DPC T60I KUSTI, MODEL 984248; DPC T60I, MODEL 984247
K061107 · Thermo Electron OY · CEM · Aug 8, 2006 · Clinical Chemistry
Device Facts
Record ID
K061107
Device Name
DPC T60I KUSTI, MODEL 984248; DPC T60I, MODEL 984247
Applicant
Thermo Electron OY
Product Code
CEM · Clinical Chemistry
Decision Date
Aug 8, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1600
Device Class
Class 2
Attributes
Pediatric
Indications for Use
The DPC T60i and DPC T60i Kusti Clinical Chemistry Analyzers are fully automated random access analyzers for in-vitro diagnostic use with clinical laboratory assays validated for use on these instrument platforms, including an ISE unit with Na+, K+ and CI- electrodes. The DPC T60 Glucose (HK) test system with associated Calibrators and Controls is intended for quantitative in-vitro diagnostic determination of glucose in serum or plasma using the DPC T60i and DPC T60i Kusti Clinical Chemistry Analyzers. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoqlycemia, and of pancreatic islet cell carcinoma. The DPC ISE Micro Volume Chloride, Potassium and Sodium Electrodes with associated Calibrators are intended for quantitative in-vitro diagnostic determination of Chloride, Potassium and Sodium in serum or plasma using the DPC T60i and DPC T60i Kusti Clinical Chemistry Analyzers. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders. Potassium measurements monitor electrolyte balance and in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels. Sodium measurements are used in the diagnosis and treatment diseases involving electrolyte imbalance.
Device Story
Fully automated random access clinical chemistry analyzer; performs photometric and direct potentiometric (ISE) assays. Inputs: serum, plasma, urine, or CSF samples; reagents. Operation: manual sample disk loading or automated KUSTI routing; samples dispensed into disposable multicell cuvettes; reaction measurements at 37°C. Outputs: quantitative analyte concentrations. Used in clinical laboratories by professionals. Data processed via Windows XP-based graphical interface; supports online, touch screen, mouse, or keyboard input. Output used by clinicians to diagnose/monitor metabolic and electrolyte disorders. Benefits: automated high-throughput testing; reduced manual handling; standardized diagnostic results.
Clinical Evidence
No clinical data provided; substantial equivalence based on bench testing and performance validation of the analytical system.
Technological Characteristics
Fully automated random-access clinical chemistry analyzer. Features ISE unit for Na+, K+, and Cl- measurement. Photometric detection for glucose (HK) assay. System is designed for in-vitro diagnostic use in clinical laboratories.
Indications for Use
Indicated for in-vitro diagnostic quantitative determination of glucose, chloride, potassium, and sodium in human serum or plasma. Used for diagnosis and treatment of carbohydrate metabolism disorders (diabetes, hypoglycemia, pancreatic islet cell carcinoma) and electrolyte/metabolic disorders.
Regulatory Classification
Identification
A potassium test system is a device intended to measure potassium in serum, plasma, and urine. Measurements obtained by this device are used to monitor electrolyte balance in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels.
Submission Summary (Full Text)
{0}
1 of 9
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k061107
B. Purpose for Submission:
New 510(k)
C. Measurand:
Glucose, Sodium, Potassium, Chloride
D. Type of Test:
Quantitative Glucose hexokinase (Glucose)
Quantitative Ion Selective Electrodes (Na⁺, K⁺, Cl⁻)
E. Applicant:
Thermo Electron Oy
F. Proprietary and Established Names:
DPC T60i KUSTI, Model 984248; Dpc T60i, Model 984247
G. Regulatory Information:
1. Regulation section:
21 CFR § 862.1345 Glucose test system. II
21 CFR § 862.1170 Chloride test system. II
21 CFR § 862.1600 Potassium test system. II
21 CFR § 862.1665 Sodium test system. II
21 CFR § 862.1150 Calibrator. II
21 CFR § 862.1660 Quality control material (assayed and unassayed). I, reserved
21 CFR § 862.2160 Discrete Photometric Chemistry Analyzer for Clinical Use
2. Classification:
See regulation section above
3. Product code:
CFR Hexokinase, Glucose
CGZ Electrode, Ion-Specific, Chloride
CEM Electrode, Ion Specific, Potassium
JGS Electrode, Ion Specific, Sodium
JIX Calibrator, Multi-Analyte Mixture
JJY Multi-Analyte Controls, All Kinds (Assayed And Unassayed)
JJE Analyzer, Chemistry (Photometric, Discrete), For Clinical Use
4. Panel:
Chemistry (75)
H. Intended Use:
1. Intended use(s):
See indications for use below
2. Indication(s) for use:
The DPC T60i and DPC T60i KUSTI Clinical Chemistry Analyzers are fully automated random access analyzers for in-vitro diagnostic use with clinical laboratory assays validated for use on these instrument platforms, including an
{1}
ISE unit with Na⁺, K⁺ and Cl⁻ electrodes.
The DPC T60 Glucose (HK) test system with associated Calibrators and Controls is intended for quantitative in-vitro diagnostic determination of glucose in serum or plasma using the DPC T60i and DPC T60i KUSTI Clinical Chemistry Analyzers. 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.
The DPC ISE Micro Volume Chloride, Potassium and Sodium Electrodes with associated Calibrators are intended for quantitative in-vitro diagnostic determination of Chloride, Potassium and Sodium in serum or plasma using the DPC T60i and DPC T60i KUSTI Clinical Chemistry Analyzers.
Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders.
Potassium measurements monitor electrolyte balance and in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels.
Sodium measurements are used in the diagnosis and treatment diseases involving electrolyte imbalance.
3. Special conditions for use statement(s):
Prescription use
4. Special instrument requirements:
DPC T60i and DPC T60i KUSTI Clinical Chemistry Analyzers
I. Device Description:
The DPC T60i is a random access discrete photometric and direct potentiometric analyzer, capable of performing 45 photometric tests and up to 5 potentiometric tests on 90 samples at a time.
The analyzer has the option for 2 sample modes; a manual load on sample disk and an automated load (KUSTI). The manual mode is where sample tubes and/or cups are manually loaded into a sample disk. The sample disk has an integrated barcode reader which allows cup/tube recognition. The barcode reader can read the following codes: code 128, code 39, USS Codabar, interleaved 2 of 5. The KUSTI option mode is where samples are automatically routed to bypass the sample module and are dispensed to a disposable KUSTI segment in the analyzer. Both samples types are dispensed by the same ISE dispenser and photometric dispenser.
Reaction cells are discrete disposable (single use) multicell cuvettes with 12 reaction measurement cells in a row. On-board capacity of 175 multicell cuvettes (equal to 2100 reaction cells), with continuous loading capability, typically 4 hours run time.
2 of 9
{2}
The quality of the reaction cells is checked at the start of the routine work automatically. The measurements are performed at 37°C.
Reagents are liquid. The reagents bottles are placed on the reagent disk, which holds 45 positions. The reagent disk is cooled to 4 - 8°C.
The operating system works with Windows ® XP. The user interface software is graphical. The data input can be done online or by touch screen or mouse or keyboard.
## Methods:
The Glucose (HK) test system uses two reagents. Reagent A (buffer) contains 100 mmol/l Tris buffer (pH7.8) 2.1 mmol/l ATP, 2.1 mmol/l NAD, 4 mmol/l Mg²⁺ and <0.1% NaN₃. Reagent B (Enzyme) contains 4 mmol/l Mg²⁺, >7.5 kU/L Hexokinase, >7.5 kU/L G-6-P-DH and <0.1% NaN₃.
The Sodium, Potassium, and Chloride Micro Volume Electrode test system is comprised of ion selective electrodes for each ion Na, K, and Cl and a reference electrode.
sCal calibrator is intended for in vitro diagnostic use on T60 analyzer as a multicalibrator for quantitative measurements using methods defined by Thermo Electron Oy.
Nortrol and Abtrol Multi-analyte Controls, are intended for in vitro diagnostic use for quantitative testing on T60 analyzer. Nortrol is a control serum to monitor trueness and precision of the analytes listed in the separate Nortrol value sheet. The given values are valid for T60 Clinical Chemistry Analyzers using methods defined by Thermo Electron Oy. Abtrol is a control serum to monitor trueness and precision of the analytes listed in the separate Abtrol value sheet. The given values are valid for T60 Clinical Chemistry Analyzers using methods defined by Thermo Electron Oy.
The ISE Calibrator 1 and 2&3 are intended for calibration of ion selective electrodes for quantitative measurements of potassium, sodium and chloride in human serum or plasma.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Bayer Corporation, model Bayer ADVIA 1650 Chemistry System
Bayer Corporation items:
- Bayer Advia 1650 Chemistry System Glucose
- Bayer Advia 1650 Chemistry System Chloride (Cl)
- Bayer Advia 1650 Chemistry System Potassium (K)
- Bayer Advia 1650 Chemistry System Sodium (Na)
- Bayer Advia 1650 Chemistry System Calibrators and Control
3 of 9
{3}
2. Predicate 510(k) number(s): k991576, k042015, k991575
3. Comparison with predicate:
Similarities
| Attribute | Device | Predicate |
| --- | --- | --- |
| Reagents | Same | Same |
| Analyzer | | |
| • Discrete Photometric Analyzer | Same | Same |
| • Software Driven | Same | Same |
| • For clinical laboratory professionals | Same | Same |
| • Automated dilutions | Same | Same |
| • Sample reruns | Same | Same |
Differences
| Attribute | Device | Predicate |
| --- | --- | --- |
| Reagents Testing Process | | |
| • Clot detection | No | Yes |
| • ISE testing | Direct | Indirect |
| Analyzer | DPC T60i KUSTI | Bayer ADVIA 1650 Chemistry System |
# K. Standard/Guidance Document Referenced (if applicable):
CLSI - Evaluation of Precision Performance of Clinical Chemistry Devices - EP05-A2
CLSI - Evaluation of the Linearity of Quantitative Analytical Methods - EP06-A
CLSI - Interference Testing in Clinical Chemistry - EP07-A2
CLSI - Method Comparison and Bias Estimation Using Patient Samples - EP09-A2
# L. Test Principle:
Glucose Hexokinase method
Sodium, Potassium and Chloride Electrolyte measurements are performed directly with ion selective electrodes.
# M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Precision was performed using CLSI (former NCCLS) Document EP5-A2 as a guideline. The results are presented below.
| | Assay | Mean | Total | | Between run | | Within run | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | CV (%) | SD | CV (%) | SD | CV (%) |
| I | Gluc(HK) | 77 mg/dl | 1.2 | 1.5 | 0.5 | 0.7 | 0.4 | 0.5 |
| II | Gluc(HK) | 265 mg/dl | 3.5 | 1.3 | 1.2 | 0.5 | 1.4 | 0.5 |
{4}
5 of 9
| I | ISE Cl⁻ | 80.3 mmol/l | 1.14 | 1.4 | 0.35 | 0.4 | 0.35 | 0.4 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| II | ISE Cl⁻ | 109.9 mmol/l | 0.83 | 0.8 | 0.33 | 0.3 | 0.35 | 0.3 |
| I | ISE K⁺ | 4.4 mmol/l | 0.05 | 1.2 | 0.03 | 0.6 | 0.02 | 0.4 |
| II | ISE K⁺ | 5.9 mmol/l | 0.08 | 1.3 | 0.03 | 0.4 | 0.03 | 0.5 |
| I | ISE Na⁺ | 128 mmol/l | 1.0 | 0.7 | 0.4 | 0.3 | 0.3 | 0.3 |
| II | ISE Na⁺ | 145 mmol/l | 0.9 | 0.6 | 0.2 | 0.2 | 0.3 | 0.2 |
b. Linearity/assay reportable range:
Linearity studies were performed using CLSI EP6-A as a guideline.
Glucose – measuring range is 5-720 mg/dl based on a dilution series with-in the claimed range. The assay recovered +/- 3mg/ml or +/- 5% from expected values.
Potassium – measuring range is 2.0-10.0 mmol/l based on a dilution series with-in the claimed range. The assay recovered +/- 0.25 mmol/l from expected values.
Sodium – measuring range is 100-200 mmol/l based on a dilution series within the claimed range. The assay recovered +/- 2.0 mmol/l or +/- 2.5% from expected values.
Chloride – measuring range is 55-150 mmol/l based on a dilution series within the claimed range. The assay recovered +/- 2.0 mmol/l or +/- 2.5% from expected values.
c. Traceability, Stability, Expected values (controls, calibrators, or methods): sCal target values are determined using assay specific methods on the DPC T60 and other Thermo analyzer models. The target value is the median of all values obtained and traceable to a reference material. Glucose is traceable to NIST SRM 965.
Stability studies have been performed:
Open vial at 2-8 C 7 days
Shelf life 2-8 C 3 years
The target values of the Nortrol and Abtrol are control solutions are determined using assay specific methods on the DPC T60 and other Thermo analyzer models (calibrated by the sCal calibrator). The target value is the median of all values obtained.
Stability studies have been performed:
Open vial at 2-8 C 7 days
Reconstituted and -20 C 30 days
The ISE Calibrator are gravimetrically prepared using purity grade chemicals and purified laboratory water. The levels of the ISE calibrators are verified to
{5}
an in house reference. Value for sodium and chloride are traceable to NIST 919 and values for potassium are traceable to NIST 918.
Real time studies are used to determine shelf life and onboard stability.
Shelf life 2-30 C 20 months
Onboard 2-30 C 18 weeks
d. Detection limit:
Glucose Analytical sensitivity 2.0 mg/dl determined by 24 replicates of saline in a single run and calculated as 3 SD above the average concentration. The claimed lower limit of the measuring range is 5.0 mg/dl.
For the electrolytes lower limit of linearity, see linearity section above.
e. Analytical specificity:
Interference studies were performed using CLSI EP7-A as a guideline.
Glucose:
Bilirubin (conjugated): No interference found up to 58 mg/dl
Hemolysate: No interference found up to 1000 mg/dl
Lipemia: No interference found up to 1000 mg/dl
Potassium:
Bilirubin (conjugated): No interference found up to 43 mg/dl
Hemolysate: do not use hemolyzed specimens
Lipemia: No interference found up to 1000 mg/dl
Sodium:
Bilirubin (conjugated): No interference found up to 43 mg/dl
Hemolysate: No interference found up to 1000 mg/dl
Lipemia: No interference found up to 1000 mg/dl
Chloride:
Bilirubin (conjugated): No interference found up to 43 mg/dl
Hemolysate: No interference found up to 800 mg/dl
Lipemia: No interference found up to 1000 mg/dl
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
The method comparison was performed using CLSI (former NCCLS) EP9-A2 as a guideline. The results compared to the Bayer Advia 1650 are presented below.
6 of 9
{6}
| Analyte | N | Slope | Intercept | R | Sample Range |
| --- | --- | --- | --- | --- | --- |
| Gluc(HK) | 127 | 1.00 | -1 | 1.00 | 11 - 688 mg/dl |
| ISE Cl | 115 | 0.95 | 2.8 | 0.981 | 80.6 - 165.2 mmol/l |
| ISE K | 121 | 1.01 | -0.1 | 0.998 | 2.1 - 9.9 mmol/l |
| ISE Na | 115 | 0.95 | 8 | 0.986 | 125-196 mmol/l |
The results comparing the manual load and the KUSTI sampling systems are presented below.
| Analyte | N | Slope | Intercept | R | Sample Range |
| --- | --- | --- | --- | --- | --- |
| Gluc(HK) | 105 | 0.99 | 1.0 | 1.00 | 30 - 416 mg/dl |
| ISE Cl | 114 | 0.98 | 1.5 | 0.979 | 78.9-122.2 mmol/l |
| ISE K | 113 | 0.98 | 0.04 | 0.997 | 2.7-6.9 mmol/l |
| ISE Na | 113 | 0.99 | 0.7 | 0.989 | 125-163 mmol/l |
## b. Matrix comparison:
Protocol (Glucose (HK): Both serum and plasma samples were used in the Method comparison study (DPC T60i vs. Bayer ADVIA (predicate device)). For sample type comparison lithium heparin plasma sample results were analyzed separately.
Protocol (Potassium Micro Volume Electrode): The use of lithium heparin plasma samples was evaluated by a method comparison study with lithium heparin plasma samples measured on a DPC T60i and a Bayer ADVIA (predicate device).
Protocol (Sodium Micro Volume Electrode, Chloride Micro Volume Electrode): The use of lithium heparin plasma samples was evaluated by a comparison study between serum samples and matched lithium heparin plasma samples (samples from Thermo personnel below) and by a comparison study with lithium heparin plasma samples measured on a DPC T60i and a Bayer ADVIA (predicate device)
DPC T60i KUSTI GLUCOSE (HK)
Method comparison study using lithium heparin samples
$$
y = 1.001x - 0.995
$$
$$
r = 1.000
$$
Range 30.8 mg/dl – 416.21 mg/dl
$$
N = 45
$$
DPC T60i KUSTI POTASSIUM MICRO VOLUME ELECTRODE
Method comparison study using lithium heparin samples
$$
y = 0.951x + 0.078
$$
$$
r = 0.992
$$
$$
N = 69
$$
{7}
Range 3.44 mmol/l – 6.29 mmol/l
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: Expect values are based on literature
N. Instrument Name: DPC T60i and DPC T60i KUSTI Clinical Chemistry Analyzers
O. System Descriptions:
1. Modes of Operation: Random access or batch operation modes are available.
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: Bar code, or manually entered
4. Specimen Sampling and Handling: Samples can be manually loaded into sample disk for direct sampling from specimen tube or sample cup, or can be automatically routed to KUSTI dispenser to be dispensed in onboard KUSTI segment sample holder. Both methods of sample loading are introduced to the same analytical dispensers.
- Max On-Board capacity: 6 segments (with 14 positions in each), 6 additional positions for STAT samples.
- Integrated barcode reader and cup/tube recognition.
- Optional sample transport interface (KUSTI). Sample cups and tubes: 0.5 ml and 2.0 ml cups, 5 ml and 7 ml tubes, 10 ml tubes with tailored segments.
- Sample types: Serum, plasma, urine, CSF.
- Sample volumes: Possible range 1-120 μl; typically 2-15 μl. For Na+, K+ and Cl- tests 50 μl.
Reagent Tray
- Reagents are placed into wedge shaped vials On-Board Storage: Continuous loading 45 positions in the 4-8 °C refrigerated reagent compartment.
- Reagent volumes: 2-250 μl; typically 120 - 200 μl. Up to four reagent
8 of 9
{8}
additions / test possible.
5. Calibration:
- Linear, non-linear or bias calibration.
- Calibration with separate calibrators or with automatically diluted series from a stock calibrator.
- Automatically repeated bias correction possibility.
- 20 positions for calibrator samples in the cooled area of the sample disk. It is also possible to load them into segments.
6. Quality Control:
- Real time QC with multiple and variable (Westgard) rules.
- Programmable control interval.
- 19 positions for control samples in the cooled area of the sample disk.
- Also possible to load them into segments. QC chart printouts, daily and cumulative reports.
- Programmable control interval
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Software documentation provided demonstrates the DPC T60i/ DPC T60i Kusti Analyzer was designed and manufactured under well developed software lifecycle processes.
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.
9 of 9
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.