VITROS Chemistry Products Cl- Slides: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products Cl- Slides quantitatively measure chloride (Cl-) concentration in serum, plasma and urine using VITROS 250/350/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/ XT 7600 Integrated Systems. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis. VITROS Chemistry Products ECO2 Slides: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products ECO2 Slides quantitatively measure total carbon dioxide (CO2) concentration in serum and plasma using VITROS 250/350/950/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/ XT 7600 Integrated Systems. Bicarbonate/ carbon dioxide measurements are used in the diagnosis and treatment of numerous potentially serious disorders associated with changes in body acid-base balance. VITROS Chemistry Products GLU Slides: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products GLU Slides quantitatively measure glucose (GLU) concentration in serum, plasma, urine, and cerebrospinal fluid using VITROS 250/350/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/ XT 7600 Integrated Systems. 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.
Device Story
VITROS Chemistry Products (Cl-, ECO2, GLU) are multilayered analytical slides for use on VITROS Integrated Systems. Cl- slides use direct potentiometry (ion-selective electrode) to measure chloride ions; ECO2 slides use enzymatic endpoint reactions (phosphoenolpyruvate carboxylase/malate dehydrogenase) to measure total CO2 via NADH absorbance; GLU slides use colorimetric enzymatic reactions (glucose oxidase/peroxidase) to measure glucose. Samples (serum, plasma, urine, CSF) are deposited on slides; spreading layers distribute sample; chemical reactions produce measurable signals (electrical potential, absorbance, or reflected light). Systems are used in clinical laboratories by trained personnel. Output provides quantitative analyte concentrations to clinicians for diagnosis and treatment monitoring of metabolic and electrolyte disorders. Benefits include rapid, automated, high-throughput diagnostic testing.
Clinical Evidence
Bench testing only. Precision/reproducibility evaluated per CLSI EP05-A3 (n=80 per analyte). Linearity evaluated per CLSI EP06-A. Detection limits (LoB, LoD, LoQ) evaluated per CLSI EP17-A2. Interference testing performed per CLSI EP07-A2. Method comparison study (n=125 per analyte) demonstrated high correlation (r=1.00) between VITROS XT 7600 and predicate VITROS 5600 systems.
Indicated for quantitative measurement of chloride, total carbon dioxide, and glucose in human serum, plasma, urine, and/or cerebrospinal fluid to aid in diagnosis/treatment of electrolyte, metabolic, acid-base, and carbohydrate disorders (e.g., diabetes, cystic fibrosis). Rx only.
Regulatory Classification
Identification
A chloride test system is a device intended to measure the level of chloride in plasma, serum, sweat, and urine. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.
Predicate Devices
VITROS Chemistry Products Cl- Slides (k162020)
VITROS Chemistry Products ECO2 Slides (k120765)
VITROS Chemistry Products GLU Slides (k163433)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k182072
B. Purpose for Submission:
Adding previously cleared assays to a new instrument platform
C. Measurand:
Chloride, total carbon dioxide (CO2), and glucose
D. Type of Test:
Chloride assay: Potentiometric assay
Total carbon dioxide (CO2) assay: Enzymatic endpoint assay
Glucose assay: Colorimetric assay
E. Applicant:
Ortho-Clinical Diagnostics, Inc.
F. Proprietary and Established Names:
VITROS Chemistry Products Cl- Slides
VITROS Chemistry Products ECO2 Slides
VITROS Chemistry Products GLU Slides
G. Regulatory Information:
| Analyte | Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- | --- |
| Cl- | CGZ | II | 21 CFR 862.1170 | Chemistry (75) |
| CO2 | KHS | II | 21 CFR 862.1160 | |
| GLU | CGA | II | 21 CFR 862.1345 | |
{1}
H. Intended Use:
1. Intended use(s):
See Indication(s) for use below.
2. Indication(s) for use:
Chloride: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products Cl-Slides quantitatively measure chloride (Cl-) concentration in serum, plasma and urine using VITROS 250/350/950/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/XT 7600 Integrated System. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.
CO2: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products ECO2 Slides quantitatively measure total carbon dioxide (CO2) concentration in serum and plasma using VITROS 250/350/950/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/XT 7600 Integrated System. Bicarbonate/carbon dioxide measurements are used in the diagnosis and treatment of numerous potentially serious disorders associated with changes in body acid-base balance.
Glucose: Rx Only. For in vitro diagnostic use only. VITROS Chemistry Products GLU Slides quantitatively measure glucose (GLU) concentration in serum, plasma, urine, and cerebrospinal fluid using VITROS 250/350/950/5,1 FS and 4600 Chemistry Systems and the VITROS 5600/XT 7600 Integrated System. 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.
3. Special conditions for use statement(s):
For prescription use only.
Not for Point-of-Care use.
4. Special instrument requirements:
Performance characteristics were determined on the VITROS XT 7600 Integrated System
I. Device Description:
VITROS Chemistry Products Cl- Slide:
The VITROS Chemistry Products Cl- Slide is a multilayered, analytical element coated on a polyester support that uses direct potentiometry for measurement of chloride ions. The reactive ingredients per cm² are silver 0.4 mg and silver chloride 0.2 mg. Other ingredients: Polymer, plasticizer, surfactant and nickel-chromium.
{2}
VITROS Chemistry Products ECO2 Slide:
The VITROS Chemistry Products ECO2 Slide is a multilayered, analytical element coated on a polyester support. The reactive ingredients per cm² are phosphoenolpyruvate carboxylase (bacteria) 0.20 U; malate dehydrogenase (porcine heart) 0.26 U; phosphoenolpyruvate 0.39 mg and nicotinamide adenine dinucleotide, reduced 0.44 mg. Other ingredients: binders, buffer, inhibitor, pigment, surfactants, enzyme cofactors, cross-linking agent and filter dye.
VITROS Chemistry Products GLU Slide:
The VITROS Chemistry Products GLU Slide is a multilayered, analytical element coated on a polyester support. The reactive ingredients per cm² are glucose oxidase (Aspergillus sp.) 0.77 U; peroxidase (horseradish root) 3.6 U; 1,7-dihydroxynaphthalene (dye precursor) 67 μg and 4-aminoantipyrine hydrochloride (dye precursor) 0.11 mg. Other ingredients: pigment, binders, buffer, surfactants, stabilizers and crosslinking agent.
J. Substantial Equivalence Information:
1. Predicate device name(s):
VITROS Chemistry Products Cl- Slides
VITROS Chemistry Products ECO2 Slides
VITROS Chemistry Products GLU Slides
2. Predicate 510(k) number(s):
k162020
k120765
k163433
3. Comparison with predicate:
Chloride:
| Similarities and Differences | | |
| --- | --- | --- |
| Device Characteristic | Candidate Device VITROS Chemistry Products Cl- Slides (k182072) | Predicate Device VITROS Chemistry Products Cl- Slides (k162020) |
| Intended Use | For the quantitative measure of chloride (Cl-) concentration in serum, plasma and urine. | Same |
| Measuring range | Serum: 50.0 -175.0 mmol/L Urine: 15-300 mmol/L | Same |
| Basic principle | Potentiometric; ion-selective electrode (ISE) | Same |
| Sample type | Serum, plasma, urine | Same |
{3}
4
| Similarities and Differences | | |
| --- | --- | --- |
| Device Characteristic | Candidate Device
VITROS Chemistry Products
Cl- Slides (k182072) | Predicate Device
VITROS Chemistry Products
Cl- Slides (k162020) |
| Sample volume | 10 μL | Same |
| Instrumentation | VITROS 250/350/950/5,1 FS
and 4600 Chemistry Systems
and the VITROS 5600/ XT
7600 Integrated
System | VITROS 250/350/950/5,1 FS
and 4600 Chemistry
Systems and the VITROS
5600 Integrated System |
CO2:
| Similarities and Differences | | |
| --- | --- | --- |
| Device Characteristic | Candidate Device
VITROS Chemistry Products
ECO2 Slides (k182072) | Predicate Device
VITROS Chemistry Products
ECO2 Slides (k120675) |
| Intended Use | For the quantitatively measure of total carbon dioxide (CO2) concentration in serum and plasma. | Same |
| Measuring range | 5-40 mmol/L | Same |
| Basic principle | Enzymatic endpoint | Same |
| Wavelength | 340 nm | Same |
| Sample type | Serum, plasma | Same |
| Sample volume | 6 μL | Same |
| Instrumentation | VITROS 250/350/950/5,1 FS
and 4600 Chemistry Systems
and the VITROS 5600/ XT
7600 Integrated
System | VITROS 250/350/950/5,1 FS
and 4600 Chemistry
Systems and the VITROS
5600 Integrated System |
Glucose:
| Similarities and Differences | | |
| --- | --- | --- |
| Device Characteristic | Candidate Device
VITROS Chemistry Products
GLU Slides (k182072) | Predicate Device
VITROS Chemistry Products
GLU Slides (k163433) |
| Intended Use | For quantitatively measure of glucose concentration in serum, plasma, urine, and cerebrospinal fluid. | Same |
| Measuring range | Serum: 20.0-625.0 mg/dL
Urine/CSF: 20.0-650.0 mg/dL | Same |
| Basic principle | Colorimetric | Same |
{4}
| Similarities and Differences | | |
| --- | --- | --- |
| Device Characteristic | Candidate Device
VITROS Chemistry
Products GLU Slides
(k182072) | Predicate Device
VITROS Chemistry Products
GLU Slides (k163433) |
| Wavelength | 540 nm | Same |
| Sample type | Serum, plasma, urine, CSF | Same |
| Sample volume | 6 μL | Same |
| Instrumentation | VITROS 250/350/950/5,1 FS
and 4600 Chemistry Systems
and the VITROS 5600/ XT
7600 Integrated
System | VITROS 250/350/950/5,1 FS
and 4600 Chemistry
Systems and the VITROS
5600 Integrated System |
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP05-A3, Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline -Third Edition.
CLSI EP06-A, Evaluation of Linearity of Quantitative Measurement Procedures, Approved Guideline;1st Edition.
CLSI EP07, Interference Testing in Clinical Chemistry; Approved Guideline-Second Edition.
CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline-Second Edition.
L. Test Principle:
VITROS Chemistry Products Cl- Slides (Potentiometric):
A drop of patient sample and a drop of VITROS Reference Fluid on separate halves of the slide results in migration of both fluids toward the center of the paper bridge. A stable liquid junction is formed connecting the reference electrode to the sample indicator electrode. Each electrode produces an electrical potential in response to the activity of chloride ions applied to it. The potential difference poised between the two electrodes is proportional to the chloride concentration in the sample.
VITROS Chemistry Products ECO2 Slides (Enzymatic endpoint):
A drop of patient sample is deposited on the slide and is evenly distributed by the spreading layer to the underlying layers. The high pH in the spreading layer ensures that essentially all CO2 in the sample is in the bicarbonate form. Bicarbonate diffuses to the gel layer and is used to carboxylate phosphoenolpyruvate in the presence of phosphoenolpyruvate carboxylase to form oxalacetate and inorganic phosphate. The final reaction involves the malate dehydrogenase-catalyzed oxidation of NADH and reduction of oxalacetate to produce
{5}
$\mathrm{NAD+}$ and malate. The slide is incubated at $37^{\circ}\mathrm{C}$ . The concentration of CO2 in the sample is determined by measuring the absorbance of the unreacted NADH by reflectance spectrophotometry.
VITROS Chemistry Products GLU Slides (Colorimetric):
A drop of patient sample is deposited on the slide and is evenly distributed by the spreading layer to the underlying layers. The oxidation of glucose in the sample is catalyzed by glucose oxidase to form hydrogen peroxide and gluconate. This reaction is followed by an oxidative coupling catalyzed by peroxidase in the presence of dye precursors to produce a dye. The intensity of the dye is measured by reflected light.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Precision studies were conducted following EP05-A3 guideline. The study was performed by testing a minimum of two quality control fluids and three human based precision pools using the chloride (Cl-), carbon dioxide (ECO2), and glucose (GLU) assays. Samples were analyzed using one VITROS XT 7600 Integrated System over 20 days, with 2 runs per day and 2 replicates per specimen $(n = 80)$ . The results of the precision study are presented in the tables below:
Cl- Serum (mmol/L):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| QC-1 | 86 | 0.4 | 0.5 | 0.5 | 0.6 | 1.0 | 1.2 |
| QC-2 | 108 | 0.4 | 0.4 | 0.6 | 0.5 | 1.2 | 1.1 |
| Serum Pool 1 | 66 | 0.3 | 0.4 | 0.4 | 0.5 | 0.6 | 0.9 |
| Serum Pool 4 | 127 | 0.4 | 0.4 | 0.6 | 0.4 | 1.4 | 1.1 |
| Serum Pool 5 | 160 | 0.6 | 0.4 | 0.6 | 0.4 | 1.8 | 1.1 |
| Serum Pool (native) | 106 | 0.4 | 0.3 | 0.5 | 0.5 | 1.2 | 1.1 |
Cl- Urine (mmol/L):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| U QC-1 | 101 | 0.4 | 0.3 | 0.6 | 0.6 | 0.9 | 0.9 |
| U QC-2 | 189 | 0.5 | 0.3 | 0.9 | 0.5 | 2.3 | 1.2 |
| Urine Pool 1 | 22 | 0.3 | 1.3 | 0.5 | 2.2 | 0.6 | 2.6 |
| Urine Pool 3 | 151 | 0.4 | 0.3 | 0.5 | 0.4 | 0.9 | 0.6 |
| Urine Pool 5 | 249 | 0.7 | 0.3 | 1.0 | 0.4 | 3.9 | 1.6 |
| Urine Pool (native) | 67 | 0.3 | 0.4 | 0.3 | 0.5 | 0.6 | 0.9 |
{6}
ECO2 Serum (mmol/L):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| QC-1 | 26 | 0.3 | 1.0 | 0.4 | 1.4 | 0.6 | 2.4 |
| QC -2 | 16 | 0.3 | 1.7 | 0.4 | 2.5 | 0.5 | 3.1 |
| Serum Pool 1 | 8 | 0.3 | 3.2 | 0.4 | 4.5 | 0.6 | 7.4 |
| Serum Pool 3 | 17 | 0.3 | 1.5 | 0.3 | 2.0 | 0.4 | 2.5 |
| Serum Pool 5 | 33 | 0.3 | 0.8 | 0.4 | 1.3 | 0.6 | 1.9 |
| Serum Pool (native) | 26 | 0.2 | 0.8 | 1.1 | 4.2 | 1.2 | 4.4 |
GLU Serum (mg/dL):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| QC -1 | 89 | 0.4 | 0.4 | 0.6 | 0.7 | 0.8 | 0.9 |
| QC -2 | 282 | 1.1 | 0.4 | 1.4 | 0.5 | 2.6 | 0.9 |
| Serum Pool 1 | 27 | 0.2 | 0.7 | 0.3 | 1.2 | 0.5 | 1.8 |
| Serum Pool 3 | 116 | 0.5 | 0.4 | 0.6 | 0.5 | 0.8 | 0.7 |
| Serum Pool 5 | 566 | 1.7 | 0.3 | 2.5 | 0.4 | 6.1 | 1.1 |
| Serum Pool (native) | 99 | 0.3 | 0.3 | 0.5 | 0.5 | 0.8 | 0.8 |
GLU Urine (mg/dL):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| QC -1 | 29 | 0.2 | 0.6 | 0.4 | 1.3 | 0.7 | 2.2 |
| QC -2 | 285 | 1.4 | 0.5 | 2.3 | 0.8 | 2.6 | 0.9 |
| Urine Pool 2 | 1.2 | 0.4 | 0.4 | 0.7 | 0.7 | 1.5 | 1.5 |
| Urine Pool 3 | 232 | 1.1 | 0.5 | 2.4 | 1.0 | 4.3 | 1.9 |
| Urine Pool 5 | 593 | 1.9 | 0.3 | 2.7 | 0.5 | 10.0 | 1.7 |
GLU CSF (mg/dL):
| Sample # | Mean | Repeatability (Within Run) | | Within Day | | Within Lab (Total) | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV |
| QC -1 | 36 | 0.2 | 0.6 | 0.3 | 0.9 | 0.5 | 1.4 |
| QC -2 | 84 | 0.4 | 0.5 | 0.5 | 0.6 | 0.6 | 0.8 |
| CSF Pool (native) | 41 | 0.2 | 0.5 | 0.3 | 0.6 | 0.5 | 1.2 |
| CSF Pool 1 | 28 | 0.1 | 0.5 | 0.3 | 1.1 | 0.5 | 1.9 |
| CSF Pool 4 | 289 | 1.3 | 0.5 | 1.7 | 0.6 | 3.1 | 1.1 |
| CSF Pool 5 | 563 | 2.6 | 0.5 | 3.7 | 0.7 | 5.8 | 1.0 |
{7}
b. Linearity/assay reportable range:
A linearity study was performed following the CLSI EP06-A guideline. A series of eleven proportionally related admixtures of low and high test fluids were tested to verify linearity; each sample was tested in duplicate.
The results of the linear regression analysis support the following claimed measuring ranges for the chloride, total CO2 and glucose assays:
| Analyte | Slope | Intercept | r | Range tested | Claimed measuring range |
| --- | --- | --- | --- | --- | --- |
| Cl- Serum (mmol/L) | 1.00 | 1.07 | 1.00 | 42 - 193 | 50-175 |
| Cl- Urine (mmol/L) | 1.00 | 4.61 | 1.00 | 15 - 326 | 15-300 |
| ECO2 Serum | 0.99 | 0.61 | 1.00 | 3.1 - 44.2 | 5.0-40.0 |
| Glucose Serum (mg/dL) | 1.01 | -2.75 | 1.00 | 5.3 - 656.6 | 20.0-625.0 |
| Glucose Urine (mg/dL) | 1.02 | 1.01 | 1.00 | 9.0 - 682.4 | 20.0-650.0 |
| Glucose CSF (mg/dL) | 1.01 | -0.41 | 1.00 | 11.3 - 676.4 | 20.0-650.0 |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
VITROS Chemistry Products Cl- Slides: Values assigned the VITROS Chemistry Products Calibrator Kit 2 for chloride are traceable to the Certified NIST (National Institute of Standards and Technology) Reference Material, SRM (Standard Reference Material) 919.
VITROS Chemistry Products ECO2 Slides: Values assigned to the VITROS Chemistry Products Calibrator Kit2 for carbon dioxide are traceable to the Certified NIST (National Institute of Standards and Technology) Reference Material, SRM (Standard Reference Material) 351.
VITROS Chemistry Products GLU Slides: Values assigned to the VITROS Chemistry Products Calibrator Kit 1 for glucose are traceable to the Certified NIST (National Institute of Standards and Technology) Reference Material, SRM (Standard Reference Material) 917.
d. Detection limit:
The limit of blank (LoB), limit of detection (LoD) and limit of quantitation (LoQ) were evaluated in accordance with CLSI EP17-A2 guideline using the VITROS XT 7600 Chemistry System.
Limit of blank (LoB) studies were performed by testing 4 blank samples in replicates of 6 over 3 days, using 3 lots of reagents, for a total of 216 observations (72 results
{8}
per reagent lot). The LoB value for each assay was defined as the highest value achieved using blank samples with the stated probability (i.e. $\alpha = 5\%$ ). Since the data for all assays were non-gaussian, a non-parametric approach was applied that estimates the LoB using the calculated rank position corresponding to the 95th percentile of the distribution of blank values observed.
Limit of detection (LoD) studies were performed by testing 4 pools of human samples with analyte concentrations close to the expected detection limit for each analyte. Samples were tested in replicates of 6 over 3 days, using 3 lots of reagents, for a total of 216 observations (72 results per reagent lot). The LoD value for the assay is the highest resultant value achieved among the combinations of reagent lots and human pools evaluated, with the stated probability (i.e. $\beta = 5\%$ ).
Limit of quantitation (LoQ) studies were performed using 4 pools of low level samples with analyte concentrations close to the expected LoQ of the corresponding assay. Samples were tested in replicates of 4 over 3 days, using 3 lots of reagents, for a total of 144 observations (48 results per reagent lot). Ortho defines LoQ as the lowest concentration with a percent total allowable error $< 8\%$ for chloride (serum); percent total allowable error $10\%$ for chloride (urine), percent total allowable error $< 30\%$ for carbon dioxide, total allowable error $< 30\%$ for glucose in serum, urine, and CSF.
The results of the detection capability studies for each assay are presented in the table below:
| | Cl- (mmol/L) | | ECO2 (mmol/L) | GLU (mg/dL) | | |
| --- | --- | --- | --- | --- | --- | --- |
| | Serum | Urine | Serum | Serum | Urine | CSF |
| LoB | 9.2202 | 3.0965 | 1.9944 | 4.5753 | 6.2966 | 4.0745 |
| LoD | 9.9798 | 4.0417 | 2.3522 | 5.2670 | 6.7212 | 4.6992 |
| LoQ | 49 | 11 | 3.7 | 13 | 20 | 19 |
| Claimed LoQ | 50 | 15 | 5.0 | 20 | 20 | 20 |
| Assay Range | 50.0-175.0 | 15-300 | 5.0-40.0 | 20.0-625.0 | 20.0-650.0 | 20.0-650.0 |
# e. Analytical specificity:
Interference testing was performed in accordance with CLSI EP07-A2 guideline. Testing on the representative assays included known chemical interferents, common chemical substances identified with potential to interfere based upon risk assessment. Testing employed "paired-difference" assessment at a minimum of two analyte levels, as specified by CLSI EP07-A2 guideline. All samples used in the interference testing were pools of human serum, plasma, CSF or urine. For all pools, samples may have been spiked or diluted in order to achieve the appropriate target analyte concentration and was tested at a minimum of two analyte concentration and bias between interferent test and control samples was calculated.
{9}
# Chloride:
The study was conducted using samples with serum chloride concentrations of 100 and 110 mmol/L. The sponsor defined non-interference as a bias < 1.1 mmol/L (vs. control condition).
The compounds and the highest concentration that don't interfere with serum chloride are listed in the table below:
| Compound | Concentration |
| --- | --- |
| Acetaminophen | 20 mg/dL |
| Acetylsalicylic Acid | 35 mg/dL |
| Allopurinol | 12.5 mg/dL |
| Alprazolam | 20 μg/dL |
| Para-Aminosalicylic Acid | 23 mg/dL |
| Amitriptyline | 1 μg/mL |
| Amoxicillin | 1500 μg/mL |
| Ascorbic Acid | 3 mg/dL |
| Atenolol | 20 μg/mL |
| Bilirubin | 40 mg/dL |
| Calcium | 16 mg/dL |
| Carbamazepine | 60 μg/mL |
| Cephalexin | 11.7 mg/dL |
| Ciprofloxacin | 1 mg/dL |
| Clarithromycin | 20.0 μg/mL |
| Codeine | 4 μg/mL |
| Dextran | 1000 mg/dL |
| Dextromethorphan | 1.0 μg/mL |
| Digoxin | 3 μg/dL |
| Diltiazem | 5 μg/mL |
| Diphenhydramine | 10 μg/mL |
| Enalapril | 1.2 μg/mL |
| Ethanol | 300 mg/dL |
| Fluoxetine | 0.8 mg/dL |
| Furosemide | 10 mg/dL |
| Gentisic Acid | 0.5 mg/dL |
| Glucose | 600 mg/dL |
| Glyburide | 6.4 μg/mL |
| Guaifenesin | 100 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Compound | Concentration |
| --- | --- |
| Hydrochlorothiazide | 2 mg/dL |
| Hydrocodone | 250 ng/mL |
| Ibuprofen | 49.5 mg/dL |
| Isoniazid | 0.4 mg/dL |
| L-Dopa | 0.6 mg/dL |
| Levothyroxine | 1 μg/mL |
| Lithium | 1 mEq/L |
| Loratadine | 100 ng/mL |
| Magnesium | 4.5 mg/dL |
| Meprobamate | 2 mg/dL |
| 6-Mercaptopurine | 1.5 mg/dL |
| Nifidepine | 0.2 mg/dL |
| Omeprazole | 20 mg/dL |
| Phenobarbital | 3 mg/dL |
| Phenytoin | 10 mg/dL |
| Phospholipids | 500 mg/dL |
| Prednisone | 0.1 mg/dL |
| Propoxyphene | 16.7 ng/mL |
| Pseudoephedrine | 10 μg/mL |
| Ranitidine | 20 μg/mL |
| Simvastatin | 500 mg/L |
| Sulfamethoxazole | 330 mg/dL |
| Sulfathiazole | 6 mg/dL |
| Tolbutamide | 22 mg/dL |
| Triamterene | 886 μg/dL |
| Trimethoprim | 40.1 μg/mL |
| Tyrosine | 24 mg/dL |
| Urea Nitrogen | 100 mg/dL |
| Warfarin | 10.7 mg/dL |
10
{10}
The results of substances that interfere with chloride determinations in serum are summarized in the table below:
| Interferent | Interferent concentration | Chloride concentration (mmol/L) | Bias (mmol/L) |
| --- | --- | --- | --- |
| 5-aminosalicylic acid | 4 μg/mL | 100 | -1.5 |
| | | 109 | +6.1 |
| Glutathione | 1 mg/dL | 104 | -1.6 |
| Naproxen | 504.5 μg/mL | 99 | +1.6 |
| Terazosin | 3.03 μg/mL | 110 | -2.4 |
| Triglycerides | 600 mg/dL | 110 | +2.1 |
The following limitations are listed in the package insert:
- Bromide and iodide from therapeutic drugs and ointments may cause a positive bias. Normal physiological levels of bromide and iodide do not interfere.
- Intralipid at 800 mg/dL may cause a positive bias of approximately 1.5 mmol/L.
- Purines, such as adenine or hypoxanthine, at significantly elevated levels may cause a negative bias of approximately mmol/L.
The sponsor also assessed the effect of potential interference in urine. The study was conducted using samples with urine chloride concentrations of 20 and 180 mmol/L. The sponsor defined non-interference as a bias < 5% (vs. control condition).
The compounds and the highest concentration that don't interfere with urine chloride are listed in the following table:
| Substance Tested | Concentration |
| --- | --- |
| Acetaminophen | 50 mg/dL |
| Allopurinol | 24 mg/dL |
| Amiloride HCl | 1.5 mg/dL |
| Ascorbic Acid | 180 mg/dL |
| Bilirubin, conjugated | 7.25 mg/dL |
| Boric Acid | 670 mg/dL |
| Boric Acid + Sodium Formate | 670 mg/dL + 335 mg/dL |
| Carbenicillin Disodium | 300 mg/dL |
| Ciprofloxacin | 1.16 mg/dL |
| Furosemide | 9 mg/dL |
| Gentamicin Sulfate | 1.5 mg/dL |
| Glacial Acetic Acid | 10 mL/L |
| Glutathione | 1.0 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Substance Tested | Concentration |
| --- | --- |
| Levodopa | 67 mg/dL |
| Lithium Carbonate | 236.5 mg/dL |
| Mannitol | 60 mg/dL |
| N-Acetyl Cysteine | 166.2 mg/dL |
| Ofloxacin | 32 mg/dL |
| pH | 4–9 |
| Penicillin G | 59.7 mg/dL |
| Phenazopyridine HCl | 19.5 mg/dL |
| Prednisone | 230 μg/dL |
| Ranitidine HCl | 670 μg/dL |
| Sodium Cefoxitin | 340 mg/dL |
| Sodium Fluoride | 500 mg/dL |
| Sodium Formate | 335 mg/dL |
| Sodium Oxalate | 60 mg/dL |
| Specific Gravity | 1.00–1.04 |
{11}
12
| Ibuprofen | 50 mg/dL | Tetracycline HCl | 70 mg/dL |
| --- | --- | --- | --- |
| Intralipid | 2524 mg/dL | Toluene | 1.3 mL/L |
# ECO2:
The study was conducted using samples with serum CO2 concentrations of 25 and 35 mmol/L. The sponsor defined non-interference as a bias < 1.9 mmol/L (vs. control condition).
| Compound | Concentration |
| --- | --- |
| Acetaminophen | 20 mg/dL |
| Acetoacetate | 20 mg/dL |
| Acetylsalicylic acid | 50 mg/dL |
| Alpha-keto-isocaproate | 20 mmol/L |
| 5-Aminosalicylate | 0.4 mg/dL |
| 4-Aminosalicylate | 91 mg/dL |
| Ammonia | 0.5 mmol/L |
| Argininosuccinate | 5 mmol/L |
| Ascorbic acid | 3 mg/dL |
| Benzamide | 20 mmol/L |
| Benzenesulfonate | 2 mmol/L |
| Benzoic acid | 4 mmol/L |
| Benzyl alcohol | 4 mmol/L |
| Bilirubin | 40 mg/dL |
| Butyric acid | 2 mmol/L |
| Capric acid | 4 mmol/L |
| Caproic acid | 2 mmol/L |
| Cholesterol | 390 mg/dL |
| Dextran | 1000 mg/dL |
| Ethanol | 350 mg/dL |
| Free fatty acids | 3 mmol/L |
| Glutamate | 2 mmol/L |
| Homogentisic acid | 2 mmol/L |
| Hydrochlorothiazide | 5 mg/dL |
| Hydroxybutyrate | 20 mg/dL |
| Hydroxyindoleacetate | 2 mmol/L |
| Hydroxyphenylacetate | 4 mmol/L |
| Compound | Concentration |
| --- | --- |
| Hydroxyphenyllactate | 2 mmol/L |
| Hydroxyphenylpyruvate | 2 mmol/L |
| Hypaque | 500 mg/dL |
| Ibuprofen | 40 mg/dL |
| Imidazole | 20 mmol/L |
| Imidazoleacetate | 20 mmol/L |
| Indomethacin | 50 mg/dL |
| Intralipid | 800 mg/dL |
| Isovaleric acid | 1 mmol/L |
| Lactate | 57 mg/dL |
| Lactose | 3 g/dL |
| Mannitol | 3 g/dL |
| Methylvaleric acid | 2 mmol/L |
| Naproxen | 10 mmol/L |
| Phenylacetate | 1 mmol/L |
| Phenylpyruvate | 2 mmol/L |
| Phospholipids | 400 mg/dL |
| Propionic acid | 2 mmol/L |
| Propylpentanoic acid | 2 mmol/L |
| Protein | 11 g/dL |
| Pyruvate | 1.5 mg/dL |
| Salicylate | 50 mg/dL |
| Spironolactone | 5 mg/dL |
| Sulfathiazole | 5 mg/dL |
| Triglycerides | 900 mg/dL |
| Urea Nitrogen | 322 mg/dL |
Known ECO2 interferent:
| Interferent | Interferent concentration | CO2 concentration | bias |
| --- | --- | --- | --- |
| Hemoglobin | 800 mg/dL | 25 mmol/L | -2.1 |
{12}
# Glucose:
The study was conducted using samples of serum glucose concentrations of $80\mathrm{mg / dL}$ with non-interference as a bias $< 7\mathrm{mg / dL}$ and serum glucose concentrations of 225 $\mathrm{mg / dL}$ with non-interference as a bias $< 7\%$ (vs. control condition).
The compounds and the highest concentration that don't interfere with glucose determinations in serum are listed in the following table:
| Compound | Concentration |
| --- | --- |
| Acetaminophen | 15 mg/dL |
| Alprazolam | 0.2 mg/dL |
| Amlodipine | 10 μg/dL |
| Amoxicillin | 7.53 mg/dL |
| Ascorbic acid | 4.5 mg/dL |
| Atorvastatin calcium | 72.6 mg/dL |
| Benazepril | 2.21 mg/dL |
| Bilirubin, conjugated | 57.64 mg/dL |
| Bilirubin, unconjugated | 40 mg/dL |
| Cefazolin | 125.9 mg/dL |
| Cefoxitin | 69.5 mg/dL |
| Ceftriaxone | 81.0 mg/dL |
| Chlorpropamide | 74.7 mg/dL |
| Cholesterol | 325 mg/dL |
| Creatinine | 15 mg/dL |
| Diphenhydramine | 0.50 mg/dL |
| Dipyrone (metamizole) | 18 mg/dL |
| Dobutamine | 30 μg/dL |
| Dopamine | 90 μg/dL |
| Ethamsylate (Etamsylate) | 3.14 mg/dL |
| Ethanol | 400 mg/dL |
| Fructose | 30 mg/dL |
| Furosemide | 6 mg/dL |
| Galactose | 60 mg/dL |
| Gentisic acid | 1.80 mg/dL |
| Glipizide | 0.20 mg/dL |
| Glyburide | 0.192 mg/dL |
| Hydralazine HCl | 0.046 mg/dL |
| Hydrochlorothiazide | 0.60 mg/dL |
| Hydroxyurea | 7 mg/dL |
| Ibuprofen | 50 mg/dL |
| Insulin | 3.12 μg/dL |
| Intralipid | 800 mg/dL |
| Compound | Concentration |
| --- | --- |
| Isomaltose | 0.09 mg/dL |
| Isoniazid | 4 mg/dL |
| L-Dopa | 0.98 mg/dL |
| Levothyroxine sodium | 103 μg/dL |
| Losartan potassium | 0.091 mg/dL |
| Maltose | 75 mg/dL |
| Metformin HCl | 5.1 mg/dL |
| Methyldopa | 2 mg/L |
| N-Acetylcysteine | 15 mg/dL |
| Naproxen sodium | 54.7 mg/dL |
| Nitrofurantoin | 0.4 mg/dL |
| Omeprazole | 0.60 mg/dL |
| Oxycodone | 0.05 mg/dL |
| Propanolol | 0.21 mg/dL |
| Pseudoephedrine | 1 mg/dL |
| Rifampicin (Rifampin) | 6.43 mg/dL |
| Salicylic acid | 60 mg/dL |
| Sodium | 1050 mg/dL |
| Spironolactone | 0.06 mg/dL |
| Theophylline | 4 mg/dL |
| Tolazamide | 28 mg/dL |
| Tolbutamide | 64.1 mg/dL |
| Tolbutamide | 64.1 mg/dL |
| Total Protein | 10 g/dL |
| Uric acid | 23 mg/dL |
| Vancomycin | 10 mg/dL |
| Warfarin | 1 mg/dL |
| Xylose | 100mg/dL |
| Mannitol | 0.09 mg/dL |
| Sorbitol | 0.09 mg/dL |
| Xylitol | 0.09 mg/dL |
| Lacitol | 0.09 mg/dL |
| Maltitol 578 | 0.09 mg/dL |
{13}
The substance that interferes with glucose determinations in serum are summarized in the table below:
| Interferent | Interferent concentrations | Glucose concentrations | Bias |
| --- | --- | --- | --- |
| Glutathione | 61.5 mg/dL | 80 mg/dL | -7.4 mg/dL |
The following limitations are listed in the package insert:
- When using samples with visible hemolysis (Hb $>200\mathrm{mg/dL}$ ), there may be a negative bias due to catalase released from the lysis of red blood cells. On VITROS Systems capable of performing Sample Indices using the MicroSensor, the GLU result will be flagged with H (Hemolysis).
- Elevated lipids may limit diffusion of oxygen to the reactants. Dilute grossly lipemic samples two-fold before analysis.
Glucose - interference testing in urine:
The study was conducted using samples with urine glucose concentrations of approximately $30\mathrm{mg / dL}$ and found not to interfere, bias $< 7\mathrm{mg / dL}$ . The substances were also tested at a glucose concentration of approximately $215\mathrm{mg / dL}$ and found not to interfere, bias $< 7\%$ (vs. control condition).
The substances that showed not to interfere in urine are summarized in the following table:
| Substances | Highest concentration tested that showed non-significant interference |
| --- | --- |
| Boric acid | 6.7 mg/mL |
| Boric acid with Sodium formate | 6.7 mg/mL, 3.35 mg/mL |
| 10% Thymol in Isopropanol | 3.3 mL/L |
| Toluene | 1.3 mL/L |
| Sodium fluoride | 5 g/L |
| Sodium formate | 3.35 mg/mL |
| Sodium oxalate | 60 mg/dL |
| Urea nitrogen | 100 mg/dL |
| Magnesium | 146 mg/dL |
| Protein | 50 mg/dL |
The following substance interferes with glucose determinations in urine:
| Interferent | Interferent concentrations | Glucose concentrations | Bias |
| --- | --- | --- | --- |
| Ascorbic Acid | 50 mg/dL | 30 mg/dL | -15.7 mg/dL |
{14}
The following limitations are listed in the package insert:
- Glacial acetic acid at 10 mL/L results in ~4% negative bias. The magnitude of the bias increases with higher concentrations of glacial acetic acid (60 mL/L). Do not use urine specimens with acetic acid as a preservative.
- 12N Hydrochloric acid (HCl) at 2.5 mL/dL results in a large negative bias, potentially resulting in values less than the measuring range. Do not use urine specimens with HCl as a preservative.
In CSF sample matrix hemoglobin was found not to interfere up to 250 mg/dL at a glucose concentration of 65 mg/dL (bias less than 5.2 mg/dL).
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
A minimum of 125 human serum samples with analyte concentrations within the measuring ranges of chloride, carbon dioxide and glucose assays were tested on the VITROS XT 7600 Integrated System and the VITROS 5600 Integrated System (predicate device).
In addition, 125 human urine samples were tested for chloride and 125 human urine samples and 125 human CSF samples were tested for glucose on the candidate and predicate test systems. The results of the regression analysis are summarized below:
| Assay | n | Slope | Intercept | r | Sample Range Tested | Claimed Measuring Range |
| --- | --- | --- | --- | --- | --- | --- |
| Cl- Serum (mmol/L) | 125 | 1.00 | -0.11 | 1.00 | 51.2-167.5 | 50.0-175.0 |
| Cl- Urine (mmol/L) | 123 | 1.00 | -0.11 | 1.00 | 15-290 | 15-300 |
| ECO2 Serum (mmol/L) | 124 | 0.99 | 0.19 | 1.00 | 7.1-38.4 | 5.0-40.0 |
| GLU Serum (mg/dL) | 124 | 1.00 | 0.49 | 1.00 | 22.1-593.8 | 20.0-625.0 |
| GLU Urine (mg/dL) | 125 | 1.00 | 0.28 | 1.00 | 25.3-600.4 | 20.0-650.0 |
| GLU CSF (mg/dL) | 125 | 1.00 | 0.22 | 1.00 | 22.9-649.5 | 20.0-650.0 |
{15}
# b. Matrix comparison:
Based on the sponsor's risk analysis for adding the VITROS Chemistry Products Cl-Slides, VITROS Chemistry Products ECO2 Slides and VITROS Chemistry Products GLU Slides to the VITROS XT 7600 Integrated system and the results of the analytical testing conducted that demonstrated that there was no impact on the assays' performance characteristics, new matrix comparison studies were not performed. FDA found this justification to be acceptable.
The sample types are:
The VITROS Chemistry Products Cl- Slides are suitable for use with serum, lithium heparin plasma, and urine.
VITROS Chemistry Products ECO2 Slides can be used with serum, lithium heparin and sodium heparin plasma.
The VITROS Chemistry Products GLU Slides are suitable for testing serum, plasma samples collected in EDTA, lithium heparin, sodium heparin, and sodium fluoride/potassium oxalate tubes, and also in urine and CSF.
# 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:
| Assay | Range |
| --- | --- |
| Serum Chloride | 98–107 (mmol/L)1 |
| Urine Chloride | Random2 18–209 mmol/L |
{16}
| Assay | Range |
| --- | --- |
| | 24 Hour 4 110–250 mmol/day* |
| CO2 | 22–30 (mmol/L) 3 |
| Serum Glucose | 74–106 mg/dL |
| Fasting adults | |
| Urine Glucose | Random <30 mg/dL |
| | 24 Hour <500 mg/day** |
| CSF Glucose | 40-70 mg/dL |
1. This reference interval is the central 95% of serum results from an internal study of 60 apparently healthy individuals from a working population.
2. This reference interval is the central 95% of urine results from an internal study of 135 apparently healthy individuals from a working population.
3. This reference interval is the central 95% of results from a study of 60 apparently healthy adults from a working population (34 females and 26 males).
4. Wu, Alan H.B. Tietz Clinical Guide to Laboratory Tests. 4th ed. Saunders Elsevier, St. Louis, MO: 2006, 234-241
* Chloride concentration (mmol/L) x 24-hour volume (L) = mmol/day
**Glucose concentration (mg/dL) x 24-hour volume (dL) = mg/day.
## N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Parts 801 and 809, as applicable.
## O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.