approach and use $50~\mathrm{U} / \mathrm{L}$ as the lowest reportable LD value.
{5}
Page 6 of 9
## Abaxis piccolo LD Sensitivity Data
| Assigned value | LD-free 7% Human Alb (diluent) 0.0 U/L | LD-Diluted NHS 9.9 U/L | LD Diluted NHS 12.5 U/L | LD Normal Human Serum NHS 54 U/L |
| --- | --- | --- | --- | --- |
| 1 | 1.2 | 3.5 | 9.2 | 51.2 |
| 2 | 5.3 | 4.5 | 13.8 | 54.8 |
| 3 | 7.8 | 8.6 | 6.5 | 57.1 |
| 4 | 1.7 | 14.7 | 27.41 | 54.7 |
| 5 | -4.8 | 0.8 | 8.55 | 58.5 |
| 6 | -0.7 | 6.9 | 13.5 | 58.0 |
| 7 | 0.7 | 3.6 | 5.1 | 55.8 |
| 8 | -5.2 | 6.9 | 9.4 | 55.9 |
| 9 | 4.1 | 10.3 | 8.5 | 52.5 |
| 10 | 4.7 | 13.8 | 17.6 | 56.4 |
| 11 | 1.6 | 7.3 | 9.8 | 65.7 |
| 12 | 3.3 | 10.3 | 10.9 | 56.1 |
| 13 | -3.6 | 7.0 | 11.0 | 57.2 |
| 14 | 0.7 | 8.9 | 18.0 | 67.7 |
| 15 | -7.2 | 1.2 | 10.0 | 52.9 |
| 16 | -3.0 | 3.7 | 15.5 | 53.1 |
| 17 | 6.1 | 9.4 | 12.1 | 66.6 |
| 18 | -0.3 | 16.7 | 14.5 | 56.76 |
| 19 | 1.8 | 6.3 | 10.9 | 62.5 |
| 20 | -1.6 | 8.2 | 18.0 | 56.3 |
| | | | | |
| Average | 0.6 | 7.6 | 12.5 | 57.5 |
| SD | 4.02 | 4.23 | 5.082 | 4.66 |
| N | 20 | 20 | 20 | 20 |
## Dynamic Range
Calibration of the Piccolo Lactate Dehydrogenase Test System makes use of a calibrator above 1000 U/L (the current calibrator is 1,203 U/L). The lowest calibrator has a value of 54 U/L. Based on the above sensitivity studies the sponsor used 50 U/L as the lowest reportable LD value. The dynamic range is indicated in below.
| Dynamic Range | | | |
| --- | --- | --- | --- |
| Analyte | Low | High | Unit |
| Lactate Dehydrogenase | 50 | 1,000 | U/L |
### e. Analytical specificity:
Analytical specificity was conducted according to NCCLS EP7-A, using supplemented human serum pools. Test pools with different
{6}
levels of potential interferents (endogenous and exogenous substances), and a control pool containing LD were tested by running 4 replicates on different Piccolo Point-of-Care Chemistry analyzers. The difference in mean LD concentrations between each test pool and the control pools was determined. The below chart indicates how values are displayed when elevated hemoglobin values are detected.
| Hemoglobin values | Displayed |
| --- | --- |
| 50-100 mg/dL | The LD value followed by an “H” |
| 100-150 mg/dL | “<H” followed by the LD value |
| Greater than 150 mg/dL | No LD value and “HEM” will be displayed. |
The "H" indicates influence from hemolysis. The sponsor used this annotation to help the operator interpret LD activity in the presence of small amounts of hemolysis. The endogenous interference limits are noted in the below chart.
| Hemolysis (Hemoglobin, mg/dL) | Icterus (Bilirubin, mg/dL) | Lipemia (Triglycerides, mg/dL) |
| --- | --- | --- |
| 50 | 64 | 1,720 |
Thirteen drugs were selected as potential interferents with the Lactate Dehydrogenase method based on literature recommendations and are presented in the below table.
| | Physiological or Therapeutic Range (mg/dL) | Concentration with No Significant Interference (mg/dL) |
| --- | --- | --- |
| Acetaminophen | 2-10 | 20 |
| Acetoacetate | 0.05-3.6 | 102 |
| Acetylsalicylic acid | 1-2 | 50 |
| Ascorbic acid | -- | 3 |
| Caffeine | -- | 10 |
| Ibuprofen | 0.5-4.2 | 40 |
| Lactic Acid | 4.5-19.8 | 60 |
| Lidocaine | 0.5-0.6 | 6 |
| Lithium Citrate | 0.4-0.8 | 3.5 |
| Methotrexate | 0.1 | 450 |
| Oxaloacetate | -- | 66 |
| Phenytoin (5,5-Diphenylhydantion) | 1-2 | 10 |
| Pyruvate | 0.3-0.9 | 44 |
{7}
# f. Assay cut-off:
See Detection Limit section above.
# 2. Comparison studies:
a. Method comparison with predicate device:
The sponsor conducted a method comparison study to assess the accuracy of the Abaxis Lactate Dehydrogenase method to the results obtained from the predicate Beckman Synchron LX20 Chemistry System. Paired samples were run on each analyzer for comparison. See the Method Comparison Data for Lactate Dehydrogenase Assayed on the Synchron LX20 Chemistry System and Piccolo Point-of-Care Analyzer below.
| Parameters | Statistics |
| --- | --- |
| Piccolo Lactate Dehydrogenase Test System: 60 specimens in singlicate | 60 |
| Synchron LX20: 60 specimens in singlicate | 60 |
| Piccolo Lactate Dehydrogenase Test System Mean | 306.2 U/L |
| Synchron LX20 Mean | 307.9 U/L |
| Piccolo Lactate Dehydrogenase Test System Std. Dev | 234.0 |
| Synchron LX20 Std. Dev | 236.7 |
| Piccolo Lactate Dehydrogenase Test System range of samples | 38-1126 U/L |
| Synchron LX20 range of samples | 44-1172 U/L |
| | Linear Regression | Deming Regression |
| --- | --- | --- |
| N | 60 | 60 |
| Slope | 0.983 | 0.989 |
| Intercept | 3.8 | 1.9 |
| Correlation coefficient | 0.994 | 0.994 |
| Std. Error of Estimate | 26.3 | N/A |
# b. Matrix comparison:
Matrix comparison studies were performed by the sponsor to compare heparinized plasma and serum on the Piccolo Point-of-Care Analyzer. Heparinized plasma and serum samples were collected from 10 subjects and run in replicates of 4 within 30 minutes. Serum values were found to be slightly higher than plasma, demonstrating
{8}
Page 9 of 9
an average positive bias of 6 U/L. The average LD in serum and plasma was 130.0 and 124.5 U/L, respectively.
3. Clinical studies:
a. Clinical sensitivity:
N/A
b. Clinical specificity:
N/A
c. Other clinical supportive data (when a and b are not applicable):
N/A
4. Clinical cut-off:
N/A
5. Expected values/Reference range:
The reference interval for the Piccolo Lactate Dehydrogenase Test System was determined in accordance with NCCLS C28-A2. The Sponsor used the data from the method comparison with the Synchron LX20. The plasma samples tested resulted in the Deming regression equation of
$$
\mathrm{Y} (\text{Piccolo LD}) = 0.989\mathrm{X} (\text{Synchron LX20 LD}) + 1.9
$$
Synchron LX20 LD has a reference interval published for plasma or serum of 98-192. The calculated reference interval for the LD assay was determined to be 99-192 mg/dL.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. 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.