K183688 · Abbott Point of Care, Inc. · JGS · Feb 7, 2020 · Clinical Chemistry
Device Facts
Record ID
K183688
Device Name
i-STAT CHEM8+ cartridge with the i-STAT 1 System
Applicant
Abbott Point of Care, Inc.
Product Code
JGS · Clinical Chemistry
Decision Date
Feb 7, 2020
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1665
Device Class
Class 2
Indications for Use
The i-STAT CHEM8+ cartridge with the i-STAT 1 System is intended for use in the in vitro quantification of sodium, potassium, chloride and blood urea nitrogen in arterial or venous whole blood in point of care or clinical laboratory settings. Sodium measurements are used for monitoring electrolyte imbalances. Potassium measurements are used in the diagnosis and monitoring of diseases and clinical conditions that manifest high and low potassium levels. Chloride measurements are primarily used in the diagnosis, monitoring, and treatment of electrolyte and metabolic disorders including, but not limited to, cystic fibrosis, diabetic acidosis, and hydration disorders. Blood urea nitrogen measurements are used for the diagnosis, monitoring, and treatment of certain renal and metabolic diseases.
Device Story
i-STAT CHEM8+ cartridge is a single-use, disposable, microfabricated silicon chip-based sensor system used with the i-STAT 1 handheld analyzer. It processes 65 μL of arterial or venous whole blood. The system utilizes ion-selective electrodes (potentiometric method) to measure potential differences between the sample and a calibrant solution. The analyzer calculates analyte concentrations using the Nernst equation. Designed for use by trained medical professionals in point-of-care or clinical laboratory settings. The device provides quantitative results for sodium, potassium, chloride, and BUN, enabling rapid assessment of electrolyte imbalances and renal function to support clinical decision-making.
Clinical Evidence
Bench testing only. Precision studies (internal and point-of-care) evaluated repeatability and reproducibility across multiple sites and analyzers. Linearity was confirmed using polynomial regression. Interference studies identified specific concentration limits for substances like lithium bromide, sodium thiosulfate, and triglycerides. Method comparison studies against the predicate device (N=177-188) showed strong correlation (r=0.92-0.99) across the reportable ranges.
Technological Characteristics
Microfabricated thin-film ion-selective electrodes on a silicon chip. Potentiometric sensing principle. Handheld analyzer with disposable cartridge containing fluid channels, pouch, and waste chamber. Traceable to NIST SRM 956 (Na, K, Cl) and NIST SRM 909 (BUN).
Indications for Use
Indicated for in vitro quantification of sodium, potassium, chloride, and blood urea nitrogen in arterial or venous whole blood for patients requiring electrolyte or renal function monitoring in point-of-care or clinical laboratory settings.
Regulatory Classification
Identification
A sodium test system is a device intended to measure sodium in serum, plasma, and urine. Measurements obtained by this device are used in the diagnosis and treatment of aldosteronism (excessive secretion of the hormone aldosterone), diabetes insipidus (chronic excretion of large amounts of dilute urine, accompanied by extreme thirst), adrenal hypertension, Addison's disease (caused by destruction of the adrenal glands), dehydration, inappropriate antidiuretic hormone secretion, or other diseases involving electrolyte imbalance.
Predicate Devices
SYNCHRON Systems Sodium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System (K042291)
SYNCHRON Systems Potassium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System (K042291)
SYNCHRON Systems Chloride Reagent on UniCel DxC 600/800 SYNCHRON Clinical System (K042291)
SYNCHRON Systems BUN Reagent on UniCel DxC 600/800 SYNCHRON Clinical System (K042291)
Submission Summary (Full Text)
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K183688
B Applicant
Abbott Point of Care Inc.
C Proprietary and Established Names
i-STAT CHEM8+ cartridge with the i-STAT 1 System
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| JGS | Class II | 21 CFR 862.1665 - Sodium Test System | CH - Clinical Chemistry |
| CDS | Class II | 21 CFR 862.1770 - Urea Nitrogen Test System | CH - Clinical Chemistry |
| CEM | Class II | 21 CFR 862.1600 - Potassium Test System | CH - Clinical Chemistry |
| CGZ | Class II | 21 CFR 862.1170 - Chloride Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Modification of a previously cleared device—modification to the i-STAT CHEM8+ (blue) cartridge run on the i-STAT 1 Analyzer
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
B Measurand:
Sodium (Na)
Potassium (K)
Chloride (Cl)
Blood Urea Nitrogen (BUN)
C Type of Test:
Quantitative, Ion Specific Electrode (Potentiometric method)
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The i-STAT CHEM8+ cartridge with the i-STAT 1 System is intended for use in the in vitro quantification of sodium, potassium, chloride and blood urea nitrogen in arterial or venous whole blood in point of care or clinical laboratory settings.
Sodium measurements are used for monitoring electrolyte imbalances.
Potassium measurements are used in the diagnosis and monitoring of diseases and clinical conditions that manifest high and low potassium levels.
Chloride measurements are primarily used in the diagnosis, monitoring, and treatment of electrolyte and metabolic disorders including, but not limited to, cystic fibrosis, diabetic acidosis, and hydration disorders.
Blood urea nitrogen measurements are used for the diagnosis, monitoring, and treatment of certain renal and metabolic diseases.
C Special Conditions for Use Statement(s):
For Prescription Use Only
For Point-of-Care or clinical laboratory setting
D Special Instrument Requirements:
i-STAT 1 Analyzer
K183688 - Page 2 of 19
{2}
K183688 - Page 3 of 19
## IV Device/System Characteristics:
### A Device Description:
The i-STAT 1 System consists of the i-STAT 1 Analyzer and the i-STAT CHEM+ (blue) cartridges. The system is designed for use by trained medical professionals at the patient point of care or in the clinical laboratory and is for prescription use only.
The i-STAT 1 Analyzer (previously cleared under k103195 as the i-STAT 1 Wireless Analyzer) is a handheld device designed to run only i-STAT test cartridges. The instrument interacts with the cartridge to move fluid across the sensors and generate a quantitative result.
The single-use, disposable i-STAT CHEM8+ cartridge contains test reagents to analyze whole blood at the point of care or in the clinical laboratory for sodium, potassium, chloride, blood urea nitrogen, and other analytes. The cartridge format allows all the tests in the cartridge to be performed simultaneously. The cartridges contain the required sensors, a fluid pouch, a sample entry well and closure, fluid channels, waste chamber, and the necessary mechanical features for controlled fluid movement within the cartridge. Cartridges require two to three drops of whole blood which are typically applied to the cartridge using a transfer device, by the trained user before the cartridge is placed within the analyzer.
### B Principle of Operation:
The sensors are microfabricated thin film electrodes on a silicon chip. A lead line connects the sensors to contact pads. The sensors and lead line are contained within the cartridge; the contact pads are exposed to allow direct contact with the analyzer. The contact pads conduct the signals generated by the sensors to the analyzer. The analyzer connects to the contact pads of the sensor via contact pins that lower inside the analyzer upon insertion of the cartridge. When the sensor generates an electrical signal (in response to contact with the patient sample and the presence or absence of each analyte of interest), the signal is carried by the lead line to the contact pad where the signal generated by the sensor is read by the analyzer.
Ion selective methods are based on the measurement of potential difference (voltage) between the ion selective electrode and the reference electrode (both are found on the biosensors within the cartridge). The biosensor chips convert the activity of the ion dissolved in the patient sample into an electrical signal which can be measured. The concentration of sodium, potassium, chloride and BUN in the patient sample is calculated (derived from the Nernst equation) from the difference between the patient sample and the calibrant solution electrical signals.
### V Substantial Equivalence Information:
#### A Predicate Device Name(s):
SYNCHRON Systems Sodium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System, SYNCHRON Systems Potassium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System, SYNCHRON Systems Chloride Reagent on UniCel DxC 600/800 SYNCHRON
{3}
Clinical System, SYNCHRON Systems BUN Reagent on UniCel DxC 600/800 SYNCHRON Clinical System.
B Predicate 510(k) Number(s): K042291
C Comparison with Predicate(s):
Sodium
| Device & Predicate Device(s): | K183688 | K042291 |
| --- | --- | --- |
| Device Trade Name | i-STAT CHEM8+ with the i-STAT 1 System (Sodium) | YNCHRON Systems Sodium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Quantitative determination of sodium
Sodium measurements are used for monitoring electrolyte imbalances. | Same |
| General Device Characteristic Differences | | |
| Sample Type | Arterial and venous whole blood | Serum, plasma, urine |
| Sample Volume | 65 μL | 0.5 mL (500 μL) |
| Reportable Range | 100-180 mmol/L | 100-200 mmol/L (serum or plasma) |
| Traceability | NIST SRM 956 | NIST SRM 919 |
| Reagent Format | Cartridge | Reagent handling system, stored within analyzer |
| Analyzer Type | Handheld | Floor model |
K183688 - Page 4 of 19
{4}
# Potassium
| Device & Predicate Device(s): | K183688 | K042291 |
| --- | --- | --- |
| Device Trade Name | i-STAT CHEM8+ with the i-STAT 1 System (Potassium) | SYNCHRON Systems Potassium Reagent on UniCel DxC 600/800 SYNCHRON Clinical System |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Quantitative determination of potassium
Potassium measurements are used in the diagnosis and monitoring of diseases and clinical conditions that manifest high and low potassium levels. | Same |
| General Device Characteristic Differences | | |
| Sample Type | Arterial and venous whole blood | Serum, plasma, urine |
| Sample Volume | 65 μL | 0.5 mL (500 μL) |
| Reportable Range | 2.0–9.0 mmol/L | 1.0–15.0 mmol/L (serum or plasma) |
| Traceability | NIST SRM 956 | NIST SRM 919 |
| Reagent Format | Cartridge | Reagent handling system, stored within analyzer |
| Analyzer Type | Handheld | Floor model |
# Chloride
| Device & Predicate Device(s): | K183688 | K042291 |
| --- | --- | --- |
| Device Trade Name | i-STAT CHEM8+ with the i-STAT 1 System (Chloride) | SYNCHRON Systems Chloride Reagent on UniCel DxC 600/800 SYNCHRON Clinical System |
K183688 - Page 5 of 19
{5}
| General Device Characteristic Similarities | | |
| --- | --- | --- |
| Intended Use/Indications For Use | Quantitative determination of chloride
Chloride measurements are primarily used in the diagnosis, monitoring, and treatment of electrolyte and metabolic disorders including, but not limited to, cystic fibrosis, diabetic acidosis, and hydration disorders. | Same |
| General Device Characteristic Differences | | |
| Sample Type | Arterial and venous whole blood | Serum, plasma, urine |
| Sample Volume | 65 μL | 0.5 mL (500 μL) |
| Chloride Reportable Range | 65-140 mmol/L | 50-200 mmol/L (serum or plasma) |
| Traceability | NIST SRM 956 | NIST SRM 919 |
| Reagent Format | Cartridge | Reagent handling system, stored within analyzer |
| Analyzer Type | Handheld | Floor model |
Blood Urea Nitrogen (BUN)
| Device & Predicate Device(s): | K183688 | K042291 |
| --- | --- | --- |
| Device Trade Name | i-STAT CHEM8+ with the i-STAT 1 System (BUN) | SYNCHRON Systems BUN Reagent on UniCel DxC 600/800 SYNCHRON Clinical System |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Quantitative determination of BUN concentration | Same |
K183688 - Page 6 of 19
{6}
| | Blood urea nitrogen measurements are used for the diagnosis, monitoring, and treatment of certain renal and metabolic diseases. | |
| --- | --- | --- |
| Principle of Measurement | Ion selective electrode | Same |
| General Device Characteristic Differences | | |
| Sample Type | Arterial and venous whole blood | Serum, plasma, urine |
| Sample Volume | 65 μL | 0.5 mL (500 μL) |
| BUN Reportable Range | 3-140 mg/L | 1-150 mg/dL (serum or plasma) |
| Traceability | NIST SRM 956 | NIST SRM 919 |
| Reagent Format | Cartridge | Reagent handling system, stored within analyzer |
| Analyzer Type | Handheld | Floor model |
VI Standards/Guidance Documents Referenced:
CLSI EP05-A3: Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline-Third Edition
CLSI EP06-A: Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline
CLSI EP07-A2: Interference Testing in Clinical Chemistry; Approved Guideline-Second Edition
CLSI EP17-A2: Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Internal site precision
A single-site precision study for the sodium, potassium, chloride, and BUN assays was conducted following the recommendations in CLSI EP05-A3. Five concentration levels of commercially available i-STAT calibration verification samples were tested using one lot of i-
K183688 - Page 7 of 19
{7}
STAT CHEM8+ (blue) cartridges and twelve i-STAT 1 Analyzers. Each sample was measured in duplicates per run, with two runs per day for 20-days resulting in a total of 80 test results per level. The results are summarized below.
Sodium:
| Level | Mean (mmol/L) | Within-run | | Between-run | | Between-day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| L 1 | 100.0 | 0.25 | 0.3 | 0.07 | 0.1 | 0.07 | 0.1 | 0.27 | 0.3 |
| L 2 | 121.6 | 0.33 | 0.3 | 0.09 | 0.1 | 0.10 | 0.1 | 0.35 | 0.3 |
| L 3 | 134.8 | 0.28 | 0.2 | 0.09 | 0.1 | 0.10 | 0.1 | 0.31 | 0.2 |
| L 4 | 160.4 | 0.39 | 0.2 | 0.10 | 0.1 | 0.10 | 0.1 | 0.41 | 0.3 |
| L 5 | 178 | 0.40 | 0.2 | 0.10 | 0.1 | 0.11 | 0.1 | 0.42 | 0.2 |
Potassium:
| Level | Mean (mmol/L) | Within-run | | Between-run | | Between-day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| L 1 | 2.07 | 0.006 | 0.3 | 0.001 | 0.05 | 0.002 | 0.1 | 0.006 | 0.3 |
| L 2 | 2.83 | 0.011 | 0.4 | 0.003 | 0.1 | 0.002 | 0.1 | 0.011 | 0.4 |
| L 3 | 3.69 | 0.008 | 0.2 | 0.004 | 0.1 | 0.003 | 0.1 | 0.010 | 0.3 |
| L 4 | 6.17 | 0.017 | 0.3 | 0.002 | 0.03 | 0.007 | 0.1 | 0.018 | 0.3 |
| L 5 | 7.75 | 0.027 | 0.3 | 0.017 | 0.2 | 0.009 | 0.1 | 0.033 | 0.4 |
Chloride:
| Level | Mean (mmol/L) | Within-run | | Between-run | | Between-day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| L 1 | 70.9 | 0.43 | 0.6 | 0.12 | 0.2 | 0.12 | 0.2 | 0.47 | 0.7 |
| L 2 | 76.2 | 0.50 | 0.7 | 0.13 | 0.2 | 0.13 | 0.2 | 0.53 | 0.7 |
| L 3 | 89.2 | 0.29 | 0.3 | 0.08 | 0.1 | 0.12 | 0.1 | 0.33 | 0.4 |
| L 4 | 107.9 | 0.40 | 0.4 | 0.11 | 0.1 | 0.12 | 0.1 | 0.43 | 0.4 |
| L 5 | 122.3 | 0.44 | 0.4 | 0.15 | 0.1 | 0.12 | 0.1 | 0.48 | 0.4 |
BUN:
| Level | Mean (mmol/L) | Within-run | | Between-run | | Between-day | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| L 1 | 107.3 | 0.81 | 0.8 | 0.41 | 0.4 | 0.04 | 0.04 | 0.91 | 0.8 |
| L 2 | 59.7 | 0.86 | 1.4 | 0.23 | 0.4 | 0.20 | 0.3 | 0.92 | 1.5 |
| L 3 | 10.5 | 0.11 | 1.0 | 0.05 | 0.5 | 0.03 | 0.3 | 0.12 | 1.1 |
| L 4 | 8.1 | 0.17 | 2.1 | 0.03 | 0.4 | 0.05 | 0.6 | 0.18 | 2.2 |
| L 5 | 4.1 | 0.14 | 3.4 | 0.04 | 1.0 | 0.03 | 0.7 | 0.15 | 3.7 |
Point of Care precision - aqueous control material
At three-site precision study was performed using a panel of five levels of aqueous control solutions, containing different levels of each analyte. Each sample was assayed at each site once per day for five days across each of six i-STAT 1 Analyzers for a total of 90
K183688 - Page 8 of 19
{8}
measurements. At each site, all testing was conducted by one operator using 6 lots of i-STAT CHEM8+ (blue) cartridges. The results were analyzed for within-run, between run, between day, and overall (summation of within run, between-run and between-day) and provided in the tables below:
Sodium:
| | | Within-day | | Within-site | | Overall | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean (mmol/L) | SD | %CV | SD | %CV | SD | %CV |
| Level 1 | 100.1 | 0.32 | 0.3 | 0.32 | 0.3 | 0.33 | 0.3 |
| Level 2 | 121.4 | 0.49 | 0.4 | 0.49 | 0.4 | 0.56 | 0.5 |
| Level 3 | 135.0 | 0.39 | 0.3 | 0.39 | 0.3 | 0.39 | 0.3 |
| Level 4 | 161.9 | 0.50 | 0.3 | 0.52 | 0.3 | 0.52 | 0.3 |
| Level 5 | 177.5 | 0.57 | 0.3 | 0.59 | 0.3 | 0.59 | 0.3 |
Potassium:
| | | Within-day | | Within-site | | Overall | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean (mmol/L) | SD | %CV | SD | %CV | SD | %CV |
| Level 1 | 2.10 | 0.000 | 0.0 | 0.000 | 0.0 | 0.000 | 0.0 |
| Level 2 | 2.80 | 0.018 | 0.7 | 0.018 | 0.7 | 0.021 | 0.7 |
| Level 3 | 3.70 | 0.000 | 0.0 | 0.000 | 0.0 | 0.000 | 0.0 |
| Level 4 | 6.21 | 0.038 | 0.6 | 0.038 | 0.6 | 0.6 | 0.040 |
| Level 5 | 7.85 | 0.049 | 0.6 | 0.049 | 0.6 | 0.059 | 0.8 |
Chloride:
| | | Within-day | | Within-site | | Overall | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean (mmol/L) | SD | %CV | SD | %CV | SD | %CV |
| Level 1 | 72.1 | 0.61 | 0.8 | 0.63 | 0.9 | 0.063 | 0.9 |
| Level 2 | 77.0 | 0.52 | 0.7 | 0.53 | 0.7 | 0.54 | 0.7 |
| Level 3 | 89.6 | 0.45 | 0.5 | 0.53 | 0.6 | 0.53 | 0.6 |
| Level 4 | 107.4 | 0.62 | 0.6 | 0.70 | 0.7 | 0.78 | 0.7 |
| Level 5 | 120.6 | 0.56 | 0.5 | 0.62 | 0.5 | 0.64 | 0.5 |
BUN:
| | | Within-day | | Within-site | | Overall | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | Mean (mg/dL) | SD | %CV | SD | %CV | SD | %CV |
| Level 1 | 106.2 | 0.96 | 0.9 | 1.05 | 1.0 | 1.07 | 1.0 |
| Level 2 | 58.8 | 0.56 | 1.0 | 0.57 | 1.0 | 0.57 | 1.0 |
| Level 3 | 10.1 | 0.29 | 2.9 | 0.30 | 3.0 | 0.30 | 3.0 |
| Level 4 | 8.1 | 0.26 | 3.2 | 0.27 | 3.3 | 0.27 | 3.4 |
| Level 5 | 5.0 | 0.00 | 0.0 | 0.00 | 0.0 | 0.00 | 0.0 |
Point of Care precision - whole blood
A three-site precision study was performed using lithium heparin venous whole blood samples targeted to three levels of each analyte. The testing was conducted by multiple operators at each site. Each sample was tested three times on each of seven i-STAT 1 Analyzers on one day for a total of 21 test results. The results were analyzed for variance from within-analyzer
K183688 - Page 9 of 19
{9}
(repeatability) and total (combined within-analyzer and between-analyzer variance components). Results are summarized in the tables below.
Sodium:
| Concentration (mmol/L) | Site | N | Mean (mmol/L) | Within-analyzer | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| ≤ 134 | 1 | 21 | 110.3 | 0.49 | 0.4 | 0.49 | 0.4 |
| | 2 | 21 | 123.9 | 0.38 | 0.3 | 0.38 | 0.3 |
| | 3 | 21 | 108.3 | 0.44 | 0.4 | 0.49 | 0.5 |
| 135-145 | 1 | 21 | 136.5 | 0.65 | 0.5 | 0.68 | 0.5 |
| | 2 | 21 | 138.3 | 0.53 | 0.4 | 0.53 | 0.4 |
| | 3 | 21 | 139.8 | 0.44 | 0.3 | 0.44 | 0.3 |
| ≥ 146 | 1 | 21 | 150.1 | 0.62 | 0.4 | 0.62 | 0.4 |
| | 2 | 21 | 163.2 | 0.49 | 0.3 | 0.49 | 0.3 |
| | 3 | 21 | 150.1 | 0.38 | 0.3 | 0.38 | 0.3 |
Potassium:
| Concentration (mmol/L) | Site | N | Mean (mmol/L) | Within-analyzer | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| 2.75-3.25 | 1 | 21 | 2.80 | 0.022 | 0.8 | 0.022 | 0.8 |
| | 2 | 21 | 2.80 | 0.000 | 0.0 | 0.000 | 0.0 |
| | 3 | 21 | 3.05 | 0.058 | 1.9 | 0.058 | 1.9 |
| >3.25-<5.55 | 1 | 21 | 3.98 | 0.049 | 1.2 | 0.049 | 1.2 |
| | 2 | 21 | 4.24 | 0.058 | 1.4 | 0.058 | 1.4 |
| | 3 | 21 | 3.97 | 0.053 | 1.3 | 0.053 | 1.3 |
| 1.35.55-6.05 | 1 | 21 | 5.80 | 0.022 | 0.4 | 0.022 | 0.4 |
| | 2 | 21 | 5.85 | 0.058 | 1.0 | 0.058 | 1.0 |
| | 3 | 21 | 5.71 | 0.038 | 0.7 | 0.038 | 0.7 |
| 7.25-7.75 | 1 | 21 | 7.60 | 0.000 | 0.0 | 0.000 | 0.0 |
| | 2 | 21 | 7.64 | 0.053 | 0.7 | 0.053 | 0.7 |
| | 3 | 21 | 7.73 | 0.053 | 0.7 | 0.053 | 0.7 |
Chloride:
| Concentration (mmol/L) | Site | N | Mean (mmol/L) | Within-analyzer | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| < 80 | 1 | 21 | 77.0 | 0.53 | 0.7 | 0.53 | 0.7 |
| | 2 | 21 | 77.4 | 0.95 | 1.2 | 0.95 | 1.2 |
| | 3 | 21 | 76.9 | 0.62 | 0.8 | 0.66 | 0.9 |
| 90-112 | 1 | 21 | 102.0 | 0.62 | 0.6 | 0.62 | 0.6 |
| | 2 | 21 | 101.3 | 0.53 | 0.5 | 0.53 | 0.5 |
| | 3 | 21 | 104.0 | 0.62 | 0.6 | 0.62 | 0.6 |
| > 120 | 1 | 21 | 126.1 | 0.58 | 0.5 | 0.58 | 0.5 |
| | 2 | 21 | 123.8 | 0.69 | 0.6 | 0.69 | 0.6 |
| | 3 | 21 | 123.2 | 0.44 | 0.4 | 0.55 | 0.4 |
K183688 - Page 10 of 19
{10}
BUN:
| Concentration (mg/dL) | Site | N | Mean (mg/dL) | Within-analyzer | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| < 10 | 1 | 21 | 5.5 | 0.49 | 8.9 | 0.51 | 9.4 |
| | 2 | 21 | 7.0 | 0.00 | 0.0 | 0.00 | 0.0 |
| | 3 | 21 | 6.9 | 0.31 | 4.5 | 0.36 | 5.3 |
| 10-25 | 1 | 21 | 14.0 | 0.00 | 0.0 | 0.00 | 0.0 |
| | 2 | 21 | 23.5 | 0.60 | 2.5 | 0.60 | 2.5 |
| | 3 | 21 | 13.9 | 0.31 | 2.2 | 0.31 | 2.2 |
| 25-50 | 1 | 21 | 38.0 | 0.44 | 1.1 | 0.50 | 1.3 |
| | 2 | 21 | 46.0 | 1.11 | 2.4 | 1.12 | 2.4 |
| | 3 | 21 | 27.8 | 0.62 | 2.2 | 0.71 | 2.6 |
| > 110 | 1 | 21 | 111.8 | 2.82 | 2.5 | 2.82 | 2.5 |
| | 2 | 21 | 125.0 | 1.72 | 1.4 | 1.97 | 1.6 |
| | 3 | 21 | 118.6 | 1.83 | 1.5 | 1.83 | 1.5 |
2. Linearity:
The linearity of the sodium, potassium, chloride, and BUN assays on i-STAT CHEM8+ (blue) cartridge was evaluated following the recommendations in CLSI EP06-A. Lithium heparin venous whole blood was obtained from a healthy subject and was altered to produce a high sample pool and a low sample pool. Samples of intermediate concentrations were prepared by intermixing the low and high pools. Each sample was measured in replicates of 3 using 5 lots of i-STAT CHEM8+ (blue) cartridges. An assessment of linearity was performed using polynomial regression analysis.
For sodium, regression analysis found that at each level, the deviation from linearity was $\leq 0.26\mathrm{mmol / L}$ or $0.18\%$.
For potassium, regression analysis found that at each level, the deviation from linearity was $\leq 0.04\mathrm{mmol / L}$ or $0.70\%$.
For chloride, regression analysis found that at each level, the deviation from linearity was $\leq 0.31\mathrm{mmol / L}$ or $0.25\%$.
For BUN, regression analysis found that at each level, the deviation from linearity was $\leq 1.65$ mg/dL or $1.50\%$.
Linear regression analysis results for all five lots combined are presented in the tables below.
Sodium:
| Range tested (mmol/L) | Slope | Intercept | R² |
| --- | --- | --- | --- |
| 89 - 205 | 1.008 | -0.672 | 0.9994 |
K183688 - Page 11 of 19
{11}
Potassium:
| Range tested (mmol/L) | Slope | Intercept | R² |
| --- | --- | --- | --- |
| 1.7 – 10.4 | 1.006 | 0.032 | 0.9997 |
Chloride:
| Range tested (mmol/L) | Slope | Intercept | R² |
| --- | --- | --- | --- |
| 76 – 158 | 0.986 | 1.208 | 0.9981 |
BUN:
| Range tested (mg/dL) | Slope | Intercept | R² |
| --- | --- | --- | --- |
| 2 - 160 | 0.910 | 0.263 | 0.9953 |
The observed proportional response supports the claim that the sodium, potassium, chloride and BUN assays on the i-STAT CHEM8+ (blue) are linear across the following measurement ranges:
Sodium: 100 - 180 mmol/L
Potassium: 2.0 - 9.0 mmol/L
Chloride: 65 - 140 mmol/L
BUN: 3 - 140 mg/dL
3. Analytical Specificity/Interference:
The analytical specificity of the sodium, potassium, chloride and BUN assays on the i-STAT CHEM8+ (blue) cartridge was established by conducting interference studies following the recommendations in CLSI EP07-ED3 and CLSI EP37. Interference from certain exogenous and endogenous substances was assessed using lithium heparin venous whole blood spiked at two concentrations of each analyte at low and high: sodium 135±5 mmol/L and 145±5 mmol/L; potassium 3.5±0.3 mmol/L and 5.0±0.3 mmol/L; chloride 100±5 mmol/L and 110±5 mmol/L; BUN 10±4 mg/dL and 30±4 mg/dL. Each low and high sample was further divided into two aliquots: control (with no added interferent) and test (with added interferent). Each sample was measured in replicates of 10 using one lot of the i-STAT CHEM8+ (blue) cartridges. A substance was identified as an interferent if the difference in the means between the control and test samples was outside of the predefined allowable error:
For Potassium: ± 0.5 mmol/L.
For Chloride: ± 5% of the control mean/median chloride result (mmol/L).
For BUN: the greater of ± 2 mg/dL or ± 9% of the control mean/median BUN result (mg/dL).
For any substances identified as an interferent, a dose response analysis was performed to assess the highest concentration without significant error, as defined above.
K183688 - Page 12 of 19
{12}
The following table lists the concentrations of each substance at which no significant interference was found:
Sodium:
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Acetaminophen | 15.6 mg/dL |
| N-Acetyl-L-Cysteine | 15.0 mg/dL |
| Acetylsalicylic Acid | 3.0 mg/dL |
| Ammonium Chloride | 10.7 mg/dL |
| Ascorbic Acid | 5.25 mg/dL |
| β-Hydroxybutyric Acid | 62.5 mg/dL |
| Bilirubin | 40 mg/dL |
| Calcium Chloride | 20 mg/dL |
| Cholesterol | 400 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Ibuprofen | 21.9 mg/dL |
| Lithium Bromide | 325.69 mg/dL |
| Lithium Chloride | 13.6 mg/dL |
| Lithium Lactate | 90 mg/dL |
| Lithium Salicylate | 2.86 mg/dL |
| Magnesium Chloride | 10 mg/dL |
| Sodium Heparin | 330 U/dL |
| Sodium Thiosulfate | 264 mg/dL |
| Triglyceride | 1500 mg/dL |
| Uric Acid | 23.5 mg/dL |
Potassium:
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Acetaminophen | 15.6 mg/dL |
| N-Acetyl-L-Cysteine | 15.0 mg/dL |
| Acetylsalicylic Acid | 3.0 mg/dL |
| Ammonium Chloride | 10.7 mg/dL |
| Ascorbic Acid | 5.25 mg/dL |
| β-Hydroxybutyric Acid | 62.5 mg/dL |
| Benzalkonium Chloride | 1.13 mg/dL |
| Bilirubin | 40 mg/dL |
| Calcium Chloride | 20 mg/dL |
| Cholesterol | 400 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Lithium Bromide | 325.69 mg/dL |
| Lithium Chloride | 13.6 mg/dL |
| Lithium Lactate | 90 mg/dL |
| Lithium Salicylate | 2.86 mg/dL |
| Magnesium Chloride | 10 mg/dL |
K183688 - Page 13 of 19
{13}
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Sodium Heparin | 330 U/dL |
| Sodium Thiosulfate | 264 mg/dL |
| Triglyceride | 1500 mg/dL |
| Uric Acid | 23.5 mg/dL |
Chloride:
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Acetaminophen | 15.6 mg/dL |
| N-Acetyl-L-Cysteine | 15.0 mg/dL |
| Ascorbic Acid | 5.25 mg/dL |
| Bicarbonate | 294 mg/dL |
| Bilirubin | 40 mg/dL |
| β-Hydroxybutyric Acid | 62.5 mg/dL |
| Cholesterol | 400 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Lithium Bromide | 325.69 mg/dL |
| Lithium Chloride | 13.6 mg/dL |
| Lithium Lactate | 90 mg/dL |
| Lithium Salicylate | 2.86 mg/dL |
| Lithium Thiocyanate | 5.22 mg/dL |
| Magnesium Chloride | 10 mg/dL |
| Sodium Iodide | 44.82 mg/dL |
| Sodium Oxalate | 1.206 mg/dl |
| Sodium Thiosulfate | 264 mg/dL |
| Triglyceride | 1500 mg/dL |
| Uric Acid | 23.5 mg/dL |
BUN:
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Acetaminophen | 15.6 mg/dL |
| N-Acetyl-L-Cysteine | 15.0 mg/dL |
| Ascorbic Acid | 5.25 mg/dL |
| Bilirubin | 40 mg/dL |
| β-Hydroxybutyric Acid | 62.5 mg/dL |
| Cholesterol | 400 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Hydroxyurea | 3.08 mg/dL |
| Lithium Bromide | 325.69 mg/dL |
| Lithium Lactate | 90 mg/dL |
| Lithium Salicylate | 2.86 mg/dL |
| pH | 8.0 pH units |
| Sodium Thiocyanate | 5.22 mg/dL |
K183688 - Page 14 of 19
{14}
| Substance | Highest concentration at which no interference was observed |
| --- | --- |
| Sodium Thiosulfate | 264 mg/dL |
| Triglyceride | 1500 mg/dL |
For those substances that on initial screening where found to interfere, dose response testing was conducted to establish the concentration limit below which no significant interference is expected. The results are summarized in the table below:
| Substance | Concentration | Interference |
| --- | --- | --- |
| Lithium Bromide | ≥ 2.4 mmol/L | Increased chloride results |
| Sodium Thiosulfate | ≥3.1 mmol/L | Increased sodium results |
| Sodium Thiosulfate | ≥ 4.19 mmol/L | Increased chloride results |
| Triglycerides | ≥ 10.2 mmol/L | Increased BUN results |
The sponsor includes the following statements in the labeling for the device:
Lithium Bromide at $\geq 2.4\mathrm{mmol / L}$ showed increased chloride results. Bromide at $2.5\mathrm{mmol / L}$ is the peak plasma concentration associated with halothane anesthesia, in which bromide is released. Bromide may result in an increased rate of star outs $(^{***})$
Nithiodote (sodium thiosulfate) at $\geq 3.1\mathrm{mmol / L}$ shows increased sodium results. Sodium thiosulfate is indicated for the treatment of acute cyanide poisoning. The journal article titled "Falsely increased chloride and missed anion gap elevation during treatment with sodium thiosulfate" indicated that sodium thiosulfate could be used in the treatment of calciphylaxis indicating that "the highest concentration likely to be seen in plasma [is] after infusion of a $12.5\mathrm{g}$ dose of sodium thiosulfate pentahydrate. Assuming that the $12.5\mathrm{g}$ dose of sodium thiosulfate pentahydrate is distributed in a typical blood volume of $5\mathrm{L}$ with a hematocrit of $40\%$ , the peak sodium thiosulfate plasma concentration expected is $16.7\mathrm{mmol / L}$ .
4. Assay Reportable Range:
See section A.2. Linearity.
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The sodium, potassium, and chloride assays on the i-STAT CHEM8+ (blue) cartridges and sodium, potassium, and chloride values assigned to i-STAT controls and calibration verification materials are traceable to the U.S. National Institute of Standards and Technology (NIST) standard reference material NIST SRM 956.
The BUN assay on the i-STAT CHEM8+ (blue) cartridges and BUN values assigned to i-STAT controls and calibration verification materials are traceable to the U.S. National Institute of Standards and Technology (NIST) standard reference material NIST SRM 909.
K183688 - Page 15 of 19
{15}
K183688 - Page 16 of 19
6. Detection Limit:
The detection limits are supported by the linearity study (please see section 2 above). In addition, a limit of quantitation (LoQ) study for each analyte on the i-STAT CHEM8+ Cartridge with the i-STAT 1 Analyzer was conducted following the recommendations in CLSI EP17-A2.
LoQ
The LoQ for sodium, potassium, chloride and BUN were evaluated using four lithium venous whole blood samples that were collected on each day from a unique healthy subject. The whole blood sample was altered to low sodium (<100 mmol/L), potassium (< 2.0 mmol/L), or BUN (<3 mg/dL) concentrations. Each of the four samples was measured in 15 replicates per day for four days across each of two i-STAT CHEM8+ (blue) cartridges for a total of 120 cartridges tested. The LoQ was calculated for each of the two lots. The sponsor defined LoQ as the greater of the two lots at which the lowest concentration met the pre-defined total error goal listed in the table below for each analyte.
The results are summarized in the table below.
| Analyte | Reportable Range | Total Error (TE) | LoQ |
| --- | --- | --- | --- |
| Sodium | 100 – 180 mmol/L | ≤ 4.00 | 91 mmol/L |
| Potassium | 2.0 – 9.0 mmol/L | ≤ 0.500 | 1.5 mmol/L |
| Chloride | 65 – 140 mmol/L | ≤ 3.25 | 56 mmol/L |
| BUN | 3 – 140 mg/dL | ≤ 2.00 | 1 mg/dL |
7. Assay Cut-Off:
Not applicable.
B Comparison Studies:
1. Method Comparison with Predicate Device:
The accuracy of the sodium, potassium, chloride, BUN assays with the i-STAT CHEM8+ (blue) cartridge on the i-STAT 1 Analyzer was evaluated by a method comparison study for agreement with the predicate devices. The study was conducted across two point of care sites.
Sodium:
A total of 141 lithium heparin venous blood specimens and 46 lithium heparin arterial whole blood specimens were tested using two lots of i-STAT CHEM 8+ (blue) cartridges. Twelve specimens were contrived. The data were analyzed by passing-Bablok regression analysis comparing the first replicate of the candidate deice results to the singlicate result of the predicate device.
{16}
| Site | N | Sample Range Tested (mmol/L) | Regression Equation | r |
| --- | --- | --- | --- | --- |
| 1 | 141 | 102 – 174 | y = 2.00 + 1.00x | 0.98 |
| 2 | 46 | 129 – 168 | y = 1.00 + 1.00x | 0.81 |
| combined | 187 | 102 - 174 | y = 2.00 + 1.00x | 0.96 |
# Potassium:
A total of 143 lithium heparin venous blood specimens and 46 lithium heparin arterial whole blood specimens were tested using two lots of i-STAT CHEM $8+$ (blue) cartridges. Twelve specimens were contrived. The data were analyzed by passing-Bablok regression analysis comparing the first replicate of the candidate deice results to the singlicate result of the predicate device.
| Site | N | Sample Range Tested (mmol/L) | Regression Equation | r |
| --- | --- | --- | --- | --- |
| 1 | 143 | 2.1 – 8.0 | y = 0.00 + 1.00x | 1.00 |
| 2 | 46 | 3.1 – 5.8 | y = 0.00 + 1.00x | 0.96 |
| combined | 188 | 2.1 – 8.0 | y = 0.00 + 1.00x | 0.99 |
# Chloride:
A total of 131 lithium heparin venous blood specimens and 46 lithium heparin arterial whole blood specimens were tested using two lots of i-STAT CHEM $8+$ (blue) cartridges. Twelve specimens were contrived. The data were analyzed by passing-Bablok regression analysis comparing the first replicate of the candidate deice results to the singlicate result of the predicate device.
| Site | N | Sample Range Tested (mmol/L) | Regression Equation | r |
| --- | --- | --- | --- | --- |
| 1 | 131 | 75 – 123 | y = 0.00 + 1.00x | 0.97 |
| 2 | 46 | 75 – 123 | y = 0.00 + 1.00x | 0.78 |
| combined | 177 | 75– 123 | y = 0.00 + 1.00x | 0.92 |
# BUN:
A total of 13 lithium heparin venous blood specimens and 46 lithium heparin arterial whole blood specimens were tested using two lots of i-STAT CHEM $8+$ (blue) cartridges. Twelve specimens were contrived. The data were analyzed by passing-Bablok regression analysis comparing the first replicate of the candidate deice results to the singlicate result of the predicate device.
| Site | N | Sample Range Tested (mg/dL) | Regression Equation | r |
| --- | --- | --- | --- | --- |
| 1 | 138 | 3 – 130 | y = 1.805 + 0.927x | 1.00 |
| 2 | 46 | 3 – 90 | y = 1.000 + 1.000x | 0.98 |
| combined | 184 | 3 – 130 | y = 1.675 + 0.940x | 0.99 |
K183688 - Page 17 of 19
{17}
2. Matrix Comparison:
Not applicable. Lithium heparin whole blood is the only acceptable sample type for this device.
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable.
2. Clinical Specificity:
Not applicable.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
D Clinical Cut-Off:
Not applicable.
E Expected Values/Reference Range:
Expected values for the sodium, potassium, chloride and BUN assays on the i-STAT CHEM8+ (blue) cartridge are cited from literature*:
| Analyte | Units | Reference Range |
| --- | --- | --- |
| Sodium | mmol/L | 138-146 |
| Potassium | mmol/L | 3.5-4.9 |
| Chloride | mmol/L | 98-109 |
| BUN/Urea | mg/dL | 8-26 |
*B.E. Statland, Clinical Decision Levels for Lab Tests (Oradell, NJ: Medical Economics Books, 1987).
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
K183688 - Page 18 of 19
{18}
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K183688 - Page 19 of 19
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.