K040160 · Inova Diagnostics, Inc. · LLL · Mar 8, 2004 · Immunology
Device Facts
Record ID
K040160
Device Name
QUANTA PLEX SLE PROFILE 8
Applicant
Inova Diagnostics, Inc.
Product Code
LLL · Immunology
Decision Date
Mar 8, 2004
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5100
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K040160 · Mar 8, 2004
QUANTA PLEX SLE PROFILE 8
Inova Diagnostics, Inc.
Clinically defined patient serum samples (SLE, scleroderma, RA, infectious disease); Normal donor serum samples from a serum broker
Retrospective clinical samples were used to determine clinical sensitivity and specificity, establish assay cut-offs, and perform method comparison studies against predicate devices.
424 serum samples: 159 SLE, 44 scleroderma, 20 Jo-1, 30 RA, 21 infectious diseases, and 150 normal samples; Sample Size: 424; Number of Sites: In-house and one external site
QUANTA Plex™ ENA Profile 6 and QUANTA Lite™ ELISA assays
Clinical sensitivity, clinical specificity, and positive/negative percent agreement
Indications for Use
The QUANTA Plex™ SLE Profile 8 is a fluorescent immunosorbent assay for the semi-quantitative detection of autoantibodies in human serum. The assay can be used in conjunction with clinical findings and other laboratory tests to aid in the diagnosis of systemic lupus erythematosus and related connective tissue diseases such as Sjögren's syndrome, scleroderma and polymyositis.
Device Story
QUANTA Plex™ SLE Profile 8 is a fluorescent immunosorbent assay (FISA) designed for laboratory use. It analyzes human serum samples to detect specific autoantibodies (Sm, RNP, SSA, SSB, SCL-70, Jo-1, Centromere B, and dsDNA). The device functions by identifying these autoantibodies, providing semi-quantitative results that clinicians use alongside patient clinical findings and other diagnostic tests to support the diagnosis of systemic lupus erythematosus and related connective tissue disorders. It is intended for professional use in a clinical laboratory setting.
Clinical Evidence
Clinical performance evaluated using 424 serum samples (159 SLE, 44 scleroderma, 20 Jo-1, 30 RA, 21 infectious disease, 150 normal). Clinical sensitivity for ribosome-P was 13.8% and chromatin was 42.8% in SLE patients. Clinical specificity was 99.6% for ribosome-P and 97.4% for chromatin in non-SLE patients. Method comparison against predicate ELISA assays showed high agreement (Total agreement 92.4%–98.6%).
Technological Characteristics
Multiplexed fluorescent immunoassay using polystyrene microspheres. Antigens (Sm, RNP, SS-A, SS-B, Scl-70, Jo-1, ribosome-P, chromatin) coupled to unique spectral-addressable beads. Detection via PE-labeled goat anti-human IgG conjugate. Instrument: Luminex 100 System. Dynamic range: 20 to >20,000 Fluorescent Units (FU).
Indications for Use
Indicated for use as an aid in the diagnosis of systemic lupus erythematosus and related connective tissue diseases such as Sjögren’s syndrome, scleroderma and polymyositis.
Regulatory Classification
Identification
An antinuclear antibody immunological test system is a device that consists of the reagents used to measure by immunochemical techniques the autoimmune antibodies in serum, other body fluids, and tissues that react with cellular nuclear constituents (molecules present in the nucleus of a cell, such as ribonucleic acid, deoxyribonucleic acid, or nuclear proteins). The measurements aid in the diagnosis of systemic lupus erythematosus (a multisystem autoimmune disease in which antibodies attack the victim's own tissues), hepatitis (a liver disease), rheumatoid arthritis, Sjögren's syndrome (arthritis with inflammation of the eye, eyelid, and salivary glands), and systemic sclerosis (chronic hardening and shrinking of many body tissues).
Submission Summary (Full Text)
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k040160
B. Analyte:
Anti-ENA antibodies (SSA, SSB, Sm, RNP, Scl-70, Jo-1, ribosomal P and chromatin)
C. Type of Test:
Flow Cytometry-based, homogeneous, multiplexed, microparticle fluorescent immunoassay, semi-quantitative
D. Applicant:
INOVA Diagnostics, Inc.
E. Proprietary and Established Names:
QUANTA Plex™ SLE Profile 8
F. Regulatory Information:
1. Regulation section:
21 CFR 866.5100, Antinuclear Antibody Immunological Test System
2. Classification:
Class II
3. Product Code:
LLL, Extractable antinuclear antibody, antigen and control
MQA, Anti-ribosomal P antibodies
4. Panel:
IM (82)
G. Intended Use:
The QUANTA Plex™ SLE Profile 8 is a fluorescent immunosorbant assay for the semi-quantitative detection of Sm, RNP, SS-A, SS-B, Scl-70, Jo-1, ribosome-P and chromatin autoantibodies in human serum. The presence of these antibodies can be used in conjunction with clinical findings and other laboratory tests to aid in the diagnosis of systemic lupus erythematosus and related connective tissue diseases such as Sjögren’s syndrome, scleroderma and polymyositis.
1. Indication(s) for use:
As an aid in the diagnosis of systemic lupus erythematosus and related connective tissue diseases such as Sjögren’s syndrome, scleroderma and polymyositis.
2. Special condition for use statement(s):
For prescription use only.
{1}
Page 2 of 7
3. Special instrument Requirements:
Luminex 100™ System
H. Device Description:
The device consists of the following: a foil package containing 12 (1x8) microwell strips with holder (each microwell contains 9 different color beads and each color bead is coated with a different purified antigen (Sm, RNP, SSA, SS-B, Scl-70, Jo-1, ribosome-P, chromatin and an IgG Control), a negative control, a low positive control, a high positive control, HRP sample diluent, PBS concentrate, PE-labeled goat anti-human IgG conjugate (Fc-specific) and conjugate diluent.
I. Substantial Equivalence Information:
1. Predicate device name(s):
INOVA QUANTA Plex™ ENA Profile 6, INOVA QUANTA Lite™
Ribosome-P ELISA and INOVA QUANTA Lite™ Chromatin ELISA.
2. Predicate K number(s):
K031450, K981237 and K982603
3. Comparison with predicate:
INOVA QUANTA Plex™ ENA Profile 6 and INOVA QUANTA Plex™ SLE
Profile 8 have the same technological characteristics except the analytes ribosome-P and chromatin are not included in the INOVA QUANTA Plex™ ENA Profile 6.
| Quanta Plex™ ENA Profile 8 | | QUANTA Lite™ ELISA assays |
| --- | --- | --- |
| A. Similarities | | |
| Intended Use. - Semi-quantitative detection of Sm, RNP, SS-A, SS-B, Scl-70, Jo-1, ribosome-P and chromatin autoantibodies in human serum. | | Same |
| Indications for Use - As an aid in the diagnosis of systemic lupus erythematosus and related connective tissue diseases such as Sjögren’s syndrome, scleroderma and polymyositis. | | Same |
| Sample Type - Serum | | Same |
| Conjugate - Polyclonal goat anti-human IgG | | Same |
| B. Differences | | |
| Assay Method - Flow cytometry based | | ELISA |
| Assay Format - Multiplexed | | Individual analytes |
| Solid Phase - Differentially colored, carboxylated microspheres | | Microtiter well |
| Conjugate label - Phycoerythrin | | HR peroxidase |
| Detection Method - Fluorescence | | Colorimetric |
| Instruments - Luminex 100™ | | ELISA reader |
| Dynamic Range - 20 to >20,000 FU | | Not furnished |
{2}
Page 3 of 7
J. Standard/Guidance Document Referenced (if applicable):
None referenced.
K. Test Principle:
The Quanta Plex™ SLE Profile 8 assay is a multiplexed, semi-quantitative, fluorescent immunoassay performed on the Luminex 100 system. Each of the antigens (Sm, RNP, SS-B, SS-A 52/SS-A 60, Scl-70, Jo-1, ribosome-P and chromatin) and the assay control (goat anti-human IgG) are coupled to sets of different colored polystyrene microspheres. Diluted patient serum is added to each well and if specific antibodies are present, they will bind to the immobilized antigens on the beads. Then β-phycoerytherin (PE)-conjugated goat anti-human IgG (Fc specific) is added to each well and incubated. The conjugate will react with the autoantibodies immobilized on the beads. No washing is required with this procedure. The bead suspension is analyzed by the Luminex 100™ System. The bead sets are identified by their unique spectral addresses and the amount of PE conjugate is determined for each bead set. The fluorescence intensity is relative to the amount of antibody present in the patient serum. The median fluorescence of the PE conjugate is converted to Luminator Units (LU) by comparing to the fluorescence of the test sample to the fluorescence of the Low Positive for that specific analyte. The test principle and performance of the assay on the Luminex 100™ System were supported in k011140, k030681 and k031450.
L. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
To evaluate both intra-assay and inter-assay reproducibility, 12 patient sera were analyzed on the INOVA QUANTA Plex™ SLE Profile 8. These samples were selected to include low, moderate and high positives for each analyte. For intra-assay reproducibility, 8 samples were run 8 times and 4 samples 7 times on one plate in a single run. As expected the low positive samples had higher %CVs than the moderate and high positive samples. Results of the low, moderate and high positive samples are summarized below.
| | >100 LU | 50 LU – 100 LU | 11 LU-49 LU |
| --- | --- | --- | --- |
| Mean CV% | 4.8 | 5.6 | 8.1 |
| Range (%) | 1-9 | 2-11 | 4-15 |
For inter-assay reproducibility, 12 samples were run on 6 assays for 3 separate days. Similar to the intra-assay precision results, the %CVs for the low positive samples were higher than the moderate and high positive samples. The range and mean %CV for high, moderate and low positive samples are summarized below.
{3}
Page 4 of 7
| | >100 LU | 50 LU – 100 LU | 11 LU-49 LU |
| --- | --- | --- | --- |
| Mean CV% | 7.7 | 9.7 | 9.4 |
| Range (%) | 2-13 | 5-15 | 4-17 |
The intra- and inter-assay reproducibility results performed by manual pipetting were compared to automated pipetting. The results for each analyte are illustrated below.
| | | SSA | SSB | Sm | RNP | Scl-70 | Jo-1 | Ribo-P | Chrom |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Manual | Mean CV% | 4.8 | 3.7 | 5.7 | 6.2 | 7.7 | 4.3 | 6.7 | 6.5 |
| | Range (%) | 1-10 | 3-4 | 4-7 | 5-9 | 5-12 | 4-5 | 5-8 | 3-11 |
| Automated | Mean CV% | 5.8 | 5.3 | 7.5 | 7.6 | 8.3 | 5.7 | 9.2 | 7.2 |
| | Range (%) | 2-13 | 3-7 | 3-12 | 4-13 | 4-15 | 3-9 | 7-12 | 6-11 |
| | | SSA | SSB | Sm | RNP | Scl-70 | Jo-1 | Ribo-P | Chrom |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Manual | Mean CV% | 6.8 | 6.6 | 8 | 8.4 | 12.7 | 8.3 | 9.2 | 115 |
| | Range (%) | 2-10 | 6-8 | 7-10 | 5-10 | 10-15 | 5-13 | 6-11 | 10-11 |
| Automated | Mean CV% | 6.6 | 10.7 | 8.2 | 8.6 | 8.3 | 10.7 | 9.7 | 11.2 |
| | Range (%) | 4-9 | 9-14 | 5-13 | 5-13 | 6-11 | 5-17 | 7-13 | 9-13 |
b. Linearity/assay reportable range:
Dynamic range of the assay is 20 to >20000 Fluorescent Units (FU). The amount of fluorescence is related to the quantity of autoantibody present on the bead but in a non-linear fashion. The antibody concentrations correspond to fluorescent signal changes but are not directly proportional.
c. Traceability (controls, calibrators, or method):
No reference standards or method available. For each assay kit, negative, low positive and high positive controls are included.
d. Detection limit (functional sensitivity):
Not relevant for this assay.
e. Analytical specificity:
To assess potential cross-reactivity to other autoantibodies, 51 serum samples consisted of 30 RA and 21 infectious disease samples (herpes simplex virus (4), toxoplasmosis (4), hepatitis C (4), parvovirus (4) and cytomegalovirus (5)) were analyzed. Cross-reactivity was observed with one HCV (20 LU) for Sm; 1 RA (24 LU) for RNP and 3 RA (31, 598 and 108 LU) for chromatin.
Interference from serum components was evaluated by testing five serum samples negative for the eight autoantibodies. The serum samples consisted of 1 hemolyzed (hemoglobin 1000 mg/mL), 2 lipemic (cholesterol 329 mg/mL and triglycerides 1016 mg/mL), 1 icteric (bilirubin 29.7 mg/mL) and 1 high IgG (80 µg/mL). No false positive results were obtained. These samples were also mixed in equal volumes with 4 positive sera (one positive for SSA, SSB, Sm,
{4}
RNPand ribosome-P, one for Scl-70, one for Jo-1 and SSA and the fourth one for Sm, RNP, ribosome-P and chromatin) to determine whether these substances would significantly decrease the antibody/antigen reactions on the microspheres and cause false negative results. Little or no interference was observed when compared to the same sera mixed with a normal sample.
# f. Assay cut-off:
The cut-off value was determined using 150 normal samples from a serum broker. Similar to the predicate devices, the cut-off was arbitrary set at 20 LU. The fluorescence unit that was assigned 20 units was based on non-parametric statistical analysis. The following table shows the cut-off values for each analyte.
| Analyte | QUANTA Plex SLE Profile 8 | | |
| --- | --- | --- | --- |
| | Mean (LU) | SD (LU) | Cut-off (LU) |
| SM | 4 | 5.9 | 4 ± 2.8SD |
| RNP | 2 | 3.5 | 2 ± 5SD |
| SSA | 3 | 3 | 3 ± 5.7SD |
| SSB | 3 | 3.5 | 3 ± 5SD |
| Scl-70 | 5 | 4.5 | 5 ± 3.4SD |
| Jo-1 | 2 | 0.8 | 2 ± 24.6SD |
| Ribosome-P | 1 | 1.0 | 1 ± 18.1SD |
| Chromatin | 5 | 6.2 | 5 ± 2.4SD |
# 2. Comparison studies:
# a. Method comparison with predicate device:
Two hundred and seventy-four clinically defined patient samples (159 SLE, 44 scleroderma, 20 Jo-1, 30 RA and 21 infectious diseases) were tested with the QUANTA Plex™ SLE Profile 8 and the QUANTA Plex™ ENA Profile 6 for analytes found in both assays. Age and sex information were available for the SLE (61/159) and scleroderma patients. For the 61 SLE patients, there were 52 females and 7 males with a mean age of 35 years (13y-79y) and for the scleroderma group; there were 36 females and 8 males with a mean age of 50 years (31y-85y). Discrepant results were retested by both devices and the retest result was used as the final result. Discrepant samples were also tested with the INOVA QUANTA Lite™ ELISA assays. Majority of the discrepant results were borderline low positives. Results of the comparison study between QUANTA Plex™ SLE Profile 8 and QUANTA Plex™ ENA Profile 6 are summarized below.
| | # samples | Both Neg | Both Pos. | Q6 Pos Q8 Neg | Q6 Neg Q8 Pos | %Positive Agreement | %Negative Agreement | %Total Agreement |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sm | 274 | 212 | 51 | 4 | 7 | 92.7 | 96.8 | 96.0 |
| RNP | 274 | 198 | 69 | 3 | 4 | 95.8 | 98.0 | 97.4 |
| SS-A | 274 | 194 | 67 | 4 | 9 | 94.4 | 95.6 | 95.3 |
| SS-B | 274 | 248 | 19 | 3 | 4 | 86.4 | 98.4 | 97.4 |
{5}
For ribosome-P and chromatin, comparisons were made between QUANTA Plex™ SLE Profile 8 and INOVA QUANTA Lite™ ELISA assays since QUANTA Plex™ ENA Profile 6 does not have these two analytes. Discrepant results were retested by IFA on HEp-2 cells. For ribosome-P, all 9 discrepant samples were negative by IFA. For chromatin, 11 of the 29 samples were positive, 10 were negative and 3 were ambiguous.
| | # samples | Both Neg | Both Pos. | E Pos Q8 Neg | E Neg Q8 Pos | %Positive Agreement | %Negative Agreement | %Total Agreement |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Ribosome-P | 274 | 244 | 21 | 7 | 2 | 72.4 | 99.2 | 96.7 |
| Chromatin | 274 | 174 | 71 | 29 | 0 | 88.7 | 100 | 89.4 |
In addition to the above in-house study, 40 patient samples (36 ribosome-P positive and 4 negative) from Germany were tested by an external site on the QUANTA Plex™ SLE Profile 8. These samples have been previously analyzed in Germany, on 4 commercial ribosome-P ELISAs and 4 experimental ELISAs. The positive agreement between QUANTA Plex™ SLE Profile 8 to QUANTA Lite™ Ribosome-P ELISA was $94.4\%$ (34/36), the negative agreement was $100\%$ (4/4) and total agreement was $95\%$ (38/40).
The following table compiles results of the 424 serum samples (150 normal, 159 SLE, 44 scleroderma, 20 Jo-1, 30 RA and 21 infectious diseases) analyzed with the Quanta Plex™ SLE Profile 8, the Quanta Plex™ ENA Profile 6 and the predicate ELISA devices for ribosome-P and chromatin. For ribosome-P, 40 additional sera were tested.
| Analyte (# samples) | Both Neg | Both Pos | Q6 Pos Q8 Neg | Q6 Neg Q8 Pos | %Positive Agreement | %Negative Agreement | %Total Agreement |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Sm (424) | 359 | 55 | 7 | 3 | 95 | 98 | 97.6 |
| RNP (424) | 343 | 71 | 5 | 5 | 93 | 99 | 97.6 |
| SS-A (424) | 341 | 68 | 9 | 6 | 92 | 97 | 96.5 |
| SS-B (424) | 397 | 19 | 5 | 3 | 86 | 99 | 98.1 |
| Scl-70 (424) | 373 | 39 | 6 | 6 | 87 | 98 | 96.9 |
| Jo-1 (424) | 401 | 18 | 5 | 0 | 100 | 99 | 98.6 |
| Analyte (# samples) | Both Neg | Both Pos | E Pos Q8 Neg | E Neg Q8 Pos | %Positive Agreement | %Negative Agreement | %Total Agreement |
| Ribosome-P (464) | 398 | 55 | 2 | 9 | 86 | 99 | 97.6 |
| Chromatin (424) | 319 | 73 | 2 | 30 | 71 | 99 | 92.4 |
b. Matrix comparison: Both devices use serum.
# 3. Clinical studies:
a. Clinical sensitivity: Since anti-ribosome-P and anti-chromatin autoantibodies are primarily found in SLE, clinical sensitivity was determined using
{6}
Page 7 of 7
SLE patient data only. For this group of SLE patients, the clinical sensitivity was 13.8% (22/159) for ribosome-P and 42.8% (68/159) for chromatin. These results were comparable to those in published literature. Clinical sensitivities for the other analytes were studied in previous QUANTA Plex™ Profile assays and were not addressed in this submission.
## b. Clinical specificity:
Clinical specificity was determined using all non-SLE patient data. The clinical specificity was 99.6% (1/265) for ribosome-P and 97.4% (7/265) for chromatin. These results were comparable to those in published literature. Clinical specificities for the other analytes were studied in previous QUANTA Plex™ Profile assays and were not addressed in this submission.
## c. Other clinical information
Not applicable
4. Clinical cut-off:
See assay cut-off.
5. Expected values/Reference range:
The normal range for each analyte was determined by testing 150 normal samples from a serum broker. The samples were from 89 males and 61 females with an average age of 33 years, ranging from 17 years to 74 years. The normal range results are shown in table below.
| | QUANTA Plex SLE Profile 8 | | |
| --- | --- | --- | --- |
| Analyte | % Negative | Range LU | Mean ± SD (LU) |
| SM | 96.5 | 0-41 | 4.0 ± 5.9 |
| RNP | 98.7 | 0-21 | 2.0 ± 3.5 |
| SSA | 99.3 | 0-27 | 3.0 ± 3.0 |
| SSB | 99.3 | 0-24 | 3.0 ± 3.5 |
| Scl-70 | 98.7 | 0-24 | 5.0 ± 4.5 |
| Jo-1 | 100 | 0-4 | 2.0 ± 0.8 |
| Ribosome-P | 100 | 0-8 | 1.0 ± 1.0 |
| Chromatin | 97.3 | 0-51 | 5.0 ± 6.2 |
## M. Conclusion:
Based on the review of the information provided in this 510 (k), QUANTA Plex™ SLE Profile 8 kit is Substantially Equivalent to the QUANTA Plex™ ENA Profile 6 kit for Sm, RNP, SS-A, SS-B, Scl-70 and Jo-1 and to the QUANTA Lite™, ELISA assays for ribosome-P and chromatin, product code LLL, Extractable Antinuclear Antibody, Antigen and Control and MQA, Anti-ribosomal P antibodies, Immunology Device Panel 82, Class II.
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.