Retrospective clinical serum samples were used to perform method comparison studies (Deming regression) to demonstrate substantial equivalence between the candidate device and the predicate device.
Correlation coefficient (r), slope, and intercept via Deming regression
Indications for Use
Diatron Glucose Hexokinase Method is for the in vitro quantitative determination of Glucose in serum for use with Diatron Pictus 700 Chemistry Analyzer. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes. Diatron ISE is for the in vitro quantitative determination of Sodium (Na+), and Chloride (Cl-) concentrations in serum on the Diatron Pictus 700 Chemistry Analyzer. Sodium measurements are used in the diagnosis and treatment of diseases involving electrolyte imbalance. Potassium measurements are used in monitoring electrolyte balance and in the diagnosis and treatment of diseases/conditions characterized by low or high blood potassium levels. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders. The Diatron Pictus 700 Clinical Chemistry Analyzer is a wet-chemistry analyzer for the direct determination of sodium, potassium, chloride and glucose concentrations in serum, and to measure a variety of analytes that may be adaptable to the analyzer depending on the reagent used. It is for in vitro diagnostic use.
Device Story
Floor-standing, automated wet-chemistry analyzer for clinical laboratories. Inputs: serum samples in barcoded tubes/cups and reagent cartridges. Operation: operator programs test requests; analyzer pipettes samples/reagents into temperature-controlled incubation rotors; performs photometric analysis (glucose) or ion-selective electrode (ISE) potentiometry (Na+, K+, Cl-). ISE module uses flow-through electrodes with selective membranes; potential measured relative to double-junction Ag/AgCl reference electrode. Glucose measured via hexokinase enzymatic reaction; NADH production monitored bichromatically (340/380 nm). Output: analyte concentrations displayed on operations computer. Healthcare providers use results for diagnosis/treatment of metabolic and electrolyte disorders.
Clinical Evidence
No clinical studies were performed. Evidence consists of bench testing, including precision (within-run and total), linearity, limit of quantitation, analytical specificity (interference), and method comparison against the predicate device. Method comparison (N=69-136) showed high correlation (R² 0.99-1.00) and slope/intercept values consistent with the predicate. Precision studies (N=80) demonstrated total CVs ranging from 0.8% to 3.2% across analytes.
Technological Characteristics
Floor-standing wet-chemistry analyzer. Photometric detection (photodiode, 12 filters, 340-750 nm) and ISE potentiometry. Reagent volume 180-700 µL. Connectivity: operations computer with screen. Software-controlled automated pipetting, mixing, and incubation. Analyte ranges: Glucose 13-500 mg/dL; Na 115-196 mmol/L; K 1.1-8.8 mmol/L; Cl 49-152 mmol/L.
Indications for Use
Indicated for in vitro quantitative determination of glucose, sodium, potassium, and chloride in human serum. Used in clinical laboratories for diagnosis and treatment of carbohydrate metabolism disorders (e.g., diabetes) and electrolyte/metabolic disorders.
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.
Predicate Devices
Diatron Pictus 400 (k101741)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k151487
B. Purpose for Submission:
Adding previously cleared assays on new instrument platform
C. Measurand:
Sodium, Potassium, Chloride and Glucose
D. Type of Test:
Quantitative, Photometric and Ion Selective Electrodes
E. Applicant:
Diatron, US, Inc.
F. Proprietary and Established Names:
Diatron Pictus 700 Clinical Chemistry Analyzer
Diatron Glucose Hexokinase Method
Diatron ISE
G. Regulatory Information:
| Product Code | Regulation Name | Classification | Regulation Section | Panel |
| --- | --- | --- | --- | --- |
| JGS | Sodium test system | II | 21 CFR 862.1665 | Chemistry (75) |
| CEM | Potassium test system | II | 21 CFR 862.1600 | Chemistry (75) |
| CGZ | Chloride test system | II | 21 CFR 862.1170 | Chemistry (75) |
| CFR | Glucose test system | II | 21 CFR 862.1345 | Chemistry (75) |
{1}
2
| JJE | Discrete photometric chemistry analyzer for clinical use | I, exempt | 21 CFR 862.2160 | Chemistry (75) |
| --- | --- | --- | --- | --- |
## H. Intended Use:
1. Intended use(s):
See Indications for Use
2. Indication(s) for use:
Diatron Glucose Hexokinase Method is for the in vitro quantitative determination of Glucose in serum for use with Diatron Pictus 700 Chemistry Analyzer. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes.
Diatron ISE is for the in vitro quantitative determination of Sodium (Na+), Potassium (K+), and Chloride (Cl-) concentrations in serum on the Diatron Pictus 700 Chemistry Analyzer. Sodium measurements are used in the diagnosis and treatment of diseases involving electrolyte imbalance. Potassium measurements are used in monitoring electrolyte balance and in the diagnosis and treatment of diseases/conditions characterized by low or high blood potassium levels. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders.
The Diatron Pictus 700 Clinical Chemistry Analyzer is a wet-chemistry analyzer for the direct determination of sodium, potassium, chloride and glucose concentrations in serum, and to measure a variety of analytes that may be adaptable to the analyzer depending on the reagent used. It is for in vitro diagnostic use.
3. Special conditions for use statement(s):
Prescription use only
4. Special instrument requirements:
Diatron Pictus 700 Clinical Chemistry Analyzer
## I. Device Description:
The Pictus 700 Clinical Chemistry Analyzer is an automated bench top, random access, open analyzer for clinical chemistry analysis on human serum, including an ISE module. The analyzer uses colorimetric and ion selective electrode methods for analysis of samples.
{2}
The instrument consists of an analyzer unit and an operations computer with a screen that allows the user to input commands for system operation and data display. The analyzer unit includes two temperature-controlled incubation rotors and a multi-wavelength photometer, a cooled carousel for loading barcoded sample tubes or micro cups and reagent cartridges, and two probes that deliver reagents and samples to the incubation rotors and the ISE measurement flow cell. The analyzer unit also houses containers for wash solution and waste. An ISE module, installed on the analyzer unit, is used to measure sodium, potassium and chloride ionic activity in serum.
The Diatron Glucose Hexokinase Method reagent is provided ready to use, and consists of the following active ingredients in a solution of nonreactive stabilizers, fillers, and buffers: ATP (2.1 mM), NAD 2.5 mM, Hexokinase (yeast, >1500 U/L), G-6-PDH (L.m., >3200 U/L), at pH (7.22 - 7.42). The Diatron Glucose Hexokinase Method reagent was previously cleared in k011900.
Diatron ISE includes sodium, potassium, chloride ion selective electrodes and ISE calibrators. The Diatron ISE calibrators consist of the following solutions: Calibrant A Solution (Na+ 140 mmol/L, K+ 4.0 mmol/L, Cl- 125 mmol/L) and Calibrant B Solution (Na+ 70 mmol/L, K+ 8.0 mmol/L, Cl- 41 mmol/L). Diatron ISE has been previously cleared in k070057.
# J. Substantial Equivalence Information:
1. Predicate device name(s):
Diatron Pictus 400, including glucose and ISE assays
2. Predicate 510(k) number(s):
k101741
3. Comparison with predicate:
Similarities and differences
| Characteristic | Candidate System Diatron Pictus 700 Analyzer | Predicate System Pictus 400, k101741 |
| --- | --- | --- |
| Intended Use | Quantitative determinations of sodium, potassium, and chloride using ion selective electrodes, and glucose by photometry in serum. | Same |
| Testing Environment | Clinical lab | Same |
| Test Principle | ISE potentiometry (electrolytes) and photometry (glucose) | Same |
{3}
| Analytical Methods | Endpoint with sample blanking | Endpoint and Kinetic with sample blanking |
| --- | --- | --- |
| Calibration | Linear and non linear | Same |
| Optical measurement unit Measurement modes | Absorbance | Same |
| Optical modes | Bichromatic, | Bichromatic, turbidimetric |
| Light source | Tungsten halogen | Same |
| Detector | Photodiode | Same |
| Wavelengths | 340, 380, 405, 450, 490, 505, 550, 590, 620, 650, 700, 750 | 330, 405, 450, 505, 550, 570, 600, 650, 700 |
| Linear Absorbance Range | -0.1 to 3.6 A. | Same |
| Photometric Tests/Hour | 450 tests/hour double reagent, 550 tests/tour mono reagent, 720 with ISE | 280 test/hour 400 with ISE |
| Reaction cuvettes | Plastic semi-disposables | Same |
| Path length | 6 mm | Same |
| Reaction Volume Range | 180 to 700 microliters | Same |
| Incubator | Room, 30°C, 37°C | Same |
| Reagents On-board Capacity | 72 | 48 |
| Sample On-board Capacity | 95 | 48 |
| Pipettor system | Syringe, motor driven | Same |
| Mixing | Motor in probe, tray shake | Same |
| Reagent refrigerator | Yes | Same |
| Sample dispensing | 2 - 100 microliters in 0.2 microliter increments | 2 - 50 microliters |
| QC/Calibration | Automatic and Manual | Same |
| LIS external connectivity | Yes | Same |
{4}
| Barcode | Samples and Reagents | Same |
| --- | --- | --- |
| Re-dilution on abnormals | Yes | Same |
| Specimen Type | Human serum | Human serum and plasma |
| Power | 110/220V, 50/60 Hz, 2000 VA | 85/230 V, 400 VA |
| Environmental conditions | 20 to 30 °C, max Hum. 80% | 15 to 30 °C, max Hum. 80% |
| ISE Principle | Ion selective, direct reading | Same |
| ISE sample type | Serum | Same |
| ISE Available tests | Na, K, Cl | Same |
| ISE calibration | Two-point and single point | Same |
| ISE Sample size | 70 ul | Same |
# K. Standard/Guidance Document Referenced (if applicable):
CLSI - EP05-A2. Evaluation of precision performance of Clinical Chemistry Devices.
CLSI - EP06-A. Evaluation of linearity of Quantitative analytical methods.
CLSI - EP07-A2. Interference testing in Clinical Chemistry
CLSI - EP17-A Protocols for the determination of Limits of Quantitation
# L. Test Principle:
The Glucose (Hexokinase) method is based on a modification of Slein, using Hexokinase and glucose-6-phosphate-dehydrogenase to catalyze the reaction. Glucose is phosphorylated with adenosine triphosphate (ATP) in the reaction catalyzed by Hexokinase (HK). The product, glucose-6-phosphate (G6P) is then oxidized with the concomitant reduction of nicotinamide adenine dinucleotide (NAD) to NADH in the reaction catalyzed by glucose-6-phosphatedehygrogenase (G6PDH). The formation of NADH caused an increasing in absorbance at $340\mathrm{nm}$ . The increase is proportional to the amount of glucose in the sample.
The ISE method uses ion selective principles to measure the sodium, potassium, and chloride. The ISE module measures the potentials developed when the sample is positioned in the electrodes. Next, Calibrant A is positioned in the electrodes. The difference in the two
{5}
potentials is related logarithmically to the concentration of the measured ions in the sample divided by their respective concentrations in the Calibrant solution.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision studies were performed according to CLSI document EP5-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline. Three levels of serum based controls were tested on the Pictus 700 Clinical Chemistry Analyzer for each analyte in one run of 20 replicates to obtain the within run precision (N=20). Three levels of serum based controls were tested in duplicate twice per day for 20 days to obtain the total precision (N=80). Results are summarized in the tables below:
Glucose
| | | Within Run | | Total Precision | |
| --- | --- | --- | --- | --- | --- |
| Level | Mean (mg/dL) | S.D. (mg/dL) | C.V. (%) | S.D. (mg/dL) | C.V. (%) |
| 1 | 43.8 | 0.70 | 1.59 | 1.5 | 3.2 |
| 2 | 89.2 | 0.81 | 0.91 | 2.8 | 3.0 |
| 3 | 295.1 | 3.52 | 1.19 | 9.5 | 3.1 |
Sodium
| | | Within Run | | Total Precision | |
| --- | --- | --- | --- | --- | --- |
| Level | Mean (mmol/L) | S.D. (mmol/L) | C.V. (%) | S.D. (mmol/L) | C.V. (%) |
| 1 | 127.1 | 0.60 | 0.48 | 1.1 | 0.9 |
| 2 | 141.8 | 0.55 | 0.39 | 2.0 | 1.4 |
| 3 | 158.9 | 0.81 | 0.51 | 1.6 | 1.0 |
Potassium
| | | Within Run | | Total Precision | |
| --- | --- | --- | --- | --- | --- |
| Level | Mean (mmol/L) | S.D. (mmol/L) | C.V. (%) | S.D. (mmol/L) | C.V. (%) |
| 1 | 3.40 | 0.00 | 0.00 | 0.04 | 1.1 |
| 2 | 4.50 | 0.00 | 0.00 | 0.07 | 1.7 |
| 3 | 5.73 | 0.04 | 0.78 | 0.08 | 1.4 |
{6}
Chloride
| | | Within Run | | Total Precision | |
| --- | --- | --- | --- | --- | --- |
| Level | Mean (mmol/L) | S.D. (mmol/L) | C.V. (%) | S.D. (mmol/L) | C.V. (%) |
| 1 | 87.0 | 0.56 | 0.65 | 0.8 | 0.9 |
| 2 | 97.6 | 0.50 | 0.51 | 1.2 | 1.2 |
| 3 | 108.5 | 0.51 | 0.47 | 0.8 | 0.8 |
b. Linearity/assay reportable range:
Linearity studies were performed on the Pictus 700 Clinical Chemistry Analyzer using serum albumin-based samples. At least nine levels of linearity standards were analyzed in quadruplicate. The observed values were compared to the expected values and the results of linear regression are summarized in the table below:
| Analyte | Claimed Measuring Range | N | Slope | Intercept | R2 | Sample Range Tested |
| --- | --- | --- | --- | --- | --- | --- |
| Glucose | 13 – 500 mg/dL | 9 | 0.97 | 2.2 | 1.0 | 13 – 622 mg/dL |
| Sodium | 115 – 196 mmol/L | 11 | 1.02 | 1.5 | 1.0 | 89 - 203 mmol/L |
| Potassium | 1.1 – 8.8 mmol/L | 9 | 0.98 | 0.0 | 1.0 | 0.9 – 12.6 mmol/L |
| Chloride | 49 – 152 mmol/L | 11 | 1.01 | -0.2 | 1.0 | 41 – 200 mmol/L |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The glucose calibrator material is traceable to NIST SRM #917b, Clinical Dextrose. The ISE calibration material is traceable to commercially-available, $99.9\%$ ACS grade materials. The glucose calibrator material was previously cleared under k020454. The ISE calibrator material for sodium, potassium and chloride (Calibrant A and B) was previously cleared under k070057.
d. Detection limit:
# Glucose:
The Level of Blank (LoB) study was performed using a glucose-depleted serum sample, run 30 times per day over three days on the Pictus 700 Clinical Chemistry Analyzer resulting in a LoB of $0\mathrm{mg / dL}$ .
The Limit of Detection (LoD) was determined to be $0.4\mathrm{mg / dL}$ using low analyte sample run 30 times/day over three days. Following CLSI EP17-A, the Limit of Quantitation (LoQ) was determined to be $7.0\mathrm{mg / dL}$ .
{7}
8
| | LoB | LoD | LoQ | Claimed measuring range |
| --- | --- | --- | --- | --- |
| Glucose | 0.0 mg/dL | 0.4 mg/dL | 7.0 mg/dL | 13 to 500 mg/dL |
Sodium, Potassium and Chloride:
Linearity studies were used to support the measuring ranges for Sodium, Potassium and Chloride. Please see M.1.b. linearity section above.
The sponsor's claimed measuring range:
| Analyte | Claimed Measuring Range |
| --- | --- |
| Sodium | 115 – 196 mmol/L |
| Potassium | 1.1 – 8.8 mmol/L |
| Chloride | 49 – 152 mmol/L |
e. Analytical specificity:
Interference studies were performed to determine the effects from potential interferents on the Glucose and the ISE assays. Various concentrations of potential interferents were spiked into two levels, (low and high concentrations) of each analyte. Testing was performed in duplicate on the Pictus 700 Clinical Chemistry Analyzer. Six levels of each interferent were tested for each analyte. The sponsor states that interference is considered to be non-significant if the bias between the tested and control samples are within +/-10%. The highest concentration tested that shows non-significant interference are summarized below:
| Reagent | Hemoglobin | Triglycerides | Bilirubin |
| --- | --- | --- | --- |
| Glucose | 600 mg/dL | 700 mg/dL | 12 mg/dL |
| Sodium | 600 mg/dL | 2500 mg/dL | 24 mg/dL |
| Potassium | * | 2500 mg/dL | 24 mg/dL |
| Chloride | 600 mg/dL | 2500 mg/dL | 24 mg/dL |
*Do not use hemolyzed samples
The labeling for the ISE Reagent Pack includes the statement:
"Hemolyzed samples should not be used with sodium, potassium and chloride assays."
The sponsor also references the literature in their labeling:
"Young, D.S. et al, Clin. Chem 21: ID (1975) for drugs and substances that may affect the accuracy of these methods."
{8}
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
Method comparison studies were performed following CLSI EP9-A2. Serum samples were run on the Pictus 700 Clinical Chemistry Analyzer and the results compared to the results run on the predicate device. Less than 10% of the samples were spiked or diluted to fully span the claimed measuring range of each analyte. The Deming regression analysis results are summarized below.
| Analyte | Slope | Intercept | R² | N | Concentration range tested |
| --- | --- | --- | --- | --- | --- |
| Glucose | 0.99 | 1.2 mg/dL | 1.00 | 136 | 26 - 484 mg/dL |
| Sodium | 1.00 | -1.2 mmol/L | 1.00 | 69 | 118 - 182 mmol/L |
| Potassium | 1.00 | 0.0 mmol/L | 1.00 | 69 | 1.7 - 8.8 mmol/L |
| Chloride | 1.02 | -1.9 mmol/L | 0.99 | 69 | 55 - 134 mmol/L |
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
{9}
5. Expected values/Reference range:
Glucose¹ 70 – 105 mg/dL
Sodium² 136 – 145 mmol/L
Potassium² 3.5 – 5.1 mmol/L
Chloride² 98 – 107 mmol/L
¹Tietz, Textbook of Clinical Chemistry, 2ⁿᵈ ed., Philadelphia, W.B. Saunders, (1994)
²Tietz, Textbook of Clinical Chemistry, Philadelphia, W.B. Saunders, (1990)
N. Instrument Name:
Diatron Pictus 700 Clinical Chemistry Analyzer
O. System Descriptions:
1. Modes of Operation:
Does the applicant’s device contain the ability to transmit data to a computer, webserver, or mobile device?
Yes ☐ or No ☑
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission?
Yes ☐ or No ☑
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☑ or No ☐
3. Specimen Identification:
Barcode identification is available for specimen tubes and reagent bottles. Manual entry is used to identify specimen cups.
4. Specimen Sampling and Handling:
Samples are manually placed on the instrument either by sample tube or sample cup. The system can run an individual sample or a batch of samples. Once the samples are tested they can be manually removed.
10
{10}
5. Calibration:
Glucose calibration frequency should be 14 days or with a change of reagent lot or as indicated by quality control procedures. The calibrator for glucose was previously cleared in k020454.
It is mandatory to perform calibration (two points) before ISE measurement at the beginning of the day or if the power switch of analyzer is turned off, eight hours have passed since the last ISE calibration, and after electrodes cleaning. The ISE calibrator material for sodium, potassium and chloride (Calibrant A and B) was previously cleared under k070057.
6. Quality Control:
The analyzer has a built in quality control program. The labeling recommends the use of two external quality control materials to be assayed according to government guidelines.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Operation conditions: Temperature and Relative humidity have been conducted and found to be acceptable. Sponsor has the following claims:
Operating temperature is 20°C – 30°C and Relative humidity is between 45% and 80%.
Carry-over studies have been conducted and found to be acceptable.
Automatic dilution studies have been conducted and found to be acceptable, supporting that the Pictus 700 is capable of performing up to 4-fold automatic dilution.
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.
11
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.