Retrospective clinical samples were used to assess potential biological interferences, establish assay threshold values, and validate the performance of the modified device against the predicate device.
Retrospective clinical samples; Interference study; Comparative performance study
Detection of interference in MPO, PR3, and GBM assays
Retrospective comparative study
Human serum samples; Sample Size: 219
Predicate FIDIS™ VASCULITIS (K053012)
Positive/Negative percent agreement
Indications for Use
The FIDIS™ VASCULITIS® kit is a semi-quantitative homogeneous fluorescent-based microparticles immunoassay using flow cytometry readings. The test system is used to detect in patient serum samples the presence of anti-neutrophil cytoplasm antibodies (ANCA) directed against Myeloperoxidase (MPO) and Serine Proteinase 3 (PR3); and anti-glomerular basement membrane (GBM) antibodies. The results of the FIDIS™ VASCULITIS® test are to be used in conjunction with the clinical findings and the other laboratory tests to aid in the diagnosis of various primary systemic small vessel vasculitis. The presence of anti-MPO and anti-PR3 antibodies associated primary systemic small vessel vasculitis: Wegener's granulomatosis, Churg Strauss syndromes, microscopic periarteritis and idiopathic crescentic glomerulonephritis; and the presence of anti-GBM antibodies is associated with Goodpasture's syndrome. FIDIS™ VASCULITIS® kit is used on the FIDIS Analyser, MLX-BOOSTER Software and FIDIS™ Washer. FIDIS™ VASCULITIS* kit could be used with CARIS™ system (diluting and dispensing device). This test is for in vitro diagnostic use.
Device Story
In vitro diagnostic kit; detects anti-MPO, anti-PR3, and anti-GBM antibodies in patient serum. Uses color-coded microspheres covalently coupled to specific antigens; multiplexed assay format. Patient serum incubated with microspheres; bound antibodies detected via phycoerythrin-labeled anti-human IgG conjugate. Benchtop flow cytometer (Luminex 100/200) uses red laser for microsphere identification and green laser for fluorescence quantification. MLX-BOOSTER software processes signals; calculates antibody titers via interpolation against calibration system. Used in clinical laboratories; operated by trained personnel. Results aid clinicians in diagnosing systemic small vessel vasculitis and Goodpasture's syndrome. Optional CARIS system automates sample dilution and dispensing.
Clinical Evidence
Comparative study on 219 clinical samples (135 positive, 84 negative) against predicate K053012. Results: MPO (97.18% positive agreement, 100% negative agreement), PR3 (95.92% positive, 99.41% negative), GBM (100% positive, 100% negative). Additional study on 117 samples compared manual vs. CARIS™ automated preparation, showing high agreement (98.29-100%). Precision studies (intra-assay and inter-assay) met acceptance criteria (CV% ≤15-20%).
Indicated for the detection of anti-neutrophil cytoplasm antibodies (ANCA) against MPO and PR3, and anti-glomerular basement membrane (GBM) antibodies in patient serum to aid in the diagnosis of primary systemic small vessel vasculitis (Wegener's granulomatosis, Churg Strauss syndrome, microscopic periarteritis, idiopathic crescentic glomerulonephritis) and Goodpasture's syndrome. Prescription use only.
Regulatory Classification
Identification
A multiple autoantibodies immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the autoantibodies (antibodies produced against the body's own tissues) in serum and other body fluids. Measurement of multiple autoantibodies aids in the diagnosis of autoimmune disorders (disease produced when the body's own tissues are injured by autoantibodies).
Predicate Devices
FIDIS™ VASCULITIS (k053012)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k070458
B. Purpose for Submission:
New device
C. Measurand:
Anti-Myeloperoxidase Antibodies (MPO)
Anti-Serine Protease 3 Antibodies (PR3)
Anti-Glomerular Membrane Antibodies (GBM)
D. Type of Test:
Semi-quantitative
E. Applicant:
Biomedical Diagnostics, S.A. (bmd)
F. Proprietary and Established Names:
FIDIS™ VASCULITIS, MX 007
G. Regulatory Information:
1. Regulation section:
21 CFR § 866.5660, Multiple autoantibodies, immunological test system
2. Classification:
Class II
3. Product codes:
MOB, Test System, antineutrophil antibodies (ANCA)
MVJ, Devices, Measure, Antibodies to Glomerular Basement Membrane (GBM)
4. Panel:
Immunology (82)
H. Intended Use:
1. Intended use(s):
The FIDIS™ VASCULITIS® kit is a semi-quantitative homogeneous fluorescent-based microparticles immunoassay using flow cytometry readings. The test system is used to detect in patient serum samples the presence of anti-neutrophil cytoplasm antibodies (ANCA) directed against Myeloperoxidase (MPO) and Serine Proteinase 3 (PR3); and anti-glomerular basement membrane (GBM) antibodies.
The results of the FIDIS™ VASCULITIS® test are to be used in conjunction with the clinical findings and the other laboratory tests to aid in the diagnosis of various primary systemic small vessel vasculitis.
The presence of anti-MPO and anti-PR3 antibodies associated primary systemic small vessel vasculitis: Wegener's granulomatosis, Churg Strauss syndromes, microscopic periarteritis and idiopathic crescentic glomerulonephritis; and the presence of anti-GBM antibodies is associated with Goodpasture's syndrome.
FIDIS™ VASCULITIS® kit is used on the FIDIS Analyser, MLX-BOOSTER Software and FIDIS™ Washer.
{1}
FIDIS™ VASCULITIS* kit could be used with CARIS™ system (diluting and dispensing device).
This test is for in vitro diagnostic use.
* Detection of the serologic markers for primary systemic small vessel vasculitis (ANCA) and for Goodpasture syndrome (GBM)
2. Indication(s) for use:
Same as Intended use.
3. Special conditions for use statement(s):
For prescription only.
4. Special instrument requirements:
FIDIS™ 100 or FIDIS™ 200 Analyzer (Luminex 100™ or 200™)
FIDIS™ MLX-007 Software
FIDIS™ XY Platform
FIDIS™ Sheath Delivery System (SD)
Computer Central Processing Unit (PC)
Computer Monitor Screen
FIDIS™ Washer (k041002)
Ultrasonic bath
I. Device Description:
Each device contains the following: distinct uniform size color-coded microspheres (each microsphere set is covalently coupled to one of the following antigens: MPO, PR3, and GBM) (ready to use); calibrator (ready to use); positive control (to be diluted); negative control (to be diluted); goat anti-human IgG coupled to phycoerythrin (ready to use); sample dilution buffer (ready to use); wash buffer PBS-Tween (ready to use); one 96 wells microplate including a filtering membrane and a lid.
J. Substantial Equivalence Information:
1. Predicate device name(s):
FIDIS™ VASCULITIS
2. Predicate K number(s):
k053012
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | New Device | Predicate Device |
| | FIDIS™ VASCULITIS (MX 007) | FIDIS™ VASCULITIS |
| Intended use | Individual determination of IgG antibodies to MPO, PR3, GBM | Same |
| Antigen | Purified MPO, PR3, GBM | Same |
| Sample type | Serum | Same |
| Type of test | Semi-quantitative | Same |
| Platform | 96 well plates | Same |
| Technology | Flow Cytometry | Same |
| Assay Format | Multiplexed | Same |
{2}
| Similarities | | |
| --- | --- | --- |
| Item | New Device | Predicate Device |
| Sample dilution | 1:200 | Same |
| Substrate | None | Same |
| Enzyme-Conjugate | Phycoerythrin | Same |
| Detection method | Fluorescence | Same |
| Solid surface (antigen coated) | Color-coded microspheres | Same |
| Result Interpretation for each specificity: Anti-MPO, Anti-PR-3, Anti-GBM Antibody | Negative: < 20 AU/mL Borderline: 20-25 AU/mL Positive: >25 AU/mL | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Instrument | Luminometer (Luminex 100™ and/or Luminex 200™) | Luminometer (Luminex 100™) |
| Calibrator | 2 Wells/Test | 1 Well/Test |
| Software version | MLX Booster version 2.2 | MLX Booster version 1.35 |
# K. Standard/Guidance Document Referenced (if applicable):
None provided.
# L. Test Principle:
FIDIS™ VASCULITIS is based on the use of distinct uniform size color-coded microspheres and a bench top flow cytometer interfaced to digital signal processing hardware and software. A red diode laser beam in the flow cytometer classifies each set of microspheres on the basis of its unique fluorescence intensity (red to orange) thus identifying which analyte is being tested. At the same time, a green laser beam illuminates the external second molecule fluorescence to quantify the reaction related to the specific analyte.
Each antigen required for the assay is covalently coupled to an individual set of microspheres through its surface functional groups. The different antigen coupled microspheres are mixed together, constituting the final microspheres reagent.
The test is performed in a 96 wells blank microplate including a filtering membrane at the bottom of the wells.
- In the first step, the sample is distributed in each well containing the microspheres mixture. If this sample contains one or more of the suspected antibodies, this(ese) antibody(ies) bind to the corresponding antigen(s) on the various sets of microspheres.
After incubation, the unbound antibodies are removed by a wash step using a filtration process.
{3}
- A phycoerythrin labeled anti-human IgG conjugate is then added that binds to the previously bound antibodies.
A final wash step stops the reaction.
- The reaction is then directly measured by the flow cytometer, which differentiates each set of microspheres according to its fluorescence color while simultaneously measures the average fluorescence emitted by the conjugate.
A calibration system permits the determination of the antibody titer of each sample by interpolation for each antigenic specificity.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
For the intra-assay study, six samples for MPO, six samples for PR3, seven samples for GBM (weak, moderate and high titers) were analyzed 10 times (for each specificity) in one run. For the inter-assay study, the same samples were analyzed 3 times in 5 different runs. The intra-assay CV ranges for Anti-MPO, Anti-PR3, and Anti-GBM were: $4.9\%$ to $12.4\%$ ; $3.3\%$ to $11.6\%$ ; and $2.3\%$ to $11.3\%$ respectively. The inter-assay CV ranges on Anti-MPO, Anti-PR3, and Anti-GBM were: $5.4\%$ to $11.2\%$ ; $10.9\%$ to $19.6\%$ ; and $3.8\%$ to $14.6\%$ respectively (see table below).
| Antigen | Sample # | Within-run | | Between-run | |
| --- | --- | --- | --- | --- | --- |
| | | Mean value | CV (%) | Mean value | CV (%) |
| MPO | 1 | 15 | 5.3 | 18 | 11.2 |
| | 2 | 28 | 7.5 | 28 | 6.2 |
| | 3 | 33 | 12.4 | 35 | 10.9 |
| | 4 | 54 | 8.0 | 56 | 10.5 |
| | 5 | 261 | 10.8 | 261 | 10.1 |
| | 6 | 391 | 4.9 | 392 | 5.4 |
| PR3 | 7 | 16 | 11.3 | 20 | 19.6 |
| | 8 | 30 | 9.7 | 31 | 12.0 |
| | 9 | 37 | 11.6 | 43 | 14.2 |
| | 10 | 73 | 3.3 | 76 | 10.9 |
| | 11 | 198 | 6.1 | 222 | 13.8 |
| | 12 | 266 | 7.2 | 303 | 13.4 |
| GBM | 13 | 10 | 11.3 | 11 | 14.6 |
| | 14 | 36 | 10.6 | 38 | 12.0 |
| | 15 | 40 | 5.8 | 46 | 6.8 |
| | 16 | 59 | 2.3 | 60 | 6.1 |
| | 17 | 120 | 7.3 | 122 | 6.9 |
| | 18 | 215 | 5.6 | 215 | 5.7 |
| | 19 | 321 | 2.7 | 326 | 3.8 |
The reproducibility performance of FIDISTM VASCULITIS with the CARIS system (diluting and dispensing device) was determined as follows: Six samples for MPO, seven samples for PR3, six samples for GBM were analyzed 10 times in one run (on each specificity) for the intra-assay study.
{4}
The same samples were analyzed 3 times in 5 different runs for the inter-assay study. The intra-assay CV ranges on Anti-MPO, Anti-PR3, and Anti-GBM were: $2.6\%$ to $10.8\%$ ; $3.8\%$ to $7.2\%$ ; and $3.8\%$ to $7.1\%$ respectively. The inter-assay CV ranges on Anti-MPO, Anti-PR3, and Anti-GBM were: $6.7\%$ to $13.6$ ; $5.9\%$ to $11.7\%$ ; and $5.9\%$ to $9.7\%$ respectively (see table below).
| Antigen | Sample # | Within-run | | Between-run | |
| --- | --- | --- | --- | --- | --- |
| | | Mean value | CV (%) | Mean value | CV (%) |
| MPO | 1 | 17 | 6.4 | 17 | 13.6 |
| | 2 | 21 | 4.9 | 22 | 6.7 |
| | 3 | 29 | 3.8 | 30 | 7.6 |
| | 4 | 37 | 4.3 | 38 | 8.4 |
| | 5 | 59 | 2.6 | 57 | 9.3 |
| | 6 | 94 | 10.8 | 96 | 9.4 |
| PR3 | 7 | 16 | 6.9 | 16 | 6.9 |
| | 8 | 21 | 5.0 | 20 | 7.8 |
| | 9 | 24 | 5.9 | 24 | 7.4 |
| | 10 | 36 | 3.8 | 34 | 5.9 |
| | 11 | 63 | 6.5 | 60 | 11.7 |
| | 12 | 83 | 7.2 | 80 | 7.6 |
| | 13 | 386 | 7.2 | 371 | 6.8 |
| GBM | 14 | 13 | 4.9 | 12 | 8.2 |
| | 15 | 42 | 7.0 | 42 | 5.9 |
| | 16 | 55 | 3.8 | 53 | 6.5 |
| | 17 | 90 | 6.4 | 87 | 7.9 |
| | 18 | 115 | 7.1 | 117 | 9.7 |
| | 19 | 392 | 4.8 | 400 | 7.5 |
# Lot to lot reproducibility:
Two lots were analyzed using 3 positive samples (2 near cut off) and 9 negative samples. The acceptable criterion is $25\%$ . The lowest variability was $2\%$ and highest variability was $15\%$ . Both lots were within the $25\%$ variability.
# b. Linearity/assay reportable range:
Linearity is not claimed in this assay.
c. Traceability, Stability, Expected values (controls, calibrators, or methods): There are no reference standards for anti-MPO, anti-PR3 and anti-GBM. The calibrators and controls (positive and negative) were prepared in-house and assigned arbitrary units (AU/mL) during the development process.
# d. Detection limit:
Not applicable.
# e. Analytical specificity:
Interference study: Twenty seven samples were selected for evaluation of potential interference and crossreactivity: 2 Cryoglobulinemia, 8 Complement, 2 IgG monoclonal immunoglobulins, 3 IgM monoclonal immunoglobulins, 7 Rheumatoid Factor, 3 citrated plasmas, and 2 hemolyzed samples. Twenty six samples were negative and one RF sample was positive
{5}
for PR3. To ensure appropriate samples are used in the test, the package insert states to avoid grossly hemolyzed, lipemic, microbially contaminated, heat-treated, specimens with visible particulates, or samples with abnormal concentration of IgG and/ or complement levels, or samples with rheumatoid factor.
f. Assay cut-off:
The cut-off value of >25 AU/mL was based on testing 65 samples consisted of 37 normal blood donor sera and 28 selected samples with potential biologic interferences. With this cut-off value, 37 normal donor and 28 selected samples (100%) were negative for MPO and GBM; and 37 normal donor and 27 selected samples (98.5%) were negative for PR3.
2. Comparison studies:
a. Method comparison with predicate device:
Testing was performed on 219 samples which included 135 positive for one or more ANCA antibodies and/or positive for GBM; and 84 negative samples. No information about age, gender, and clinical status were available.
Equivocal results were considered negative. The positive, negative and total percent agreements for Anti-MPO, Anti-PR3, and Anti-GBM are shown in tables below.
| Anti-MPO | FIDISTM VASCULITIS MPO | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| FIDISTM VASCULITIS (MX 007) MPO | Positive | 69 | 0 | 69 |
| | Negative | 2 | 148 | 150 |
| | Total | 71 | 148 | 219 |
Positive percent agreement: 97.2% (69/71)
Negative percent agreement: 100% (148/148)
Overall percent Agreement: 99.1% (217/219)
| Anti-PR3 | FIDISTM VASCULITIS PR3 | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| FIDISTM VASCULITIS (MX 007) PR3 | Positive | 47 | 1 | 48 |
| | Negative | 2 | 169 | 171 |
| | Total | 49 | 170 | 219 |
Positive percent agreement: 95.9% (47/49)
Negative percent agreement: 99.4% (169/170)
Overall percent Agreement: 98.6% (216/219)
| Anti-GBM | FIDISTM VASCULITIS GBM | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| FIDISTM VASCULITIS (MX 007) GBM | Positive | 25 | 0 | 25 |
| | Negative | 0 | 194 | 194 |
| | Total | 25 | 194 | 219 |
{6}
Positive percent agreement: 100% (25/25)
Negative percent agreement: 100% (194/194)
Overall percent Agreement: 100% (219/219)
Comparison of manual preparation and the automated CARISTM System: Testing was performed on 117 samples: 75 positive for one or more ANCA parameters and/or positive for GBM; and 42 negative samples including some samples evaluated for their potential biological interferences. Results are summarized in tables below.
| Anti-MPO | Manual FIDIS | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| CARISTM FIDIS | Positive | 34 | 2 | 36 |
| | Negative | 0 | 81 | 81 |
| | Total | 34 | 83 | 117 |
Positive percent agreement: 100% (34/34)
Negative percent agreement: 97.6% (81/83)
Overall agreement: 98.3% (115/117)
| Anti-PR3 | Manual FIDIS | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| CARISTM FIDIS | Positive | 25 | 2 | 27 |
| | Negative | 0 | 90 | 90 |
| | Total | 25 | 92 | 117 |
Positive percent agreement: 100% (25/25)
Negative percent agreement: 97.8% (90/92)
Overall agreement: 98.3% (115/117)
| Anti-GBM | Manual FIDIS | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| CARISTM FIDIS | Positive | 23 | 0 | 23 |
| | Negative | 0 | 94 | 94 |
| | Total | 23 | 94 | 119 |
Positive percent agreement: 100% (23/23)
Negative percent agreement: 100% (94/94)
Overall agreement: 100% (117/117)
b. Matrix comparison:
Serum is the only recommended matrix.
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):
{7}
Not applicable.
4. Clinical cut-off:
Same as assay cut-off.
5. Expected values/Reference range:
Expected values in the normal population should be negative.
Table of incidence on Diseases with PR3, MPO and GBM antibodies
| Diseases | PR3 | MPO | GBM | Reference |
| --- | --- | --- | --- | --- |
| Wegener's granulomatosis | 30-90% | | | 14 |
| | 50-90% | | | 15 |
| Churg Strauss Syndrome | 35% | 35% | | 14 |
| | 31% | 7% | | 15 |
| Microscopic periarteritis | 20-40% | 50% | | 14 |
| | 25-30% | 36% | | 15 |
| Idiopathic glomerulonephritis | 20-40% | 50% | | 14 |
| | | 80% | | 15 |
| Goodpasture's syndrome or anti-GBM nephritis | | | 98% | 16 |
(14) Molloy P. ANCA and Associated disease: Update. PSA Consult, 2000, vol III, 5.
(15) Sanchez-Lallyoyer N. ANCA. Spectra Biologie, 1993; 93/3: 38-42.
(16) Rossert J. Goodpasture's disease. Orphanet encyclopedia, 2002: 1-4.
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.