K131791 · Euroimmun US · DHN · Feb 26, 2014 · Immunology
Device Facts
Record ID
K131791
Device Name
IFA 40: HEP-20-10
Applicant
Euroimmun US
Product Code
DHN · Immunology
Decision Date
Feb 26, 2014
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
K131791 · Feb 26, 2014
IFA 40: HEP-20-10
Euroimmun US
Retrospective clinical serum samples from routine health screenings; Retrospective clinical serum samples from routine ANA screening (University of Pennsylvania)
Retrospective clinical samples were used to verify the assay cut-off and to perform method comparison studies (qualitative and semi-quantitative) against the predicate device.
Retrospective analysis of routine health screening samples
138 individuals (53 men, 85 women) submitted for routine health screening; Sample Size: 138; Number of Sites: 1
Not applicable for this study
Prevalence of ANA in healthy individuals
Retrospective method comparison
200 patients sent for routine ANA screening; Sample Size: 200; Number of Sites: 1
ImmunoConcepts® HEp-2000 ANA-Ro IFA (K972145)
Positive, negative, and overall percent agreement
Retrospective method comparison
156 patients sent for routine ANA screening; Sample Size: 156; Number of Sites: 1
ImmunoConcepts® HEp-2000 ANA-Ro IFA (K972145)
Positive, negative, and overall percent agreement; titer agreement
Indications for Use
The EUROIMMUN IFA 40: HEp-20-10 is an indirect immunofluorescence antibody test for the qualitative or semi-quantitative detection of antibodies against cell nuclei (ANA) in human serum. This test system is used as an aid in the diagnosis of systemic rheumatic diseases in conjunction with other laboratory and clinical findings.
Device Story
Device uses indirect immunofluorescence (IFA) to detect ANA in human serum. Input: patient serum samples; BIOCHIP slides coated with HEp-20-10 cells. Process: serum incubation with cells; wash; incubation with fluorescein-labeled anti-human IgG; wash; embedding. Output: fluorescence patterns and intensity levels (0 to 4+) read via fluorescence microscope. Used in clinical laboratories by trained technicians. Healthcare providers use reported titers and patterns alongside clinical findings to aid diagnosis of systemic rheumatic diseases. Benefits include standardized detection of autoantibodies associated with autoimmune conditions.
Clinical Evidence
No clinical diagnostic sensitivity/specificity studies performed. Performance established via method comparison with predicate using 356 prospective patient samples. Qualitative agreement: 92.4% positive, 95.5% negative. Semi-quantitative agreement: 100% positive/negative agreement in a separate cohort. Pattern agreement: 91.4%. Precision/reproducibility studies (intra-assay, inter-assay, inter-lot, inter-observer) showed fluorescence intensity variation within ±1 level. Analytical specificity verified using CDC reference panel and samples from various autoimmune/infectious diseases; no cross-reactivity observed. Interfering substances (hemoglobin, bilirubin, triglycerides, HAMA, RF) showed no effect on results.
Technological Characteristics
Indirect immunofluorescence assay using BIOCHIPs coated with HEp-20-10 cells. Requires fluorescence microscope (488 nm excitation, 510 nm separator, 520 nm blocking filter, 100W mercury or LED blue light). Conjugate: FITC-labeled goat anti-human IgG. Mounting medium: glycerol. Qualitative/semi-quantitative output based on visual intensity (0 to 4+). Stability supported by DIN EN 13640:2002.
Indications for Use
Indicated for qualitative or semi-quantitative detection of anti-nuclear antibodies (ANA) in human serum to aid in the diagnosis of systemic rheumatic diseases. For prescription use only.
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 ASSAY ONLY TEMPLATE
A. 510(k) Number:
k131791
B. Purpose for Submission:
New Assay
C. Measurand:
Anti-nuclear antibodies (ANA)
D. Type of Test:
Qualitative and/or semi-quantitative, indirect immunofluorescence
E. Applicant:
EUROIMMUN US INC.
F. Proprietary and Established Names:
EUROIMMUN IFA 40: HEp-20-10
G. Regulatory Information:
1. Regulation section:
21 §CFR 866.5100 - Antinuclear antibody immunological test system
2. Classification:
Class II
3. Product code:
DHN – Antinuclear Antibody, Indirect Immunofluorescent, Antigen, Control
4. Panel:
Immunology (82)
H. Intended Use:
1. Intended use(s):
The EUROIMMUN IFA 40: HEp-20-10 is an indirect immunofluorescence antibody test for the qualitative or semi-quantitative detection of antibodies against cell nuclei (ANA) in human serum. This test system is used as an aid in the diagnosis of systemic rheumatic diseases in conjunction with other clinical and laboratory findings.
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
This device is for prescription use only
{1}
4. Special instrument requirements:
Fluorescent Microscope: Equipped with a $488~\mathrm{nm}$ excitation filter; $510~\mathrm{nm}$ color separator; and $520~\mathrm{nm}$ blocking filter with a 100 watt (W) mercury vapor lamp light source or LED blue light.
# I. Device Description:
The test system consists of BIOCHIPs coated with HEp-20-10 cells. It includes a fluorescein-labeled goat anti-human IgG, a positive and negative control, salt for PBS, Tween 20, embedding medium, cover glasses and instruction booklet. Reagent trays for the TITERPLANE technique are required but ordered separately.
# J. Substantial Equivalence Information:
1. Predicate device name(s) and 510(k) number(s):
ImmunoConcepts Hep-2000 ANA-Ro IFA, k972145
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | Qualitative or semi-quantitative detection of antibodies against cell nuclei (ANA). The test system is used as an aid in the diagnosis of systemic rheumatic diseases in conjunction with other clinical and laboratory findings. | Same |
| Methodology | IFA | Same |
| Procedure | Standard IFA technique; serum incubation with cells, followed by a wash step, incubation with fluorescein-labelled anti-human globulin, wash step, embedding and reading fluorescence with a fluorescence microscope. | Same |
| Recommended Sample Dilution for Screen | 1:40 | Same |
| Cut-off Level | 1:40 | Same |
| Reported Results | Qualitative, Semi-quantitative Titer | Same |
| Sample Matrix | Serum | Same |
| Mounting Medium | Glycerol | Same |
{2}
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Conjugate | FITC-labelled goat anti-human IgG | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Slide format/Antigen Source | BIOCHIP TITERPLANE / HEp-20-10 cells are bound to the BIOCHIPs | IFA slides/ HEp-2000 cells are bound to the test wells |
| Controls | 1 Positive Control (homogenous pattern) 1 Negative Control | 5 Positive controls (one each for the following patterns: SSA/Ro, homogeneous, speckled, nucleolar, centromere) 1 Titratable control serum 1 Negative control serum |
# 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).
# L. Test Principle:
Patient samples are diluted 1:40 in PBS-Tween, $30~\mu \mathrm{L}$ of each diluted patient sample are added to each reaction field of the reagent tray. Reactions are started by fitting the BIOCHIP Slides containing the sections from the substrate (HEp-20-10 cells) into the corresponding recesses of the reagent tray and incubated for 30 minutes at room temperature. Specific antibodies attach to the HEp-20-10 antigens. After incubation the BIOCHIP Slides are washed with PBS-Tween to remove unbound antibodies. In the meantime, $25~\mu \mathrm{L}$ of fluorescein-labelled anti-human globulin are added to each reaction field of a clean reagent tray and the BIOCHIP Slides placed into the recesses of the tray. After 30 minutes incubation at room temperature, the BIOCHIPs are again washed with PBS-Tween to remove any unbound fluorescein-labelled reagent. $10~\mu \mathrm{L}$ of Embedding medium are placed for each reaction field on a cover glass and the BIOCHIP Slides, with the BIOCHIPs facing downwards, placed onto the prepared cover glass. Fluorescence is read with a fluorescence microscope.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
The fluorescence intensity level is the intensity of the specific fluorescence expressed as a numeric value. These values can vary from "0" (no specific fluorescence) to "4+" (strong specific fluorescence). The evaluation of the fluorescence intensity is performed according to the following table:
{3}
| Intensity | Interpretation |
| --- | --- |
| 0 | Negative: no specific fluorescence |
| 1+ | Positive: Weak visible reaction; dim subdued fluorescence |
| 2+ | Positive: Moderate visible reaction; green fluorescence |
| 3+ | Positive: Strong visible reaction; brilliant green fluorescence |
| 4+ | High Positive: Very strong visible reaction; brilliant green |
Interpretation of test results: A serum dilution is considered negative for ANA antibodies if the cells exhibit $< 1+$ fluorescence and no discernible pattern. Cells appear reddish-orange due to the Evans Blue counterstain. Likewise, a serum dilution is considered positive for ANA antibodies if the cells exhibit $\geq 1+$ fluorescence and a discernible pattern. A sample is considered positive for ANA antibodies if it exhibits exhibit $\geq 1+$ fluorescence and a discernible pattern at a sample dilution of 1:40 or greater. Technicians should report all titers and patterns seen.
a. Precision/Reproducibility:
Reproducibility was investigated using a panel of serum samples representing the range of patterns at different intensities. Samples were manually diluted in two-fold steps from a starting dilution of 1:40.
Intra-Assay Reproducibility: Twenty-nine (29) samples with different patterns and titers were each tested 10 times according to the package insert and evaluated by the same technician. None of the readings between replicates differed by more than $\pm 1$ fluorescence level; positive samples were not found negative (and vice versa) and the observed patterns did not change.
Inter-Assay Reproducibility: Twenty-nine (29) samples with different patterns and titers were each tested by 20 measurements obtained on 5 different days with 2 runs per day and 2 replicates (total 20 replicates) according to the package insert and evaluated by the same technician. None of the readings between replicates differed by more than $\pm 1$ fluorescence level; positive samples were not found negative (and vice versa) and the observed patterns did not change.
Inter-Lot Reproducibility: Twenty-nine (29) samples with different patterns and titers were each tested by 6 measurements obtained by testing each sample in duplicate on three separate lots in three runs, 1 run per lot (total 6 replicates). The EUROIMMUN IFA 40: HEp-20-10 assays were processed according to the package insert and evaluated by the same technician. The results of the different lots did not exceed the fluorescence intensity of $\pm 1$ intensity level, positive samples were not found negative and vice versa, and the observed patterns did not change.
Inter-Observer Reproducibility was determined by a separate independent reading of the Inter- Assay slides by a second technician for all 29 samples. The results of the different assays did not exceed the acceptable deviation of fluorescence intensity of $\pm 1$ intensity level, positive samples were not found negative and vice versa, and the observed patterns did not change. The Inter-Observer Reproducibility Study was performed in a US laboratory setting.
Semi-quantitative Reproducibility: Fourteen (14) positive samples and one negative sample were serially diluted from 1:40 to 1:10,240 then tested in duplicate in
{4}
four separate runs and read by two different observers (total 16 replicates). Three different lots were used in the experiment. Each of the seven main patterns (homogeneous, granular, nucleolar, centromeres, nuclear dots, nuclear membrane and cytoplasmic) were represented by a lower titer (1:80 – 1: 320) positive sample and a higher titer (1:1,280 – 1:10,240) positive sample. Fluorescence intensities ranged from 1+ to 4+. The results of the different assays for each dilution did not exceed the fluorescence intensity of ± 1 intensity level, so the endpoint titer did not deviate more than ± 1 titer level, and the observed patterns did not change.
b. Linearity/assay reportable range:
Six samples with different combinations of mixed staining patterns were serially diluted and tested with the EUROIMMUN IFA 40: HEp-20-10 assay. The samples were assayed according to the package insert. Each sample/dilution combination was tested and the fluorescence intensity and pattern were recorded.
Mixed patterns could be distinguished in every dilution, and the samples showed a decrease in fluorescence intensity as the samples were diluted. The pattern of the samples did not change with dilution. Acceptable deviation of fluorescence intensity: ± 1 intensity level.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability: A recognized standard or reference material for Anti-Nuclear Antibodies is not available.
Controls: Negative and positive controls are included in the kit. The negative control should exhibit less than 1+ or no specific fluorescence (autoantibody negative). The positive control should exhibit a homogenous staining pattern with a fluorescence intensity of >1+ (3 to 4+). The homogenous pattern of the positive control was confirmed via testing. EUROIMMUN Inc. recommends using the positive and negative controls as stated within the labeling (Instructions for Use).
Stability: Ongoing real-time stability tests of the kit are being conducted in accordance with DIN EN 13640:2002: Stability testing of in vitro diagnostics reagents. Three production lots of all kit reagents are tested. Current testing supports a stability claim of 12 months when stored at +2°C – +8°C.
d. Detection limit:
Not applicable.
e. Analytical specificity:
Cross-reactivity: The specificity of the EUROIMMUN IFA 40: HEp-20-10 was verified using the ANA reference panel of the CDC (Centers for Disease Control and Prevention, Atlanta, USA). The CDC samples were assayed according to the package insert by the same technician at the same day. The results are in line with the characterization by the CDC with the exception of CDC sample No. 12. This sample was also tested using the EUROIMMUN ANA IFA: HEp-20-10 (K070763) and the ImmunoConcepts® °HEp-2000 ANA-Ro IFA (K972145). The sample was found negative with all three test systems.
5
{5}
In addition to the CDC panel, clinical samples positive for ANCA-associated vasculitis, Crohn's disease, ulcerative colitis, celiac disease and infectious diseases (Chlamydia pneumoniae and Epstein-Barr virus) each 10 samples were investigated. The results do not indicate any cross reactivity.
Interfering substances: The effect of interfering substances on assay results were tested by spiking 20 clinical samples with hemoglobin (0, 250 & 500 mg/dL), bilirubin (0, 10 & 40 mg/dL) and triglycerides (0, 500 & 2000 mg/dL). The samples consisted of negative (< 1:40), weak positive and strong positive samples with varying pattern specificities. Interferences from human anti-mouse antibodies (HAMA) and rheumatoid factor (RF) was tested by diluting these samples 1:1 with high positive HAMA serum or a high positive RF serum respectively. The spiked samples were incubated with the EUROIMMUN IFA 40: HEp-20-10 according to the package insert by the same technician on the same day. The deviation in fluorescence intensity level did not exceed ± 1. The results indicated that hemoglobin (up to 1000 mg/dL), bilirubin (up to 40 mg/dL), triglyceride (up to 2000 mg/dL), HAMA and RF at the concentrations indicated have no effect on assay results. No interference was observed.
f. Assay cut-off:
The recommended starting dilution, above which the result is reported as positive and below which the result is reported as negative, is 1:40. The manufacturer suggests performing four-fold dilutions but recommends that each laboratory establish its own titering protocol. The titers of 1:40 and 1:80 are considered low titers, 1:160 and 1:320 are considered medium titers, and 1:640 and greater are considered high titers. Assay cut-off of 1:40 was determined from the literature (Range of antinuclear antibodies in "healthy" individuals, Arthritis & Rheumatism 40, 1997; Guidelines for Clinical Use of the Antinuclear Antibody Test and Tests for Specific Autoantibodies to Nuclear Antigens, Arch Pathol Lab Med. 124, 2000).
2. Comparison studies:
a. Method comparison with predicate device:
Qualitative: A comparison study of patient samples sent for routine ANA testing at an academic research center was performed using a cohort of 200 blinded prospective samples where age and sex information were available. The samples were tested concurrently with EUROIMMUN HEp-20-10 IFA 40 and the predicate ImmunoConcepts HEp-2000 ANA-Ro IFA. The panel consisted of 59 men and 141 women; patient age ranged from 19 to 89 years with an average age of 52 years. The tests were performed (1:40 dilution) in single determinations.
| | ImmunoConcepts
HEp-2000 ANA-Ro IFA | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| EUROIMMUN
IFA 40:HEp-20-10 | Positive | 61 | 6 | 67 |
| | Negative | 5 | 128 | 133 |
| | Total | 66 | 134 | 200 |
% Positive Agreement
61/66 = 92.4%
95% CI: 83.2% - 97.5%
{6}
% Negative Agreement
128/134 = 95.5%
95% CI: 90.5% - 98.3%
Semi-Quantitative/Quantitative: A comparison study of reciprocal titers and patterns was performed using a different cohort of 156 prospective blinded samples from patients sent for routine ANA screening. The samples were tested with EUROIMMUN HEp-20-10 IFA 40 concurrently with the ImmunoConcepts® HEp-2000 ANA-Ro IFA predicate. The panel consisted 62 men and 94 women, average age of 52 years, age ranged from 19 to 90 years. The tests were performed according to the package insert in single determinations.
| | Predicate | | | |
| --- | --- | --- | --- | --- |
| | | Positive | Negative | Total |
| EUROIMMUN IFA 40:HEp-20-10 | Positive | 110 | 0 | 110 |
| | Negative | 0 | 46 | 46 |
| | Total | 110 | 46 | 156 |
Positive % Agreement = 110/110 = 100% (95% CI: 96.7% - 100%)
Negative % Agreement = 46/46 = 100% (95% CI: 92.3% - 100%)
Pattern agreement is tabulated below. Some samples had more than one pattern; each was reported individually; overall agreement was 91.4%.
| | | Observed Pattern | | |
| --- | --- | --- | --- | --- |
| Pattern | n | Predicate | EUROIMMUN | % Agreement |
| Homogenous | 41 | 41 | 41 | 100 |
| Granular/Speckled | 28 | 26 | 28 | 92.9 |
| Nucleolar | 24 | 23 | 22 | 87.5 |
| Centromere | 15 | 15 | 15 | 100 |
| Nuclear Dot | 9 | 9 | 9 | 100 |
| Nuclear Membrane | 3 | 2 | 3 | 67 |
| Cytoplasmic | 28 | 28 | 26 | 93 |
Comparison of reciprocal titers between the predicate and the new assay is shown below. If multiple patterns were reported, those titers are reported separately:
| | Predicate: reciprocal titer | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | <40 | 40 | 80 | 160 | 320 | 640 | 1280 | 2560 | 5120 | 10240 | Total |
| <40 | 46 | | 1 | 2 | | | | | | | 49 |
| 40 | | | 2 | | | | | | | | 2 |
| 80 | | 7 | 7 | 4 | | | | | | | 18 |
| 160 | 2 | | 18 | 13 | 7 | | 2* | | | | 42 |
| 320 | 2 | | | 16 | 14 | 3 | | 1* | | | 36 |
| 640 | | | | | 9 | 5 | 2 | 1* | | | 17 |
| 1280 | | | | | | 4 | 6 | 3 | | | 13 |
| 2560 | | | | | | | 5 | 2 | 1 | 2* | 10 |
| 5120 | | | | | | | | 3 | | | 3 |
| 10240 | | | | | | | | | 1 | 2 | 3 |
| Total | 50 | 7 | 28 | 35 | 30 | 12 | 15 | 10 | 2 | 4 | 193 |
{7}
*HEp-2000 Fluorescent ANA-Ro Test System overexpresses the SS-A/Ro autoantigen in the HEp-2000® cells; samples that contain anti-Ro/SS-A antibodies may show higher titer values on these cells than the values obtained on non-transfected HEp-2 cells. A distinct speckled and nucleolar pattern is seen in 10 - 20% of the interphase nuclei; some cells may show staining in the cytoplasm.
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):
4. Clinical cut-off:
Not applicable.
5. Expected values/Reference range:
A panel of 200 sera from normal healthy adult blood donors of mixed age and gender (155 men, 45 women, mean age 38 years, age range 18-68 years) was tested with the EUROIMMUN IFA 40: HEp-20-10 kit to establish of the assay. The samples were assayed according to the package insert on the same day by three technicians. Prevalence, defined as titers of >1:40, was found about 3.5%. As per the American College of Rheumatology a “prevalence of ANAs in healthy individuals is about 3.0 – 15.0%”.
In a separate study, 138 samples with age and sex data available sent for ANA antibody testing were collected in sequential order for two days. The panel consisted of samples from 53 men and 85 women submitted for a routine health screening. Age ranged from 0 to 89 years with an average age of 51 years. Testing, at initial dilution of 1:40, was performed. Sixteen (16) of the 138 samples were positive for anti-nuclear antibodies using the EUROIMMUN IFA 40: HEp-20-10 kit, resulting in a prevalence of 11.6% (95% C.I.: 6.8% – 18.6%). Clinical diagnosis was not available.
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.