ADVIA CHEMISTRY CARDIOPHASE HIGH SENSITIVITY C-REACTIVE PROTEIN (HSCRP), CALIBRATORS
Applicant
Siemens Healthcare Diagnostics, Inc.
Product Code
NQD · Immunology
Decision Date
Jul 29, 2008
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5270
Device Class
Class 2
Indications for Use
The ADVIA Chemistry CardioPhase™ High Sensitivity C-Reactive Protein assay is for in vitro diagnostic use in the quantitative determination of the concentration of C-Reactive Protein (CRP) in human serum and plasma (lithium heparin and potassium EDTA) on the ADVIA Chemistry systems. In acute phase response, increased levels of a number of plasma proteins, including CRP, are observed. Measurement of CRP is useful for the detection and evaluation of infection, tissue injurv, inflammatory disorders, and associated diseases. High sensitivity CRP (hsCRP) measurements may be used as an independent risk marker for the identification of individuals at risk for future cardiovascular disease. Measurement of hsCRP, when used in conjunction with traditional clinical laboratory evaluation of acute coronary syndromes, may be useful as an independent marker of prognosis for recurrent events in patients with stable coronary disease or acute coronary syndromes. The ADVIA Chemistry CardioPhase™ High Sensitivity C-Reactive Protein Calibrators are for in vitro diagnostic use in the calibration of ADVIA Chemistry systems for the CardioPhase High Sensitivity C-Reactive Protein method.
Device Story
Device is an in vitro diagnostic assay for quantitative CRP measurement in human serum/plasma. Operates on Siemens ADVIA Chemistry systems using latex-enhanced immunoturbidimetric principle; polystyrene latex particles coated with rabbit anti-CRP antibodies agglutinate in presence of CRP, increasing turbidity measured at 571 nm. Calibration uses 6-level recombinant human CRP calibrators. Used in clinical laboratory settings by trained personnel. Output is CRP concentration (mg/L) used by clinicians to assess inflammation, evaluate infection/tissue injury, and stratify cardiovascular disease risk. Benefits include standardized, automated high-sensitivity detection of CRP levels to aid in prognosis and risk assessment.
Clinical Evidence
No clinical trials performed. Substantial equivalence supported by analytical performance data (precision, linearity, interference, and detection limits) and a method comparison study. Comparison study (n=167) against the predicate BNII system showed high correlation (r=0.9978, slope 1.01). Reference range established via 190 healthy volunteers.
Indicated for quantitative determination of CRP in human serum and plasma to detect/evaluate infection, tissue injury, inflammatory disorders, and associated diseases. Also indicated as an independent risk marker for future cardiovascular disease and as a prognostic marker for recurrent events in patients with stable coronary disease or acute coronary syndromes.
Regulatory Classification
Identification
A C-reactive protein immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the C-reactive protein in serum and other body fluids. Measurement of C-reactive protein aids in evaluation of the amount of injury to body tissues.
Predicate Devices
CardioPhase™ High Sensitivity C-Reactive Protein (hsCRP) on the BNII Systems (K033908)
{0}
1 of 10
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k081294
B. Purpose for Submission:
New device
C. Measurand:
C-Reactive Protein (CRP)
D. Type of Test:
Quantitative, immunoturbidimetric
E. Applicant:
Siemens Healthcare Diagnostics Inc.
F. Proprietary and Established Names:
Advia Chemistry Cardiophase High Sensitivity C-Reactive Protein (hsCRP)
G. Regulatory Information:
1. Regulation section:
21CFR Sec.- 866.5270-C-reactive protein immunological test system
21CFR Sec.- 862.1150 Calibrator
2. Classification:
Class 2
3. Product code:
NQD - C-Reactive Protein, Antigen, Antiserum, and Control
JIX - Calibrator, Multi-Analyte Mixture
4. Panel:
Chemistry (75)
H. Intended Use:
1. Intended use(s):
See indication(s) for use below.
2. Indication(s) for use:
The ADVIA Chemistry CardioPhase High Sensitivity C-Reactive Protein assay is for in vitro diagnostic use in the quantitative determination of the concentration of C-Reactive Protein (CRP) in human serum and plasma (lithium heparin or
{1}
potassium EDTA) on the ADVIA Chemistry systems. In acute phase response, increased levels of a number of plasma proteins, including CRP, are observed. Measurement of CRP is useful for the detection and evaluation of infection, tissue injury, inflammatory disorders, and associated diseases. High sensitivity CRP (hsCRP) measurements may be used as an independent risk marker for the identification of individuals at risk for future cardiovascular disease. Measurement of hsCRP, when used in conjunction with traditional clinical laboratory evaluation of acute coronary syndromes, may be useful as an independent marker of prognosis for recurrent events in patients with stable coronary disease or acute coronary syndromes.
The ADVIA Chemistry CardioPhase High Sensitivity C-Reactive Protein Calibrators are for in vitro diagnostic use in the calibration of ADVIA Chemistry systems for the CardioPhase High Sensitivity C-Reactive Protein method.
3. Special conditions for use statement(s): For prescription use
4. Special instrument requirements: Siemens ADVIA Chemistry systems
I. Device Description:
| Reagent | Component | Concentration |
| --- | --- | --- |
| Reagent 1 | Glycine | 170 mmol/L |
| | Sodium Chloride | 100 mmol/L |
| | EDTA Disodium Salt Dihydrate | 50 mmol/L |
| | Sodium Azide | 0.09% w/v |
| Reagent 2 | CRP Antibody (rabbit) – synthetic latex | Lot specific |
| | Sodium Azide | 0.09% w/v |
Calibrator
Amount 1.0 mL/vial of 6 levels
Ingredients Recombinant human CRP in a stabilized protein matrix; sodium azide 0.09%
J. Substantial Equivalence Information:
1. Predicate device name(s): CardioPhase High Sensitivity C-Reactive Protein (hsCRP) ADVIA Chemistry Wide Range C-Reactive Protein Calibrators
2. Predicate 510(k) number(s): k033908, k022682
3. Comparison with predicate:
{2}
| | Device | Predicate Device |
| --- | --- | --- |
| Item | ADVIA® Chemistry CardioPhase™ High Sensitivity C-Reactive Protein (hsCRP) | Siemens Healthcare (formerly Dade Behring) CardioPhase™ High Sensitivity CRP on the BNII Systems (formerly Dade Behring) |
| Intended Use | For the quantitative determination of C-Reactive Protein (CRP) on the ADVIA Chemistry Systems | For the quantitative determination of C-Reactive Protein (CRP) using the BN Systems |
| Indications for Use | In acute phase response, increased levels of a number of plasma proteins, including CRP, are observed. Measurement of CRP is useful for the detection and evaluation of infection, tissue injury, inflammatory disorders, and associated diseases. High sensitivity CRP (hsCRP) measurements may be used as an independent risk marker for the identification of individuals at risk for future cardiovascular disease. Measurement of hsCRP, when used in conjunction with traditional clinical laboratory evaluation of acute coronary syndromes, may be useful as an independent marker of prognosis for recurrent events, in patients with stable coronary disease or acute coronary syndromes. | In acute phase response, increased levels of a number of plasma proteins including C-reactive protein, is observed. Measurement of CRP is useful for the detection and evaluation of infection, tissue injury, inflammatory disorders and associated diseases. Measurements may also be used as an aid in the identification of individuals at risk for future cardiovascular disease. High sensitivity CRP (hsCRP) measurements, when used in conjunction with traditional clinical laboratory evaluation of acute coronary syndromes, may be useful as an independent marker of prognosis for recurrent events, in patients with stable coronary disease or acute coronary syndromes. |
| Specimen Type | Human serum and plasma (lithium heparin, potassium EDTA) | Human serum, heparin plasma, and EDTA plasma |
| Assay Principle | Latex enhanced immunoturbidimetric assay | Particle enhanced immunonephelometry assay |
| Reagents | Ready to use reagents (R1 and R2) | Ready to use reagent |
| Antibody | Rabbit Polyclonal | Mouse Monoclonal |
| Calibration | Multipoint calibration (6 levels) | Reference curves generated by multi-point calibration |
| Calibrator | ADVIA Chemistry CardioPhase™ High Sensitivity C-Reactive Protein Calibrators | N Rheumatology Standard SL N Diluent |
| Analytical Range* | 0.16 – 10.0 mg/L | 0.175 to 20 mg/L |
| Standardization | IRMM Reference Material CRM 470 | IRMM Reference Material CRM 470 |
3 of 10
{3}
| | Device | Predicate |
| --- | --- | --- |
| Item | ADVIA® Chemistry CardioPhase™ High Sensitivity CRP Calibrators | ADVIA® Chemistry Wide Range CRP Calibrators |
| Intended Use | For in vitro diagnostic use in the calibration of ADVIA Chemistry systems for the CardioPhase hsCRP method | For in vitro diagnostic use in the calibration of ADVIA Chemistry systems for the wrCRP method |
| Specimen Type (calibrated method) | Human serum and plasma | Human serum and plasma |
| Matrix | Liquid | Liquid |
| Instructions for Use (Preparation) | The calibrators are ready to use | The calibrators are ready to use |
| Calibrator Levels | 6 | 6 |
| Calibrator Ingredients | Recombinant human CRP in a stabilized protein matrix; contains sodium azide | Recombinant human CRP in a stabilized protein matrix; contains sodium azide |
| Expected Values | Lot specific: 0, 0.53, 1.05, 1.58, 5.25, and 10.50 mg/L | Lot specific: 0, 2.5, 10, 20, 80, and 160 mg/L |
| Standardization | CRM-470 | CRM-470 |
# K. Standard/Guidance Document Referenced (if applicable):
CLSI - Evaluation of Precision Performance of Clinical Chemistry Devices - EP05-A2
CLSI - Evaluation of the Linearity of Quantitative Analytical Methods - EP06-A
CLSI - Protocols for Determination of Limits of Detection and Limits of Quantitation - EP17-A
# L. Test Principle:
The CardioPhase hsCRP latex reagent is a suspension of uniform polystyrene latex particles coated with anti-CRP antibody. When serum or plasma containing CRP is mixed with the latex reagent, agglutination takes place resulting in an increase in turbidity. This turbidity is measured at $571~\mathrm{nm}$ . The CRP concentration in serum or plasma is determined from a calibration curve that is generated with the calibrator materials.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Within run and total imprecision were evaluated by testing five serum pools and three levels of control materials. Each sample was assayed 2 times per run and 2 runs per day for 10 days. All runs were done with one instrument calibration. Precision estimates were computed according to CLSI document EP05-A2, Evaluation of Precision Performance of Quantitative Measurement
{4}
Methods; Approved Guideline.
| | | Within-run | | Total | |
| --- | --- | --- | --- | --- | --- |
| Specimen type | CRP Level (mg/L) | SD | CV (%) | SD | CV (%) |
| BR Control 1 | 0.42 | 0.01 | 2.9 | 0.01 | 3.5 |
| BR Control 2 | 1.83 | 0.01 | 0.7 | 0.02 | 0.9 |
| BR Control 3 | 5.39 | 0.05 | 0.9 | 0.05 | 1.0 |
| Serum Pool-low | 0.16 | 0.01 | 5.3 | 0.01 | 6.8 |
| Serum Pool | 0.21 | 0.01 | 3.2 | 0.01 | 4.2 |
| Serum Pool | 1.04 | 0.01 | 1.1 | 0.01 | 1.2 |
| Serum Pool | 3.12 | 0.03 | 0.8 | 0.04 | 1.3 |
| Serum Pool | 10.27 | 0.14 | 1.4 | 0.16 | 1.6 |
BR Control = BioRad Liquicheck™ Cardiac Markers Plus Controls
# b. Linearity/assay reportable range:
The assay range of this method is from $0.16\mathrm{mg / L}$ to $10\mathrm{mg / L}$ based on Functional Sensitivity (Limit of Quantitation, LOQ) see detection limit below, to the CRP concentration of the highest level linearity.
The linearity of this method was evaluated following the guidelines of CLSI EP6-A protocol where recombinant CRP was spiked into pooled human serum for the high CRP level, which was then diluted with a zero pool to make nine equally spaced linearity pools within the assay range. The observed CRP results on the ADVIA 1650 were compared with the expected CRP concentration. The resulting recovery information is presented in the table below:
| Linearity pool | Expected mg/L (calculated) | Mean Observed (n=3) mg/L | %Recovery (vs. Expected) |
| --- | --- | --- | --- |
| Level 1 | 0.00 | 0.00 | NA |
| Level 2 | 1.59 | 1.54 | 96.80 |
| Level 3 | 3.18 | 3.13 | 98.58 |
| Level 4 | 4.76 | 4.70 | 98.62 |
| Level 5 | 6.35 | 6.23 | 98.11 |
| Level 6 | 7.94 | 7.69 | 96.92 |
| Level 7 | 9.53 | 9.26 | 97.22 |
| Level 8 | 11.11 | 10.81 | 97.31 |
| Level 9 | 12.70 | 12.70 | 100.00 |
Testing the nine samples, the resulting linear regression equation was obtained: Slope $= 0.9857$ (0.9651 to 1.0062), Intercept $= -0.0303$ (-.1857 to 0.1252), $\mathrm{r} = 0.9997$
{5}
Recovery at the lower end of the range was also shown with serial dilutions of the CRM 470 reference material. The linear regression equation obtained from testing the 4 samples was: Slope = 0.9730 (0.9020 to 1.0440), Intercept = -0.0017 (-0.1620 to 0.1587), r = 0.9997
ADVIA 1650 Low End Linearity Data
| Linearity Pool | Expected (mg/L) | Observed (mg/L) | Recovery% |
| --- | --- | --- | --- |
| level 1 | 0.490 | 0.511 | 104.270 |
| level 2 | 0.980 | 0.939 | 95.857 |
| level 3 | 1.960 | 1.862 | 95.020 |
| level 4 | 3.920 | 3.833 | 97.776 |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability to CRM 470 is claimed for the calibrator materials.
The ADVIA® Chemistry CardioPhaseTM High Sensitivity C-Reactive Protein (hsCRP) Calibrators are used to calibrate the hsCRP method. The calibrators consist of six (6) levels of protein stabilized matrices containing varying concentrations of recombinant human CRP (synthesized in bacteria - not human source). The Calibrators have targeted expected values (lot specific) of 0, 0.53, 1.05, 1.58, 5.25, and 10.50 mg/L, and these values are traceable to IRMM reference material CRM 470.
Shelf Life Stability
The ADVIA Chemistry hsCRP calibrator materials have a shelf stability of 18 months stored at 2 – 8°C, and have open-vial stability of 60 days when stored at 2 – 8°C.
Real Time:
The Shelf Life of the ADVIA Chemistry hsCRP calibrator materials was evaluated with Real Time Stability testing at the recommended storage temperature (2 – 8°C). Two lots of calibrators were tested at Day 0 (QC release) and at 19 months (for one lot) and at 117 weeks (or 27 months for another lot), respectively.
Open Vial:
Open Vial Stability of the ADVIA Chemistry hsCRP calibrator materials was tested up to 60 days (64 days for the 2nd lot). On Day 0, calibrators were used
6 of 10
{6}
to calibrate ADVIA 1650 hsCRP method, and recoveries of the controls were obtained using this calibration. The opened calibrator vials (each level) were then recapped and stored at $2 - 8^{\circ}\mathrm{C}$ . At each checkpoint following Day 0, these stored, opened vials of calibrators were used for calibration and control recovery, and compared to control recoveries from calibration with freshly opened vials of calibrators.
The sponsor's acceptance criteria are as follows: less than $+10\%$ difference in control recovery using calibration with open calibrator materials versus calibration with fresh calibrator materials
# d. Detection limit:
The functional sensitivity (Limit of Quantitation) of this assay is $0.16\mathrm{mg / L}$ , which is the lowest CRP concentration in a sample where total imprecision is less than $10\%$ .
CRM 470 material was serially diluted to $0.99\mathrm{mg / L}$ , $0.495\mathrm{mg / L}$ , $0.247\mathrm{mg / L}$ , $0.124\mathrm{mg / L}$ and $0.062\mathrm{mg / L}$ . Each level was run at 8 reps/run, 5 runs total (40 reps total) on the ADVIA 1650. $\% \mathrm{CV}$ and $\%$ deviation from the target were calculated. To determine the CRP concentration at which $20\%$ deviation of accuracy and $10\%$ precision and the observed recovery vs. deviation from target data was plotted.
| Target | Recovered | CV% | Deviation% |
| --- | --- | --- | --- |
| 0.990 | 0.990 | 1.41 | 0.0% |
| 0.495 | 0.510 | 1.58 | 3.1% |
| 0.247 | 0.269 | 2.35 | 8.8% |
| 0.124 | 0.154 | 5.11 | 24.6% |
| 0.062 | 0.095 | 6.64 | 53.7% |

{7}
e. Analytical specificity:
Interference was evaluated by spiking human serum pools with hemoglobin (from lysed human red blood cells), unconjugated (free) bilirubin, conjugated bilirubin, triglycerides (Intralipid) and Rheumatoid Factor (RF). Multiple levels of each of the interfering substances were tested at a clinically relevant CRP concentration. Samples were assayed in duplicate. The results for each analyzer are presented in the labeling. There was no significant interference for bilirubin up to 30 mg/dL, for hemolysis up to 500 mg/dL, lipemia up to 750 mg/dL and rheumatoid factor up to 1040 IU/mL.
All results passed Siemens Diagnostics internal acceptance criteria for interference of ≤10% up to the acceptable level of interferent.
The labeling includes a limitation that there is a potential that heterophilic antibodies may interfere with this method. Also, the labeling includes a statement that the performance of this method has not been evaluated with patients containing heterophilic antibodies.
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
The ADVIA Chemistry CardioPhase hsCRP correlation studies were performed on the ADVIA 1650, against the Siemens CardioPhase High Sensitivity CRP assay on the BNII instrument.
The correlation studies were done over 7 days using 167 patient serum samples. Testing was done in duplicate on the ADVIA 1650 and in singlicate on the BNII; the data was processed using only the first result from the ADVIA 1650 (singlicate).
| Comparison method | N | Slope (95% CI) | Intercept (95% CI) | Sy.x | r | Sample range (mg/L) |
| --- | --- | --- | --- | --- | --- | --- |
| BNII hsCRP (Least squares) | 167 | 1.01 (1.00 – 1.02) | -0.01 (-0.04 – 0.02) | 0.1304 | 0.9978 | 0.17 – 9.05 |
{8}

# b. Matrix comparison:
The serum/plasma equivalency study was done on the ADVIA 1650 using lithium heparin and potassium EDTA plasma samples and their corresponding serum samples. A total of 29 matched samples were tested in duplicate; some samples (6) were spiked with recombinant CRP to span the reporting range.
| Matrix tested | N | Slope (95% CI) | Intercept (95% CI) | Sy.x | r | Sample range (mg/L) |
| --- | --- | --- | --- | --- | --- | --- |
| Plasma (Potassium EDTA); least squares | 58 | 0.97 (0.96 – 0.98) | 0.00 (-0.06 – 0.05) | 0.1451 | 0.9986 | 0.14 – 9.56 |
| Plasma (Li Hep); least squares | 58 | 0.98 (0.97 – 0.99) | 0.00 (-0.04 – 0.04) | 0.1004 | 0.9994 | 0.14 – 9.56 |
# 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): The method comparison studies between the device and the former Dade Behring CardioPhase™ hsCRP on the BNII system (this predicate device was used in the clinical studies supporting an indication for cardiovascular use) demonstrate acceptable correlation between both methods, thus the performance and accuracy of the device is substantially equivalent to those of the predicate device.
{9}
4. Clinical cut-off: Not Applicable
5. Expected values/Reference range:
The expected values provided in the labeling for healthy individuals as noted in the literature are typically ≤ 3 mg/L.
The below referenced AHA/CDC Scientific Statement concerning inflammation and cardiovascular markers also reports that CRP values < 1 mg/L are low risk for cardiovascular disease prediction, values between 1 – 3 mg/L are average risk for cardiovascular disease prediction and values > 3 mg/L are high risk for cardiovascular disease prediction.
Pearson TA, Mensah GA, Alexander RW, et al. Markers of inflammation and cardiovascular diseases; application to clinical and public health practice: A statement for healthcare professionals from the Centers for Disease Control and Prevention and the American Heart Association. Circulation 2003; 107:499-511.
Studies performed by Siemens on 190 apparently healthy volunteers yielded a median serum CRP concentration of 1.21 mg/L and an upper 97.5th percentile serum CRP concentration of 7.59 mg/L.
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
10 of 10
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.