URISTIK H Series Reagent Strips provide qualitative and semi-quantitative tests for ketones (acetoacetic acid), blood, protein, nitrite, ascorbic acid, pH, specific gravity, leukocytes, glucose, bilirubin, and urobilinogen in urine. Test results may provide information regarding the status of carbohydrate metabolism, kidney and liver function, acid-base balance and bacteriuria. Dirui H Series Reagent Strips are for single use in professional near-patient (point-of-care) and centralized laboratory locations. The strips are intended for use in screening for the following areas: Kidney function; Urinary tract infections; Carbohydrate metabolism (e.g. diabetes mellitus); Liver function; Acid-base balance; Urine concentration. Test results can be used along with other diagnostic information to rule out certain conditions and to determine if microscopic analysis is needed.
Device Story
URISTIK H Series Reagent Strips are firm plastic, dry reagent strips for qualitative/semi-quantitative urinalysis. Input: urine sample applied to reagent pads. Principle: chemical reactions (e.g., glucose oxidase/peroxidase for glucose; peroxidase activity for blood) produce color changes on pads. Output: visual color comparison against chart or instrumental reading via Dirui H-50, H-100, or H-500 Urine Analyzers. Used in hospitals, clinics, and labs by professional staff. Results available within one minute; assists diagnosis of metabolic, renal, and hepatic status; aids in screening for bacteriuria and acid-base balance.
Clinical Evidence
Clinical laboratory studies conducted by professional users in centralized and point-of-care settings. Performance evaluated by comparing visual and instrumental (Dirui H Series Analyzers) readings of URISTIK H strips against Bayer MULTISTIX 10 SG strips and standard laboratory methods. Results demonstrated that professional users can obtain valid, consistent urinalysis test results comparable to the predicate device.
Technological Characteristics
Firm plastic dry reagent strips; colorimetric chemical reaction principle. Analyte detection via spectrophotometric analysis (525nm, 620nm, 660nm) when used with Dirui H-50, H-100, or H-500 analyzers. Connectivity via RS-232 port. Calibration performed using a dedicated calibration strip. Software-controlled analysis with 1,000-result memory capacity.
Indications for Use
Indicated for professional use in point-of-care and clinical laboratory settings for screening kidney function, urinary tract infections, carbohydrate metabolism (e.g., diabetes), liver function, acid-base balance, and urine concentration in patients requiring urinalysis.
Regulatory Classification
Identification
An occult blood test is a device used to detect occult blood in urine or feces. (Occult blood is blood present in such small quantities that it can be detected only by chemical tests of suspected material, or by microscopic or spectroscopic examination.)
Special Controls
*Classification.* Class II (special controls). A control intended for use with an occult blood test is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
Predicate Devices
Bayer Corporation MULTISTIX 10 SG Regent Strips
Behring Diagnostics Rapignost Total Screen L Urine Test Strips (k861255)
Boehringer Mannheim Chemstrip 10 with SG Urine Test Strips (k896454)
International Newtech Development Urinalysis Reagent Strips (10 parameters) (k993850)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY DEVICE AND INSTRUMENT TEMPLATE
A. 510(k) Number:
k040703
B. Purpose for Submission:
Premarket Notification 510(k) of intention to manufacture and market the Dirui Industrial Co. Ltd. Uristik H Series Reagent Strips for Urinalysis.
C. Analyte:
Urine Urobilinogen, Bilirubin, Ketone (acetoacetic acid), Blood, Protein, Nitrite, Leukocytes, Glucose, Specific Gravity, pH, and Ascorbic Acid.
D. Type of Test:
Qualitative and semi-quantitative urinalysis.
E. Applicant:
Dirui Industrial Co. Ltd.
95 Yunhe Street
New & High Technology Development Zone
Changchun, 130012, China
F. Proprietary and Established Names:
URISTK H Series Reagent Strips for Urinalysis.
G. Regulatory Information:
1. Regulation section:
| Classification Name | Product Code | Panel Name | Device Class | Regulation Number |
| --- | --- | --- | --- | --- |
| Blood occult, colorimetric, in urine | JIO | 82 Hematology | II | 21 CFR §864.6550 |
| Urinary glucose (non-quantitative) test system | JIL | 75 Chemistry | II | 21 CFR §862.1340 |
| Classification Name | Product Code | Panel Name | Device Class | Regulation Number |
| --- | --- | --- | --- | --- |
| Urinary urobilinogen (non-quantitative) test system | CDM | 75 Chemistry | I | 21 CFR §862.1785 |
{1}
Page 2 of 11
| Urinary bilirubin and its conjugates (non-quantitative) test system | JJB | 75 Chemistry | I | 21 CFR §862.1115 |
| --- | --- | --- | --- | --- |
| Ketones (non-quantitative) test system | JIN | 75 Chemistry | I | 21 CFR §862.1435 |
| Urinary protein or albumin (non-quantitative) test system | JIR | 75 Chemistry | I | 21 CFR §862.1645 |
| Nitrite (non-quantitative) test system | JMT | 75 Chemistry | I | 21 CFR §862.1510 |
| Test, Urine Leukocyte | LJX | 82 Hematology | I | 21 CFR §864.7675 |
| Urinary pH (non-quantitative | CEN | 75 Chemistry | I | 21 CFR §862.1550 |
| Ascorbic acid test system | JMA | 75 Chemistry | I | 21 CFR §862.1095 |
| Refractometer for clinical use | JRE | 75 Chemistry | I | 21 CFR §862.2800 |
| Automated urinalysis system | KQO | 75 Chemistry | I | 21 CFR §862.2900 |
## H. Intended Use:
1. Intended use(s):
The URISTIK H Series Urinalysis Reagent Strips for Urinalysis provide qualitative and semi-quantitative test for ascorbic acid, pH, specific gravity, ketones, blood, protein, nitrite, leukocytes, glucose, bilirubin, and urobilinogen in urine. Test results may provide information regarding the status of carbohydrate metabolism, kidney and liver function, acid-base balance, and bacteria.
2. Indication(s) for use:
The URISTIK H Series Urinalysis Reagent Strips for Urinalysis provide qualitative and semi-quantitative test for ascorbic acid, pH, specific gravity, ketones, blood, protein, nitrite, leukocytes, glucose, bilirubin, and urobilinogen in urine. Test results may provide information regarding the status of carbohydrate metabolism, kidney and liver function, acid-base balance, and bacteria.
Dirui H Series Reagent Strips are for single use in professional near-patient (point-of-care) and centralized laboratory locations. The strips are intended for use in screening at-risk patients to assist diagnosis in the following areas:
{2}
Page 3 of 11
- Kidney function
- Urinary tract infections
- Carbohydrate metabolism (e.g. diabetes mellitus)
- Liver function
- Acid-base balance
- Urine concentration
The results can be used along with other diagnostic information to rule out certain disease states and to determine if microscopic analysis is needed.
3. Special condition for use statement(s):
For prescription use
4. Special instrument Requirements:
The URISTIK H-8, H-10, and H-11 Reagent Strips are intended for use on the Dirui H-50, H-100 or H-500 Urine Analyzers only.
Summary of Dirui H-50, H-100, and H-500 Urine Analyzers
| Type of Strip | For Urine Analyzer | Available Tests |
| --- | --- | --- |
| H-8 | Dirui H-100 | Urobilinogen, Bilirubin, Ketone (acetoacetic acid), Blood, Protein, Nitrite, Glucose, pH |
| H-10 | Dirui H-50, H-100, and H-500 | Urobilinogen, Bilirubin, Ketone (acetoacetic acid), Blood, Protein, Nitrite, Leukocytes, Glucose, Specific Gravity, pH |
| H-11 | Dirui H-100 and H-500 | Urobilinogen, Bilirubin, Ketone (acetoacetic acid), Blood, Protein, Nitrite, Leukocytes, Glucose, Specific Gravity, pH, and Ascorbic Acid |
I. Device Description:
The URISTIK H Series Reagent Strips for Urinalysis provide qualitative and semi-quantitative test for Urobilinogen, Bilirubin, Ketone (acetoacetic acid), Blood, Protein, Nitrite, Leukocytes, Glucose, Specific Gravity, pH, and Ascorbic Acid in urine. The URISTIK H Series Reagent Strips for Urinalysis are firm plastic, dry reagent strips impregnated with chemicals. The reagent areas are dipped into the urine sample and read visually according to a color chart or are read instrumentally with a Dirui H-50, H-100, or H-500 Urine Analyzer. The results are available within one minute. To obtain optimal results, it is necessary to use fresh, well mixed and uncentrifuged urine.
{3}
Page 4 of 11
# J. Substantial Equivalence Information:
1. Predicate device name(s):
Bayer Corporation MULTISTIX 10 SG Regent Strips
Behring Diagnostics Rapignost Total Screen L Urine Test Strips (k861255)
Boehringer Mannheim Chemstrip 10 with SG Urine Test Strips (k896454)
International Newtech Development Urinalysis Reagent Strips (10 parameters)
(k993850)
2. Predicate K number(s): See J. 1 above
3. Comparison with predicate:
Similarities and Differences between Urinalysis Test Strips
| Area of Comparison | Dirui URISTIK H-11 | Bayer Multistix 10 SG | Behring Rapignost Total Screen L | Boehringer Mannheim Chemstrip 10 with SG | International Newtech Urinalysis Reagent Strips |
| --- | --- | --- | --- | --- | --- |
| Intended Use | Professional use in point-of-care urine testing | Same | Same | Same | Same |
| Target Population | Patients of physicians, hospitals, and clinics | Same | Same | Same | Same |
| Test Principles | Established clinical chemistry methods | Same for all tests | Same for all tests | Same for all tests | Same for all tests |
| Area of Comparison | Dirui URISTIK H-11 | Bayer Multistix 10 SG | Behring Rapignost Total Screen L | Boehringer Mannheim Chemstrip 10 with SG | International Newtech Urinalysis Reagent Strips |
| Test reagents | Ingredients that change color in reaction with analytes | X | Different ingredients or percentages for glucose, protein, ketones, blood, nitrite, | Different ingredients or percentages for glucose, protein, ketones, blood, bilirubin, | Different ingredients or percentages for nitrite, pH, specific gravity tests |
{4}
Page 5 of 11
| | | | leukocytes, urobilinogen, pH tests | nitrite, urobilinogen, pH, specific gravity tests | |
| --- | --- | --- | --- | --- | --- |
| Sensitivity | Trace or clinically low levels of analytes | X | Unspecified for ascorbic acid and leukocytes, different units for all other tests | Not compared | Different units for blood, same units and levels for all other tests |
| Output values | Negative and 2 to 6 positive values | X | Negative and 1 to 6 positive values | Not compared | Negative an 1 to 6 positive values |
K. Standard/Guidance Document Referenced (if applicable):
None Referenced
L. Test Principle:
Protein - The test is based on the protein-error-of-indicators principle. An ion in the specific pH indicator attracted by cation on the protein molecule makes the indicator further ionized, which changes its color.
Glucose - The assay for glucose is based on the glucose-specific glucose oxidase/peroxidase method. Oxidation of glucose forms hydrogen peroxide, which in turn oxidizes a chromogen in the peroxidase reaction to generate a green or blue color.
Blood - The assay for blood is based on the peroxidase activity of hemoglobin and myoglobin creating a green color with oxidation of a chromogen. Intact erythrocytes which hemolyze on the test paper will produce a green dot.
Ketones - The acetoacetate and sodium nitroprusside cause a reaction in the alkaline medium, which produces a violet color.
Leukocytes - Granulocyte leukocytes in urine contain esterase that catalyze the hydrolysis of the pyrrole amino acid ester to liberate 3-hydro-5-phenyl pyrrole. This pyrrole reacting with diazonium forms a purple color.
Nitrite - Nitrite in the urine and aromatic amino sulphanilamide are diazotized to form a diazonium compound. The diazonium compound reacting with tetrahydro benzo(h) quinolin 3-phenol causes the color change.
{5}
Page 6 of 11
Specific Gravity - Electrolyte $(\mathbf{M}^{+}\mathbf{X}^{-})$ in the form of salt in urine reacts with poly methyl vinyl ether and maleic acid (-COOH), which is a weak acid ionic exchanger. The reaction produces hydrogenous ionogen, which reacts with a pH indicator that causes a color change.
pH - This test is based on a double indicator principle that gives a broad range of colors covering the entire urinary pH range.
Bilirubin - The direct bilirubin and dichlorobenzene diazonium produce azo dyes n a strongly acid medium.
Urobilinogen - Urobilinogen and diazonium produce pink azo dyes under the function of strong acid medium.
Ascorbic acid - Ascorbic acid, with 1,2-dihydroxy alkenes, under the alkaline condition, deoxidizes the blue 2, 6-dichloroindophenolate into colorless N-(p-phenol)-2,6-dichloro-p-amine phenol.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility
Bio-Rad Urinalysis Control, Level 1 and Level 2 were used in the precision study. The same lot number of urinalysis control and lot number of reagent strips were used in this study. Two runs per day were performed for 10 days. All three reagent strips (H11, H10, H8) were repeated 10 times. The results of each reagent strip type, for the same read mode (pad) and urinalysis control were the same. The following data for H11 reagent strips read with the H-100 urine analyzer is representative. The results for the same pads on the H10 and H8 reagent strips were the same.
The performance characteristics of the strips are determined by clinical analysis and study. The results for visual readings and instrument readings represent an actual range of analyte concentrations. The following table shows the $\pm 1$ color block $\%$ agreement using 1599 samples in laboratory comparison studies between Uristik H Series Reagent Strips and Bayer Multistix 10 SG Reagent Strips.
| Analyte | % Agreement | Analyte | % Agreement |
| --- | --- | --- | --- |
| Urobilinogen | 95.1% 1520/1599 | Bilirubin | 96.3% 1540/1599 |
| Ketone | 96.6% 1544/1599 | Blood | 96.8% 1548/1599 |
| Protein | 95.4% 1526/1599 | Nitrite | 97.6% 1561/1599 |
| Leukocytes | 97.2% 1544/1599 | Glucose | 97.4% 1558/1599 |
| pH | 92.4% 1478/1599 | Specific Gravity | 92.7% 1482/1599 |
{6}
# b. Linearity/assay reportable range:
Uristik H Series Reagent Strips are qualitative and semi-quantitative. The methodology references are NCCLS EP9-A2 and NCCLS EP 10-A. The strips give results over a small range of concentration of each analyte. For a weak positive laboratory assay, the strips may give negative results because of low sensitivity.
The laboratory assay ranges include the output values of Uristik H Series Reagent Strips. The following table is the assay laboratory range for each analyte in the linearity study.
| Analyte | Unit | Lab Assay Range | Reportable Range |
| --- | --- | --- | --- |
| Urobilinogen | μmol/L | 0.2-300 | 3.3-131 |
| Bilirubin | μmol/L | 0-313 | 0-100 |
| Ketone | mmol/L | 0.02-35 | 0-16 |
| Blood | Ery/μL | 0-350 | 0-200 |
| Protein | g/L | 0.003-50 | 0-200 |
| Nitrite | μmol/L | 1.0-400 | Neg-Pos |
| Leukocytes | Leu/μL | 0-800 | 0-500 |
| Glucose | mmol/L | 0-300 | 0-110 |
| Specific Gravity | | 1.000-1.040 | 1.000-1.030 |
| pH | | 0-14.0 | 5.0-9.0 |
| Ascorbic Acid | mmol/L | 0.1-14.0 | 0-6.0 |
c. Traceability (controls, calibrators, or method): Not Provided
d. Detection limit:
Sensitivity was demonstrated to the lowest reporting block. See b. above
e. Analytical specificity:
Twenty five common drug components were tested for interferents. The only components having significant effects that were large enough to affect the test results were a high level of ketones ( $\geq 1.0 \, \text{mmol/L}$ ) and an abnormally high level of ascorbic acid ( $\geq 5 \, \text{mmol/L}$ ). These components may cause false negative or lower positive results. High levels of ketones and ascorbic acid are listed as interferences in the labeling.
{7}
Page 8 of 11
# Interference List
| Urine and Common Drug Components | Amount Not Affecting URISTIK H Series Test |
| --- | --- |
| Albumin | 800 mg/dL |
| Ascorbic Acid | 20 mg/dL |
| Hemoglobin^{1} | 50 mg/dL |
| Citric Acid | 50 mg/dL |
| Bilirubin | 3.0 mg/dL |
| Creatine | 8 mg/dL |
| Acetoacetate Acid | 1 mmol/L |
| Ammonium Chloride | 189 mg/dL |
| Calcium Chloride | 50 mg/dL |
| Creatinine | 800 mg/dL |
| Glucose^{2} | 2000 mg/dL |
| Glycine | 1000 mg/dL |
| KCL | 550 mg/dL |
| NaCl | 2800 mg/dL |
| Oxalic Acid | 70 mg/dL |
| Sodium Acetate | 1200 mg/dL |
| Sodium Bicarbonate | 1500 mg/dL |
| Sodium Nitrate | 0.26 mg/dL |
| Sodium Nitrite | 0.3 mg/dL |
| Sodium Phosphate | 16 mg/dL |
| Urobilinogen | 3.0 mg/dL |
| Urea | 3000 mg/dL |
| Riboflavin | 100 mg/L |
| Theophylline | 100 mg/L |
| Phenolphthalein | 1200 mg/L |
1. The affect on only glucose reagent shown.
2. The affect on only blood reagent shown.
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
When the urine samples were tested with the Uristik H 11 Reagent Strips for urinalysis, the samples were also tested with the predicate Bayer 10 SG Reagent Strip for Urinalysis. Results were read by urine analyzers and visually. The results are listed in the table below.
{8}
Page 9 of 11
# H11 Compared to Bayer 10 SG Reagent Strips For Urinalysis Both Read With Urine Analyzer
| Analyte | Agreement Total | % Agreement within ± 1 color block | Analyte | Agreement Total | % Agreement within ± 1 color block |
| --- | --- | --- | --- | --- | --- |
| Glucose | 1620/1661 | 97.5 | Protein | 1620/1661 | 97.5 |
| Blood | 1610/1661 | 96.9 | Ketone | 1606/1661 | 96.7 |
| Leukocytes | 1616/1661 | 97.3 | Urobilinogen | 1582/1661 | 95.2 |
| Nitrite | 1623/1661 | 97.7 | Bilirubin | 1602/1661 | 96.4 |
| pH | 1549/1661 | 93.3 | Specific Gravity | 1543/1661 | 92.9 |
# H11 Compared to Bayer 10 SG Reagent Strips For Urinalysis Both Read Visually
| Analyte | Agreement Total | % Agreement within ± 1 color block | Analyte | Agreement Total | % Agreement within ± 1 color block |
| --- | --- | --- | --- | --- | --- |
| Glucose | 1604/1661 | 96.6 | Protein | 1614/1661 | 97.2 |
| Blood | 1604/1661 | 96.6 | Ketone | 1610/1661 | 96.9 |
| Leukocytes | 1613/1661 | 97.1 | Urobilinogen | 1572/1661 | 94.7 |
| Nitrite | 1605/1661 | 96.6 | Bilirubin | 1605/1661 | 96.6 |
| pH | 1536/1661 | 92.5 | Specific Gravity | 1530/1661 | 92.1 |
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):
4. Clinical cut-off: Not Applicable
5. Expected values/Reference range:
Expected Values are referenced to European Urinalysis Guidelines, The Clinical Analysis Of Urine Recent Period Compendium – Urinalysis With Test Strips [2, 4, 5].
{9}
Page 10 of 11
2. "European Urinalysis Guidelines", The Scandinavian Journal of Clinical & Laboratory Investigation, Scand J Clin Lab Invest-Vol. 60-Supplement 231.2000.
4. "The Clinical Analysis of Urine Recent Period", The Science and Technology Publishing House, Yu Long Cong, Jun Long Ma, Editor's; 1998; pp. 37-81, 96-97.
5. "Compendium- Urinalysis With Test Strips" Roche Diagnostics, Combur® Reagent Strips.
## N. Instrument Name:
Dirui Industrial Co., Ltd H- 50 Urine Analyzer
Dirui Industrial Co., Ltd H-100 Urine Analyzer
Dirui Industrial Co., Ltd H-500 Urine Analyzer
## O. System Descriptions:
1. Modes of Operation:
Semi-automatic – must manually place reagent strips on strip table.
2. Software:
RS-232 Port communication connection
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☑ or No ☐
3. Sample Identification:
Data Memory - will store 1,000 patient results
4. Specimen Sampling and Handling:
Test Speed - fast mode 120 specimens per hour
- slow mode 60 specimens per hour
5. Assay Types:
Qualitative and semi-quantitative
6. Reaction Types:
Spectrophotometric readings at 525nm 620nm and 660nm
{10}
Page 11 of 11
7. Calibration:
Calibration Strip – The calibration strip that comes with the analyzer has the function of calibrating the urine analyzer, so that you get the correct test results. When the calibration results are the same after comparison, the urine analyzer has passed the calibration, it can be used normally. When the calibration results are not the same, the calibration has failed, and you must contact the supplier.
8. Quality Control:
Quality control monitoring is recommended and should be conducted under the following conditions:
- before daily use
- whenever new test strips are opened
- when there is a different operator
- whenever you suspect erroneous results
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "L. Performance Characteristics" Section Of The SE Determination Decision Summary:
Q. Conclusion:
The submitted material 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.