K073490 · Olympus America, Inc. · CFN · Feb 11, 2008 · Immunology
Device Facts
Record ID
K073490
Device Name
OLYMPUS IGG REAGENT
Applicant
Olympus America, Inc.
Product Code
CFN · Immunology
Decision Date
Feb 11, 2008
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5510
Device Class
Class 2
Indications for Use
System reagent for the quantitative determination of IgG immunoglobulins in human serum, plasma and cerebrospinal fluid on OLYMPUS analyzers. For in vitro diagnostic use.
Device Story
Olympus IgG reagent (OSR6X172) is an immunoturbidimetric assay for quantitative IgG measurement. Input samples include human serum, plasma (Li-heparin or EDTA), and cerebrospinal fluid (CSF). The device utilizes goat anti-IgG antibodies to form insoluble immune complexes with IgG in the sample; these complexes scatter light. Olympus analyzers (AU400/400e, 600/640/640e, 2700/5400) measure the decrease in transmitted light intensity (absorbance increase) to quantify IgG concentration. The assay is performed in clinical laboratory settings by trained technicians. Results are used by clinicians to assess protein metabolism and immune function. The device provides automated dilution and measurement, facilitating diagnostic decision-making regarding infectious disease and metabolic status.
Clinical Evidence
No clinical trials were performed. Evidence consists of analytical bench testing, including precision (CLSI EP5-A2), linearity (CLSI EP6-A), limit of quantitation/detection (CLSI EP17-A), interference testing (CLSI EP7-A2), and method comparison studies (CLSI EP9-A2) against predicate devices. Precision studies (n=80) showed total CVs ranging from 1.51–4.66% for serum/plasma and 2.81–10.24% for CSF. Method comparison correlation coefficients (r) were ≥0.996.
Technological Characteristics
Quantitative immunoturbidimetric assay. Reagents: R1 (Tris buffer, polyethylene glycol 6000) and R2 (goat anti-IgG antiserum) with sodium azide preservative. Sensing principle: light scattering/absorbance measurement. Form factor: liquid, on-board refrigerated storage. Connectivity: integrated with Olympus AU-series analyzers. Calibration: multipoint, traceable to CRM 470. Stability: 90-day on-board reagent stability.
Indications for Use
Indicated for the quantitative determination of IgG immunoglobulins in human serum, plasma, and cerebrospinal fluid to aid in the diagnosis of abnormal protein metabolism and the body's inability to resist infectious agents. For use on Olympus analyzers.
Regulatory Classification
Identification
An immunoglobulins A, G, M, D, and E immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the immunoglobulins A, G, M, D, an E (serum antibodies) in serum. Measurement of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
Predicate Devices
Olympus IgG reagent (OSR6X45) (k951013)
Roche Tina QUANT IgG Gen. 2 (k050113)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k073490
B. Purpose for Submission:
Addition of plasma (Li-heparin and EDTA) and cerebrospinal fluid (CSF) matrix claim to the predicate device
C. Measurand:
Immunoglobulin G (IgG)
D. Type of Test:
Quantitative immunoturbidimetric assay
E. Applicant:
Olympus America, Inc.
F. Proprietary and Established Names:
Olympus IgG reagent (OSR6X172)
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CFN Method, Nephelometric, Immunoglobulins (G, A, M) | Class II | 21 CFR 866.5510
Immunoglobulins A, G, M, D, E
Immunological Test System | Immunology (IM82) |
H. Intended Use:
1. Intended use(s):
System reagent for the quantitative determination of IgG immunoglobulins in human serum and plasma on OLYMPUS analyzers
2. Indication(s) for use:
The spectrum of abnormalities in serum immunoglobulin concentration is broad. Abnormal concentrations range from a virtual absence of one or more of the three major classes of immunoglobulins (IgA, IgG and IgM) to polyclonal increases in one or more immunoglobulins. Measurement of these immunoglobulins aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
OLYMPUS analyzers: AU400/400ᵉ, 600/640/640ᵉ and 2700/5400
I. Device Description:
The device consists of two reagents: R1 buffer (Tris buffer pH 7.2, polyethylene glycol 6000) and R2 (goat anti-IgM antiserum). The reagents contain sodium azide as preservative.
{1}
2
J. Substantial Equivalence Information:
1. Predicate device name(s):
Olympus IgG reagent (OSR6X45)
Roche Tina QUANT IgG Gen. 2
2. Predicate 510(k) number(s):
k951013
k050113
3. Comparison with predicate:
| Similarities: SERUM/PLASMA | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Olympus IgG reagent (OSR6X172) | Olympus IgG reagent (OSR6X45) |
| Intended Use | System reagent for the quantitative determination of IgG immunoglobulins in human serum, plasma and CSF on Olympus analyzers | Same but in serum only |
| Indications for Use | Aid in the diagnosis of abnormal protein metabolism and the body’s lack of ability to resist infection | Same |
| Test principle | Immunoturbidimetric | Same |
| Antibody | Goat anti-IgG | Same |
| Reagent form and storage | Liquid, on-board storage | Same |
| On-board reagent stability | 90 days | Same |
| Calibrator | Olympus Serum Protein Multi-calibrator | Same |
| Calibrator traceability | International Reference Preparation CRM 470 | Same |
| Calibration frequency | 90 days | Same |
| Expected values | 635-1741 mg/dL | Same |
| Differences: SERUM/PLASMA | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Olympus IgG reagent (OSR6X172) | Olympus IgG reagent (OSR6X46) |
| Matrix | Serum, plasma (Li heparin or EDTA) | Serum only |
{2}
| Similarities: CSF | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Olympus IgG reagent (OSR6X172) | Roche Tina Quant IgG |
| Intended Use | System reagent for the quantitative determination of IgG immunoglobulins in human serum, plasma and CSF on Olympus analyzers | In Vitro test for the quantitative determination of IgG in human serum, plasma and cerebrospinal fluid on Roche/Hitachi Cobas c systems |
| Matrix | Serum, plasma (Li-heparin or EDTA), CSF | Same |
| Test principle | Immunoturbidimetric | Same |
| Antibody | Goat anti-IgG | Same |
| Reagent form and storage | Liquid, on-board storage | Same |
| Calibrator traceability | International Reference Preparation CRM 470 | Same |
| Calibration | Multipoint | Same |
| Differences: CSF | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Olympus IgG reagent (OSR6X172) | Roche Tina Quant IgG |
| Expected values | 15-20y, 3.5 mg/dL ± 2.0mg/dL 21-40y, 4.2 mg/dL ± 1.4mg/dL 41-60y, 4.7 mg/dL ± 1.0mg/dL | 1-3 mg/dL |
| Instrument required | Olympus AU400/400e, 600/640/640e and 2700/5400 | Roche/Hitachi Cobas c systems |
| Reagent on-board stability | Open reagents stable 90 days stored in refrigerated compartment | Open reagents stable 84 days stored in refrigerated compartment |
| Calibration frequency | 2 days | As required |
# K. Standard/Guidance Document Referenced (if applicable):
EN14971 (2000) ISO Medical Devices – Application of Risk Management to Medical Devices; EP7-A2 (2005) CLSI Interference Testing in Clinical Chemistry; EP5-A2 (2004) CLSI Evaluation of Precision Performance of Clinical Chemistry Devices; EP9-A2 (2002) CLSI Method Comparison and Bias Estimation Using Patient Samples; CEN 13640 (2002) Stability Testing of In Vitro Diagnostic Reagents; C28-A2 (2000) CLSI How to Define and Determine Reference Intervals in the Clinical Laboratory; EP6-A (2003) CLSI Evaluation of the Linearity of Quantitative
{3}
Measurement Procedures: A Statistical Approach; FDA: Draft Guidance document for 510(k) Submission of Immunoglobulins A, G, M, D and E Immunoglobulin Test System In Vitro Devices.
## L. Test Principle:
When a sample is mixed with R1 buffer and R2 antiserum solution, human IgG reacts specifically with anti-human IgG antibodies to yield insoluble aggregates. Immune complexes formed in solution scatter light in proportion to their size, shape and concentration. The Olympus analyzer measures the decrease in intensity of light transmitted (increase in absorbance) through particles suspended in solution as a result of complexes formed during the antigen-antibody reaction.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
**Serum/Plasma**
Precision is checked, based on CLSI EP5-A2, by testing low, medium and high analyte human serum pools; 2 runs in duplicate for 20 days (n=80) on the AU400/400ᵉ, AU600/640/640ᵉ, and AU2700/5400. The within run precision covering the platforms ranged from 0.88–3.41% and the total precision ranged from 1.51–4.66%.
AU400/400ᵉ
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 432 | 4 | 0.88 | 9 | 2.18 |
| 1098 | 14 | 1.27 | 25 | 2.29 |
| 2237 | 76 | 3.41 | 77 | 3.43 |
AU600/640/640ᵉ
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 431 | 5 | 1.14 | 14 | 3.29 |
| 1088 | 16 | 1.45 | 38 | 3.49 |
| 2173 | 49 | 2.24 | 101 | 4.66 |
AU2700/5400
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 444 | 4 | 0.95 | 7 | 1.51 |
| 1060 | 17 | 1.87 | 20 | 1.87 |
| 2191 | 26 | 2.03 | 44 | 2.03 |
## CSF
Precision is checked, based on CLSI EP5-A2, by testing low, medium and high analyte human serum pools (set to cover the reportable range for CSF); 2 runs in duplicate for 20 days (n=80) on the AU400/400ᵉ, AU600/640/640ᵉ, and AU2700/5400. The within run precision ranged from 0.89–7.93% and the
{4}
total precision ranged from 2.81-10.24%.
AU400/400°
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 3.5 | 0.1 | 2.88 | 0.3 | 9.82 |
| 10.2 | 0.1 | 1.44 | 0.4 | 4.08 |
| 35.8 | 0.6 | 1.65 | 1.3 | 3.61 |
AU600/640/640°
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 3.5 | 0.1 | 2.68 | 0.3 | 9.53 |
| 10.1 | 0.1 | 0.89 | 0.4 | 3.67 |
| 35.6 | 0.3 | 0.93 | 1.0 | 2.81 |
AU2700/5400
| N=80 | Within-run | | Total | |
| --- | --- | --- | --- | --- |
| Mean (mg/dL) | SD | %CV | SD | %CV |
| 3.6 | 0.1 | 7.93 | 0.4 | 10.24 |
| 10.1 | 0.1 | 2.91 | 0.6 | 6.29 |
| 35.4 | 0.6 | 1.31 | 1.3 | 3.83 |
**Auto dilution:**
Accuracy: Three auto-dilution samples were diluted manually and run on the instrument. The same samples were diluted automatically by the AU640 and %difference was calculated
Accuracy 1:5
| Level | Automatic dilution (mg/dl) | Manual dilution (mg/dl) | % Difference |
| --- | --- | --- | --- |
| 1 | 3911 | 3680 | -6.3 |
| 2 | 3123 | 3051 | -2.4 |
| 3 | 1986 | 1906 | -4.2 |
Accuracy 1:10
| Level | Automatic dilution (mg/dl) | Manual dilution (mg/dl) | % Difference |
| --- | --- | --- | --- |
| 1 | 3767 | 3613 | -4.3 |
| 2 | 2997 | 2923 | 2.5 |
| 3 | 2263 | 2176 | 4.0 |
Precision: Three auto-dilution samples were run with the automated dilution protocol on the AU640 to generate 20 replicates per sample. %CVs were calculated.
{5}
Precision (within run) 1:5
| Level | Mean (mg/dL) | SD (mg/dL) | CV (%) | Essential Specification | |
| --- | --- | --- | --- | --- | --- |
| 1 | 392 | 4 | 1.01 | ≤4.2% CV | Pass |
| 2 | 521 | 6 | 1.11 | | |
| 3 | 653 | 7 | 1.08 | | |
Precision (within run) 1:10
| Level | Mean (mg/dL) | SD (mg/dL) | CV (%) | Essential Specification | |
| --- | --- | --- | --- | --- | --- |
| 1 | 197 | 3 | 1.60 | ≤4.2% CV | Pass |
| 2 | 256 | 3 | 1.16 | | |
| 3 | 322 | 5 | 1.65 | | |
b. Linearity/assay reportable range:
Serum/Plasma
The measuring range for the assay is 75-3000 mg/dL. The procedure used to demonstrate linearity was based on CLSI EP6-A. A series of at least ten analyte concentrations, covering the linear dynamic range was prepared by dilution of a high pool sample. Each dilution was assayed in quadruplicate and the mean analytical results were plotted versus the relative analyte concentrations (% dilution). Studies were performed on the AU400, AU640 and AU2700 analyzers. The acceptance criteria for deviation from the regression line for 75-375 mg/dL and 375-3000 mg/dL ranges were ± 30 mg/dL and ± 8%. The studies showed the assay was linear from 75-3000 mg/dL. There was no high dose hook effect up to 30,000 mg/dL.
CSF
The measuring range for the assay is 2-50 mg/dL. The procedure used to demonstrate linearity was based on CLSI EP6-A. A series of at least ten analyte concentrations, covering the linear dynamic range was prepared by dilution of a high pool sample. Each dilution was assayed in quadruplicate and the mean analytical results were plotted versus the relative analyte concentrations (% dilution). Studies were performed on the AU400, AU640 and AU2700 analyzers. The acceptance criteria for the deviation from the regression line for 2-5 mg/dL and 5-50 mg/dL ranges were ± 0.5 mg/dL and ± 10% respectively. The studies showed the assay was linear from 2-50 mg/dL. There was no high dose hook effect up to 6,000 mg/dL.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The calibrator is traceable to the International Reference Preparation CRM470 (US designation RPPHS lot 91/0619).
Serum/Plasma
Reagent on-board stability was demonstrated according to internal procedures where the linearity displayed at day 90 and the % drift from Day 0 from control recovery were calculated. A change of ≤ 8% was demonstrated over the 90 days. Data confirm the calibration stability of 90 days.
{6}
# CSF
Reagent on-board stability was demonstrated according to internal procedures where the linearity displayed at day 90 and the $\%$ drift from Day 0 from control recovery were calculated. A change of $\leq 10\%$ was demonstrated over the 90 days. Data confirm the calibration stability of 2 days for CSF.
# d. Detection limit:
# Serum/Plasma
The Limit of Quantitation (LoQ) for the new assay was determined by testing 3 patient pools, 40 fold at an analyte concentration below the lower end of the measuring range on the AU400, AU640 and AU2700. The analyte level with a CV of less than $20\%$ was determined to be $< 74 \mathrm{mg} / \mathrm{dL}$ . This was determined using a method based on the CLSI protocol EP17-A.
| | Mean Concentration (mg/dL) | CV (%) |
| --- | --- | --- |
| AU400 | 33 | 16.8 |
| AU640 | 35 | 6.6 |
| AU2700 | 21 | 12.4 |
The Limit of Detection (LoD) or the concentration of analyte which is significantly different from zero was determined by testing an analyte free sample twenty-fold on the AU400, AU640 and AU2700. The lowest detectable level was determined to be $\leq 7\mathrm{mg / dL}$ .
# CSF
The Limit of Quantitation (LoQ) for the new assay (CSF) was determined by testing 3 patient pools, 40 fold at an analyte concentration below the lower end of the measuring range. The analyte level with a CV of less than $20\%$ was determined to be $2\mathrm{mg / dL}$ . This was determined using a method based on the CLSI protocol EP17-A.
The Limit of Detection (LoD) or the concentration of analyte which is significantly different from zero was determined by testing an analyte free sample (water) twenty-fold on the AU400, AU640 and AU2700. The lowest detectable level was determined to be $\leq 1\mathrm{mg / dL}$ .
# e. Analytical specificity:
The impact of bilirubin, lipids and hemoglobin were assessed in accordance with CLSI EP7-A2.
Serum/Plasma
| Substance | Levels up to | Interference | | |
| --- | --- | --- | --- | --- |
| | | AU400/400e | AU600/640/640e | AU2700/5400 |
| Bilirubin | 40 mg/dL | ≤2% | ≤3% | ≤1% |
| Lipids | 1000 mg/dL | ≤3% | ≤5% | ≤2% |
| Hemoglobin | 500 mg/dL | ≤3% | ≤3% | ≤3% |
| RF | 1200 IU/mL | ≤7% | ≤7% | ≤7% |
{7}
CSF
| Substance | Levels up to | % Interference | | |
| --- | --- | --- | --- | --- |
| | | AU400/400° | AU600/640/640° | AU2700/5400 |
| Bilirubin | 36 mg/dL | ≤ 10% | ≤ 10% | ≤ 10% |
| Hemoglobin | 500 mg/dL | ≤ 10% | ≤ 10% | ≤ 10% |
f. Assay cut-off:
See reference range
2. Comparison studies:
a. Method comparison with predicate device:
Serum/Plasma
| Y method (new) | AU2700 | AU2700/5400 | AU2700/5400 |
| --- | --- | --- | --- |
| X method (predicate) | AU2700 | AU400 | AU640/640° |
| Slope | 0.945 | 1.026 | 0.990 |
| Intercept | 37.2 | -23.4 | 5.8 |
| Correlation coefficient (r) | 0.998 | 0.996 | 0.998 |
| Number of samples | 120 | 120 | 120 |
| Range (mg/dL) Y method | 195-2986 | 195-2986 | 195-2986 |
| Range (mg/dL) X method | 118-2973 | 177-2906 | 190-2963 |
CSF
| Y method (new) | AU2700 | AU2700/5400 | AU2700/5400 |
| --- | --- | --- | --- |
| X method (predicate) | Tina Quant | AU400 | AU640/640° |
| Slope | 1.067 | 0.996 | 0.969 |
| Intercept | -0.069 | -0.127 | 0.14 |
| Correlation coefficient (r) | 0.998 | 0.998 | 0.998 |
| Number of samples | 55 | 85 | 86 |
| Range (mg/dL) Y method | 2.0-42.9 | 2.1-47.2 | 2.1-47.2 |
| Range (mg/dL) X method | 1.98-40.0 | 2.2-47.8 | 2.1-48.6 |
b. Matrix comparison:
Studies were performed based on CLSI EP9-A2.
| Y method | Li-heparin plasma | EDTA plasma |
| --- | --- | --- |
| X method | Serum | Serum |
| Slope | 0.940 | 0.910 |
| Intercept | 24.1 | 35.9 |
| Correlation coefficient | 0.999 | 0.998 |
| Number of samples | 45 | 45 |
| Patient mean value – serum mg/dL | 1111.4 | 1111.4 |
| Patient mean value – plasma mg/dL | 1068.2 | 1047.2 |
| Reference range – serum mg/dL | 214.6-2904.7 | 214.6-2904.7 |
| Reference range - plasma mg/dL | 201.2-2581.4 | 202.2-2512.6 |
3. Clinical studies:
{8}
a. Clinical Sensitivity: Not determined
b. Clinical specificity: Not determined
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: Expected values may vary with age, sex, diet and geographical location.
Serum/Plasma
The reference range of 635-1741 mg/dL established for the predicate device was re-verified according to CLSI C28-A2 on the Olympus AU400/AU600 and AU5400.
CSF
Reference ranges for CSF are 15-20 years: 3.5 mg/dL ± 2.0 mg/dL; 21-40 years: 4.2 mg/dL ± 1.4 mg/dL; and 41-60 years: 4.7 mg/dL ± 1.0 mg/dL. These ranges are based on Tietz Textbook of Clinical Chemistry, 1999.
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.
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.