The Alkaline Phosphatase2 assay is used for the quantitation of alkaline phosphatase in human serum or plasma on the ARCHITECT c System. Measurements of alkaline phosphatase or its isoenzymes are to be used as an aid in the diagnosis and treatment of liver, bone, parathyroid, and intestinal diseases.
Device Story
The Alkaline Phosphatase2 assay is an automated in vitro diagnostic test for use on the ARCHITECT c System. It measures alkaline phosphatase activity in human serum or plasma samples. The assay principle involves the catalysis of colorless para-nitrophenyl phosphate (p-NPP) into para-nitrophenol (yellow phenoxide) and inorganic phosphate by the alkaline phosphatase present in the sample. The reaction is performed at an alkaline pH, and the rate of absorbance increase at 404 nm is measured, which is directly proportional to the alkaline phosphatase activity. The reagent includes zinc and magnesium ions to activate the enzyme. The device is intended for use by laboratory professionals in clinical settings to assist physicians in diagnosing and monitoring liver, bone, parathyroid, and intestinal conditions. Results are provided as quantitative values (U/L) to inform clinical decision-making regarding patient treatment and disease management.
Clinical Evidence
No clinical data. Bench testing only. Performance validated via precision/reproducibility (CLSI EP05-A3), linearity (CLSI EP06), interference (CLSI EP07), and method comparison (CLSI EP09-A3) against the predicate. Method comparison (N=145) showed high correlation (r=1.00) with the predicate device. Analytical measuring range established at 4-4522 U/L.
Indicated for the quantitation of alkaline phosphatase in human serum or plasma to aid in the diagnosis and treatment of liver, bone, parathyroid, and intestinal diseases. Not validated for use with neonatal specimens.
Regulatory Classification
Identification
An alkaline phosphatase or isoenzymes test system is a device intended to measure alkaline phosphatase or its isoenzymes (a group of enzymes with similar biological activity) in serum or plasma. Measurements of alkaline phosphatase or its isoenzymes are used in the diagnosis and treatment of liver, bone, parathyroid, and intestinal diseases.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K223317
B Applicant
Abbott Ireland Diagnostics Division
C Proprietary and Established Names
Alkaline Phosphatase2
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CJE | Class II | 21 CFR 862.1050 - Alkaline Phosphatase Or Isoenzymes Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
New device
B Measurand:
Alkaline Phosphatase
C Type of Test:
Quantitative, photometric/colorimetric
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K223317 - Page 2 of 13
# III Intended Use/Indications for Use:
## A Intended Use(s):
See Indications for Use below.
## B Indication(s) for Use:
The Alkaline Phosphatase2 assay is used for the quantitation of alkaline phosphatase in human serum or plasma on the ARCHITECT c System. Measurements of alkaline phosphatase or its isoenzymes are to be used as an aid in the diagnosis and treatment of liver, bone, parathyroid, and intestinal diseases.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## D Special Instrument Requirements:
ARCHITECT c8000
# IV Device/System Characteristics:
## A Device Description:
The Alkaline Phosphatase2 assay kit consists of two ready to use reagent solutions, R1 and R2.
R1 is a buffer solution containing 179.550 g/L of 2-amino-2-methylpropanol(AMP) and sodium azide as a preservative. R2 is a substrate solution containing 30.430 g/L of 4-nitrophenyl phosphate and sodium azide as a preservative.
The Alkaline Phosphatase2 assay has two approaches to calculate results, i.e., calibration method and calibration factor method. The user decides which of the two methods to use. The calibration factor method allows users to perform testing without using a physical calibrator. There are separate assay parameter files that user must upload to the instrument for use with each method.
- The calibration method utilizes the linear data reduction method based on the Consolidated Chemistry Calibrator to generate a calibration and results.
- The calibration factor method utilizes the factor data reduction method to generate a calibration and results. The calibration factor for the Alkaline Phosphatase2 assay is 1931.
## B Principle of Operation:
Alkaline Phosphatase in a sample catalyzes the hydrolysis of colorless para-nitrophenyl phosphate (p-NPP) to give para-nitrophenol (yellow phenoxide form at alkaline pH) and inorganic phosphate.
The rate of absorbance increase at 404 nm is directly proportional to the alkaline phosphatase activity in the sample. Optimized concentrations of zinc and magnesium ions are present to activate the alkaline phosphatase in the sample.
{2}
V Substantial Equivalence Information:
A Predicate Device Name(s):
Alkaline Phosphatase
B Predicate 510(k) Number(s):
K023807
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K223317 | K023807 |
| --- | --- | --- |
| Device Trade Name | Alkaline Phosphatase2 | Alkaline Phosphatase |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The assay is used for the quantitation of alkaline phosphatase in human serum or plasma. | Same |
| Specimen Type | Human serum or plasma | Same |
| General Device Characteristic Differences | | |
| Standardization | IFCC traceable | Molar extinction of p-nitrophenol (non-IFCC method) |
| Calibration Method | Calibration and Calibration Factor method | Factor method |
| Assay Range | Analytical Measuring Interval: 4-4522 U/L | Analytical Measuring Interval: 5-4555 U/L |
| Lower Limits of Measurement | Limit of Blank: 1 U/L
Limit of Detection: 3 U/L
Limit of Quantification: 4 U/L | Limit of Detection: 5 U/L
Limit of Quantification: 5U/L |
VI Standards/Guidance Documents Referenced:
Clinical and Laboratory Standards Institute (CLSI) EP05-A3: Evaluation of Precision of Quantitative Measuring Procedures-Third Edition.
K223317 - Page 3 of 13
{3}
CLSI EP06: Evaluation of the Linearity of Quantitative Measurement Procedure.- Second Edition.
CLSI EP07: Interference Testing in Clinical Chemistry- Third Edition.
CLSI EP09-A3: Measurement Procedure Comparison and Bias Estimation using Patient Samples-Third Edition.
CLSI EP17-A2: Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures-Second Edition.
CLSI EP 37: Supplemental Tables for Interference Testing in Clinical Chemistry.
## VII Performance Characteristics (if/when applicable):
## A Analytical Performance:
The sponsor has validated the analytical performance of the candidate device using both the calibration method and the calibration factor method.
## 1. Precision/Reproducibility:
The precision study was performed according to the CLSI EP05-A3 guideline. Three (3) instruments and three (3) lots of reagents. Two (2) controls and four (4) human serum panels were tested in a minimum of two (2) replicates, twice (2) per day for twenty (20) days for a minimum of 80 replicates per sample per each unique instrument/reagent/calibrator combination. The results of the precision studies are summarized below. The within-laboratory SD and %CV includes within-run, between-run, and between-day variance components.
Calibration Method
| Specimen | Reagent/Instrument combination | N | Mean (U/L) | Repeatability | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| Control Level 1 | 1 | 80 | 115 | 0.8 | 0.7 | 2.7 | 2.3 |
| | 2 | 80 | 116 | 0.8 | 0.7 | 3.0 | 2.6 |
| | 3 | 80 | 115 | 1.0 | 0.8 | 2.9 | 2.6 |
| Control Level 2 | 1 | 80 | 430 | 1.2 | 0.3 | 7.5 | 1.7 |
| | 2 | 80 | 428 | 1.4 | 0.3 | 7.8 | 1.8 |
| | 3 | 80 | 428 | 1.7 | 0.4 | 8.4 | 2.0 |
| Sample A | 1 | 80 | 10 | 0.8 | 8.1 | 0.8 | 8.7 |
| | 2 | 80 | 9 | 0.6 | 6.3 | 0.6 | 6.7 |
| | 3 | 80 | 9 | 1.1 | 11.7 | 1.1 | 11.8 |
| Sample B | 1 | 80 | 42 | 0.8 | 2.0 | 1.2 | 2.9 |
| | 2 | 80 | 42 | 0.7 | 1.6 | 1.0 | 2.3 |
| | 3 | 80 | 41 | 0.9 | 2.3 | 1.2 | 2.9 |
| Sample C | 1 | 80 | 2135 | 6.3 | 0.3 | 40.5 | 1.9 |
K223317 - Page 4 of 13
{4}
Calibration Factor Method
| Specimen | Reagent/Instrument combination | N | Mean (U/L) | Repeatability | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | %CV | SD | %CV |
| Control Level 1 | 1 | 80 | 116 | 0.8 | 0.7 | 2.7 | 2.3 |
| | 2 | 80 | 114 | 0.9 | 0.8 | 3.0 | 2.6 |
| | 3 | 80 | 116 | 0.9 | 0.8 | 3.1 | 2.6 |
| Control level 2 | 1 | 80 | 435 | 1.2 | 0.3 | 7.5 | 1.7 |
| | 2 | 80 | 423 | 1.3 | 0.3 | 7.9 | 1.9 |
| | 3 | 80 | 434 | 1.7 | 0.4 | 8.3 | 1.9 |
| Sample A | 1 | 80 | 10 | 0.8 | 8.5 | 0.8 | 8.7 |
| | 2 | 80 | 9 | 0.7 | 7.2 | 0.7 | 7.2 |
| | 3 | 80 | 9 | 1.0 | 11.3 | 1.1 | 11.5 |
| Sample B | 1 | 80 | 42 | 0.7 | 1.6 | 1.1 | 2.7 |
| | 2 | 80 | 41 | 0.7 | 1.7 | 0.9 | 2.1 |
| | 3 | 80 | 41 | 0.9 | 2.2 | 1.2 | 2.9 |
| Sample C | 1 | 80 | 2158 | 6.4 | 0.3 | 39.5 | 1.8 |
| | 2 | 80 | 2017 | 6.7 | 0.3 | 44.9 | 2.2 |
| | 3 | 80 | 2172 | 13.4 | 0.6 | 40.1 | 1.8 |
| Sample D | 1 | 80 | 4478 | 18.8 | 0.4 | 91.9 | 2.1 |
| | 2 | 80 | 4248 | 14.4 | 0.3 | 81.0 | 1.9 |
| | 3 | 80 | 4508 | 28.5 | 0.6 | 94.5 | 2.1 |
The reproducibility study was performed according to the CLSI EP05-A3 guideline. Testing was conducted using one (1) lot of the Alkaline Phosphatase2 reagent, one (1) lot of the Consolidated Chemistry Calibrator, one (1) lot each of two (2) commercially available control sets, and three (3) instruments. Each instrument was operated by a different technician and each technician prepared an individual sample set. Five levels of controls were tested in three (3) replicates at two (2) separate times per day on five (5) different days. Reproducibility study results are summarized below:
K223317 - Page 5 of 13
{5}
Calibration Method
| Specimen | N | Meana(U/L) | Repeatability | | Within-Laboratoryb | | Reproducibilityc | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV |
| Control Level 1 | 90 | 113 | 1.1 | 1.0 | 2.6 | 2.3 | 2.6 | 2.3 |
| Control level 2 | 90 | 460 | 2.6 | 0.6 | 5.6 | 1.2 | 6.6 | 1.4 |
| Control Level A | 90 | 71 | 0.8 | 1.2 | 0.9 | 1.3 | 1.1 | 1.5 |
| Control Level B | 90 | 177 | 1.7 | 0.9 | 4.4 | 2.5 | 4.4 | 2.5 |
| Control Level C | 90 | 359 | 2.1 | 0.6 | 6.3 | 1.8 | 7.0 | 2.0 |
aThe values provided are the mean values across all instruments.
bIncludes within-run, between-run, and between-day variability
cIncludes within-run, between-run, between-day, and between-instrument variability
Calibration Factor Method
| Specimen | N | Meana(U/L) | Repeatability | | Within-Laboratoryb | | Reproducibilityc | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV |
| Control Level 1 | 90 | 108 | 1.0 | 0.9 | 2.4 | 2.3 | 2.7 | 2.5 |
| Control level 2 | 90 | 443 | 2.6 | 0.6 | 5.4 | 1.2 | 8.0 | 1.8 |
| Control Level A | 90 | 68 | 0.8 | 1.2 | 0.9 | 1.3 | 1.5 | 2.2 |
| Control Level B | 90 | 171 | 1.6 | 0.9 | 4.4 | 2.6 | 5.2 | 3.0 |
| Control Level C | 90 | 345 | 2.1 | 0.6 | 6.1 | 1.8 | 8.9 | 2.6 |
# 2. Linearity:
Linearity studies were performed according to the CLSI EP06-2nd edition guideline. Fourteen (14) levels of samples were prepared by mixing different portions of a high sample and a blank sample. Each sample was tested in four (4) replicates on a single instrument using a single reagent lot in a single run. The results were analyzed using weighted least squares linear regression analysis. The results of the linearity regression analysis of the data are summarized below:
Calibration Method
| Test | Slope | Intercept | R | Range Tested | Claimed Analytical Measuring Range |
| --- | --- | --- | --- | --- | --- |
| Alkaline Phosphatase | 1.0181 | NA* | 0.9999 | 0-4978 U/L | 4-4522 U/L |
K223317 - Page 6 of 13
{6}
Calibration Factor Method
| Test | Slope | Intercept | R | Range Tested | Claimed Analytical Measuring Range |
| --- | --- | --- | --- | --- | --- |
| Alkaline Phosphatase | 1.0221 | NA* | 1.000 | 0-4978 U/L | 4-4522 U/L |
*NA: Model is forced through zero
# 3. Analytical Specificity/Interference:
The analytical specificity of the Alkaline Phosphatase2 assay on the ARCHITECT c8000 was established by conducting interference testing following the recommendations in the CLSI EP07 third edition guideline.
Interference from endogenous and exogenous substances was assessed using two serum samples with alkaline phosphatase concentration of 70U/L and 200 U/L. Each sample was further divided into two aliquots: a test sample (with added interferent) and a control sample (with no added interferent). Each sample was tested in ten (10) replicates using one (1) instrument and one (1) reagent lot. The difference and % difference between the mean concentration of the test and control sample were calculated.
The following tables list the highest concentration of each substance at which no significant interference was found, defined as a difference of less than or equal to ±10% between the test sample and control.
Potentially Interfering Endogenous Substances
| Substances | Highest level tested that demonstrated no significant interference |
| --- | --- |
| Bilirubin - conjugated | 15 mg/dL |
| Bilirubin - unconjugated | 20 mg/dL |
| Hemoglobin | 250 mg/dL |
| Total protein | 15 g/dL |
| Triglycerides | 1500 mg/dL |
Potentially Interfering Exogenous Substances
| Substances | Highest level tested that demonstrated no significant interference |
| --- | --- |
| Acetaminophen | 160 mg/L |
| Acetylcysteine | 150 mg/L |
| Acetylsalicylic acid | 30 mg/L |
| Ampicillin-Na | 80 mg/L |
| Ascorbic acid | 60 mg/L |
K223317 - Page 7 of 13
{7}
| Substances | Highest level tested that demonstrated no significant interference |
| --- | --- |
| Biotin | 4250 ng/mL |
| Ca-dobesilate | 60 mg/L |
| Cefotaxime | 60 mg/L |
| Cefoxitin | 6600 mg/L |
| Cyclosporine | 2 mg/L |
| Desacetylcefotaxime | 6 mg/L |
| Doxycycline | 20 mg/L |
| Ibuprofen | 220 mg/L |
| Levodopa | 8 mg/L |
| Magnesium sulfate | 50 mg/L |
| Methyldopa | 25 mg/L |
| Metronidazole | 130 mg/L |
| Phenylbutazone | 330 mg/L |
| Rifampicin | 50 mg/L |
| Sodium heparin | 4 U/mL |
| Theophylline (1,3-dimethylxanthine) | 60 mg/L |
Bilirubin conjugated (40 mg/dL), bilirubin unconjugated (40 mg/dL and 60 mg/dL) and hemoglobin (1000 mg/dL) were found to interfere at alkaline phosphatase levels of 70 U/L and 200 U/L. The following interference information was added to the labeling.
| Potentially Interference Substance | Interference Level | | Analyte Level | | %Interference (95%CI) |
| --- | --- | --- | --- | --- | --- |
| | Default Unit | Alternative Units | Default Unit | Alternative Units | |
| Bilirubin-Conjugated | 40 mg/dL | 474 μmol/L | 70 U/L | 1.17 μkat/L | 28% (27%, 29%) |
| Bilirubin Conjugated | 40 mg/dL | 474 μmol/L | 200 U/L | 3.33 μkat/L | 11% (10%, 11%) |
| Bilirubin Unconjugated | 40 mg/dL | 684 μmol/L | 70 U/L | 1.17 μkat/L | 21% (20%, 22%) |
| Bilirubin – Unconjugated | 60 mg/dL | 1026 μmol/L | 200 U/L | 3.33 μkat/L | 10% (10%, 11%) |
| Hemoglobin | 1000 mg/dL | 10g/L | 70 U/L | 1.17 μkat/L | -33% (-34%, -31%) |
| Hemoglobin | 1000 mg/dL | 10 g/L | 200 U/L | 3.33 μkat/L | -13% (-14%, -13%) |
The following limitation information is included in the Alkaline Phosphatase 2 reagent package insert:
K223317 - Page 8 of 13
{8}
"Specimens from patients undergoing alkaline phosphatase replacement therapy (asfotase alfa) may exhibit positive interference with alkaline phosphatase assay."
"Neonatal specimens have not been validated with this assay and should not be used."
"Specimens with conjugated bilirubin levels greater than 15 mg/dL or unconjugated bilirubin greater than 20 mg/dL may cause falsely elevated results with the Alkaline Phosphatase2 assay. Refer to the SPECIFIC PERFORMANCE CHARACTERISTICS, Analytical Specificity, Interference section of this package insert. To estimate sample icterus levels, refer to the Sample Interference Indices instructions for use to assess hemolysis (H), icterus (I) and lipemia (L) (HIL) indices."
"Specimens with Hemoglobin Levels greater than 250 mg/dL may cause falsely depressed results with the Alkaline Phosphatase2 assay. Refer to the SPECIFIC PERFORMANCE CHARACTERISTICS, Analytical Specificity, Interference section of this package insert. To estimate sample hemoglobin levels, refer to the Sample Interference Indices instructions for use to assess hemolysis (H), icterus (I) and lipemia (L) (HIL) indices."
4. Assay Reportable Range:
4 – 4522 U/L
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
The Alkaline Phosphatase2 assay is traceable to the International Federation of Clinical Chemistry and Laboratory Medicine (IFCC) reference method.
6. Detection Limit:
Detection capability studies were conducted following the recommendations in CLSI EP17-A2. Studies were conducted using three (3) lots of the Alkaline Phosphatase2 reagents on each of 2 instruments (i.e., 6 conditions) over a minimum of three (3) days using both the calibration method and calibration factor method.
The limit of blank (LoB) was evaluated and determined by running a zero-analyte sample. The limit of detection (LoD) and the limit of quantitation (LoQ) were determined using low-analyte samples. Each sample was measured in at least 60 replicates using each of three lots of reagents and two instruments (total of six instrument and reagent lot combinations). The highest LoB, LoD, and LoQ estimate from the six instrument and reagent lot combinations was used as the LoB, LoD and LoQ for the assay.
The LoB was determined non-parametrically as the 95th percentile from n=60 replicates of the zero-target samples. LoD was analyzed using a parametric data analysis method where the lowest concentration at which the analyte can be detected with 95% probability based on n=60 replicates of low-analyte level samples is considered the LoD. The LoQ was defined as the lowest concentration of analyte which has imprecision less than or equal to 20% CV. The results are summarized in the table below.
K223317 - Page 9 of 13
{9}
K223317 - Page 10 of 13
Calibration Method
| | LoB | LoD | LoQ | AMI |
| --- | --- | --- | --- | --- |
| Serum | 1 U/L | 3 U/L | 4 U/L | 4 to 4522 U/L |
Calibration Factor Method
| | LoB | LoD | LoQ | AMI |
| --- | --- | --- | --- | --- |
| Serum | 1 U/L | 3 U/L | 4 U/L | 4 to 4522 U/L |
7. Assay Cut-Off:
Not applicable
B Comparison Studies:
1. Method Comparison with Predicate Device:
A method comparison study was performed following CLSI EP09-A3. The accuracy of the Alkaline Phosphatase2 assay on the ARCHITECT c8000 for serum samples was evaluated for agreement with the predicate device.
In this study, a total of 145 serum samples were tested and less than 10% of the samples were prepared by spiking or diluting specimens. The data were analyzed by Passing-Bablok regression using the first replicate of the candidate device results compared to the mean of the duplicate results from the comparator device. Method comparison study results are summarized below.
Calibration Method
| N | Correlation Coefficient [95% CI] | Intercept [95% CI] | Slope [95% CI] | Concentration Range (per predicate) (U/L) |
| --- | --- | --- | --- | --- |
| 145 | 1.00 [0.99, 1.00] | -1 [-4, 0] | 1.07 [1.06, 1.07] | 8 – 4534 |
{10}
Calibration Factor Method
| N | Correlation Coefficient [95% CI] | Intercept [95% CI] | Slope [95% CI] | Concentration Range (per predicate) (U/L) |
| --- | --- | --- | --- | --- |
| 143 | 1.00 [1.00, 1.00] | -2 [-3, 0] | 1.08 [1.07, 1.08] | 8 – 4042 |
## 2. Matrix Comparison:
A matrix equivalency study was conducted to support use of the Alkaline Phosphatase2 assay with the following additional specimen matrix types claimed in the product labeling: serum (separator tubes), lithium heparin plasma, lithium heparin (separator tubes) plasma and sodium heparin plasma. In the study, matched venous specimens were collected into each anticoagulant tube (i.e., evaluation tubes) and the serum control tube.
Each specimen was tested using one lot of reagents and one ARCHITECT c8000 instrument. The first replicate of the evaluation tubes was compared to the mean of the control serum measurements. A Passing-Bablok evaluation was performed, and results are summarized below:
Calibration Method:
| Collection Tube | N | Min* | Max* | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- | --- |
| Lithium heparin | 63 | 34 | 3627 | 1.00 | 1.00 (0.99,1.01) | -2.59 (-3.24, -1.85) |
| Lithium heparin (separator tube) | 63 | 33 | 3631 | 1.00 | 1.00 (0.99,1.01) | -1.93 (-2.68, -1.12) |
| Serum (separator tube) | 63 | 36 | 3577 | 1.00 | 1.00 (0.99, 1.01) | 0.33 (-0.42,1.20) |
| Sodium heparin | 63 | 34 | 3581 | 1.00 | 0.99 (0.99, 1.00) | 0.47 (-0.17, 1.38) |
K223317 - Page 11 of 13
{11}
Calibration Factor Method:
| Collection Tube | N | Min* | Max* | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- | --- |
| Lithium heparin | 63 | 34 | 3641 | 1.00 | 1.00 (1.00,1.01) | -2.00 (-2.95, -1.77) |
| Lithium heparin(separator tube) | 63 | 34 | 3646 | 1.00 | 1.00 (0.99,1.01) | -1.91 (-2.59, -0.85) |
| Serum (separator tube) | 63 | 36 | 3591 | 1.00 | 1.00 (1.00, 1.01) | 0.30 (-0.44,0.77) |
| Sodium heparin | 63 | 35 | 3595 | 1.00 | 0.99 (0.99, 1.00) | 0.48 (-0.07, 1.08) |
*Min, Max from the Evaluation Tube Type
## 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
K223317 - Page 12 of 13
{12}
K223317 - Page 13 of 13
# E Expected Values/Reference Range:
The expected values for alkaline phosphatase in serum are from literature references.
| Age | Range (U/L) |
| --- | --- |
| *29 days to < 1 year | 134 – 518 |
| 1 year to < 3 years | 156 – 369 |
| 3 to 5 years | 144 – 327 |
| 6 to 10 years | 153 – 367 |
| 11 to 15 years, Male | 113 – 438 |
| 11 to 15 years, Female | 64 – 359 |
| 16 to 21 years, Male | 56 – 167 |
| 16 to 21 years, Female | 44 – 107 |
| 22 to 79 years, Female | 50 –116 |
| 30 to 79 years, Female | 46 –122 |
*This age interval has been modified to exclude neonates.
Rifai N, Horvath AR, Wittwer C, editors, Tietz Textbook of Clinical Chemistry and Molecular Molecular Diagnostics, 6th ed. St. Louis, Mo: Elsevier: 2018.
# 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.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
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.