K173403 · Instrumentation Laboratory CO · CHL · Dec 29, 2017 · Clinical Chemistry
Device Facts
Record ID
K173403
Device Name
GEM Premier 5000
Applicant
Instrumentation Laboratory CO
Product Code
CHL · Clinical Chemistry
Decision Date
Dec 29, 2017
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1120
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K173403 · Dec 29, 2017
GEM Premier 5000
Instrumentation Laboratory CO
Residual whole blood patient samples from clinical point-of-care (POC) sites
Residual patient samples were used to evaluate the precision and method comparison of the GEM Premier 5000 in a clinical point-of-care setting, comparing performance against the predicate device.
Point-of-care; Residual patient samples; Method comparison; Precision study
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Prospective precision study using residual patient samples; Follow-up/Duration: 5 days
Patients at an external point-of-care (POC) site; Sample Size: Minimum of 20 residual whole blood samples; Number of Sites: 1
Not applicable for this study
Within-sample SD and %CV for pCO2, K+, Cl-, Hct, and tHb
Method comparison study
Patients at an external POC site; Sample Size: Minimum of 40 native capillary samples (external) and 80 native samples (internal CSL); Number of Sites: 2 (External POC site and Internal CSL)
GEM Premier 4000 (predicate device)
Bias at medical decision levels, regression analysis (slope, intercept, r)
Indications for Use
The GEM Premier 5000 is a portable critical care system for use by health care professionals to rapidly analyze heparinized whole blood samples at the point of health care delivery in a clinical setting and in a central laboratory. The instrument provides quantitative measurements of pH, pCO2, pO2, sodium, potassium, chloride, ionized calcium, glucose, lactate, hematocrit, total bilirubin and CO-Oximetry (tHb, O2Hb, COHb, MetHb, HHb, sO2*) parameters from arterial, venous or capillary heparinized whole blood. These parameters, along with derived parameters, aid in the diagnosis of a patient's acid/base status, electrolyte and metabolite balance and oxygen delivery capacity. *sO2 = ratio between the concentration of oxyhemoglobin and oxyhemoglobin plus deoxyhemoglobin.
Device Story
Portable critical care system; analyzes heparinized whole blood samples (arterial, venous, capillary). System components: GEM Premier 5000 analyzer and GEM Premier 5000 PAK (disposable cartridge containing reagents, sensors, optical cell, sampler, waste bag). Principle of operation: potentiometric sensors (pCO2, K+, Cl-); electrical conductivity (hematocrit); spectrophotometric absorbance (total hemoglobin). Operator: healthcare professional at point-of-care or central lab. Workflow: sample aspiration into cartridge; automated analysis; results displayed on analyzer. Output: quantitative measurements of blood parameters; aids clinical decision-making regarding acid-base status, electrolyte balance, and oxygen delivery. Benefits: rapid diagnostic information for critical care patients.
Clinical Evidence
No clinical trials; performance established via bench and method comparison studies. Precision evaluated internally and at an external POC site using whole blood samples (n=56-120 per study). Method comparison against predicate (GEM Premier 4000) performed with 136-141 samples (native and contrived) spanning reportable ranges. Results showed high correlation (R=0.980-0.995) and acceptable bias at medical decision levels for pCO2, K+, Cl-, Hct, and tHb.
Technological Characteristics
System uses PVC-based ion-selective electrodes (potentiometry) for electrolytes, electrical conductivity for hematocrit, and LED-based spectrophotometry for total hemoglobin. Disposable GEM PAK cartridge contains sensors, optical cell, and reagents. Connectivity: standalone analyzer. Software: embedded firmware. Sterilization: not specified. Materials: PVC, Ag/AgCl electrodes.
Indications for Use
Indicated for health care professionals to analyze heparinized whole blood (arterial, venous, or capillary) for diagnosis of acid-base disturbances, electrolyte/metabolite balance, and oxygen delivery capacity in clinical and central laboratory settings. Used for patients requiring monitoring of pH, blood gases, electrolytes (Na, K, Ca, Cl), glucose, lactate, bilirubin, and CO-Oximetry parameters.
Regulatory Classification
Identification
A blood gases (PCO2 , PO2 ) and blood pH test system is a device intended to measure certain gases in blood, serum, plasma or pH of blood, serum, and plasma. Measurements of blood gases (PCO2 , PO2 ) and blood pH are used in the diagnosis and treatment of life-threatening acid-base disturbances.
Predicate Devices
GEM Premier 4000 (k133407)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k173403
B. Purpose for Submission:
Addition of capillary heparinized whole blood claims for pCO2, potassium, chloride, hematocrit and total hemoglobin on the GEM Premier 5000.
C. Measurand:
pCO2, potassium, chloride, hematocrit and total hemoglobin.
D. Type of Test:
Quantitative, potentiometric for pCO2, potassium, and chloride
Quantitative, electrical conductivity for hematocrit
Quantitative, spectrophotometric method for total hemoglobin
E. Applicant:
Instrumentation Laboratory Co.
F. Proprietary and Established Names:
GEM Premier 5000
G. Regulatory Information:
| Analyte | Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- | --- |
| pCO2 | CHL | Class II | 862.1120; Blood Gases (pCO2, pO2) and Blood pH system | Chemistry (75) |
| Potassium | CEM | | 862.1600; Potassium test system | |
| Chloride | CGZ | | 862.1170; Chloride test system | |
{1}
| Analyte | Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- | --- |
| Hematocrit | GKF | Class II | 862.5600; Automated hematocrit instrument | Hematology (81) |
| Total Hemoglobin | GKR | | 864.5620; Automated hemoglobin system | |
| | GLY | | 864.7500; Whole blood hemoglobin assays | |
H. Intended Use:
1. Intended use(s):
See Indications for use below
2. Indication(s) for use:
The GEM Premier 5000 is a portable critical care system for use by health care professionals to rapidly analyze heparinized whole blood samples at the point of health care delivery in a clinical setting and in a central laboratory. The instrument provides quantitative measurements of pH, $p\mathrm{CO}_2$, $p\mathrm{O}_2$, sodium, potassium, chloride, ionized calcium, glucose, lactate, hematocrit, total bilirubin and CO-Oximetry (tHb, $\mathrm{O}_2\mathrm{Hb}$, COHb, MetHb, HHb, $\mathrm{sO}_2^*$) parameters from arterial, venous or capillary heparinized whole blood. These parameters, along with derived parameters, aid in the diagnosis of a patient's acid/base status, electrolyte and metabolite balance and oxygen delivery capacity.
*sO₂ = ratio between the concentration of oxyhemoglobin and oxyhemoglobin plus deoxyhemoglobin.
- pH, $p\mathrm{CO}_2$, and $p\mathrm{O}_2$ measurements in whole blood are used in the diagnosis and treatment of life-threatening acid-base disturbances.
- Electrolytes in the human body have multiple roles. Nearly all metabolic processes depend on or vary with electrolytes:
- Sodium (Na⁺) measurements are used in the diagnosis and treatment of aldosteronism, diabetes insipidus, adrenal hypertension, Addison’s disease, dehydration, inappropriate antidiuretic secretion, or other diseases involving electrolyte imbalance.
- Potassium (K⁺) measurements are used to monitor electrolyte balance in the diagnosis and treatment of disease conditions characterized by low or high blood potassium levels.
- Ionized calcium (Ca²⁺) measurements are used in the diagnosis and treatment of parathyroid disease, a variety of bone diseases, chronic renal disease and tetany.
- Chloride (Cl⁻) measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders, such as cystic fibrosis and diabetic acidosis.
- Hematocrit (Hct) measurements in whole blood of the packed red cell volume of a
{2}
blood sample are used to distinguish normal from abnormal states, such as anemia and erythrocytosis (an increase in the number of red cells).
- Glucose (Glu) measurement is used in the diagnosis, monitoring and treatment of carbohydrate metabolism disturbances including diabetes mellitus, neonatal hypoglycemia, idiopathic hypoglycemia, and pancreatic islet cell carcinoma.
- Lactate (Lac) measurement is used:
- to evaluate the acid-base status of patients suspected of having lactic acidosis;
- to monitor tissue hypoxia and strenuous physical exertion;
- in the diagnosis of hyperlactatemia.
- Total Bilirubin (tBili) measurement is used to aid in assessing the risk of kernicterus and hyperbilirubinemia in neonates.
- CO-Oximetry (tHb, COHb, MetHb, O₂Hb, HHb, and sO₂) evaluates the ability of the blood to carry oxygen by measuring total hemoglobin and determining the percentage of functional and dysfunctional hemoglobin species.
- Total Hemoglobin (tHb): Total hemoglobin measurements are used to measure the hemoglobin content of whole blood for the detection of anemia.
- COHb: Carboxyhemoglobin measurements are used to determine the carboxyhemoglobin content of human blood as an aid in the diagnosis of carbon monoxide poisoning.
- MetHb: Methemoglobin measurements are used to determine different conditions of methemoglobinemia.
- HHb: Deoxyhemoglobin, as a fraction of total hemoglobin, is used in combination with oxyhemoglobin to measure oxygen status.
- O₂Hb: Oxyhemoglobin, as a fraction of total hemoglobin, is used in combination with deoxyhemoglobin to measure oxygen status.
- sO₂: Oxygen saturation, more specifically the ratio between the concentration of oxyhemoglobin and oxyhemoglobin plus deoxyhemoglobin, is used to measure oxygen status.
3. Special conditions for use statement(s):
For prescription use only at point-of-care and central laboratory settings
4. Special instrument requirements:
GEM Premier 5000 analyzer
I. Device Description:
The GEM Premier 5000 system contains 2 key components: the GEM Premier 5000 analyzer and the GEM Premier 5000 PAK (cartridge). The GEM Premier 5000 PAK contains reagents, sensors, optical cell for Co-Ox and total bilirubin, sampler and waste bag. It enables analysis of 75 to 600 samples per cartridge. There are 5 process control solutions (A, B, C, D and E), 1 reference electrode solution and 1 lysing solution in each GEM Premier 5000 PAK. The 5 process control solutions are utilized each day at different frequencies to confirm sensor, CO-Ox and PAK performance.
{3}
The target values of the Process Control Solutions are stated in the following table:
| Analyte | Units | A | B | C | D | E |
| --- | --- | --- | --- | --- | --- | --- |
| K+ | mmol/L | 7.1 | 1.9 | N/A | 7.2 | 4.5 |
| Cl- | mmol/L | 49 | 88 | N/A | 141 | 101 |
| pCO2 | mmHg | 65 | 33 | 33 | 25 | 67 |
| Hct | (%) | 28 | 19 | N/A | 26 | 38 |
| tHb | (g/dL) | 14.2 | 0 | N/A | 7.3 | 16.5 |
# J. Substantial Equivalence Information:
1. Predicate device name(s):
GEM Premier 4000
2. Predicate $510(\mathbf{k})$ number(s):
k133407
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Candidate Device GEM Premier 5000 k173403 | Predicate Device GEM Premier 4000 k133407 |
| Intended Use | A portable critical care system for use by health care professionals to rapidly analyze whole blood samples at the point of health care delivery in a clinical setting and in a central laboratory. | Same |
| Intended User | Central Laboratory and Point-of-Care sites | Same |
| Sample Introduction | Aspiration | Same |
| PAK Shelf-Life Stability | Up to 180 days | Same |
| PAK Storage Temperature | 15-25°C | Same |
| System Operating Temperature | 12-32°C | Same |
| Calibration | 2-point | Same |
| Reportable range pCO2 | 6 to 125 mmHg | Same |
| Reportable range Cl- | 40 to 158 mmol/L | Same |
| Reportable range Hct | 15 to 72% | Same |
| Reportable range tHb | 3.0 to 23.0 g/dL | Same |
{4}
| Differences | | |
| --- | --- | --- |
| Item | Candidate Device GEM Premier 5000 | Predicate Device GEM Premier 4000 |
| Reportable range K+ | 1.0 to 19.0 mmol/L | 0.2 to 19.0 mmol/L |
# K. Standard/Guidance Document Referenced (if applicable):
- CLSI EP5-A3, Evaluation of Precision Performance of Quantitative Measurement Methods; Third Edition, 2014.
- CLSI EP9-A3; Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Third Edition, 2013
# L. Test Principle:
The electrolyte sensors $(\mathrm{K}+,$ and Cl-) are polyvinyl chloride (PVC) based ion selective electrodes consisting of an internal $\mathrm{Ag / AgCl}$ reference electrode and an internal electrolyte layer. Their potentials are measured against the card reference electrode $(\mathrm{Ag / Ag + })$ . The electrolyte sensors are based on the principle of ion selective electrodes; in which electrical potential can be established across a membrane resulting from chemical selectivity of the membrane to a specific ion. The electrical potential is proportional to the logarithm of the analyte activity in the sample, and the concentration of the desired ions is calculated using Nernst equation.
pCO2 is measured by potentiometry using a sensor on the GEM Premier 5000 PAK. The result may be corrected for actual patient temperature if different than $37^{\circ}\mathrm{C}$ .
Hematocrit is measured by an electrical conductivity technique. The conductivity technique is based on the principle that because plasma is more conductive than blood cells due to the high resistance of the cell membranes, the resistivity of blood will increase as the concentration of cells increases. This relationship is expressed by the Maxwell-Fricke equation: $r = Rp \times (1 + Hct / 100) / (1 - Hct / 100)$ , where "r" is the blood resistivity, $Rp$ is a constant based on the plasma resistivity, and $Hct$ is hematocrit. The electrode chamber contains a miniature conductivity cell. By applying an alternating potential through the cell, the resistance of the fluid in the cell can be determined by means of Ohm's Law.
Total hemoglobin measurement is based on an optical absorbance measurement of the sample. An in-line optical cell is integrated in the flow path of the hemolyzed sample to provide a measure of hemoglobin and its derivatives. The optical cell is a flow through channel with two parallel plate optical windows separated by a well-defined path length. The chemical lysing of the sample is implemented to minimize the scattering effect of the blood and to make the spectral measurement more reliable. The optical measurement hardware, consisting of a white light-emitting diode (LED) light source, a neon reference and a high resolution spectrometer with a holographic diffraction grating and a charge-coupled device
{5}
(CCD) array, are all contained in the analyzer. Only the optical cell is located in the disposable cartridge (GEM PAK) and is aligned with the analyzer optics for spectral measurements following installation of the GEM PAK.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Three separate studies were conducted to evaluate the precision of the GEM Premier 5000 system for $\mathrm{pCO_2}$ , $\mathrm{K}^+$ , Cl, - Hct and tHb.
Internal Precision Studies
i. An internal precision study was performed using 5 whole blood samples with different concentrations of analytes, each run on 3 GEM Premier 5000 analyzers (a different cartridge lot was used with each instrument) for 5 days, with 1 run per day and 8 replicates measured per run per level. Samples were transferred from syringe to a capillary device prior testing. The results are summarized below:
| Analyte | System Evaluator Level | N | Mean | Within Run | | Between Instrument/Lot | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV | SD | %CV |
| pCO2 (mmHg) | 1 | 120 | 9.9 | 0.5 | 5.1 | 0.7 | 7.6% | 0.9 | 9.1 |
| | 2 | 120 | 34.5 | 0.6 | 1.9 | 0.4 | 1.2% | 0.8 | 2.2 |
| | 3 | 120 | 49.0 | 0.5 | 1.1 | 0.7 | 1.4% | 0.9 | 1.8 |
| | 4 | 120 | 68.9 | 1.6 | 2.3 | 1.4 | 2.1% | 2.1 | 3.1 |
| | 5 | 120 | 108.9 | 2.4 | 2.2 | 2.3 | 2.1% | 3.3 | 3.0 |
| K+ (mmol/L) | 1 | 120 | 1.46 | 0.05 | 3.2 | 0.02 | 1.4% | 0.05 | 3.5 |
| | 2 | 120 | 2.70 | 0.06 | 2.1 | 0.01 | 0.3% | 0.06 | 2.1 |
| | 3 | 120 | 5.43 | 0.04 | 0.8 | 0.02 | 0.4% | 0.05 | 0.9 |
| | 4 | 120 | 7.16 | 0.07 | 1.0 | 0.04 | 0.5% | 0.08 | 1.1 |
| | 5 | 120 | 17.29 | 0.15 | 0.9 | 0.12 | 0.7% | 0.20 | 1.1 |
| Cl- (mmol/L) | 1 | 120 | 53.4 | 0.4 | 1.0 | 0.1 | 0.2% | 0.4 | 0.8 |
| | 2 | 120 | 75.8 | 0.4 | 0.9 | 0.2 | 0.2% | 0.4 | 0.5 |
| | 3 | 120 | 89.8 | 0.4 | 0.8 | 0.1 | 0.1% | 0.4 | 0.4 |
| | 4 | 120 | 110.7 | 0.4 | 0.5 | 0.3 | 0.3% | 0.5 | 0.5 |
| | 5 | 120 | 152.8 | 0.7 | 0.4 | 0.6 | 0.4% | 0.9 | 0.6 |
| Hct (%) | 1 | 120 | 19.3 | 0.6 | 2.9 | 0.2 | 1.0% | 0.6 | 3.0 |
| | 2 | 120 | 32.8 | 0.6 | 1.9 | 0.2 | 0.5% | 0.6 | 2.0 |
| | 3 | 120 | 44.7 | 0.6 | 1.3 | 0.3 | 0.6% | 0.6 | 1.4 |
| | 4 | 120 | 55.0 | 0.8 | 1.5 | 0.4 | 0.8% | 0.9 | 1.6 |
| | 5 | 120 | 63.7 | 1.3 | 2.0 | 0.9 | 1.4% | 1.6 | 2.5 |
{6}
| Analyte | System Evaluator Level | N | Mean | Within Run | | Between Instrument/Lot | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV | SD | %CV |
| tHb (g/dL) | 1 | 120 | 7.02 | 0.16 | 2.3 | 0.00 | 0.0% | 0.16 | 2.3 |
| | 2 | 120 | 11.06 | 0.09 | 0.8 | 0.03 | 0.3% | 0.09 | 0.9 |
| | 3 | 120 | 14.47 | 0.10 | 0.7 | 0.05 | 0.3% | 0.11 | 0.8 |
| | 4 | 120 | 17.34 | 0.09 | 0.5 | 0.02 | 0.1% | 0.09 | 0.5 |
| | 5 | 120 | 19.92 | 0.25 | 1.3 | 0.00 | 0.0% | 0.25 | 1.3 |
# ii. Capillary Finger-stick Samples
An internal study was conducted in a Customer Simulation Laboratory (CSL) using native capillary whole blood samples. POC operators collected 2 capillary tubes per donor via finger stick puncture and tested each capillary tube in singlicate. Each sample pair was analyzed on the same GEM Premier 5000 analyzer. The results are summarized below:
| Analyte | n | Mean | Within Sample Precision | |
| --- | --- | --- | --- | --- |
| | | | SD | %CV |
| pCO2 (mmHg) | 56 | 39 | 1.3 | 3.3 |
| K+(mmol/L) | 56 | 4.1 | 0.11 | 2.6 |
| Cl-(mmol/L) | 56 | 106 | 0.3 | 0.3 |
| Hct (%) | 56 | 43 | 0.7 | 1.7 |
| tHb (g/dL) | 56 | 14.2 | 0.14 | 1.0 |
# External precision study
iii. A precision study was performed on a GEM Premier 5000 at an external point-of-care (POC) site, using venous heparinized whole blood patient samples transferred from syringe to a capillary device and run by 3 POC operators. The study used a minimum of 20 residual whole blood samples run over 5 days. Each sample was run in triplicate. The results are summarized below:
| Analyte | n | Mean | Within Sample precision | |
| --- | --- | --- | --- | --- |
| | | | SD | %CV |
| pCO2(mmHg) | 63 | 42 | 0.9 | 2.0 |
| | 3 | 88 | 0.6 | 0.7 |
| K+(mmol/L) | 66 | 4.0 | 0.05 | 1.2 |
| Cl-(mmol/L) | 66 | 107 | 0.5 | 0.5 |
| Hct (%) | 66 | 30 | 0.7 | 2.4 |
| tHb (g/dL) | 60 | 11.0 | 0.29 | 2.6 |
{7}
b. Linearity/assay reportable range:
Previously established in k160225, k160412, and k160415.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
As described in k160225, k160412, k160415.
d. Detection limit:
Previously established in k160225, k160412, and k160415.
e. Analytical specificity:
Previously established in k160225, k160412, and k160415.
f. Assay cut-off:
Not applicable
# 2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study for capillary whole blood was performed at an external POC site with 6 POC operators and an internal laboratory with 3 POC operators. Two capillary samples were collected via finger-stick from each patient/donor. One sample was analyzed in singlicate on the GEM Premier 5000 (test device) and the other samples was analyzed in singlicate on the GEM Premier 4000 (predicate device). To span the reportable range for each analyte, $<10\%$ of contrived samples were prepared, transferred into capillary tubes and run in singlicate on the GEM Premier 5000 and GEM Premier 4000. The study results are shown below.
| Analyte | N | Slope | Intercept | R | Sample range |
| --- | --- | --- | --- | --- | --- |
| pCO2(mmHg) | 139 | 1.000 | 1.000 | 0.980 | 11 to 87 |
| K+(mmol/L) | 140 | 1.000 | 0.100 | 0.995 | 1.5 to 17.6 |
| Cl-(mmol/L) | 141 | 1.000 | -1.000 | 0.995 | 45 to 149 |
| Hct (%) | 136 | 1.003 | -0.407 | 0.987 | 15 to 64 |
| tHb (g/dL) | 137 | 1.028 | -0.470 | 0.994 | 4.5 to 20.5 |
{8}
Results based on native samples at Medical Decision Level (MDL) are shown below:
| Analyte | N | Range Min | Range Max | ML | Bias at MDL | 95% CI of Bias at MDL |
| --- | --- | --- | --- | --- | --- | --- |
| pCO2 (mmHg) | 130 | 26 | 50 | 35 | 1.0 | 1.0 to 2.0 |
| | | | | 50 | 1.0 | 1.0 to 2.0 |
| | | | | 70 | 1.4% | 1.4% to 3.1% |
| K+ (mmol/L) | 130 | 3.1 | 6.7 | 3.0 | 0.1 | -0.03 to 0.19 |
| | | | | 5.8 | 0.1 | 0.05 to 0.30 |
| | | | | 7.5 | 1.3% | 0.7% to 6.8% |
| Cl- (mmol/L) | 129 | 90 | 111 | 90 | -1.1% | -1.1% to 0.0% |
| | | | | 112 | -0.9% | -0.9% to 0.0% |
| Ht (%) | 13 | 24 | 51 | 21 | -0.4 | -1.3 to 0.5 |
| | | | | 33 | -0.3 | -0.7 to 0.1 |
| | | | | 56 | -0.1 | -0.7 to 0.5 |
| tHb (g/dL) | 131 | 6.9 | 17.3 | 7.0 | -0.27 | -0.43 to -0.12 |
| | | | | 10.5 | -0.17 | -0.25 to -0.09 |
| | | | | 18.0 | 0.05 | -0.07 to 0.16 |
b. Matrix comparison:
Not applicable. Sponsor stated that only lithium heparin whole blood is the acceptable sample type to be used for their device.
# 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
{9}
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
k160225, k160412, k160415
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.
10
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.