TC-THUNDERBOLT AUTOMATED URINE ANALYZER SYSTEM AND TC-THUNDERBOLT URS-10 STRIPS
Applicant
Teco Diagnostics
Product Code
JIL · Clinical Chemistry
Decision Date
Jul 24, 2015
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1340
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K141289 · Jul 24, 2015
TC-THUNDERBOLT AUTOMATED URINE ANALYZER SYSTEM AND TC-THUNDERBOLT URS-10 STRIPS
Teco Diagnostics
External clinical site urine samples
Clinical urine samples were used in a method comparison study to evaluate the performance of the TC-Thunderbolt Automated Urine Analyzer System against the predicate Uritek-720+ analyzer.
Method Comparison Study; Method comparison study using clinical urine samples; Follow-up/Duration: Not applicable
Human urine samples; Sample Size: 487
Uritek-720+ Urine Analyzer
Percent exact match agreement and percent agreement within 1 color block
Indications for Use
The TC-Thunderbolt Automated Urine Analyzer System is an in vitto diagnostic device used to automate the urine chemistry analysis using TC-Thunderbolt URS-10 strips. It produces semi-quantitative results of glucose, protein, pH, bilirubin, blood, ketone, urobilinogen, nitrite, specific gravity and leukocytes in urine. TC-Thunderbolt URS-10 strips are intended for use only with TC-Thunderbolt Automated Urine Analyzer System, they are not intended for manual visual reading. This device is for clinical laboratory use only. This device is not for Point of Care Use. These measurements are used to aid in the diagnosis of metabolic disorders, kidney function anomalies, urinary tract infections and liver function.
Device Story
Automated urine chemistry analyzer; uses TC-Thunderbolt URS-10 reagent strips. Input: urine sample via automated suction needle/pipe. Operation: reflectance photometry measures color changes on reagent pads; digital analysis determines semi-quantitative results for 10 analytes. Output: printed/saved analysis report. Used in clinical laboratories by trained personnel. Benefits: automates sample application and reading, reducing manual handling compared to predicate. Healthcare providers use results to aid diagnosis of metabolic, renal, urinary, and liver conditions.
Clinical Evidence
Bench testing only. Precision/reproducibility evaluated with 3 control levels (20 replicates/level). Linearity/reportable range validated with spiked urine samples. Analytical specificity tested against 19 potential interferents; interference noted for specific analytes (e.g., ascorbic acid, hemoglobin, glucose). Method comparison study performed against predicate (n=487 clinical specimens) showing high agreement (overall exact match >95% for most analytes).
Technological Characteristics
Reflectance photometer; automated sample-suction/strip-application mechanism. Uses 10-pad plastic reagent strips (110mm x 5mm). Calibration via dedicated calibration strip. Connectivity includes barcode scanner for specimen ID. Software-controlled analysis. Operates at 25°C ± 5°C, <75% humidity.
Indications for Use
Indicated for clinical laboratory use to automate urine chemistry analysis for semi-quantitative measurement of glucose, protein, pH, bilirubin, blood, ketone, urobilinogen, nitrite, specific gravity, and leukocytes in urine to aid in diagnosis of metabolic disorders, kidney function anomalies, urinary tract infections, and liver function. Not for Point of Care use.
Regulatory Classification
Identification
A urinary glucose (nonquantitative) test system is a device intended to measure glucosuria (glucose in urine). Urinary glucose (nonquantitative) measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, hypoglycemia, and hyperglycemia.
Predicate Devices
Uritek-720+ Urine Analyzer with Teco Diagnostic URS-10 strips (k051526)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k141289
B. Purpose for Submission:
New Device
C. Measurand:
Urinary glucose, blood, leukocyte, pH, nitrite, protein, ketones, urobilinogen, bilirubin, and specific gravity
D. Type of Test:
Qualitative and semi-quantitative urinalysis
E. Applicant:
Teco Diagnostics
F. Proprietary and Established Names:
TC-Thunderbolt Automated Urine Analyzer System
G. Regulatory Information:
| Device / Analyte | Product Code | Device Class | Regulation |
| --- | --- | --- | --- |
| Urinary Glucose (non-quantitative) Test System | JIL | II | 21 CFR 862.1340 |
| Occult Blood Test | JIO | II | 21 CFR 864.6550 |
| Automated Urinalysis System | KQO | I | 21 CFR 862.2900 |
| Leukocytes Peroxidase Test | LJX | I | 21 CFR 864.7675 |
| Urinary pH (non-quantitative) Test System | CEN | I | 21 CFR 862.1550 |
| Nitrite (non-quantitative) Test System | JMT | I | 21 CFR 862.1510 |
| Urinary Protein or Albumin (non-quantitative) Test System | JIR | I | 21 CFR 862.1645 |
| Ketones (non-quantitative) Test System | JIN | I | 21 CFR 862.1435 |
| Urinary Urobilinogen (non-quantitative) Test System | CDM | I | 21 CFR 862.1785 |
{1}
| Device / Analyte | Product Code | Device Class | Regulation |
| --- | --- | --- | --- |
| Urinary Bilirubin and conjugates (non-quantitative) Test System | JJB | I | 21 CFR 862.1115 |
| Refractometer for clinical use | JRE | I | 21 CFR 862.2800 |
Panel:
(75) Clinical Chemistry and (81) Hematology
H. Intended Use:
1. Intended use(s):
See Indication for use below.
2. Indication(s) for use:
The TC-Thunderbolt Automated Urine Analyzer System is an in vitro diagnostic device used to automate the urine chemistry analysis using TC-Thunderbolt URS-10 strips. It produces semi-quantitative results of glucose, protein, pH, bilirubin, blood, ketone, urobilinogen, nitrite, specific gravity, and leukocytes in urine. TC-Thunderbolt URS-10 strips are intended for use only with TC-Thunderbolt Automated Urine Analyzer System, they are not intended for manual visual reading. This device is for clinical laboratory use only. This device is not for Point of Care Use. These measurements are used to aid in the diagnosis of metabolic disorders, kidney function abnormalities, urinary tract infection, and liver function.
3. Special conditions for use statement(s):
For prescription use
4. Special instrument requirements:
TC-Thunderbolt Automated Urine Analyzer
I. Device Description:
The TC-Thunderbolt Automated Urine Analyzer System is an automated urine chemistry analyzer design for use with the TC-Thunderbolt Urine Reagent Strips. The system transfers a urine sample via a sample-suction needle and pipe, which extracts and applies the sample to the test strip; the test module then uses the principle of light-reflection to determine the changes in paper color, conduct a digital analysis on the central portion most uniform in color of the paper, and obtain results. When one specimen is finished, the device automatically cleans itself and extracts the next specimen to repeat the testing process, and if required, prints and saves the urine analysis report.
{2}
The TC-Thunderbolt Urine Reagent Strips (URS) are firm plastic strips to which ten different reagent pads are affixed. The TC-Thunderbolt URS-10 Reagent Strips are for the semi-quantitative and qualitative detection of glucose, bilirubin, ketones, specific gravity, blood, pH, protein, urobilinogen, nitrite, and leukocytes in urine. The reagent strips are packaged along with a drying agent in a plastic bottle with a twist-off cap. Each strip is stable and ready to use upon removal from the bottle. The entire strip is disposable.
## J. Substantial Equivalence Information:
1. Predicate device name(s):
Teco Diagnostic 720+ Urine Analyzer and Teco Diagnostic URS-10 strips
2. Predicate 510(k) number(s):
k051526
3. Comparison with predicate:
| Similarities / Difference | | |
| --- | --- | --- |
| Item | Candidate Device
TC-Thunderbolt Automated
Urine Analyzer System
(k141289) | Predicate Device
Uritek-720+ Urine Analyzer
with Teco Diagnostic URS-10 strips
(k051526) |
| Intended Use | Analysis of glucose, protein, pH, bilirubin, blood, ketone, urobilinogen, nitrite, specific gravity and leukocytes in urine of glucose, protein, pH, bilirubin, blood, ketones, urobilinogen, nitrite, specific gravity, and leukocytes in urine. | Same |
| Analyzer Basic Operating Principle | Reflectance Photometer | Same |
| Analyzer Calibration method | Calibration strip | Same |
| Specimen | Urine | Same |
| Strip physical description | Plastic strips affixed with reagent pads | Same |
| Urine Application to the Analyzer | Automatic sample suction, strip advance, and sample application technology | Test strip must be dipped in urine. Dry the strip on an absorbent paper and place on the test table manually. |
{3}
| Similarities / Difference | | |
| --- | --- | --- |
| Item | Candidate Device
TC-Thunderbolt Automated
Urine Analyzer System
(k141289) | Predicate Device
Uritek-720+ Urine Analyzer
with Teco Diagnostic URS-10 strips
(k051526) |
| Analyzer Environment requirement | Ambient temperature: 25°C+5°C; Relative humidity: <75% | Ambient temperature: 0°C to 40°C; Relative humidity: <85% |
| Strip Dimension | 110mm (length) x 5mm (width) | 108mm (length) x 5mm (width) |
K. Standard/Guidance Document Referenced (if applicable):
None Referenced.
L. Test Principle:
Glucose: This test is based on a double sequential enzyme reaction. One enzyme, glucose oxidase, catalyzes the formation of gluconic acid and hydrogen peroxide from the oxidation of glucose. A second enzyme, peroxidase, catalyzes the reaction of hydrogen peroxide with potassium iodide chromogen to oxidize the chromogen to colors ranging from blue-green to greenish-brown through brown and dark brown.
Bilirubin: This test is based on the coupling of bilirubin with a diazotized dichloroaniline in a strongly acid medium. The colors range from light tan to reddish-brown.
Ketone: This test is based on the reaction of acetoacetic acid with sodium nitroprusside in a strongly basic medium. The colors range from beige or buff-pink color for a "Negative" reading to pink and pink-purple for a "Positive" reading.
Specific Gravity: This test is based on the apparent pKa change of certain pretreated polyelectrolytes in relation to the ionic concentration. In the presence of an indicator, the colors range from dark blue or blue-green in urine of low ionic concentration to green and yellow-green in urine of higher ionic concentration.
Blood: This test is based on the pseudoperoxidase action of hemoglobin and erythrocytes, which catalyzes the reaction of 3',3',5',5'-tetramethyl-benzidine and buffered organic peroxide. The resulting colors range from orange to yellow-green and dark green. Very high blood concentration may cause the color development to continue to dark blue.
pH: This test is based on the well known double pH indicator method, where bromothymol blue and methyl red give distinguishable colors over the pH range of 5-9. The colors range from red-orange to yellow and yellow-green to blue-green.
{4}
Protein: This test is based on the protein error-of-indicator principle. At a constant pH, the development of any green color is due to the presence of protein. Colors range from yellow for a "Negative" reaction to yellow-green and green to blue-green for a "Positive" reaction.
Urobilinogen: This test is based on a modified Ehrlich reaction in which $p$-diethylaminobenzaldehyde reacts with urobilinogen in a strongly acid medium. Colors range from light pink to bright magenta.
Nitrite: This test depends on the conversion of nitrate to nitrite by the action of Gram-negative bacteria in the urine. The nitrite reacts with $p$-arsanilic acid to form a diazonium compound in an acid medium. The diazonium compound in turn couples with 1,2,3,4-tetrahydrobenzo(h) quinolin to produce a pink color.
Leukocytes: This test is based on the action of esterase present in leukocytes, which catalyzes the hydrolysis of an indoxyl ester derivative. The indoxyl ester liberated reacts with a diazonium salt to produce a beige-pink to purple color.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
The repeatability of the TC-Thunderbolt Automated Urine Analyzer System was evaluated using three levels of urine controls. 20 replicates of each level (negative, low positive, and high positive) were analyzed on one TC-Thunderbolt Automated Urine Analyzer with three lots of TC-Thunderbolt URS-10 strips by three operators on one day. The results are summarized below:
Control level 1:
| Analyte | Control Level 1 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | 500 mg/dL | 58/60 (96.67%) | 60/60 (100%) |
| Bilirubin | Moderate | 60/60 (100%) | 60/60 (100%) |
| Ketone | 40 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Specific Gravity | 1.015 | 60/60 (100%) | 60/60 (100%) |
| Blood | Moderate | 59/60 (98.34%) | 60/60 (100%) |
| Nitrite | Positive | 60/60 (100%) | 60/60 (100%) |
| Protein | 300 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 8 EU/dL | 60/60 (100%) | 60/60 (100%) |
| Leukocytes | Moderate | 60/60 (100%) | 60/60 (100%) |
| pH | 7.5 | 60/60 (100%) | 60/60 (100%) |
{5}
Control level 2:
| Analyte | Control Level 2 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | 100 mg/dL | 58/60 (96.67%) | 60/60 (100%) |
| Bilirubin | Small | 60/60 (100%) | 60/60 (100%) |
| Ketone | 40 mg/dL | 59/60 (98.83%) | 60/60 (100%) |
| Specific Gravity | 1.015 | 57/60 (95%) | 60/60 (100%) |
| Blood | Trace | 59/60 (100%) | 60/60 (100%) |
| Nitrite | Positive | 60/60 (100%) | 60/60 (100%) |
| Protein | negative | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 0.2 EU/dL | 60/60 (100%) | 60/60 (100%) |
| Leukocytes | Small | 60/60 (100%) | 60/60 (100%) |
| pH | 7.5 | 60/60 (100%) | 60/60 (100%) |
Control level 3:
| Analyte | Control Level 3 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | Negative | 60/60 (100%) | 60/60 (100%) |
| Bilirubin | Negative | 60/60 (100%) | 60/60 (100%) |
| Ketone | Negative | 60/60 (100%) | 60/60 (100%) |
| Specific Gravity | 1.005 | 58/60 (96.67%) | 60/60 (100%) |
| Blood | Negative | 60/60 (100%) | 60/60 (100%) |
| Nitrite | Negative | 60/60 (100%) | 60/60 (100%) |
| Protein | Negative | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 0.2EU/dL | 60/60 (100%) | 60/60 (100%) |
| Leukocytes | Negative | 60/60 (100%) | 60/60 (100%) |
| pH | 6.5 | 60/60 (100%) | 60/60 (100%) |
A run-to-run precision study was performed testing 2 replicates of each control level (negative, low positive, and high positive) for 2 non-consecutive runs per day over 5 days. The samples were analyzed on one TC-Thunderbolt Automated Urine Analyzer with three lots of TC-Thunderbolt URS-10 strips. Run 1 and Run 2 were separated by 1 hour.
The results are summarized below:
| Analyte | Control Level 1 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | 500 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Bilirubin | Moderate | 60/60 (100%) | 60/60 (100%) |
| Ketone | 40 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Specific Gravity | 1.015 | 59/60 (98.83%) | 60/60 (100%) |
{6}
| Analyte | Control Level 1 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Blood | Moderate | 60/60 (100%) | 60/60 (100%) |
| Nitrite | Positive | 60/60 (100%) | 60/60 (100%) |
| Protein | 300 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 8 EU/dL | 59/60 (98.83%) | 60/60 (100%) |
| Leukocyte | Moderate | 60/60 (100%) | 60/60 (100%) |
| pH | 7.5 | 60/60 (100%) | 60/60 (100%) |
| Analyte | Control Level 2 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | 100 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Bilirubin | Small | 60/60 (100%) | 60/60 (100%) |
| Ketone | 40 mg/dL | 60/60 (100%) | 60/60 (100%) |
| Specific Gravity | 1.015 | 56/60 (95%) | 60/60 (100%) |
| Blood | Trace | 60/60 (100%) | 60/60 (100%) |
| Nitrite | Positive | 60/60 (100%) | 60/60 (100%) |
| Protein | Negative | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 0.2 EU/dL | 60/60 (100%) | 60/60 (100%) |
| Leukocytes | Small | 58/60 (96.67%) | 60/60 (100%) |
| pH | 7.5 | 60/60 (100%) | 60/60 (100%) |
| Analyte | Control Level 3 | Exact Block Agreement % | ±1 Color Block Agreement % |
| --- | --- | --- | --- |
| Glucose | Negative | 60/60 (100%) | 60/60 (100%) |
| Bilirubin | Negative | 60/60 (100%) | 60/60 (100%) |
| Ketone | Negative | 60/60 (100%) | 60/60 (100%) |
| Specific Gravity | 1.005 | 60/60 (100%) | 60/60 (100%) |
| Blood | Negative | 60/60 (100%) | 60/60 (100%) |
| Nitrite | Negative | 60/60 (100%) | 60/60 (100%) |
| Protein | Negative | 60/60 (100%) | 60/60 (100%) |
| Urobilinogen | 0.2 EU/dL | 60/60 (100%) | 60/60 (100%) |
| Leukocytes | Negative | 60/60 (100%) | 60/60 (100%) |
| pH | 6.5 | 60/60 (100%) | 60/60 (100%) |
b. Linearity/assay reportable range:
The study to evaluate the reportable range (percent recovery) for each analyte color block on the TC-Thunderbolt URS-10 strip was evaluated by measuring a negative
{7}
urine and a negative urine pool spiked with known increasing and decreasing concentrations of analytes relative to each color block on the test strip. Samples were performed in replicates of 7 by three operators on three reagents strip lots for a total of 21 measurements for every sample. A pH meter was used to confirm the pH results. The specific gravity was confirmed by a clinical, handheld refractometer. A specific gravity reading of 1.000 was obtained from distilled water. The reportable range for each pad is defined as the concentration(s) at which there is a >90% exact match for that concentration with one block/result.
The percent recovery results where a >90% exact match was obtained for each analyte at each concentration block is shown in the table below:
| Analyte | TC-Thunderbolt Color Block Output Units (Reportable Range) | Conventional Units corresponding to block | Concentrations Tested resulting in >90% exact match with a block | Percent Exact Match |
| --- | --- | --- | --- | --- |
| Glucose | - | 0 mg/dL | 0 – 50 mg/dL | 100% |
| | ± | 100 mg/dL | 100 – 175 mg/dL | 100% |
| | 1+ | 250 mg/dL | 250 – 375 mg/dL | 100% |
| | 2+ | 500 mg/dL | 500 – 625 mg/dL | 100% |
| | 3+ | 1000 mg/dL | 1000 mg/dL | 100% |
| Bilirubin | - | Negative | 0.0 – 0.25 mg/dL | 100% |
| | 1+ | Small | 0.5 – 0.75mg/dL | 100% |
| | 2+ | Moderate | 1.0 – 2.0 mg/dL | 100% |
| | 3+ | Large | 3.0 mg/dL | 100% |
| Ketone | - | Negative | 0.0 – 1.25 mg/dL | 100% |
| | ± | Trace | 5.0 – 7.5 mg/dL | 100% |
| | 1+ | 15 mg/dL | 15 mg/dL | 100% |
| | 2+ | 40 mg/dL | 33.75 – 40.0 mg/dL | 100% |
| | 3+ | 80 mg/dL | 70 – 80 mg/dL | 100% |
| Blood | - | Negative | 0.0 mg/dL | 100% |
| | ± | Trace | 0.03 – 0.043 mg/dL | 100% |
| | 1+ | Small | 0.075 – 0.158mg/dL | 100% |
| | 2+ | Moderate | 0.24 – 0.495 mg/dL | 100% |
| | 3+ | Large | 0.628 – 0.75 mg/dL | 90% |
| Protein | - | Negative | 0.0 – 3.75 mg/dL | 100% |
| | ± | Trace | 15 – 18.75 mg/dL | 90% |
| | 1+ | 30 mg/dL | 30 – 47.5 mg/dL | 100% |
| | 2+ | 100 mg/dL | 82.5 – 100 mg/dL | 95% |
| | 3+ | 300 mg/dL | 250 – 300 mg/dL | 95% |
{8}
| Analyte | TC-Thunderbolt Color Block Output Units (Reportable Range) | Conventional Units corresponding to block | Concentrations Tested resulting in >90% exact match with a block | Percent Exact Match |
| --- | --- | --- | --- | --- |
| | 4+ | 2000 mg/dL | 1575 – 2000 mg/dL | 90% |
| Nitrite | - | Negative | 0.025 – 0.075 mg/dL | 100% |
| | + | Positive | > 0.1 mg/dL | 100% |
| Leukocyte | - | Negative | 0.0 – 11.25 ca cells/μL | 95% |
| | ± | Trace | 15 – 28.75 ca cells/μL | 95% |
| | 1+ | Small | 56.25 – 83.75 ca cells/μL | 95% |
| | 2+ | Moderate | 111.25 – 312.5 ca cells/μL | 100% |
| | 3+ | Large | 500 ca cells/μL | 100% |
| Urobilinogen | 0.2 | 0.2 mg/dL | 0.2 – 0.6 mg/dL | 100% |
| | 1.0 | 1.0 mg/dL | 1.0 - 1.50 mg/dL | 90% |
| | 2.0 | 2.0 mg/dL | 2.0 – 3.0 mg/dL | 90% |
| | 4.0 | 4.0 mg/dL | 4.0 – 5.0 mg/dL | 100% |
| | 8.0 | 8.0 mg/dL | 8.0 mg/dL | 100% |
| pH | 5.0 | 5.0 | 5.0 | 95% |
| | 6.0 | 6.0 | 6.0 | 95% |
| | 6.5 | 6.5 | 6.5 | 95% |
| | 7.0 | 7.0 | 7.0 | 95% |
| | 7.5 | 7.5 | 7.5 | 95% |
| | 8.0 | 8.0 | 8.0 | 95% |
| | 8.5 | 8.5 | 8.5 | 95% |
| SG | 1.005 | 1.005 | 1.005 | 100% |
| | 1.010 | 1.010 | 1.010 | 100% |
| | 1.015 | 1.015 | 1.015 | 100% |
| | 1.020 | 1.020 | 1.020 | 100% |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Calibration is performed using a calibration strip. This ready-to-use calibration strip provided with the TC-Thunderbolt Automated Urinalysis System to evaluate the alignment of the strip.
{9}
Shelf-life and open-vial stability protocols and acceptance criteria were reviewed and found to be acceptable for the TC-Thunderbolt URS-10 strips. The stability studies support the following manufacturer's claim: The strips can be stored between $15^{\circ}\mathrm{C}$ - $30^{\circ}\mathrm{C}$ ( $59^{\circ}\mathrm{F} - 86^{\circ}\mathrm{F}$ ) out of direct sunlight for 28 months. The open-vial stability is for 90 days at room temperature ( $15 - 30^{\circ}\mathrm{C}$ ).
# d. Detection limit:
A study was performed to validate the cutoff concentration for each analyte on the TC-Thunderbolt URS-10 strip. Urine samples were prepared by spiking a negative urine pool with a minimum of 4 levels across the measuring range for each analyte concentration. The samples were analyzed in replicates of 7 by three operators on three reagent strip lots, for a total of 21 data points for each level. The low cut-off concentration for each color block was defined as the lowest concentration at which $\geq 55\%$ of the test results are positive for each color block.
Summary of the performance at each color block for the tested analyte concentrations:
| Analyte | Color Block | Low Cut-off Concentration | % Positive Results at the Low Cutoff Concentration |
| --- | --- | --- | --- |
| Glucose | 100 mg/dL | 75 mg/dL | 90% |
| | 250 mg/dL | 212.5 mg/dL | 85% |
| | 500 mg/dL | 437.5 mg/dL | 85% |
| | 1000 mg/dL | 875 mg/dL | 85% |
| Bilirubin | Small | 0.375mg/dL | 57% |
| | Moderate | 1 mg/dL | 100% |
| | Large | 2.5 mg/dL | 57% |
| Ketone | Trace | 3.75mg/dL | 95% |
| | 15 mg/dL | 10 mg/dL | 55% |
| | 40 mg/dL | 27.5 mg/dL | 55% |
| | 80 mg/dL | 60 mg/dL | 95% |
| Blood | Trace | 0.023 mg/dL | 61% |
| | Small | 0.064 mg/dL | 76% |
| | Moderate | 0.199 mg/dL | 90% |
| | Large | 0.628 mg/dL | 90% |
| Protein | Trace | 11.25 mg/dL | 75% |
| | 30 mg/dL | 26.25 mg/dL | 85% |
| | 100 mg/dL | 82.5 mg/dL | 95% |
| | 300 mg/dL | 200 mg/dL | 85% |
| | 2000 mg/dL | 1150 mg/dL | 70% |
| Nitrite | Positive | 0.1 mg/dL | 55% |
{10}
| Analyte | Color Block | Low Cut-off Concentration | % Positive Results at the Low Cutoff Concentration |
| --- | --- | --- | --- |
| Leukocyte | Trace | 15 ca cells/μL | 100% |
| | Small | 56.25 ca cells/μL | 95% |
| | Moderate | 97.5 ca cells/μL | 60% |
| | Large | 406.25 ca cells/μL | 55% |
| Urobilinogen | 0.2 mg/dL | 0.2 mg/dL | 100% |
| | 1.0 mg/dL | 0.8 mg/dL | 71% |
| | 2.0 mg/dL | 2.0 mg/dL | 90% |
| | 4.0 mg/dL | 3.5 mg/dL | 55% |
| | 8.0 mg/dL | 6.0 mg/dL | 80% |
| pH | 5.0 | 5.0 | 95% |
| | 6.0 | 6.0 | 95% |
| | 6.5 | 6.5 | 95% |
| | 7.0 | 7.0 | 95% |
| | 7.5 | 7.5 | 95% |
| | 8.0 | 8.0 | 100% |
| | 8.5 | 8.5 | 100% |
| SG | 1.005 | 1.005 | 100% |
| | 1.010 | 1.010 | 100% |
| | 1.015 | 1.015 | 100% |
| | 1.020 | 1.020 | 100% |
| | 1.025 | 1.025 | 100% |
| | 1.030 | 1.030 | 100% |
e. Analytical specificity:
Studies were performed to assess the effect of various potential interferents on the test results of the TC-Thunderbolt Automated Urine Analyzer System. Testing was performed using two urine pools with negative and positive concentrations for all analytes. The positive pool was prepared by spiking each analyte into a negative urine sample. Each urine sample was tested in 3 replicates using the TC-Thunderbolt Automated Urine Analyzer System. Possible interference was noted when a difference of one color pad in any of the three replicates for the particular test analyte compared to either the negative (specificity) or analyte-spiked positive sample (interference).
{11}
The concentrations of the potential interfering substances that will not have influence on the tests are shown below:
| Potential Interfering Substances | Highest Concentration not affecting the test (mg/dL) |
| --- | --- |
| Ascorbic Acid | 10 mg/dL |
| Ammonia chloride | 400 (mg/dL) |
| Albumin | 300 (mg/dL) |
| Bilirubin | 4 (mg/dL) |
| Calcium Chloride | 80 (mg/dL) |
| Citric Acid | 65 (mg/dL) |
| Creatinine | 600 (mg/dL) |
| D (+) Glucose | 500(mg/dL) |
| Glycine | 900 (mg/dL) |
| Hemoglobin | 0.3 (mg/dL) |
| Potassium Chloride | 1000 (mg/dL) |
| Sodium Chloride | 2000 (mg/dL) |
| Oxalic Acid | 20 (mg/dL) |
| Sodium Nitrate | 10 (mg/dL) |
| Sodium Nitrite | 0.5 (mg/dL) |
| Sodium Phosphate | 1000 (mg/dL) |
| Urea | 3000 (mg/dL) |
| D(+) Galactose | 300 (mg/dL) |
| Tetracycline | 100 (mg/dL) |
The following table shows the substances that did interfere with one or more of the analytes tested with the TC-Thunderbolt Automated Urine Analyzer System. Results are expressed as the lowest concentration of interfering substances that exhibit interference and the resulting change in output of color block:
| Analyte | Concentration of Substance at which Interference was observed | Change in Color Block Output |
| --- | --- | --- |
| Glucose | Ascorbic Acid | -1 |
| Protein | Hemoglobin ≥ 50 mg/dL, D(+) Glucose ≥ 2000 mg/dL | +1, -1 |
| Bilirubin | Ascorbic Acid ≥30 mg/dL. MESNA ≥ 50 mg/dL, Sodium Nitrite ≥ 2 mg/dL, Sodium Nitrate ≥ 10 mg/dL, D(+) Glucose ≥ 2000 mg/dL | -1 |
| Urobilinogen | - | - |
| Blood | Albumin ≥ 1000 mg/dL, Ascorbic Acid ≥30 mg/dL | +1 |
| Nitrite | D(+) Glucose ≥ 2000 mg/dL | -1 |
| Leukocytes | D(+) Glucose ≥ 2000 mg/dL, Ascorbic Acid ≥30 mg/dL | -1 |
{12}
| Analyte | Concentration of Substance at which Interference was observed | Change in Color Block Output |
| --- | --- | --- |
| Ketone | MESNA ≥ 50 mg/dL | +3 |
| pH | Acetoacetate ≥ 60 mg/dL, Oxalic Acid ≥70, Citric Acid ≥ 130 mg/dL | +1, -1, -1 |
In addition to the interference described in the table above, the sponsor states the following in the labeling regarding other potential interfering substances: The TC-Thunderbolt URS-10 Reagent strips may be affected by substances that cause abnormal urine color such as drugs containing azo dyes (e.g. Pyridium, Azo Gantrisin, Azo Gantanol), Cephalexin and Gentamicin.
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study was performed using a single replicate of each clinical specimen between the TC-Thunderbolt URS-10 Strips on the TC-Thunderbolt Automated Urine Analyzer System and the Teco Diagnostic's URS-10 strips on the Uritek-720+ Urine Analyzer. Clinical samples were analyzed for the first positive color block above the negative. No spiked samples were used. Clinically positive spiked samples were used when insufficient numbers of high concentration samples were not available. These spiked samples represent less than 5% of the total samples tested.
Comparison Study Summary:
| Glucose | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 1000 | 500 | 250 | 100 | Neg | Overall |
| 1000 | 11 | | | | | |
| 500 | | 19 | 4 | | | |
| 250 | | 3 | 22 | 1 | | |
| 100 | | | 1 | 4 | | |
| Neg | | | | | 423 | |
| Total | 11 | 22 | 26 | 5 | 423 | 487 |
| % Agreement (Exact Match) | 100.0 | 86.36 | 84.62 | 80.0 | 100.0 | 98.36 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
{13}
| Bilirubin | | | | | |
| --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 3+ | 2+ | 1+ | Neg | Overall |
| 3+ | 6 | | | | |
| 2+ | | 7 | | | |
| 1+ | | | 40 | | |
| Neg | | | 2 | 432 | |
| Total | 6 | 7 | 42 | 432 | 487 |
| % Agreement (Exact Match) | 100.0 | 100.0 | 95.24 | 100.0 | 99.59 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.00 | 100.0 |
| Ketones | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 80 | 40 | 15 | TRACE | Neg | Overall |
| 80 | 6 | | | | | |
| 40 | | 10 | 3 | | | |
| 15 | | 3 | 25 | 2 | | |
| TRACE | | | 2 | 14 | 1 | |
| Neg | | | | | 421 | |
| Total | 6 | 13 | 30 | 16 | 422 | 487 |
| % Agreement (Exact Match) | 100.0 | 76.92 | 83.33 | 87.50 | 99.76 | 97.74 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.00 | 100.00 | 100.0 |
| Specific Gravity | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | >1.030 | 1.025 | 1.020 | 1.015 | 1.010 | <1.005 | Overall |
| >1.030 | 9 | 1 | | | | | |
| 1.025 | 3 | 118 | 12 | | | | |
| 1.020 | | 5 | 44 | 4 | | | |
| 1.015 | | | 7 | 101 | 3 | 2 | |
| 1.010 | | | | 30 | 68 | 5 | |
| <1.005 | | | | 2 | 24 | 49 | |
| Total | 12 | 124 | 63 | 137 | 95 | 56 | 487 |
| % Agreement (Exact Match) | 75.0 | 95.16 | 69.84 | 73.72 | 71.58 | 87.50 | 79.88 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 98.54 | 100.00 | 96.43 | 99.18 |
{14}
| Blood | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 3+ | 2+ | 1+ | TRACE | Neg | Overall |
| 3+ | 13 | 3 | | | | |
| 2+ | 1 | 45 | 6 | | | |
| 1+ | | 4 | 20 | 5 | | |
| TRACE | | | | 17 | 1 | |
| Neg | | | | 2 | 370 | |
| Total | 14 | 52 | 26 | 24 | 371 | 487 |
| % Agreement (Exact Match) | 92.86 | 86.54 | 76.92 | 70.83 | 99.73 | 95.48 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
| Protein | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | >300 | 100 | 30 | TRACE | Neg | Overall |
| >300 | 40 | 3 | | | | |
| 100 | 3 | 32 | | | | |
| 30 | | | 17 | | | |
| TRACE | | | 3 | 20 | | |
| Neg | | | | 1 | 368 | |
| Total | 43 | 35 | 20 | 21 | 368 | 487 |
| % Agreement (Exact Match) | 93.02 | 91.43 | 85.00 | 95.24 | 100.0 | 97.95 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
| Urobilinogen | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | >8.0 | 4.0 | 2.0 | 1.0 | 0.2 | Overall |
| >8.0 | 10 | 1 | | | | |
| 4.0 | 1 | 66 | 4 | | | |
| 2.0 | | 1 | 27 | 1 | | |
| 1.0 | | | | 31 | 13 | |
| 0.2 | | | | 6 | 332 | |
| Total | 11 | 68 | 31 | 32 | 345 | 487 |
| % Agreement (Exact Match) | 90.91 | 97.06 | 87.10 | 96.88 | 96.23 | 95.69 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
{15}
| pH | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 8.5 | 8.0 | 7.5 | 7.0 | 6.5 | 6.0 | 5.0 | Overall |
| 8.5 | 10 | | | | | | | |
| 8.0 | | 12 | | | | | | |
| 7.5 | | | 111 | 4 | 1 | | | |
| 7.0 | | | 3 | 59 | 2 | 1 | | |
| 6.5 | | | | 3 | 94 | 33 | | |
| 6.0 | | | | | | 64 | 18 | |
| 5.0 | | | | | | 1 | 71 | |
| Total | 10 | 12 | 114 | 66 | 97 | 99 | 89 | 487 |
| % Agreement (Exact Match) | 100 | 100 | 97.37 | 89.39 | 96.91 | 64.65 | 79.78 | 86.45 |
| % Agreement (+/- Color Block) | 100 | 100 | 100.0 | 100 | 98.97 | 98.99 | 100 | 99.59 |
| Nitrite | | | |
| --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | + | - | Overall |
| + | 70 | | |
| - | 1 | 416 | |
| Total | 71 | 416 | 373 |
| % Agreement (Exact Match) | 98.59 | 100 | 99.79 |
| % Agreement (+/- Color Block) | 100.0 | 100 | 100.0 |
| Leukocyte | | | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| Thunderbolt Uritek 720+ | 3+ | 2+ | 1+ | TRACE | Neg | Overall |
| 3+ | 12 | | | | | |
| 2+ | 1 | 17 | 4 | | | |
| 1+ | | 5 | 27 | 5 | | |
| Trace | | | 1 | 15 | | |
| Neg | | | | | 400 | |
| Total | 13 | 22 | 32 | 20 | 400 | 487 |
| % Agreement (Exact Match) | 92.31 | 77.27 | 84.38 | 75.0 | 100.0 | 96.71 |
| % Agreement (+/- Color Block) | 100.0 | 100.0 | 96.88 | 100.0 | 100.0 | 100.0 |
{16}
b. Matrix comparison:
Not applicable.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable.
b. Clinical specificity:
Not applicable.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable.
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
Glucose: Small amounts of glucose are normally excreted by the kidney.³ Concentrations as little as 0.1 g/dl glucose, read either at 10 or 30 seconds, may be significantly abnormal if found consistently.
Bilirubin: Normally, no bilirubin is detectable in urine by even the most sensitive method. Even trace amounts of bilirubin are sufficiently abnormal to require further investigation. Atypical colors (colors produced which are different than the negative or positive color blocks shown on the Color Chart) may indicate that bilirubin derived bile pigments are present in the urine sample and are possibly masking the bilirubin reaction.
Ketone: Normally, no ketones are present in urine. Detectable levels of ketone may occur in urine during physiological stress conditions such as fasting, pregnancy, and frequent strenuous exercise.⁴⁻⁶ In starvation diets, or in other abnormal carbohydrate metabolism situation, ketones appear in the urine in excessively large amounts before serum ketones are elevated.⁷
Specific Gravity: Random urine may vary in specific gravity from 1.003-1.040+. Twenty-four hour urine from normal adults with normal diets and normal fluid intake will have a specific gravity of 1.016-1.022.⁸ In severe renal damage, the specific gravity is fixed at 1.010, the value of the glomerular filtrate.
Blood: Any green spots or green color developing on the reagent area within 40 seconds is significant and the urine should be examined further. Blood is frequently, but not invariably found in the urine of menstruating females.
pH: 4.5-8.0 average: 6.0.¹
{17}
Protein: In 24-hour urine, 1-14 mg/dl of protein may be excreted by the normal kidney.² A color matching any color block greater than trace indicates significant proteinuria. For urine with high specific gravity, the test area may most closely match the trace color block even though only normal concentrations of protein are present. Clinical judgment is needed to evaluate the significance of trace results.
Urobilinogen: In a healthy population, the normal urine urobilinogen range obtained with this test is 0.2-1.0 Ehrlich Unit/dl. A result of 2.0 EU/dl may be of clinical significance and the same patient sample should be evaluated further.
Nitrite: Normally no detectable amount of nitrite is present in urine.¹ The nitrite area will be positive in a proportion of cases of significant infection, depending on how long the urine specimens were retained in the bladder prior to collection. Retrieval of positive cases with the nitrite test range from as low as 40%, in instances where little bladder incubation occurred, to as high as 80% in instances where a minimum of 4 hours incubation occurred.
Leukocytes: Normal urine specimens generally yield negative results with this test. A trace result may be of questionable clinical significance and it is recommended that the test be repeated using a fresh sample from the same patient. Repeated trace and positive results are of clinical significance.
1. Tietz, N.W.: Clinical Guide to Laboratory Tests; W.B. Saunders Company, (1976).
2. Burtis, C.A. and Ashwood, E.R.: Tietz Textbook of Clinical Chemistry 2nd Ed. 2205; (1994).
3. Schersten, B. and Fritz, H.: Subnormal Levels of Glucose in Urine. JAMA 201:129-132; (1967).
4. McGarry, J.D.: Lilly Lecture, 1978: New Perspectives in the Regulation of Ketogenesis. Diabetes 28: 517-523 May, (1978).
5. Williamson, D.H.: Physiological ketoses, or Why Ketone Bodies? Postgrad. Med. J. (June Suppl.): 371-375: (1971).
6. Paterson, P. et al.: Maternal and Fetal Ketone Concentrations in Plasma and Urine. Lancet: 862-865; April 22, (1967).
7. Fraser, J. et al.: Studies with a Simplified Nitroprusside Test for Ketone Bodies in Urine, Serum, Plasma and Milk. Clin. Chem. Acta II: 372-378; (1965).
8. Henry, J.B. et al.: Clinical Diagnosis and Management by Laboratory Methods, 16th Ed. Philadelphia: Saunders; (1979).
N. Instrument Name:
TC-Thunderbolt Automated Urine Analyzer
{18}
O. System Descriptions:
1. Modes of Operation:
Automatic sample-suction, strip advance, and sample application.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ X ☐ or No ☐
The following sections are presented in the submission and they appear adequate based on the level of concern and information provided in the Guidance for Content of Premarket Submissions for Software Contained in Medical Devices, May 11, 2005.
Level of Concern – The sponsor has classified their device as a Moderate Level of Concern.
3. Specimen Identification:
Bar-code scanner.
4. Specimen Sampling and Handling:
The TC-Thunderbolt Automated Urine Analyzer uses automatic sample-suction, strip advance, and sample-application technologies.
5. Calibration:
The TC-Thunderbolt Automated Urine Analyzer System uses a plastic calibration strip to perform a calibration reflectance check and test module alignment. The calibration strip is included with the system. There are two different kinds of calibration. One is to ensure the stability of the light source; it is performed every time the instrument is switched on. The other is to align the test module and should be performed every 4 to 6 months.
6. Quality Control:
The labeling states:
For best results, performance of TC-Thunderbolt Urine Reagent Strips should be confirmed by controls whenever a new bottle is first opened. Each laboratory should establish its own goals for adequate standards of performance, and should question handling and testing procedures if these standards are not met.
{19}
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
None.
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.