Clinically and serologically characterized patient samples from clinical sites; Healthy blood donor samples
Retrospective clinical samples were used to evaluate the device's clinical sensitivity and specificity across various autoimmune and infectious disease conditions, and to perform a method comparison against a predicate device.
Clinical performance evaluation; Retrospective clinical evaluation; Follow-up/Duration: Not applicable
432 clinically characterized samples (MCTD, SLE, systemic sclerosis, Sjögren's, polymyositis/dermatomyositis, celiac disease, Wegener's, rheumatoid arthritis, other autoimmune, and infectious diseases); Sample Size: 432; Number of Sites: Multiple sites
Not applicable for this study
Clinical sensitivity and specificity
Indications for Use
The EUROIMMUN Anti-ENA Pool ELISA (IgG) is intended for the qualitative determination of IgG class antibodies against nuclear antigens (mixture of nRNP/Sm, Sm, SS-A (SS-A 60/Ro-52), SS-B, Scl-70 and ribosomal P proteins) in human serum. It is used as an aid in the diagnosis of mixed connective tissue diseases (MCTD), systemic lupus erythematosus, Sjögren's syndrome and progressive systemic sclerosis, in conjunction with other laboratory and clinical findings.
Device Story
EUROIMMUN Anti-ENA Pool ELISA (IgG) is a qualitative enzyme immunoassay for human serum. Device uses 96-well microtiter plates coated with a mixture of nuclear antigens (nRNP/Sm, Sm, SS-A, SS-B, Scl-70, ribosomal P). Procedure involves two-step incubation: patient sample incubation followed by wash, then anti-human IgG peroxidase-labeled conjugate incubation, wash, and TMB substrate addition. Stop solution added; optical density measured at 450nm using a microwell plate reader. Results expressed as OD ratio; ratio ≥ 1.0 indicates positive result. Used in clinical laboratories by trained personnel to aid diagnosis of autoimmune connective tissue diseases. Two-step design minimizes matrix effects and interference compared to one-step assays. Provides clinicians with serological evidence to support diagnosis of MCTD, SLE, Sjögren's syndrome, and systemic sclerosis.
Clinical Evidence
Clinical study evaluated 432 characterized samples. Overall sensitivity 60.9% (95% CI: 54.7-66.9%) and specificity 96.5% (95% CI: 92.5-98.7%). Sensitivity by condition: MCTD 100%, SLE 55.3%, Scleroderma 45.5%, Sjögren's 72.7%. Specificity confirmed against various autoimmune and infectious disease controls. Analytical performance included precision/reproducibility studies (intra-assay and inter-assay) and interference testing (hemoglobin, triglycerides, bilirubin, rheumatoid factor) showing no significant interference.
Indicated for qualitative detection of IgG antibodies against nuclear antigens in human serum to aid in the diagnosis of mixed connective tissue disease (MCTD), systemic lupus erythematosus, Sjögren’s syndrome, and progressive systemic sclerosis in patients suspected of these conditions.
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).
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k112996
B. Purpose for Submission:
New device
C. Measurand:
IgG antibodies to nRNP/Sm, Sm, SS-A (SS-A 60/Ro-52), SS-B, Scl-70, ribosomal P proteins
D. Type of Test:
Qualitative, enzyme-linked immunosorbent assay (ELISA)
E. Applicant:
EUROIMMUN US Inc.
F. Proprietary and Established Names:
EUROIMMUN Anti-ENA Pool ELISA (IgG)
G. 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
4. Panel:
Immunology (82)
H. Intended Use:
1. Intended use(s):
The EUROIMMUN Anti-ENA Pool ELISA (IgG) is intended for the qualitative determination of IgG class antibodies against nuclear antigens (mixture of nRNA/Sm, Sm, SS-A (SS-A 60/Ro-52), SS-B, Scl-70, and ribosomal P proteins) in human serum. It is used as an aid in the diagnosis of mixed connective tissue disease (MCTD), systemic lupus erythematosus, Sjögren’s syndrome and progressive systemic sclerosis, in conjunction with other laboratory and clinical findings.
2. Indication(s) for use:
Same as Intended Use
{1}
3. Special conditions for use statement(s):
For prescription use only
4. Special instrument requirements:
Dual (450 nm and 620-650 nm reference) wavelength spectrophotometer (microwell plate reader)
I. Device Description:
The EUROIMMUN Anti-ENA Pool ELISA (IgG) contains the following components: microplate strips coated with a mixture of nuclear antigens (nRNA/Sm, Sm, SS-A (SS-A 60/Ro-52), SS-B, Scl-70, and ribosomal P proteins), calibrator, positive and negative controls, horseradish peroxidase (HRP)-conjugated rabbit anti-human IgG, sample buffer, 10x wash buffer, TMB/H₂O₂ (3,3',5,5'-tetramethylbenzidine/hydrogen peroxide) chromogenic substrate solution, and 0.5 M sulphuric acid stop solution.
J. Substantial Equivalence Information:
1. Predicate device name(s) and Predicate 510(k) number(s):
AESKULISA® ANA HEp-2, k081104
2. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | Detection of IgG class antibodies against nuclear antigens | Same |
| Indications for Use | Aids in the diagnosis of mixed connective tissue disease (MCTD), systemic lupus erythematosus, Sjögren’s syndrome and progressive systemic sclerosis, in conjunction with other laboratory and clinical findings | Aids in the diagnosis of certain systemic rheumatic diseases and should be used in conjunction with other serological tests and clinical findings. |
| Assay Measurement | Qualitative | Same |
| Methodology | ELISA | Same |
| Assay platform | 96-well microtiter plate | Same |
| IgG Enzyme conjugate | HRP-labeled anti-human IgG | Same |
| Substrate | TMB | Same |
| Matrix | Serum | Same |
| Reported results | Optical density (OD) ratio | Same |
| Cut-off | OD ratio 1.0 | Same |
{2}
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Antigen Mixture | nRNA/Sm, Sm, SS-A (SS-A 60/Ro-52), SS-B, Scl-70, and ribosomal P proteins | dsDNA, histones, SS-A (Ro), SS-B (La), Sm, snRNP/Sm, Scl-70, Jo-1 and centromeric antigens and lysed HEp-2 cells |
| Calibrators and Controls | 1 calibrator
2 controls: 1 positive, 1 negative | 3 controls: 1 positive, 1 cut-off, 1 negative |
| Sample buffer | Ready to use | 5x concentrate |
| Wash buffer | 10x concentrate | 50x concentrate |
| Stop solution | 0.5 M sulphuric acid | 1 M hydrochloric acid |
| Sample dilution | 1:201 | 1:101 |
# K. Standard/Guidance Document Referenced (if applicable):
Guidance for Industry and FDA Staff: Recommendations for Anti-Nuclear Antibody (ANA) Test System Premarket (510(k)) Submissions (January 22, 2009)
DIN EN 13640: 2002 Stability testing of in vitro diagnostic reagent; German version EN 13640: 2002 German and English texts
# L. Test Principle:
Antibodies present in patient samples bind to the antigen mixture-coated microtiter wells during an incubation step. The unbound sample is washed away and anti-human IgG enzyme conjugate is added. After washing away unbound enzyme conjugate, the remaining conjugate is incubated with chromogenic substrate solution. The reaction is stopped by adding "stop solution" and color intensity is measured as OD units by spectrophotometer. The ODs are proportional to the amount of bound conjugate, which in turn is proportional to the amount of antibodies bound to the antigen mixture in microtiter wells. Results are expressed as ratios which is a ratio of the OD of the control or patient sample to the OD value of the calibrator.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Intra- and inter-assay reproducibility of the device was evaluated using 16 and 14 serum samples with different concentrations, respectively. Intra-assay reproducibility was assessed from 16 or 20 determinations on one day. Inter-assay reproducibility was based on 26-30 results from 10 runs performed on 5 days with 2 runs per day. Each sample was assayed in triplicate for each run. For all samples, $100\%$ of the results corresponded to the expected results.
{3}
Intra-assay reproducibility
| Sample | Mean Ratio | Ratio Range | Expected Result | % Correct Result |
| --- | --- | --- | --- | --- |
| 1 | 0.4 | 0.3 - 0.4 | Negative | 100% |
| 2 | 0.8 | 0.7 - 0.8 | Negative | 100% |
| 3 | 1.4 | 1.3 - 1.4 | Positive | 100% |
| 4 | 2.4 | 2.2 - 2.6 | Positive | 100% |
| 5 | 5.7 | 5.4 - 6.0 | Positive | 100% |
| 6 | 8.3 | 7.8 - 9.0 | Positive | 100% |
| 7 | 0.1 | 0.1 | Negative | 100% |
| 8 | 7.4 | 6.8 - 7.6 | Positive | 100% |
| 9 | 2.8 | 2.5 - 3.0 | Positive | 100% |
| 10 | 4.9 | 4.7 - 5.2 | Positive | 100% |
| 11 | 2.5 | 2.1 - 2.7 | Positive | 100% |
| 12 | 8.3 | 8.0 - 8.6 | Positive | 100% |
| 13 | 10.3 | 9.5 - 11.1 | Positive | 100% |
| 14 | 2.1 | 2.0 - 2.3 | Positive | 100% |
| 15 | 5.6 | 4.9 - 6.2 | Positive | 100% |
| 16 | 2.8 | 2.5 - 3.0 | Positive | 100% |
Inter-assay reproducibility
| Sample | Mean Ratio | Ratio Range | Expected Result | % Correct Result |
| --- | --- | --- | --- | --- |
| 1 | 0.4 | 0.3 - 0.5 | Negative | 100% |
| 2 | 0.8 | 0.7 - 0.9 | Negative | 100% |
| 3 | 1.3 | 1.2 - 1.4 | Positive | 100% |
| 4 | 2.7 | 2.5 - 3.0 | Positive | 100% |
| 5 | 5.6 | 4.9 - 6.1 | Positive | 100% |
| 6 | 8.4 | 7.6 - 9.1 | Positive | 100% |
| 7 | 0.2 | 0.2 - 0.3 | Negative | 100% |
| 8 | 6.5 | 5.3 - 7.3 | Positive | 100% |
| 9 | 2.0 | 1.5 - 2.8 | Positive | 100% |
| 10 | 3.5 | 2.6 - 4.9 | Positive | 100% |
| 11 | 1.8 | 1.1 - 2.1 | Positive | 100% |
| 12 | 6.8 | 5.4 - 8.9 | Positive | 100% |
| 13 | 7.1 | 4.5 - 9.8 | Positive | 100% |
| 14 | 2.0 | 1.6 - 2.4 | Positive | 100% |
Lot-to-lot reproducibility was investigated using 15 sera (3 negative and 12 positive) with a range of ratio values. Each sample/lot combination was tested between 6 and 11 times. The expected result was determined from the sample mean. All of the results correctly matched the expected results.
| Sample ID | Mean Ratio | Ratio Range | Lots | Runs/Lot | Total Replicates | Expected Result | Correct Result |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | 1.1 | 1.1 - 1.2 | 3 | 2 | 6 | Positive | 100% |
| 2 | 0.9 | 0.8 - 0.9 | 3 | 2 | 6 | Negative | 100% |
| 3 | 0.1 | 0.1 - 0.2 | 11 | 1 | 11 | Negative | 100% |
| 5 | 2.7 | 2.5 - 3.3 | 9 | 1 | 9 | Positive | 100% |
{4}
| Sample ID | Mean Ratio | Ratio Range | Lots | Runs/Lot | Total Replicates | Expected Result | Correct Result |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 6 | 3.6 | 3.0 - 4.2 | 11 | 1 | 11 | Positive | 100% |
| 7 | 5.0 | 4.1 - 5.7 | 11 | 1 | 11 | Positive | 100% |
| 8 | 8.5 | 7.0 - 9.8 | 9 | 1 | 9 | Positive | 100% |
| 9 | 0.2 | 0.1 - 0.3 | 3 | 2 | 6 | Negative | 100% |
| 10 | 6.3 | 5.5 - 7.6 | 3 | 2 | 6 | Positive | 100% |
| 11 | 2.4 | 1.9 - 3.0 | 3 | 2 | 6 | Positive | 100% |
| 12 | 3.9 | 2.9 - 5.2 | 3 | 2 | 6 | Positive | 100% |
| 13 | 2.2 | 1.9 - 2.7 | 3 | 2 | 6 | Positive | 100% |
| 14 | 6.8 | 5.9 - 8.2 | 3 | 2 | 6 | Positive | 100% |
| 15 | 8.2 | 7.0 - 9.7 | 3 | 2 | 6 | Positive | 100% |
| 16 | 2.0 | 1.8 - 2.3 | 3 | 2 | 6 | Positive | 100% |
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
i. **Traceability**: A recognized international standard or reference material for anti-nuclear antibodies is not available. Results of this assay are based on OD reading expressed as in ratios.
ii. **Calibrator and Controls**: The OD values of the calibrator and the ratios of the positive and negative controls must lie within the limits stated in the quality control certificate provided with the relevant test kit lot.
iii. **Stability**:
Three lots of all kit reagents were tested in real time stability studies. Original sealed products were demonstrated to be stable for 12 months when stored at 2-8°C. Opened products were demonstrated to be stable for 12 months when stored at 2-8°C. The reconstituted wash buffer is stable for up to 28 days (4 weeks).
d. Detection limit:
Not applicable
e. Analytical specificity:
i. **Interference**: Four samples with different ENA concentrations (ratios from 0.7 to 8.4) were spiked with varying concentrations of hemoglobin up to 1,000 mg/dL, triglycerides up to 2,000 mg/dL, or bilirubin up to 40 mg/dL. Recoveries of all spiked sample/interferent combinations compared to the measurements for the unspiked samples were calculated. The individual recovery of all samples was within the range of 91% to 105%.
Six samples with ENA concentration ratios from 1.1 to 11.7 were spiked with rheumatoid factor at 500 IU/mL. Recovery in relation to the original unspiked sample was calculated and found to be between 96% and 106%.
{5}
ii. Cross Reactivity: The reactivity of the EUROIMMUN Anti-ENA Pool ELISA (IgG) was verified using twelve human reference sera from the CDC ANA reference panel. Samples characterized as homogenous/rim/nDNA (No. 1), nucleolar/U3 RNP (Fibrillarin) (No. 6), centromere (No. 8), and PM-Scl (No. 11) tested negative. All samples with target antigens (Nos. 2, 3, 4, 5, 7, 9, and 12) included in the kit tested positive. CDC sample characterized as anti-Jo-1 positive (No. 10) was also positive. Further testing was conducted to determine whether anti-Jo-1 reactivity was due to the presence of Ro-52 antibodies in the sample. Five samples positive for both anti-Jo-1 and anti-Ro-52 (but negative for nRNA/Sm, Sm, SS-A 60, SS-B, Scl70, and ribosomal P proteins) were positive with the EUROIMMUN Anti-ENA Pool ELISA (IgG). Two anti-Jo-1 positive samples that were negative for anti-Ro-52 antibodies tested negative with the EUROIMMUN Anti-ENA Pool ELISA (IgG). No cross reactivity to Jo-1 is expected.
Cross reactivity was investigated in other disease conditions using 82 clinically and serologically characterized samples. The samples were as follows: 10 celiac disease with antibodies against gliadin and tissue transglutaminase, 17 Wegener's granulomatosis with anti-neutrophil cytoplasmic antibodies (ANCA), 39 rheumatoid arthritis with anti-CCP antibodies, and 16 infectious diseases antibody positive. All samples except 2 Wegener's granulomatosis samples were negative with the EUROIMMUN Anti-ENA Pool ELISA (IgG).
f. Assay cut-off:
The assay cut-off is OD ratio of 1.0. Results ≥ 1.0 are positive, and results < 1.0 are negative.
2. Comparison studies:
a. Method comparison with predicate device:
Two hundred seventy-eight (278) clinically characterized samples from patients and control groups were tested with the predicate device and the EUROIMMUN Anti-ENA Pool ELISA (IgG). The samples were from 49 mixed connective tissue disease (MCTD), 26 systemic lupus erythrematosus (SLE), 29 Sjögren's syndrome, 22 systemic sclerosis, 20 polymyositis/dermatomyositis, 10 celiac disease, 17 Wegener's granulomatosis, 39 rheumatoid arthritis, and 16 infectious disease patients. Fifty healthy individuals were also included.
| | Predicate | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| EUROIMMUN Anti-ENA Pool ELISA (IgG) | Positive | 135 | 1 | 136 |
| | Negative | 3 | 139 | 142 |
| | Total | 138 | 140 | 278 |
Positive agreement: 135/138 = 97.8% (95% CI: 93.8% – 99.5%)
Negative agreement: 139/140 = 99.3% (95% CI: 96.1% – 100%)
6
{6}
Overall agreement: $274 / 278 = 98.6\%$ (95% CI: 96.4% - 99.6%)
# Method comparison with individual ENA ELISAs
A comparison study was performed with six monospecific autoantibody ELISAs to ensure that all targets are recognized by the EUROIMMUN Anti-ENA Pool ELISA (IgG). Samples from MCTD, SLE, Sjögren's syndrome, systemic sclerosis, rheumatoid arthritis, fibromyalgia, infectious diseases and healthy individuals. The combined positive percent agreement was $100\%$ (95%CI: 94.7%-100%), negative percent agreement was $91.7\%$ (95% CI: 80.0%-97.7%) and overall agreement of $96.6\%$ (95%CI: 91.4%-99.1%). There were two false positive samples each for the SSA/SSB and Scl-70 comparison.
# b. Matrix comparison:
Serum is the only sample specimen.
# 3. Clinical studies:
# a. Clinical Sensitivity:
Clinical sensitivity was determined from 261 clinically characterized samples from patients with MCTD $(n = 44)$ , SLE $(n = 85)$ , systemic sclerosis $(n = 66)$ , and Sjögren's syndrome $(n = 66)$ . The EUROIMMUN Anti-ENA Pool ELISA (IgG) showed an overall sensitivity of $60.9\%$ (95% CI: $54.7 - 66.9\%$ ). The results are in the table below.
| Condition | Total Samples | Anti-ENA Pool ELISA (IgG) | | |
| --- | --- | --- | --- | --- |
| | | Positive | % Positive | 95% CI |
| MCTD | 44 | 44 | 100.0 | 92.0 – 100.0 |
| SLE | 85 | 47 | 55.3 | 44.1 – 66.1 |
| Systemic sclerosis | 66 | 30 | 45.5 | 33.1 – 58.2 |
| Sjögren's syndrome | 66 | 48 | 72.7 | 60.4 – 83.0 |
| Total | 261 | 159 | 60.9 | 54.7 – 66.9 |
# b. Clinical specificity:
Clinical specificity was determined from 171 clinically characterized samples from the following control groups: polymyositis/dermatomyositis $(n = 26)$ , celiac disease $(n = 21)$ , Wegener's granulomatosis $(n = 17)$ , rheumatoid arthritis $(n = 39)$ , other autoimmune diseases $(n = 52)$ , and bacterial/viral infections $(n = 16)$ . The EUROIMMUN Anti-ENA Pool ELISA (IgG) showed an overall specificity of $96.5\%$ (95% CI: $92.5 - 98.7\%$ ). The results are listed below.
| Control Group | Total Samples | Anti-ENA Pool ELISA (IgG) | | |
| --- | --- | --- | --- | --- |
| | | Negative | % | 95% CI |
| Polymyositis/dermatomyositis | 26 | 22 | 84.6 | 65.1 – 95.6 |
| Celiac disease | 21 | 21 | 100.0 | 83.9 – 100.0 |
| Wegener's granulomatosis | 17 | 15 | 88.2 | 63.6 – 98.5 |
{7}
| Control Group | Total Samples | Anti-ENA Pool ELISA (IgG) | | |
| --- | --- | --- | --- | --- |
| | | Negative | % | 95% CI |
| Rheumatoid arthritis | 39 | 39 | 100.0 | 91.0 – 100.0 |
| Other autoimmune diseases* | 52 | 52 | 100.0 | 93.2 – 100.0 |
| Bacterial/viral infections | 16 | 16 | 100.0 | 79.4 – 100.0 |
| Total | 171 | 165 | 96.5 | 92.5 – 98.7 |
*Other autoimmune diseases includes autoimmune hepatitis (n=8), primary biliary cirrhosis (n=9), Grave’s disease (n=12), Hashimoto’s disease (n=11), and type I diabetes (n=12).
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
See Assay cut-off
5. Expected values/Reference range:
The levels of anti-ENA antibodies (IgG) were analyzed in a panel of 200 samples from apparently healthy blood donors. With a cut-off ratio of 1.0, a prevalence of 1.5% was obtained. The mean ratio was 0.2 (SD = 0.37) and the values ranged from 0.0 to 5.0. Users of the kit should generate their own ranges, as stated in the product insert.
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.