ENA IGG BEADCHIP TEST SYSTEM, ARRAY IMAGING SYSTEM, MODELS 800-00025, AIS 400
Applicant
Bioarray Solutions, Ltd.
Product Code
LLL · Immunology
Decision Date
May 31, 2005
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5100
Device Class
Class 2
Indications for Use
The BioArray Solutions ENA IgG BeadChip™ Test System is intended for use in testing human serum for the presence of human IgG class antibodies to six extractable nuclear antigens, SSA, SSB, Sm, Sm/RNP, Scl-70, and Jo-1. The presence of these autoantibodies can be used in conjunction with clinical findings and other laboratory tests to aid in the diagnosis of systemic lupus erythematosus, Sjögren's syndrome, scleroderma and myositis. This ENA IgG BeadChip is for use with Array Imaging System 400 (AIS400). This test is for in vitro diagnostic use.
Device Story
The ENA IgG BeadChip™ Test System is a microarray-based immunoassay for detecting IgG antibodies to six extractable nuclear antigens (SSA, SSB, Sm, Sm/RNP, Scl-70, Jo-1). Antigens are covalently immobilized on spectrally distinguishable beads, which are then arranged as a microarray on a silicon chip. Patient serum is incubated with the chip; if specific antibodies are present, they bind to the corresponding antigen beads. After washing, Alexa-Fluor 647 conjugated goat anti-human IgG is added as a detection conjugate. The Array Imaging System 400 (AIS 400) images the chip to measure fluorescent signals from individual beads. The ENA Analysis program processes these signals—calculating average intensity, coefficient of variance, and bead counts—to assess internal controls and generate qualitative test results. Used in clinical laboratory settings by trained personnel, the device provides diagnostic aid for autoimmune diseases. Results are interpreted by healthcare providers alongside clinical findings to support patient diagnosis.
Clinical Evidence
Performance evaluated via method comparison study against the predicate using 229 samples. Positive agreement ranged from 91.2% to 100% and negative agreement from 91.7% to 99.5% across the six antigens. Reproducibility assessed via day-to-day, operator-to-operator, and three-site studies (192 samples per site). Site-to-site total agreement for positive/negative calls ranged from 90.6% to 97.2%. Analytical sensitivity and interference (hemolysis, bilirubin, hemoglobin) were characterized; lipidemic samples were found to interfere with assay performance.
Technological Characteristics
Microarray-based immunoassay using spectrally distinguishable beads immobilized on a silicon chip. Detection via Alexa-Fluor 647 fluorescent conjugate and AIS 400 fluorometer. Qualitative assay format. Requires 1:10 sample dilution. System includes internal control beads (positive, negative, system).
Indications for Use
Indicated for testing human serum for IgG antibodies to SSA, SSB, Sm, Sm/RNP, Scl-70, and Jo-1 to aid in the diagnosis of systemic lupus erythematosus, Sjögren's syndrome, scleroderma, and myositis.
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:
K043067
B. Purpose for Submission:
New Device
C. Measurand:
Anti-ENA antibodies (SSA, SSB, Sm, Sm/RNP, Scl-70, and Jo-1)
D. Type of Test:
Microarray based immunoassay, Qualitative
E. Applicant:
BioArray Solutions, Ltd.
F. Proprietary and Established Names:
ENA IgG BeadChip™ Test System on the Array Imaging System (AIS 400)
G. Regulatory Information:
1. Regulation section:
21 CFR 866.5100, Antinuclear antibody immunological test system
2. Classification:
II
3. Product code:
LLL, Extractable antinuclear antibody, antigen and control
4. Panel:
Immunology 82
H. Intended Use:
1. Intended use(s):
The BioArray Solutions ENA IgG BeadChip Test System is intended for use in testing human serum for the presence of human IgG class antibodies to six extractable nuclear antigens: SSA, SSB, Sm, Sm/RNP, Scl-70, and Jo-1. The presence of these autoantibodies can be used in conjunction with clinical findings and other laboratory tests to aid in the diagnosis of systemic lupus erythematosus, Sjögren’s syndrome, scleroderma and myositis. This ENA IgG BeadChip is for use with the BioArray Solutions Array Imaging System (AIS 400). This test is for in vitro diagnostic use.
2. Indication(s) for use:
Same as Intended use
3. Special conditions for use statement(s):
For Prescription use
4. Special instrument requirements:
Array Imaging System (AIS 400)
{1}
# I. Device Description:
The ENA IgG BeadChip™ Test System consists of an ENA IgG BeadChip (12 carriers x 8- BeadChip arrays), a positive human serum control, a negative human serum control, sample diluent/wash buffer and goat anti-human detection conjugate.
The AIS 400 system is an automated image acquisition system with an integrated analysis system designed for BioArray Solutions BeadChip microarrays. The major components are the microscope, automatic stage, focus motor, light source, CCD camera, computer and a software package that includes BioArray Solution Reader (BASR), Client Merger, and New Batch programs.
# J. Substantial Equivalence Information:
1. Predicate device name(s): ENA IgG ImmuStrip™ Test System, Distributed by SLR Research Corporation
2. Predicate 510(k) number(s): K964787
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended use | Intended for use in testing human serum for the presence of human IgG class antibodies to six extractable nuclear antigens to aid in the diagnosis of systemic lupus erythematosus, Sjögren's syndrome, scleroderma and myositis. | Same |
| Assay Type | Immunoassay | Same |
| Antigens | SSA, SSB, Sm, Sm/RNP, Scl-70, and Jo-1 | Same |
| Assay format | Qualitative | Same |
| Sample Type | Serum | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Technology | Microarray based immunoassay | ELISA |
| Solid phase | Microparticle | Strip |
| Assay Incubation Time | 30/15 minutes | 30/30/15 minutes |
| Reporter Conjugate | Alexa Fluor 647 | Alkaline Phosphatase |
| Method of detection | Fluorometer | Visual |
{2}
K. Standard/Guidance Document Referenced (if applicable):
FDA Guidance for the content of Premarket Submissions for Software Contained in Medical Devices.
L. Test Principle:
The ENA IgG BeadChip™ Test System is a randomly encoded microarray-based immunoassay for antibodies to extractable nuclear antigens. The device is designed to detect IgG class antibodies in human serum to six extractable nuclear antigens: SSA, SSB, Sm, RNP/Sm, Jo-1, and SCL-70. Each antigen is covalently immobilized to a spectrally distinguishable bead type. A pool of bead types is constructed by mixing all of the bead types of interest including antigen beads, positive control beads, negative control beads, and system control beads. The bead mixture is immobilized as a BeadChip™ microarray on a silicon chip allowing for the simultaneous detection of the auto-antibodies of interest by the AIS 400. Each BeadChip is identified by a carrier ID, which is bar coded on the carrier label.
Patient samples are diluted prior to incubation with the BeadChip microarray. If ENA specific antibodies are present in the sample, they will bind to the immobilized antigen on one or more bead types. After washing the unbound serum from the BeadChip, Alexa-Fluor 647 conjugated goat anti-human IgG is added to the BeadChip and briefly incubated. After removing unbound detection conjugate, the BeadChip is imaged with the Array Imaging System 400 (AIS 400) to measure the fluorescent signal associated with the conjugate bound on individual beads. The average signal intensity, coefficient of variance of the intensities, and the number of beads measured for each type is determined and reported. The ENA Analysis Software imports the instrument results, assesses the validity of the internal controls and generates test results. The ENA Analysis Software performs all calculations. The fluorescent signal is normalized based on the intensity of the conjugate control (hIgG) and characteristics of the individual serum sample. The normalized signal is compared with the predetermined analyte cut-off value and a result of positive, negative or equivocal is determined. These cutoff values are lot-specific values predetermined at BioArray Solutions. These values are stored in the CD provided in the kit and must be used with the ENA Analysis Software.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
i. Study design: Reproducibility studies performed included Day-to-Day reproducibility, Operator-to-Operator reproducibility and Site-to-Site reproducibility.
Day-to-Day reproducibility: The day-to-day reproducibility study was conducted with a pooled positive sample (PDP) containing antibodies to SSA, SSB, Sm, Sm/RNP, Jo-1, and Scl-70 and a pooled normal serum sample (PNS). The ENA IgG BeadChip assay was performed in duplicate for ten consecutive days for a total of twenty runs per sample using three lots of BeadChips. The pooled positive and negative controls were prepared, aliquoted, and stored in a −20°C freezer. A new aliquot was used each day to prepare fresh dilutions. The three
3
{3}
lots of BeadChips were manufactured from three independently coupled ENA bead libraries.
Operator-to-Operator reproducibility: The operator-to-operator reproducibility was conducted with the pooled disease positive (PDP) control, the pooled negative control or pooled normal serum (PNS) sample and ten disease positive samples. PNS-10 is 1:10 diluted pooled normal serum sample. PDP-30 is 1:30 diluted pooled disease positive sample. Two researchers performed the ENA IgG BeadChip assays in duplicate.
Site-to-Site reproducibility: A site-to-site reproducibility study was performed to assess the assay variability between sites, instruments and operators. Identical serum samples (commercially obtained) were provided to the three testing sites for on-site testing. The three testing sites included BioArray Solutions and two clinical laboratories. These samples were randomly encoded to eliminate any references to identity or diagnosis prior to distributing the samples to the investigational sites. A total of 176 samples comprised of 52 normal samples and approximately 25 positive samples for each antigen were used. A total of 192 samples were run at each site. Ten samples were excluded due to specimen control failure at one or more sites and one sample was excluded due to a sample preparation error. Results for two samples for the Scl-70 marker were excluded due to cluster QC failure at one site. These samples were not repeated at that site.
ii. Results/Acceptance criteria: Day-to-Day Reproducibility: The results for the pooled positive sample are reported in Table 1 by antigen, including the mean of the relative activity (RA), standard deviation (SD), and the coefficient of variance (CV) for each lot (intra-lot reproducibility) and the Mean, SD, and CV of relative activity of all three lots (inter-lot reproducibility). The RA is the ratio between the antigen Normalized Intensity (NMI) and the lot specific cutoff multiplied by 100. The CVs of the RAs were less than $15\%$ .
Table 1: Day-to-Day Reproducibility: Pooled Positive Sample
| RELATIVE ACTIVITY (RA) | | | SSA | SSB | Sm | RNP/Sm | Jo-1 | Scl-70 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Lot-A (n=20) | MEAN | 826.1 | 423.4 | 661.1 | 1016.0 | 458.6 | 123.3 |
| | | SD | 92.5 | 50.7 | 78.6 | 125.3 | 62.2 | 14.0 |
| | | CV(%) | 11.2 | 12.0 | 11.9 | 12.3 | 13.6 | 11.3 |
| | Lot-B (n=20) | MEAN | 890.3 | 435.4 | 777.6 | 1198.9 | 549.8 | 135.3 |
| | | SD | 76.1 | 64.4 | 123.3 | 120.1 | 69.1 | 18.6 |
| | | CV(%) | 8.5 | 14.8 | 15.9 | 10.0 | 12.6 | 13.7 |
| | Lot-C (n=20) | MEAN | 776.5 | 442.7 | 751.1 | 1115.6 | 522.8 | 136.3 |
| | | SD | 56.4 | 37.4 | 87.7 | 88.8 | 54.7 | 15.0 |
| | | CV(%) | 7.3 | 8.4 | 11.7 | 8.0 | 10.5 | 11.0 |
| | Lot-A,B,C (n=60) | MEAN | 831.0 | 433.9 | 730.0 | 1110.2 | 510.4 | 131.6 |
| | | SD | 88.6 | 51.7 | 109.0 | 133.9 | 72.4 | 16.8 |
| | | CV(%) | 10.7 | 11.9 | 14.9 | 12.1 | 14.2 | 12.7 |
Day-to-Day reproducibility studies were also performed with pooled negative control samples and the results were acceptable.
{4}
Operator-to-Operator reproducibility: The %CVs were less than 10% for all positive signals; PNS-10 is a pooled negative control and as expected, the %CV for the weak nonspecific signals for each antigen are much higher when compared to disease positive markers.
Site-to-Site reproducibility: Comparative analysis of the results obtained from three sites showed that the total agreement of positive/negative calls between three sites for SSA, SSB, Sm, Sm/RNP, JO-1, and Scl-70 is 97.2%, 95.6%, 96.7%, 90.6%, 97.2% and 96.1% respectively.
Table 2: Site-to-Site reproducibility
| | +/+/+ | -/-/- | ?/?/? | -/? | +/? | +/- | Total # | (%) Total Agreement |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| SSA | 38 | 138 | | 3 | 2 | | 181 | 97.2 |
| SSB | 35 | 137 | 1 | 5 | 2 | 1 | 181 | 95.6 |
| SM | 40 | 135 | | 5 | 1 | | 181 | 96.7 |
| RNP/Sm | 38 | 125 | 1 | 15 | 1 | 1 | 181 | 90.6 |
| Jo-1 | 37 | 138 | 1 | 3 | 1 | 1 | 181 | 97.2 |
| Scl-70 | 27 | 144 | 1 | 5 | 2 | | 179 | 96.1 |
Note: (+) Positive (-) Negative (?) Equivocal
b. Linearity/assay reportable range:
No linearity studies were performed
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Stability studies of the kit support a shelf life of 2 weeks from the date of manufacture.
d. Detection limit:
To determine the analytical sensitivity of the assay, the limit of blank was determined using assays performed with sample diluent in place of serum during the sample incubation. A total of seven assays were performed. The mean and SD of the RA for each antigen are given in Table 3.
Table 3: Analytical sensitivity
| RA | SSA | SSB | Sm | RNP/Sm | Jo-1 | Scl-70 |
| --- | --- | --- | --- | --- | --- | --- |
| Mean | 2.4 | 0.3 | 2.0 | 2.9 | 0.4 | 1.2 |
| SD | 3.6 | 1.3 | 0.7 | 2.9 | 0.7 | 0.3 |
| Mean +3SD | 13.3 | 4.2 | 4.1 | 11.6 | 2.4 | 2.1 |
e. Analytical specificity:
To test whether rheumatoid factor or anti-ds DNA antibodies cross-react with the
{5}
BeadChip ENA antigen panel, two and six purchased samples characterized by the vendor as positive for rheumatoid factor and anti-ds DNA respectively were tested side-by-side with the BeadChip and the predicate device. No cross-reaction was detected from rheumatoid factor or anti-ds DNA antibodies.
Interference testing with a hemolyzed sample and a lipidemic sample showed apparent interference with the lipidemic sample, but not with the hemolytic sample. The limitations of test in package insert specify not to use any lipidemic samples. Limitation also recommends avoiding any heterophile antibodies to rabbit or bovine derived materials.
Additional tests to identify the operating range of the assay in the presence of interfering substances showed that bilirubin at concentrations of 10, 20, and 40 mg/dl and hemoglobin at concentrations of 250, 500, and 1000 mg/dl were not found to interfere with the assay within the tested limits.
f. Assay cut-off:
To determine the cut-off for each antigen in the ENA IgG BeadChip assay, 130 normal samples from healthy, asymptomatic human subjects were assayed. The mean and standard deviation of the relative activity (RA) is listed in Table 4. The upper limit of the normal range for each antigen is the mean plus 3~3.5 standard deviations (SD) and the lower limit of the positive range (Cut-off) for each antigen is the mean plus 6SD.
Table 4: Cut-off determination
| (RA Value) | SSA | SSB | Sm | Sm/RNP | Jo-1 | Scl-70 |
| --- | --- | --- | --- | --- | --- | --- |
| Data Points Used | 130 | 130 | 129 | 130 | 130 | 130 |
| MEAN | 5.7 | 6.0 | 11.6 | 16.7 | 9.2 | 21.0 |
| SD | 15.9 | 15.5 | 15.0 | 14.0 | 15.1 | 13.2 |
| Upper limit - normal range | 60 | 60 | 60 | 60 | 60 | 60 |
| Positive Cut-off | 100 | 100 | 100 | 100 | 100 | 100 |
| Equivocal | (60-100) | (60-100) | (60-100) | (60-100) | (60-100) | (60-100) |
2. Comparison studies:
a. Method comparison with predicate device:
i. Study design: A comparative study to demonstrate the performance characteristics of the ENA IgG BeadChip Test System relative to the predicate device was conducted using 229 human serum samples from commercial vendors. The samples included 54 from normal, healthy subjects and 175 from subjects with confirmed or suspected autoimmune disease. Subject ages ranged from 19 to 77 years of age. The gender was known for 171 subjects with 39 male subjects and 132 two female subjects.
{6}
ii. Results: Samples assayed by the predicate device are positive/negative calls for each antigen. Samples assayed by BeadChips are assigned positive, negative or equivocal calls. Percent agreement between the ENA IgG BeadChip Test System and the predicate is listed in Table 5. Samples for which results could not be determined with the predicate device or were equivocal with the ENA IgG BeadChip Test System are not included in the sub-totals or the calculation of the percent agreement.
Table 5: Percent agreement between the ENA IgG BeadChip Test System and the predicate
| Predicate BeadChip | POS/POS | NEG/NEG | POS/NEG | NEG/POS | KILLNO | Total | % Positive Agreement | % Negative Agreement |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| SSA | 47 | 159 | 2 | 10 | 11 | 229 | 95.9 | 94.1 |
| SSB | 21 | 195 | 0 | 8 | 5 | 229 | 100.0 | 96.1 |
| Sm | 48 | 156 | 1 | 10 | 14 | 229 | 98.0 | 94.0 |
| RNP/Sm | 50 | 155 | 0 | 14 | 10 | 229 | 100.0 | 81.7 |
| Jb-1 | 21 | 314 | 0 | 1 | 3 | 229 | 100.0 | 89.5 |
| Sci-70 | 31 | 183 | 3 | 2 | 10 | 229 | 91.2 | 98.9 |
b. Matrix comparison: Not applicable.
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): Not applicable.
4. Clinical cut-off: Same as Assay cut-off.
5. Expected values/Reference range: Same as Assay cut-off.
N. Instrument Name: Array Imaging System
O. System Descriptions: The AIS 400 system is an automated image acquisition system with an integrated analysis system designed for BioArray Solutions BeadChip microarrays. The major components are the microscope, automatic stage, focus motor, light source, CCD camera, computer and a software package that includes BioArray Solution Reader (BASR), Client Merger, and New Batch programs.
{7}
The BioArray Solutions Reader (BASR) is the software that controls the operation of the microscope and the acquisition of the assay images, including the auto-positioning and auto-focus features. The hardware components are responsible for acquiring the images necessary for analysis of the BeadChip microarray.
The New Batch program copies the cluster data for a new batch of BeadChips™ from the CD provided with the slides to customers hard drive. It only has to be run once for every new batch of BeadChips™.
Bioarray's Client Merger software processes the assay image and merges the assay signal with cluster information. The merge result files will be generated and saved in the cluster folder.
1. **Modes of Operation:**
The AIS 400 operates in a semi-automatic fashion. The operator is required to manually position and focus on the first BeadChip on a carrier; subsequent BeadChips are positioned and focused automatically. While the instrument generally functions in a batch mode, individual BeadChips may be read selectively.
2. **Software:**
FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types:
Yes ☑ or No ☐
3. **Specimen Identification:**
Specimen information is entered manually into the software program for its position on the BeadChip. Each BeadChip is identified by a carrier ID, which is bar coded on the carrier label.
4. **Specimen Sampling and Handling:**
Diluted serum samples are applied directly to the top of the BeadChip by manual or automated pipetting. After incubating with diluted conjugated antibody, unbound detection conjugate is removed and the BeadChip is imaged with the AIS 400 to measure the fluorescent signal associated with the conjugate bound on individual beads.
5. **Calibration:**
The system measures arbitrary fluorescent units therefore no calibration is required. However, a performance check is conducted using a company defined standard, calibration slide, to ensure the uniformity and change in intensity of illumination in the AIS 400.
6. **Quality Control:**
Several controls are used in this system which includes positive and negative serum controls, a system control (internal standard), a background control (h-SA bead), a specimen control (Protein-L) and a procedural control or conjugate control (hIgG).
8
{8}
The system control (internal standard) is present on every BeadChip. This ensures that the AIS 400 is operating within expected parameters by monitoring the system performance and output data quality. The background control (h-SA bead) monitors non-specific binding and assay background. The specimen control (Protein L) detects the presence of immunoglobulins with kappa chains in adequate amounts. The procedural control or conjugate control (hIgG) verifies the addition of the Conjugate Detection Antibody and adequate incubation time. The positive and negative serum controls are included in each run which determines the run validity of the system. The positive serum control must be positive for each antigen, negative for the background control (h-SA bead), and positive for the specimen control. The negative serum control must be negative for each antigen, including the background control (h-SA bead), and positive for the specimen control.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above: None
Q. Proposed Labeling: The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion: The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
9
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.