The ACR | LAB Urine Analysis Test System is comprised of a smartphone application, a proprietary Color-Board, and ACR Reagent Strips. It is intended for the semi-quantitative detection of albumin and creatinine in urine, as well as the presentation of their ratio. The ACR | LAB Urine Analysis Test System is intended for in-vitro diagnostic use by a healthcare professional in a point of care setting. These results may be used in conjunction with clinical evaluation as an aid in the diagnosis for kidney function.
Device Story
System uses smartphone camera to capture images of urine-dipped reagent strips placed on proprietary Color-Board; Color-Board provides reference for color calibration. App guides professional user through testing process; performs boundary condition analysis on captured images. If scan approved, images sent to cloud-based Backend server for analysis; image recognition algorithm classifies results. Results transmitted to patient Electronic Medical Record (EMR) for clinician review. Device used in point-of-care settings by healthcare professionals; patients do not access results. System provides semi-quantitative albumin and creatinine levels and ratio to assist in kidney function assessment.
Clinical Evidence
Clinical study at three U.S. sites with 375 subjects and 60 contrived samples. Compared ACR | LAB (iPhone 7) results against predicate (Mission U120 Ultra). Primary endpoints: percent exact match and ±1 color block agreement. Results: 89% exact match for albumin, 84% for creatinine, 93% for ratio. Agreement within ±1 color block was 100% for all metrics. Analytical testing included precision (repeatability/reproducibility), interference, limit of detection, linearity, and timing flex studies, all confirming performance.
Technological Characteristics
Reflectance photometry using ACON Mission Urinalysis Reagent Strips. System comprises iPhone 7 (iOS 12.0), proprietary Color-Board, and cloud-based image recognition software. Connectivity via internet to cloud server and EMR. No calibration required. Software performs image analysis of colorimetric patches on strips against Color-Board reference.
Indications for Use
Indicated for healthcare professionals in point-of-care settings to detect albumin and creatinine in human urine and calculate their ratio to aid in kidney function diagnosis. Prescription use only. Contraindicated for samples with blood levels >= 80 erythrocytes/microliter (>= 2+) or visible color interferents.
Regulatory Classification
Identification
A creatinine test system is a device intended to measure creatinine levels in plasma and urine. Creatinine measurements are used in the diagnosis and treatment of renal diseases, in monitoring renal dialysis, and as a calculation basis for measuring other urine analytes.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k182384
B. Purpose for Submission:
New device
C. Measurand:
Albumin and creatinine in urine
D. Type of Test:
Semi-quantitative urinalysis
E. Applicant:
Healthy.io, Ltd.
F. Proprietary and Established Names:
ACR | LAB Urine Analysis Test System
G. Regulatory Information:
1. Regulation section:
| Name | Regulation | Product Code | Device Class |
| --- | --- | --- | --- |
| Creatinine test system | 21 CFR 862.1225 | JFY | II |
| Urinary protein or albumin (nonquantitative) test system | 21 CFR 862.1645 | JIR | I |
| Automated urinalysis system | 21 CFR 862.2900 | KQO | I |
2. Panel:
Chemistry (75)
{1}
H. Intended Use:
1. Intended use(s):
See Indication(s) for use below.
2. Indication(s) for use:
The ACR | LAB Urine Analysis Test System is comprised of a smartphone application, a proprietary Color-Board, and ACR Reagent Strips. It is intended for the semi-quantitative detection of albumin and creatinine in urine, as well as the presentation of their ratio. The ACR | LAB Urine Analysis Test System is intended for in-vitro diagnostic use by a healthcare professional in a point of care setting. These results may be used in conjunction with clinical evaluation as an aid in the diagnosis for kidney function.
3. Special conditions for use statement(s):
For prescription use only.
For in vitro diagnostic use only.
Samples should be screened for blood prior to testing.
4. Special instrument requirements:
A dedicated iPhone 7 (iOS 12.0) should be used for testing.
I. Device Description:
The device is provided as a kit that comprises a canister of 100 ACON Mission Urinalysis Reagent Strips (Microalbumin/Creatinine) (ACON Laboratories Inc., k150330), 10 individually-wrapped Color-Boards, and a User Manual. The ACR | LAB Urine Analysis Test System also consists of a smartphone application for use on a dedicated iPhone 7 (iOS 12.0), and an image recognition algorithm running on a back-end, cloud-based server.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Mission U120 Ultra Urine Analyzer and Mission Urinalysis Reagent Strips (Microalbumin/Creatinine)
2. Predicate 510(k) number(s):
k142391
{2}
3. Comparison with predicate:
| Similarities |
| --- |
| Item | Subject Device k182384 ACR | LAB Urine Analysis Test System | Predicate Device k142391 Mission U120 Ultra Urine Analyzer and Mission Urinalysis Reagent Strips (Microalbumin/Creatinine) |
| Intended Use | For the semi quantitative measurement of albumin and creatinine to assist diagnosis for kidney function. | Same |
| Sample Type | Human urine | Same |
| Measurement Principle | Reflectance photometry | Same |
| Differences |
| --- |
| Item | Subject Device k182384 ACR | LAB Urine Analysis Test System | Predicate Device k142391 Mission U120 Ultra Urine Analyzer and Mission Urinalysis Reagent Strips (Microalbumin/Creatinine) |
| Reader | iPhone 7 (iOS 12.0) | Mission U120 Ultra Urine Analyzer |
| Data Transfer | Internet connection between the dedicated smartphone, back-end server, and patient's electronic medical records | USB port and standard RS232C port |
K. Standard/Guidance Document Referenced (if applicable):
- IEC 62304:2006, Medical device software - Software life cycle processes
- CLSI EP5-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 EP7-A2, Interference Testing in Clinical Chemistry; Approved Guideline - Second Edition
- CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline - Second Edition
{3}
# L. Test Principle:
The albumin test is based on affinity binding of albumin to a sulfonephthalein dye at a constant pH. The development of pale green to aqua blue indicates the presence of albumin. The creatinine test is based on the peroxidase-like activity of a copper creatinine complex that catalyzes the reaction of diisopropylbenzene dihydroperoxide and $3,3^{\prime},5,5^{\prime}$ -tetramethylbenzidine. The resulting color ranges from orange through green to blue.
The ACR | LAB Urine Analysis Test System scans and analyzes the test strip using a mobile device running the smartphone application.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Repeatability testing was conducted at 3 sites using one iPhone 7 (iOS 12.0) smartphone at each site. Each site had one operator performing the tests using 3 spiked urine samples, 3 strip lots, and 7 test strips per lot for a total of 63 results per level across sites (21 per site). The results are summarized by site in the tables below.
Albumin
| Level (mg/L) | N | Within Run % Agreement (Exact Match) Site 1 | Within Run % Agreement (Exact Match) Site 2 | Within Run % Agreement (Exact Match) Site 3 | % Agreement (±1 Color Block) |
| --- | --- | --- | --- | --- | --- |
| 10 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
| 30 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
| 150 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
Creatinine
| Level (mg/dL) | N | Within Run % Agreement (Exact Match) Site 1 | Within Run % Agreement (Exact Match) Site 2 | Within Run % Agreement (Exact Match) Site 3 | % Agreement (±1 Color Block) |
| --- | --- | --- | --- | --- | --- |
| 10 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
| 50 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
| 300 | 63 | 100% (21/21) | 100% (21/21) | 100% (21/21) | 100% (63/63) |
{4}
Reproducibility testing was conducted at 3 sites using five iPhone 7 (iOS 12.0) smartphones at each site. Each site had one operator performing the tests using 3 spiked urine samples, 3 strip lots, and 2 runs per day in singlicate over 20 days for a total of 360 results per level across sites (120 per site). The results are summarized by site in the tables below.
Albumin
| Level (mg/L) | N | % Agreement (Exact Match) | % Agreement (± 1 Color Block) |
| --- | --- | --- | --- |
| 10 | 360 | 100% (360/360) | 100% (360/360) |
| 30 | 360 | 100% (360/360) | 100% (360/360) |
| 150 | 360 | 99.7% (359/360) | 100% (360/360) |
Creatinine
| Level (mg/dL) | N | % Agreement (Exact Match) | % Agreement (± 1 Color Block) |
| --- | --- | --- | --- |
| 10 | 360 | 100% (360/360) | 100% (360/360) |
| 50 | 360 | 98.9% (356/360) | 100% (360/360) |
| 300 | 360 | 100% (360/360) | 100% (360/360) |
b. Linearity/assay reportable range:
The reportable range for each analyte was evaluated by measuring five levels of creatinine (10, 50, 100, 200, and 300 mg/dL) and four levels of albumin (10, 30, 80, and 150 mg/L). The study was performed by 3 operators using 3 lots of test strips in replicates of 10 per lot for a total of 90 measurements per sample. Each operator used one iPhone 7 (iOS 12.0).
Albumin
| Block Cut-off (mg/L) | Concentrations Tested (mg/L) | % Exact Match | % ± 1 Color Block |
| --- | --- | --- | --- |
| 10 | 6-14 | 100 | 100 |
| 30 | 18-50 | 100 | 100 |
| 80 | 60-108 | 98.89 | 100 |
| 150 | > 122 | 100 | 100 |
{5}
6
Creatinine
| Block Cut-off (mg/dL) | Concentrations Tested (mg/dL) | % Exact Match | % ± 1 Color Block |
| --- | --- | --- | --- |
| 10 | 6-26 | 100 | 100 |
| 50 | 34-70 | 97.78 | 100 |
| 100 | 80-140 | 98.89 | 100 |
| 200 | 160-240 | 98.89 | 100 |
| 300 | > 260 | 100 | 100 |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability:
The device is traceable to a commercially available method.
d. Detection limit:
A limit of detection study was conducted to determine the cut-off points for every color block for both albumin and creatinine. Urine samples spiked with albumin (6 mg/L to 210 mg/L) or creatinine (6 mg/dL to 420 mg/dL) were each tested using 3 test strip lots and 6 replicates per lot using one iPhone 7 (iOS 12.0) smartphone. The cut-off for each color block is defined as the lowest concentration at which over 55% of the test results were positive. The results of the study are shown below.
Albumin
| Color Block (mg/L) | Cut-off Concentration (mg/L) | (% positive) |
| --- | --- | --- |
| 10 | 6 | 100 |
| 30 | 18 | 66.7 |
| 80 | 60 | 55.56 |
| 150 | 122 | 66.7 |
Creatinine
| Color Block (mg/dL) | Cut-off Concentration (mg/dL) | (% positive) |
| --- | --- | --- |
| 10 | 6 | 100 |
| 50 | 34 | 83.33 |
| 100 | 80 | 66.67 |
| 200 | 160 | 55.56 |
| 300 | 260 | 66.67 |
e. Analytical specificity:
Interference
Urine samples spiked with albumin (10 mg/L, 30 mg/L, 150 mg/L) or creatinine (10
{6}
mg/dL, 50 mg/dL, 300 mg/dL) were spiked with each potentially interfering substance at low and high concentrations or not spiked (control). Each sample was tested with 1 lot of test strips with 8 replicates using one iPhone 7 (iOS 12.0) smartphone. Interference was defined as a change in output of one or more color blocks between spiked and control samples. When interference was observed, further testing was conducted to identify the lowest concentration at which interference was observed.
The interferents and the highest concentrations tested are listed in the table below:
| Substance | Highest Concentration Tested (mg/dL) | Substance | Highest Concentration Tested (mg/dL) |
| --- | --- | --- | --- |
| Lithium acetoacetate | 250 | Sodium chloride | 5500 |
| Ammonium chloride | 100 | Oxalic acid | 70 |
| Ascorbic acid | 200 | Sodium acetate | 2.25 |
| Uric acid | 150 | Riboflavin | 10 |
| Unconjugated bilirubin | 170 | Sodium bicarbonate | 1500 |
| Calcium chloride | 275 | Sodium nitrate | 10 |
| Creatine | 10 | Sodium nitrite | 10 |
| Creatinine | 600 | Sodium phosphate | 500 |
| Fructose | 100 | Theophylline | 100 |
| Galactose | 80 | Urea | 400 |
| Glycine | 450 | Blood | 0.05% |
| Glucose | 5000 | Leucocytes | 2500 |
| Lactose | 10 | Human IgG | 25 |
| Hemolysate | 10 | Citric acid | 75 |
| Potassium chloride | 1500 | | |
| Glycine | 450 | | |
The following table shows the substances that interfered with the proposed device. Results are expressed as the lowest concentration of the interfering substance that exhibited interference and the resulting change in output of the color block. The lowest concentration causing interference will be included in the ACR | LAB Urine Analysis Test System user manual.
{7}
Albumin
| Interferent | Lowest Concentration Interference was Observed | Analyte Level | Affect on Results |
| --- | --- | --- | --- |
| Hemoglobin | 2.13 mg/dL | 10 mg/L | Falsely elevated by one color block |
| | | 30 mg/L | |
| Blood | 0.033% | 10 mg/L | Falsely elevated by one color block |
| | | 30 mg/L | |
| Sodium phosphate | 218.75 mg/dL | 10 mg/L | Falsely elevated by one color block |
| | | 30 mg/L | |
| Sodium chloride | 1787.5 mg/dL | 30 mg/L | Falsely decreased by one color block |
| Unconjugated bilirubin | 6.38 mg/dL | 10 mg/L | Falsely elevated by one color block |
| | | 30 mg/L | Falsely decreased by one color block |
| Pastassium chloride | 656.25 mg/dL | 30 mg/L | Falsely decreased by one color block |
| Riboflavin | 6.625 mg/dL | 30 mg/L | Falsely decreased by one color block |
| Human IgG | 8.13 mg/dL | 10 mg/L | Falsely elevated by one color block |
| | | 30 mg/L | |
| pH | 10 | 30 mg/L | Falsely elevated by one color block |
Creatinine
| Interferent | Lowest Concentration Interference was Observed | Analyte Level | Affect on Results |
| --- | --- | --- | --- |
| Hemoglobin | 2.13 mg/dL | 10 mg/dL | Falsely elevated by one color block |
| | | 50 mg/dL | |
| Blood | 0.033% | 10 mg/dL | Falsely elevated by one color block |
| | | 50 mg/dL | |
| Sodium phosphate | 162.5 mg/dL | 50 mg/dL | Falsely decreased by one color block |
| | | 300 mg/dL | |
| Unconjugated bilirubin | 93.5 mg/dL | 10 mg/dL | Falsely elevated by one color block |
| | | 50 mg/dL | |
{8}
| Interferent | Lowest Concentration Interference was Observed | Analyte Level | Affect on Results |
| --- | --- | --- | --- |
| Pastassium chloride | 825 mg/dL | 50 mg/dL | Falsely elevated by one color block |
| Sodium chloride | 1787.5 mg/dL | 10 mg/dL
50 mg/dL | Falsely elevated by one color block |
| Sodium bicarbonate | 159.38 mg/dL | 50 mg/dL
300 mg/dL | Falsely decreased by one color block |
| Calcium chloride | 120.31 mg/dL | 50 mg/dL | Falsely elevated by one color block |
| Ascorbic acid | 42.5 mg/dL | 50 mg/dL
300 mg/dL | Falsely decreased by one color block |
All urine samples evaluated by this device should be tested for blood using a urinalysis device that tests for blood. If testing indicates the presence of blood equal to or greater than 80 erythrocytes/microliter ( $\geq 2+$ ), the sample should not be tested with this assay.
Urine samples with visible levels of color interferents (e.g., riboflavin, ascorbic acid) should not be tested with the device.
## Specific gravity (SG)
Urine samples spiked with albumin (10 mg/L, 30 mg/L, 150 mg/L) or creatinine (10 mg/dL, 50 mg/dL, 300 mg/dL) were adjusted to specific gravities of 1.000, 1.005, 1.015, 1.020, 1.025, 1.030, 1.035, and 1.040. No interference from SG was detected on albumin or creatinine measurements in the examined range.
## pH
Urine samples spiked with albumin (10 mg/L, 30 mg/L, 150 mg/L) or creatinine (10 mg/dL, 50 mg/dL, 300 mg/dL) were adjusted to pH 4.0, 5.0, 6.0, 8.0, and 9.0. pH of 10 showed interference at the 30 mg/L albumin block, and generated falsely increased results of +1 block. None of the other pH levels had an interfering effect at any other concentration of albumin or creatinine.
## f. Assay cut-off:
Not applicable.
{9}
2. Comparison studies:
a. Method comparison with predicate device:
375 male and female subjects, aged 18 – 80 years and older undergoing routine physical examinations, or with diseases such as Type 1 or Type 2 diabetes, hypertension, heart disease, kidney disease, and subjects with other ailments that represent the target population for this device were enrolled for testing at three sites. 60 spiked samples were used to supplement some analyte concentrations. All subjects provided a urine sample, which was measured with the device by one operator, and on the predicate device by a second technician. Results were consistent across the three test sites; results are summarized in the tables below.
| Candidate | Predicate | | | | |
| --- | --- | --- | --- | --- | --- |
| Albumin (mg/L) | 10 | 30 | 80 | 150 | Total count |
| 10 | 229 (92.0%) | 3 (3.7%) | 0 | 0 | 232 |
| 30 | 20 (8.0%) | 65 (80.2%) | 4 (10.0%) | 0 | 89 |
| 80 | 0 | 13 (16%) | 35 (87.5%) | 5 (7.8%) | 53 |
| 150 | 0 | 0 | 1 (2.5%) | 59 (92.2%) | 60 |
| Total count | 249 | 81 | 40 | 64 | 434 |
| % Exact Match | 92.0% | 80.2% | 87.5% | 92.2% | |
| % ± 1 color block | 100% | 100% | 100% | 100% | |
{10}
| Candidate | Predicate | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Creatinine (mg/dL) | 10 | 50 | 100 | 200 | 300 | Total count |
| 10 | 124 (86.1%) | 0 | 0 | 0 | 0 | 124 |
| 50 | 20 (13.9%) | 82 (82.0%) | 5 (5.4%) | 0 | 0 | 107 |
| 100 | 0 | 18 (18.0%) | 77 (82.8%) | 5 (8.5%) | 0 | 100 |
| 200 | 0 | 0 | 11 (11.8%) | 48 (81.4%) | 3 (7.8%) | 62 |
| 300 | 0 | 0 | 0 | 6 (10.2%) | 35 (92.2%) | 41 |
| Total count | 144 | 100 | 93 | 59 | 38 | 440 |
| % Exact Match | 86.1% | 82.0% | 82.8% | 81.4% | 92.2% | |
| % ± 1 color block | 100% | 100% | 100% | 100% | 100% | |
| Candidate | Predicate | | | |
| --- | --- | --- | --- | --- |
| Albumin:Creatinine ratio (ACR) | Normal | Abnormal | High-Abnormal | Total count |
| Normal | 264 | 2 | 0 | 266 |
| | 92.0% | 2.1% | | |
| Abnormal | 23 | 87 | 1 | 111 |
| | 8% | 92.6% | 1.9% | |
| High-Abnormal | 0 | 5 | 52 | 57 |
| | | 5.3% | 98.1% | |
| Total count | 287 | 94 | 53 | 434 |
| % exact agreement | 92.0% | 92.6% | 98.1% | 92.86 |
b. Matrix comparison:
Not applicable. This device is for testing with human urine only.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable.
{11}
b. Clinical specificity:
Not applicable.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
The following statements regarding expected values are provided in the ACR | LAB Urine Analysis Test System user manual:
Albumin: Normally, albumin is present in urine at concentrations $< 20\mathrm{mg/L}^1$. Results of $20-200\mathrm{mg/L}$ may indicate microalbuminuria. It is associated with early-stage kidney disease when a small amount of Albumin, also called Microalbumin, is consistently present in urine. Clinical albuminuria is indicated by results of $>200\mathrm{mg/L}$. These levels can be predictive of albumin excretion rates of $30-300\mathrm{mg/24}$ hours and $>300\mathrm{mg/24}$ hours, respectively$^{2-3}$. Exercise, acute illness and fever, and urinary tract infections may temporarily elevate urinary albumin excretions.
Creatinine: Creatinine concentrations of $10-300\mathrm{mg/dL}$ are normally present in urine.
Albumin-to-Creatinine Ratio (microalbumin/Creatinine): Albumin is normally present in urine at concentrations of $< 30\mathrm{mg/g}$. Microalbuminuria is indicated at a ratio result of $30 - 300\mathrm{mg/g}$ (moderately increased) and clinical albuminuria at a ratio of $>300\mathrm{mg/g}$ (severely increased)$^{4}$.
1. Burtis C.A.; and Ashwood ER.: Tietz Textbook of Clinical Chemistry 3rd ed. Philadelphia: Saunders; 1999; pp. 483-484.
2. Mangili, R. et al.: Prevalence of Hypertension and Microalbuminuria in Adult Type 1 (Insulin-Dependent) Diabetic patients Without Renal Failure in Italy-Validation of Screening Techniques to Detect Microalbuminuria. Acta Diabetol. 29: 156-166; 1992.
3. American Diabetes Association, Clinical Practice Recommendations, Diabetes Care, Vol. 31, Suppl. 1, January 2008.
4. Position Statement: Diabetic Nephropathy. Diabetes Care 20: S24-S27; 1997.
N. Instrument Name:
iPhone 7 (iOS 12.0)
{12}
O. System Descriptions:
1. Modes of Operation:
Does the applicant’s device contain the ability to transmit data to a computer, webserver, or mobile device?
Yes ☐ X or No ☐
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission?
Yes ☐ X or No ☐
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ X or No ☐
3. Specimen Identification:
Operators manually enter the patient identification number into the device.
4. Specimen Sampling and Handling:
The test is performed by dipping the urinalysis reagent strip into a urine sample collected into a cup.
5. Calibration:
No calibration is required.
6. Quality Control:
The app has internal controls designed to account for environmental conditions that impact the accuracy of the test. The sponsor recommends testing commercially available positive and negative quality controls per the laboratory policies, in accordance with local, state, and federal regulations.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
1. Carryover study: Test strips were held in both the "up" (with the creatinine on top) and
{13}
"down" (with the albumin on top) positions for 0 (control), 15, 30, 60, 90, and 120 seconds after being dipped in solutions. The "up" experiment used a high-positive creatinine solution (300 mg/dL) and a negative albumin solution. The "down" experiment used a high-positive albumin solution (150 mg/L) with a negative creatinine solution. The experiment consisted of 240 measurements (6 timings x 2 test strips lots x 5 replicates x 2 operating systems x 2 configurations ("up" / "down") = 240 results). Though none of these configurations demonstrated any impact, labeling directs the user to place the test strips on the Color-Board after dipping it in the urine to prevent run-off from flowing from one patch into another.
2. Dipping study: Test strips were dipped in samples containing negative, low positive, and high positive concentrations (measured as 10, 30, and 150 mg/L albumin, respectively and 10, 50, and 300 mg/dL creatinine, respectively). Samples were measured for four different time durations to test the impact of various dipping times on the ACR | LAB's ability to perform accurate measurements: 1 second (control), 2 seconds, 5 seconds, and 10 seconds. Wetting time was held constant at 0 seconds and assay time was held constant at 60 seconds. The experiment consisted of 80 measurements (4 timings x 2 test strip lots x 5 replicates x 2 operating systems = 80 results). For creatinine, none of the various dipping times impacted the accuracy of the device. For albumin, at times 5- and 10-seconds there was an increase in false positive results. The user manual and in-app instructions direct the professional user to dip the ACR Reagent Strip for 1-second, and state that increasing the dipping time longer than 5 seconds can cause falsely increased results for albumin.
3. Wetting ("Blotting") study: This experiment tested different "blotting" times, i.e. the tester dipped the test strips and then waited a specific amount of time before blotting the test strips and scanning it with the ACR | LAB device. Samples containing negative, low positive, and high positive concentrations (measured as 10, 30, and 150 mg/L albumin, respectively and 10, 50, and 300 mg/dL creatinine, respectively) were measured. There were six different waiting times: 0 seconds (control), 5 seconds, 10 seconds, 20 seconds, 40 seconds, and 60 seconds. Dipping time was held constant at 1 second and assay time was held constant at 60 seconds. The experiment consisted of 60 measurements per sample (6 timings x 2 test strip lots x 5 replicates x 1 iPhone). For creatinine, none of the various dipping times impacted the accuracy of the device. For albumin, waiting 60-seconds to blot the strip resulted in false positive results. The labeling and the in-app instructions direct the user to wipe the strip on the edge of the urine cup and then immediately absorb it on a paper towel for 1 second to remove any excess urine after dipping. The labeling also includes a warning that waiting longer than 60 seconds before blotting the strip can cause falsely increased results for albumin.
4. Assay time study: This experiment tested how different assay times impact the ACR | LAB's ability to measure accurate results. Test strips were dipped and then immediately blotted, per the device's instructions. The user then waited a predetermined amount of time before scanning the test strips: 60 seconds (control), 80 seconds, 100 seconds, and 120 seconds. Dipping time was held constant at 1 second and wetting time was held constant at 0 seconds. Samples containing negative, low positive, and high positive
14
{14}
concentrations (measured as 10, 30, and 150 mg/L albumin, respectively and 10, 50, and 300 mg/dL creatinine, respectively) were measured. The experiment consisted of 40 measurements per sample (4 timings x 2 test strip lots x 5 replicates x 1 iPhone). None of the assay time durations had any impact on the ACR | LAB's ability to accurately measure albumin or creatinine. Labeling and in-app instructions direct the user to wait for 60 seconds and then scan the test strip and Color-Board.
5. Illumination study: The accuracy of the subject device was tested under ten simulated lighting conditions (fluorescent 6000K, fluorescent 2700K, compact fluorescent lamp 6000K, compact fluorescent lamp 6500K, compact fluorescent lamp 2700K, LED 6000K, LED 6500K, incandescent, halogen, CW LED). Two operators used one iPhone 7 (iOS 12.0) to test 2 spiked urine samples (10 mg/L or 150 mg/L albumin and 10 mg/dL or 300 mg/dL creatinine) with 2 strip lots and 3 replicates per lot or 5 printed test strip configurations (with creatinine at 10, 50, 100, 200, and 300 mg/dL and albumin at 10, 30, 80, and 150 mg/L) at 4 replicates per lot. All results were reported as an exact match with expected results.
6. Boundary study: The accuracy of the subject device was tested under 5 boundary conditions (i.e., different distances, angles, and extreme lighting conditions). One iPhone 7 (iOS 12.0) was used to test 2 spiked urine samples (10 mg/L or 150 mg/L albumin and 10 mg/dL or 300 mg/dL creatinine) with 2 strip lots and 3 replicates per lot or 5 printed test strip configurations (with creatinine at 10, 50, 100, 200, and 300 mg/dL and albumin at 10, 30, 80, and 150 mg/L) at 5 replicates per lot. All results were reported as an exact match with expected results.
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Parts 801 and 809, as applicable.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
15
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.