The K-ASSAY® RF (Ver.2) assay is for the quantitative determination of human IgG rheumatoid factor antibodies in patient serum or plasma (citric acid, EDTA, or lithium heparin) based on immunoturbidimetric assay. The presence of IgG RF antibodies, in conjunction with clinical findings and other laboratory tests, is an aid in the diagnosis of rheumatord arthritis (RA). FOR IN VITRO DIAGNOSTIC USE. The K-ASSAY® RF Calibrator (Ver.2) is intended to be used to calibrate the K-ASSAY® RF (Ver.2) immunoturbidimetric assay. FOR IN VITRO DIAGNOSTIC USE.
Device Story
K-ASSAY® RF (Ver.2) is an in vitro diagnostic immunoturbidimetric assay for measuring human IgG rheumatoid factor antibodies in serum or plasma samples. The device utilizes an immunoturbidimetric principle where the presence of IgG RF antibodies in the sample is quantified via light scattering/absorbance changes. It is intended for use in clinical laboratory settings by trained personnel. The output is a quantitative concentration of IgG RF, which clinicians use alongside clinical findings and other laboratory tests to assist in the diagnosis of rheumatoid arthritis. The K-ASSAY® RF Calibrator (Ver.2) is used to calibrate the assay to ensure accurate measurement.
Clinical Evidence
No clinical data provided in the document; the submission is for an in vitro diagnostic assay.
Technological Characteristics
Latex-enhanced immunoturbidimetric assay. Reagents: Phosphate buffer and latex particles sensitized with human gamma globulin. Energy source: clinical chemistry analyzer light source. Connectivity: standalone analyzer integration. Calibration: 6-point liquid calibrator set. Traceability: NIBSC 64/002. Measuring range: 6.65–600 IU/mL.
Indications for Use
Indicated for the quantitative determination of human IgG rheumatoid factor antibodies in patient serum or plasma to aid in the diagnosis of rheumatoid arthritis (RA). For prescription use only.
Regulatory Classification
Identification
A rheumatoid factor immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the rheumatoid factor (antibodies to immunoglobulins) in serum, other body fluids, and tissues. Measurement of rheumatoid factor may aid in the diagnosis of rheumatoid arthritis.
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
K192727
B Applicant
Kamiya Biomedical Company
C Proprietary and Established Names
K-ASSAY RF (Ver.2)
K-ASSAY RF Calibrator (Ver.2)
D Regulatory Information:
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| DHR | Class II | 21 CFR 866.5775 - Rheumatoid Factor Immunological Test System | IM - Immunology |
| JIS | Class II Exempt | 862.1150 - Calibrator | Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
New assay
B Measurand:
Rheumatoid Factor (RF)
C Type of Test:
Quantitative latex turbidimetric assay
## III Intended Use/Indications for Use:
A Intended Use(s):
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
The K-ASSAY RF (Ver.2) assay is for the quantitative determination of human IgG rheumatoid factor antibodies in patient serum or plasma (citric acid, EDTA or lithium heparin) based on immunoturbidimetric assay. The presence of IgG RF antibodies, in conjunction with clinical findings and other laboratory tests, is an aid in the diagnosis of rheumatoid arthritis (RA). FOR IN VITRO DIAGNOSTIC USE.
The K-ASSAY® RF Calibrator (Ver.2) is intended to be used to calibrate the K-ASSAY® RF (Ver.2) immunoturbidimetric assay. FOR IN VITRO DIAGNOSTIC USE.
## B Indication(s) for Use:
See Intended Use above
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## D Special Instrument Requirements:
Clinical Chemistry Analyzer
## IV Device/System Characteristics:
## A Device Description:
The K-ASSAY RF (Ver.2) assay is comprised of the following reagents:
(a) R1: Buffer Reagent (Phosphate Buffer)
(b) R2: Latex Reagent (suspension of latex particles sensitized with human γ globulin and Phosphate Buffer)
The K-ASSAY® RF Calibrator (Ver.2) is comprised of six calibrators: A, B, C, D, E, and F. Calibrator A contains sodium chloride and sodium azide; Calibrator B-F contain pooled human serum with assigned values for the rheumatoid factor and sodium azide. The K-ASSAY® RF Calibrator (Ver.2) is sold separately.
## B Principle of Operation:
The K-ASSAY RF (Ver.2) quantifies the rheumatoid factor in the patient's serum based on latex-enhanced immunoturbidimetric assay. Calibrators, controls, and patient samples are pipetted into sample cups. Microvolumes of samples and reagent diluent are automatically pipetted into individual cuvettes.
Following an initial incubation and measurement of sample solution, gamma globulin containing aggregated human IgG is added to the cuvettes. The patient sample (autoantibodies) solution and gamma globulin reagent (antigen) are then mixed in the reaction cuvettes. Insoluble antigen-antibody (immune) complexes form. The immune complexes cause an increase in light scattering, which correlates with the concentration of rheumatoid factor. Following an incubation period lasting approximately 5 minutes, the absorbance change of the solution is measured. A calibration curve is generated by assaying a series of calibrators with known concentrations of proteins and using the instrument's data reduction capability or manually plotting the change in absorbance versus concentration. Concentration of the controls and patient samples are interpolated from the calibration curve.
K192727 - Page 2 of 9
{2}
The K-ASSAY RF (Ver.2) should be run using the K-ASSAY RF Calibrator (Ver.2). These six calibrators are used to prepare a calibration curve for quantifying the levels of rheumatoid factor present in the patient's serum or plasma sample.
K192727 - Page 3 of 9
V Substantial Equivalence Information:
A Predicate Device Name(s): K-ASSAY Rheumatoid Factor
B Predicate 510(k) Number(s): K991409
C Comparison with Predicate(s):
Assay:
| Device & Predicate Device(s): | Device K192727 | Predicate K991409 |
| --- | --- | --- |
| Device Trade Name | K-ASSAY RF (Ver.2) | K-ASSAY RF |
| General Device Characteristic Similarities | | |
| Antigen | Polyclonal IgG RF antibody | Same |
| Expected value | <11.0 IU/mL | Same |
| General Device Characteristic Differences | | |
| Intended Use/Indications For Use | The K-ASSAY RF (Ver.2) assay is for the quantitative determination of human IgG rheumatoid factor antibodies in patient serum or plasma (citric acid, EDTA or lithium heparin) based on immunoturbidimetric assay. The presence of IgG RF antibodies, in conjunction with clinical findings and other laboratory tests, is an aid in the diagnosis of rheumatoid arthritis (RA). For in vitro diagnostic use. | The K-ASSAY RF assay is for the quantitative determination of human rheumatoid factor antibodies, in patient serum based on immunoturbidimetric assay. For in vitro diagnostic use. |
| Method | Latex-enhanced immunoturbidimetric | Immunoturbidimetric |
| Sample type | Serum and Plasma (citric acid, EDTA and lithium | Serum |
{3}
| Device & Predicate Device(s): | Device K192727 | Predicate K991409 |
| --- | --- | --- |
| | heparin) | |
| Analytical Measuring Range | 6.65 – 600 IU/mL | 5 – 320 IU/mL |
| Calibrators | Six calibrator-set: 0, 15, 75, 150, 300, 600 IU/mL | Three calibrator-set: 50, 150, 300 IU/mL (saline blank is also needed, resulting in four levels) |
| Traceability | NIBSC Rheumatoid Arthritis serum 64/002 | None specified |
Calibrators:
| Device & Predicate Device(s): | Device K192727 | Predicate K991409 |
| --- | --- | --- |
| Device Trade Name | K-ASSAY RF Calibrator (Ver.2) | K-ASSAY RF |
| General Device Characteristic Similarities | | |
| Form | Liquid | Same |
| Matrix | Human serum based | Same |
| Units | IU/mL | Same |
| General Device Characteristic Differences | | |
| Intended Use/Indications For Use | The K-ASSAY® RF Calibrator (Ver.2) is intended to be used to calibrate the K-ASSAY® RF (Ver.2) immunoturbidimetric assay. for in vitro diagnostic use. | RF Calibrator was part of the cleared RF Kit and the PI listed it as required but not supplied; it had no separate IU |
VI Standards/Guidance Documents Referenced:
CLSI EP05-A3, Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition
CLSI EP6-A, Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline
CLSI EP07 3rd Edition, Interference Testing in Clinical Chemistry; Approved Guideline - Third Edition
CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline – Second Edition
K192727 - Page 4 of 9
{4}
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
All studies were performed on Abbott c8000 instruments.
1. Precision/Reproducibility:
Precision – single site evaluation study: The single site precision of the RF (Ver.2) assay was evaluated according to CLSI EP05-A3 by running eight clinical samples across the assay ranges and two commercial controls. Samples were run in duplicates, twice a day, for 20 days and one calibrator lot (total of n = 80 per sample). Three lots were evaluated independently and the results are summarized in the tables below:
Lot 1:
| | | | Repeatability | | Between-Run | | Within-Day | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean (IU/mL) | N | CV | SD | CV | SD | CV | SD | CV | SD | CV | SD |
| Control Level 1 | 43.38 | 80 | 0.6% | 0.28 | 0.0% | 0 | 0.6% | 0.28 | 0.5% | 0.23 | 0.8% | 0.36 |
| Control Level 2 | 91.46 | 80 | 0.3% | 0.27 | 0.5% | 0.45 | 0.6% | 0.52 | 0.0% | 0 | 0.6% | 0.52 |
| Sample 1 | 13.65 | 80 | 4.3% | 0.59 | 1.2% | 0.17 | 4.5% | 0.61 | 0.0% | 0 | 4.5% | 0.61 |
| Sample 2 | 21.92 | 80 | 2.0% | 0.45 | 0.8% | 0.18 | 2.2% | 0.48 | 1.4% | 0.31 | 2.6% | 0.58 |
| Sample 3 | 99.17 | 80 | 0.3% | 0.34 | 0.6% | 0.61 | 0.7% | 0.70 | 0.7% | 0.70 | 1.0% | 0.9 |
| Sample 4 | 250.94 | 80 | 0.5% | 1.30 | 0.3% | 0.78 | 0.6% | 1.52 | 0.5% | 1.21 | 0.8% | 1.94 |
| Sample 5 | 285.02 | 80 | 0.6% | 1.57 | 0.6% | 1.71 | 0.8% | 2.32 | 0.2% | 0.60 | 0.8% | 2.40 |
| Sample 6 | 313.93 | 80 | 0.6% | 1.88 | 0.0% | 0 | 0.6% | 1.88 | 0.2% | 0.73 | 0.6% | 2.02 |
| Sample 7 | 349.20 | 80 | 0.6% | 2.21 | 0.1% | 0.50 | 0.6% | 2.27 | 0.2% | 0.85 | 0.7% | 2.42 |
| Sample 8 | 521.95 | 80 | 0.6% | 3.33 | 0.0% | 0 | 0.6% | 3.33 | 0.5% | 2.42 | 0.8% | 4.11 |
Lot 2:
| | | | Repeatability | | Between-Run | | Within-Day | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean (IU/mL) | N | CV | SD | CV | SD | CV | SD | CV | SD | CV | SD |
| Control Level 1 | 43.38 | 80 | 0.6% | 0.28 | 0.0% | 0 | 0.6% | 0.28 | 0.5% | 0.23 | 0.8% | 0.36 |
| Control Level 2 | 91.46 | 80 | 0.3% | 0.27 | 0.5% | 0.45 | 0.6% | 0.52 | 0.0% | 0 | 0.6% | 0.52 |
| Sample 1 | 13.65 | 80 | 4.3% | 0.59 | 1.2% | 0.17 | 4.5% | 0.61 | 0.0% | 0 | 4.5% | 0.61 |
| Sample 2 | 21.92 | 80 | 2.0% | 0.45 | 0.8% | 0.18 | 2.2% | 0.48 | 1.4% | 0.31 | 2.6% | 0.58 |
| Sample 3 | 99.17 | 80 | 0.3% | 0.34 | 0.6% | 0.61 | 0.7% | 0.70 | 0.7% | 0.70 | 1.0% | 0.99 |
| Sample 4 | 250.94 | 80 | 0.5% | 1.30 | 0.3% | 0.78 | 0.6% | 1.52 | 0.5% | 1.21 | 0.8% | 1.94 |
| Sample 5 | 285.02 | 80 | 0.6% | 1.58 | 0.6% | 1.71 | 0.8% | 2.32 | 0.2% | 0.60 | 0.8% | 2.40 |
| Sample 6 | 313.93 | 80 | 0.6% | 1.88 | 0.0% | 0 | 0.6% | 1.88 | 0.2% | 0.73 | 0.6% | 2.02 |
| Sample 7 | 349.20 | 80 | 0.6% | 2.21 | 0.1% | 0.50 | 0.6% | 2.27 | 0.2% | 0.85 | 0.7% | 2.42 |
| Sample 8 | 521.95 | 80 | 0.6% | 3.33 | 0.0% | 0 | 0.6% | 3.33 | 0.5% | 2.42 | 0.8% | 4.11 |
Lot 3:
| | | | Repeatability | | Between-Run | | Within-Day | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean (IU/mL) | N | CV | SD | CV | SD | CV | SD | CV | SD | CV | SD |
| Control Level 1 | 42.00 | 80 | 0.8% | 0.34 | 0.4% | 0.17 | 0.9% | 0.38 | 0.5% | 0.19 | 1.0% | 0.42 |
| Control Level 2 | 89.31 | 80 | 0.3% | 0.28 | 0.6% | 0.50 | 0.6% | 0.58 | 0.6% | 0.52 | 0.9% | 0.78 |
| Sample 1 | 13.48 | 80 | 3.7% | 0.50 | 0.0% | 0 | 3.7% | 0.50 | 2.1% | 0.28 | 4.2% | 0.57 |
| Sample 2 | 21.67 | 80 | 1.9% | 0.42 | 0.0% | 0 | 1.9% | 0.42 | 1.5% | 0.32 | 2.4% | 0.53 |
| Sample 3 | 99.08 | 80 | 0.5% | 0.50 | 0.2% | 0.16 | 0.5% | 0.53 | 0.8% | 0.80 | 1.0% | 0.96 |
| Sample 4 | 249.19 | 80 | 0.8% | 1.90 | 0.4% | 1.07 | 0.9% | 2.18 | 0.9% | 2.28 | 1.3% | 3.16 |
| Sample 5 | 283.26 | 80 | 1.5% | 4.17 | 0.0% | 0 | 1.5% | 4.17 | 1.4% | 4.02 | 2.0% | 5.80 |
| Sample 6 | 313.12 | 80 | 0.7% | 2.06 | 0.4% | 1.26 | 0.8% | 2.42 | 1.2% | 3.72 | 1.4% | 4.44 |
| Sample 7 | 349.03 | 80 | 0.6% | 2.07 | 0.6% | 2.02 | 0.8% | 2.90 | 1.1% | 3.73 | 1.4% | 4.72 |
| Sample 8 | 515.85 | 80 | 0.5% | 2.65 | 0.0% | 0 | 0.5% | 2.65 | 0.9% | 4.90 | 1.1% | 5.57 |
K192727 - Page 5 of 9
{5}
Precision - multiple site evaluation study:
The multiple site precision of the RF (Ver.2) assay was evaluated according to CLSI EP05-A3 by running five clinical samples and two commercial controls across the assay range. Samples were run in five replicates/sample, once a day, for 5 days using one reagent lot, one calibrator lot on three Abbott Architect c8000 instruments (total of $n = 525$ ). The results of multiple site precision on one lot are summarized in the table below:
| | | | Repeatability | | Between-Run | | Within-Laboratory | | Between-Laboratory | | Reproducibility | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean | N | CV | SD | CV | SD | CV | SD | CV | SD | CV | SD |
| Control Level 1 | 38.41 | 75 | 1.5% | 0.59 | 1.2% | 0.47 | 2.0% | 0.76 | 0.0% | 0 | 2.0% | 0.76 |
| Control Level 2 | 86.40 | 75 | 0.8% | 0.66 | 0.4% | 0.35 | 0.9% | 0.75 | 0.8% | 0.70 | 1.2% | 1.03 |
| Sample 1 | 14.13 | 75 | 4.5% | 0.64 | 5.6% | 0.79 | 7.2% | 1.02 | 0.0% | 0 | 7.2% | 1.02 |
| Sample 2 | 21.24 | 75 | 2.5% | 0.54 | 4.1% | 0.88 | 4.9% | 1.03 | 0.0% | 0 | 4.9% | 1.03 |
| Sample 3 | 101.69 | 75 | 0.7% | 0.75 | 1.4% | 1.42 | 1.6% | 1.61 | 0.0% | 0 | 1.6% | 1.61 |
| Sample 4 | 302.35 | 75 | 1.4% | 4.16 | 2.2% | 6.68 | 2.6% | 7.86 | 0.4% | 1.25 | 2.6% | 7.96 |
| Sample 5 | 532.83 | 75 | 0.8% | 4.44 | 1.2% | 6.15 | 1.4% | 7.58 | 0.4% | 2.05 | 1.5% | 7.86 |
# 2. Linearity:
The linearity of K-Assay RF (Ver.2) Assay was evaluated by a study performed according to CLSI EP6-A. The linearity was evaluated using a high human serum samples and an analyte-depleted serum to create a dilution series to cover the range of 6.65–600.0 IU/mL. Each dilution was tested in triplicate. The regression equation for the linear range was: $y = 0.992x + 2.41$ IU/mL with an r value of 0.999. The assay claimed reportable range/linear range is 6.65–600 IU/mL.
Hook effect was evaluated, and no hook effect was observed up to $1700\mathrm{IU / mL}$
# 3. Analytical Specificity/Interference:
The interference studies were performed according to CLSI EP07-3rd Ed. Four serum specimens (below the LoQ sample: $\sim 10$ IU/mL, low positive: $\sim 15$ IU/mL, middle: $\sim 100$ IU/mL and high positive: $\sim 300$ IU/mL) were aliquoted. Interfering substances at different concentrations were spiked into aliquots and compared results to the unspiked aliquot containing no interferent (control). The highest concentration tested with no interference is shown in the following table:
| Endogenous Interferent | Concentration | | Exogenous Interferent | Concentration |
| --- | --- | --- | --- | --- |
| Bilirubin C | 20 mg/dL | | Ascorbic Acid | 50 mg/dL |
| Bilirubin F | 20 mg/dL | | | |
| Chyle | 1500 FTU | | | |
| Hemoglobin | 500 mg/dL | | | |
| Total Cholesterol | 400 mg/dL | | | |
| Total Triglyceride | 1000 mg/dL | | | |
# 4. Assay Reportable Range:
The claimed measuring range is 6.65-600 IU/mL.
K192727 - Page 6 of 9
{6}
K192727 - Page 7 of 9
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Traceability: The in-house RF secondary standards are traceable to the NISBC – Rheumatoid Arthritis Serum (NIBSC code: 64/002).
Stability:
RF Reagent (Ver.2), RF Calibrator stability (unopened): The real-time and accelerated stability of each kit was tested using three lots of kits (i.e., with three different lots of RF reagent, one lot of calibrator, and one lot of each control sample 1 and control sample 2). The real-time stability testing supports the reagent claim of 13 months at stability for unopened reagent kits and 10 months of unopened calibrator and controls stored at 2–8°C.
Opened RF Reagent (Ver.2): To establish the in-use stability of the reagent, three reagent lots were tested with two RF control samples at two levels. The samples were tested at 0, 7, 14, 21, 28, 35, 42, 49, 56, and 63 days. The opened RF (Ver.2) reagent stability supports the claim for 63 days stored at 2–8°C.
Opened RF Calibrator stability
To establish the in-use stability of the calibrator, one lot of calibrator was tested with two RF control samples. The samples were tested at 0, 7, 14, 21, 28, 35, 42, 49, and 56 days. The opened RF Calibrator stability supports the claim for 56 days stored at 2–8°C.
Calibration curve stability: To establish the calibration curve stability, calibration was performed only on day zero. Two levels of control were measured using this single calibration curve every 2–3 days for up to 43 days. Reagent was stored at 2–8°C and the same bottles were used for all 43 days. On day zero, the controls were prepared and then aliquoted. Aliquots were frozen at -80°C for future use. For each new day of testing, a new aliquot was thawed and used. The calibration curve stability study met the acceptance criteria that the daily mean of each control is within ±10% from the day zero mean. The calibration curve stability claim is 43 days.
Sample stability: The following claims are cited from literature reference: "Use of Anticoagulants in Diagnostic Laboratory Investigations and Stability of Blood, Plasma and Serum Samples", WHO/DIL/LAB/99.1 Rev.2:41 WHO reference by Ehret W. et. al (p. 41):
- 20–25 °C: 1 day
- 4–8 °C: 8 days
- –20 °C: 3 months (and no repeat freeze–thaw)
6. Detection Limit:
Limit of Blank study (LoB):
The LoB of the RF assay was determined by assaying five blank samples in four replicates per day for three days with three reagent lots. Sixty data points were generated for each lot. The calculation was as follows: α=β=0.05 for Type I and Type II error risks for LoB and LoD. The LoB for each lot was calculated separately. The claimed LoB value was defined by the highest calculated value, 2.21 IU/mL.
{7}
Limit of Detection study (LoD):
The LoD of RF assay was determined by assaying five low-level samples with RF tested in four replicates over three days on three reagent lots. Sixty data points were generated for each lot. The LoD for each lot was calculated separately. The claimed LoD was defined as the highest calculated value, 4.29 IU/mL.
Limit of Quantitation study (LoQ):
The accuracy goal of the LoQ of the assay was defined as a 10% CV. The LoQ of the RF assays was determined by testing seven low-level samples run in two replicates per day, two runs per day and tested for 20 days on two reagent lots. For both lots, the percent CV (%CV) for each sample was calculated and a precision profile curve was plotted. The claimed RF LoQ is 6.65 IU/mL.
7. Assay Cut-Off:
The assay cut-off was determined as <11 IU/mL through the verification of the predicate's <11 IU/mL expected values which studied 125 normal U.S. serum samples taken from apparently healthy individuals (77% of samples were Caucasian and/or Hispanic, 13% were African American and 10% Asian American).
B Comparison Studies:
1. Method Comparison with Predicate Device:
To show comparison between the K-Assay RF (Ver.2) and the predicate K-ASSAY RF, a total of 178 clinical samples were with sample ranges were from 5.10–558.8 IU/mL. The regression equation is as follows: y = 1.001x + 1.331 with an r = 0.989.
2. Matrix Comparison:
A total of 59 patient samples were collected; each sample was processed to make four samples — serum, citric acid plasma, Li-heparin plasma, and EDTA plasma. Each processed sample from each patient was tested; the plasma sample results were compared to the serum results and the regression equation are as follows:
- Serum vs. citric acid plasma: y = 0.9854x - 0.4601 with an R² = 0.9929
- Serum vs. Li-heparin plasma: y = 0.9897x + 1.4617 with an R² = 0.9985
- Serum vs. EDTA plasma: y = 0.9971x - 0.2719 with an R² = 0.9985
C Clinical Studies:
1. Clinical Sensitivity/Specificity:
Not applicable
2. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable
D Clinical Cut-Off:
Same as assay cut-off
K192727 - Page 8 of 9
{8}
E Expected Values/Reference Range:
Same as assay cut-off
VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K192727 - Page 9 of 9
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.