Retrospective clinical samples were used to establish the assay cutoff, evaluate analytical specificity (cross-reactivity), and validate negative percent agreement (NPA) in large cohorts.
Retrospective analysis; Study Period: Pre-October 2019 (negative); 0-29 days post-PCR confirmation (positive)
899 clinical samples: 727 pre-pandemic negative samples and 172 positive samples from hospitalized patients with prior PCR-confirmed SARS-CoV-2 infection; Sample Size: 899
Not applicable for this study
Assay cutoff optimization
Retrospective cross-reactivity study; Study Period: Collected before October 2019
1582 human serum and plasma samples from individuals with antibodies to other microorganisms or autoimmune disorders; Sample Size: 1582
Not applicable for this study
Cross-reactivity
Retrospective observational study; Study Period: Collected before October 2019
3,612 samples (Diagnostic Routine and Blood donors); Sample Size: 3612
Not applicable for this study
Negative Percent Agreement (NPA)
Indications for Use
Elecsys Anti-SARS-CoV-2 S is an electrochemiluminescence immunoassay intended for quantitative detection of total antibodies to SARS-CoV-2 in human serum and plasma (lithium heparin, K2-EDTA, K3-EDTA, and sodium citrate) samples collected on or after 15 days post-symptom onset. The Elecsys Anti-SARS-CoV-2 S assay is intended for use as an aid in identifying individuals with an adaptive immune response to SARS-CoV-2, indicating recent or prior infection. The electrochemiluminescence immunoassay “ECLIA” is intended for use on cobas e immunoassay analyzers.
Device Story
Elecsys Anti-SARS-CoV-2 S is a quantitative, double-antigen sandwich immunoassay (ECLIA) for use on cobas e immunoassay analyzers. Input: 12 µL human serum or plasma. Process: 1st incubation with biotinylated and ruthenium-labeled SARS-CoV-2 recombinant antigens forms sandwich complexes; 2nd incubation with streptavidin-coated microparticles binds complexes to solid phase. Microparticles are magnetically captured on an electrode; voltage application induces chemiluminescent emission measured by a photomultiplier. Results are calculated via a master curve. Used in clinical laboratories by trained personnel. Output: Quantitative antibody concentration (BAU/mL). Clinical utility: Aids identification of adaptive immune response to SARS-CoV-2, indicating recent or prior infection.
Clinical Evidence
Clinical performance evaluated via PPA and NPA. PPA: 118 specimens (≥15 days post-symptom onset) compared to a composite comparator (majority rule of 3 EUA assays); 116/118 reactive, PPA 100% (95% CI 96.79–100%). NPA: 3612 pre-pandemic samples showed 99.97% NPA (95% CI 99.84–100%). A second NPA study of 490 pre-pandemic samples showed 100% NPA (95% CI 99.22–100%).
Technological Characteristics
Electrochemiluminescence immunoassay (ECLIA); double-antigen sandwich principle. Materials: streptavidin-coated microparticles, biotinylated and ruthenium-labeled recombinant SARS-CoV-2 antigens. Analyzers: cobas e 801. Calibration: 2-point on-site calibration with master curve. Traceability: NIBSC 20/136. Software: automated calculation of BAU/mL.
Indications for Use
Indicated for quantitative detection of total antibodies to SARS-CoV-2 in human serum and plasma (lithium heparin, K2-EDTA, K3-EDTA, sodium citrate) in individuals collected on or after 15 days post-symptom onset to identify adaptive immune response indicating recent or prior infection.
Regulatory Classification
Identification
The VITROS Immunodiagnostic Products Anti-SARS-CoV-2 IgG test is a qualitative chemiluminescent immunoassay intended for the detection of IgG antibodies to SARS-CoV-2 in human serum and plasma (K2-EDTA and K3-EDTA). It is performed on the VITROS ECi/ECiQ/3600 Immunodiagnostic Systems and the VITROS 5600/XT 7600 Integrated Systems. The test is intended for use as an aid in identifying individuals with an adaptive immune response to SARS-CoV-2, indicating recent or prior infection.
Predicate Devices
VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Reagent Pack, VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Calibrators (DEN210040)
Submission Summary (Full Text)
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
# DECISION SUMMARY
# ASSAY AND INSTRUMENT
# I Background Information:
A 510(k) Number
K252280
B Applicant
Roche Diagnostics
C Proprietary and Established Names
Elecsys Anti-SARS-CoV-2 S
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QVP | Class II | 21 CFR 866.3983 - SARS-Cov-2 Serology Test | MI - Microbiology |
| JJX | Class I | 21 CFR 862.1660 - Quality control material (assayed and unassayed) | CH - Clinical Chemistry |
# II Submission/Device Overview:
A Purpose for Submission:
To obtain clearance for a new device.
B Measurand:
Total antibodies against SARS-CoV-2.
C Type of Test:
Electrochemiluminescence immunoassay (ECLIA).
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
### III Intended Use/Indications for Use:
#### A Intended Use(s):
Elecsys Anti-SARS-CoV-2 S is an electrochemiluminescence immunoassay intended for quantitative detection of total antibodies to SARS-CoV-2 in human serum and plasma (lithium heparin, K2-EDTA, K3-EDTA, and sodium citrate) samples collected on or after 15 days post-symptom onset. The Elecsys Anti-SARS-CoV-2 S assay is intended for use as an aid in identifying individuals with an adaptive immune response to SARS-CoV-2, indicating recent or prior infection.
The electrochemiluminescence immunoassay “ECLIA” is intended for use on cobas e immunoassay analyzers.
#### B Indication(s) for Use:
NA
#### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
#### D Special Instrument Requirements:
For use on cobas e 801 analyzer.
### IV Device/System Characteristics:
#### A Device Description:
The Elecsys Anti-SARS-CoV-2 S is an automated two-step double-antigen sandwich immunoassay using streptavidin microparticles, a biotinylated recombinant SARS-CoV-2-specific antigen and a separate SARS-CoV-2-specific recombinant antigen labeled with a ruthenium complex for electrochemiluminescence detection. The results are determined automatically by the software comparing the electrochemiluminescence signal obtained from the reaction product of the sample with the signal of the cutoff value previously obtained by calibration to establish reactivity, and then separately converting that signal intensity from the sample into a final concentration using a 2-point calibration and a master curve from the reagent barcode.
The assay is performed using the Elecsys Anti-SARS-CoV-2 S Reagent Pack in combination with the CalSet Anti-SARS-CoV-2 S calibrator and the PreciControl Anti-SARS-CoV-2 S controls.
The Elecsys Anti-SARS-CoV-2 S Reagent Pack contains:
- M: Streptavidin-coated microparticles.
- R1: Biotin-labeled SARS-CoV-2-S recombinant Ag.
- R2: Ruthenium complex-labeled SARS-CoV-2-S recombinant Ag.
K252280 - Page 2 of 20
{2}
The following additional materials are required, and provided separately:
- CalSet Anti-SARS-CoV-2 S: Two-level positive calibrators (ACOV2S Cal1 and ACOV2S Cal2:) containing anti-SARS-CoV-2 antibody in human serum spiked with serum from anti-SARS-CoV-2-S positive donors in 2 concentration ranges.
- PreciControl Anti-SARS-CoV-2 S - Two-level quality controls, PC ACOV2S1 (non-reactive), and PC ACOV2S2 (reactive)
- Diluent Universal for sample dilution
- Instrument reagents - System solutions for processing/measurement and cleaning solutions for maintenance.
The following additional materials are optional, not provided with the assay:
- CalCheck Anti-SARS-CoV-2 S five-level calibration verification material:
o CalCheck 1 non-reactive in analyte free human serum and
o CalCheck 2 to 5, containing serum spiked with human serum from anti-SARS-CoV-2 S positive donors in varying concentrations.
### B Principle of Operation:
This assay is based on the sandwich principle. Total duration of assay is 18 minutes.
- 1st incubation: 12 μL of sample, biotinylated SARS-CoV-2 S-RBD-specific recombinant antigen and SARS-CoV-2 S-RBD-specific recombinant antigen labeled with a ruthenium complex a) form a sandwich complex.
- 2nd incubation: After addition of streptavidin-coated microparticles, the complex becomes bound to the solid phase via interaction of biotin and streptavidin.
- The reaction mixture is aspirated into the measuring cell where the microparticles are magnetically captured onto the surface of the electrode. Unbound substances are then removed with ProCell II M. Application of a voltage to the electrode then induces chemiluminescent emission which is measured by a photomultiplier.
- Results are determined via a calibration curve which is instrument- specifically generated by 2-point calibration and a master curve provided via the e-barcode.
a)Tris(2,2'-bipyridyl)ruthenium(II)-complex (Ru(bpy)F)
Interpretation of Results: The cobas e system automatically calculates the analyte concentration of each sample in the international standard units BAU/mL (binding antibody units).
K252280 - Page 3 of 20
{3}
Table 1. Elecsys Anti-SARS-CoV-2 S Results Interpretation
| Result | Interpretation | Description |
| --- | --- | --- |
| < 0.40 BAU/mL | Negative. Result below the lower limit of quantitation (LLOQ) of the method. Numerical result is reported outside the laboratory indicating that the result is below 0.40 BAU/mL. | Antibodies for SARS-CoV-2 are not detected |
| ≥ 0.40 – < 0.80 BAU/mL | Negative. Result above the LLOQ but below the assay cutoff. Numerical result is reported outside the laboratory, with numeric value within the analytical measuring interval (AMI). | Antibodies to SARS-CoV-2 are detected at levels above the LLoQ and below the assay cutoff. At this level of antibodies, samples are negative. |
| ≥ 0.80 BAU/mL – ≤ 250 BAU/mL | Positive. Numerical result is reported outside the laboratory, with numeric value within the analytical measuring interval (AMI) | Antibodies for SARS-CoV-2 are detected |
| > 250 BAU/mL – ≤ 100000 BAU/mL | Positive. Numerical result is reported outside the laboratory, with numeric value within the extended measuring interval (EMI, specimen requires dilution per IFU) | Antibodies for SARS-CoV-2 are detected |
| > 100000 BAU/mL | Positive. Report outside the laboratory indicates that the result is above 100000 BAU/mL | Antibodies for SARS-CoV-2 are detected |
### C Instrument Description Information:
1. Instrument Name:
Cobas e 801 analyzer
2. Specimen Identification:
The Elecsys Anti-SARS-CoV-2-S is intended for use with Serum, lithium-heparin, dipotassium EDTA (K2-EDTA), tripotassium EDTA (K3-EDTA), and sodium citrate plasma specimens.
3. Specimen Sampling and Handling:
- Samples may be stored for up to 14 days at room temperature (15-25 °C) or at 2 - 8 °C.
- Samples may be stored frozen at ≤ -20 °C for 3 months.
- Samples may be subjected to up to three freeze-thaw cycles.
K252280 - Page 4 of 20
{4}
# 4. Calibration:
CalSet Anti-SARS-CoV-2 S is used for calibrating the Elecsys Anti-SARS-CoV-2 S assay on cobas e immunoassay analyzers. The CalSet contains anti-SARS-CoV-2 antibody in human serum spiked with serum from anti-SARS-CoV-2-S positive donors in 2 concentration ranges (Cal1 and Cal2).
The calibrator is supplied lyophilized and requires reconstitution with 1.0 mL of distilled or deionized water. Results are calculated in BAU/mL based on standardization against the International Standard for anti-SARS-CoV-2 immunoglobulin (human), NIBSC code: 20/136.
The assay results are determined using an instrument-specific calibration curve that combines a master curve (provided through the reagent kit's electronic barcode) with a 2-point on-site calibration.
# 5. Quality Control:
The PreciControl Anti-SARS-CoV-2 S controls are provided separately and contain Control 1 (PC ACOV2S1): Anti-SARS-CoV-2 non-reactive human serum control and Control 2 (PC ACOV2S2): Anti-SARS-CoV-2 reactive human serum control. Target values and ranges were determined by Roche and available electronically or via barcodes.
# V Substantial Equivalence Information:
# A Predicate Device Name(s):
VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Reagent Pack, VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Calibrators
# B Predicate 510(k) Number(s):
DEN210040
# C Comparison with Predicate(s):
| Device & Predicate Device(s): | Predicate Device DEN210040 | Candidate Device K252280 |
| --- | --- | --- |
| Device Trade Name | VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Reagent Pack, VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Calibrators | Elecsys Anti-SARS-CoV-2 S |
| Intended Use/Indications For Use | The VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total Reagent Pack when used in combination with the VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total | Elecsys Anti-SARS-CoV-2 S is an electrochemiluminescence immunoassay intended for quantitative detection of total antibodies to SARS-CoV-2 in human serum and plasma (lithium heparin, K₂-EDTA, |
K252280 - Page 5 of 20
{5}
| | Calibrator is a chemiluminescent immunoassay intended for the qualitative detection of total antibodies to SARS-CoV-2 in human serum and plasma (K2-EDTA, K3-EDTA and lithium heparin) samples collected on or after 15 days post-symptom onset using the VTTROS ECi/ECiQ/3600 Immunodiagnostic Systems and the VITROS 5600/XT 7600 Integrated Systems. The VITROS Immunodiagnostic Products Anti-SARS-CoV-2 Total test is intended for use as an aid in identifying individuals with an adaptive immune response to SARS-CoV-2, indicating recent or prior infection. | K_{3}-EDTA, and sodium citrate) samples collected on or after 15 days post-symptom onset. The Elecsys Anti-SARS-CoV-2 S assay is intended for use as an aid in identifying individuals with an adaptive immune response to SARS-CoV-2, indicating recent or prior infection. The electrochemiluminescence immunoassay “ECLIA” is intended for use on **cobas e** immunoassay analyzers. |
| --- | --- | --- |
| Regulation Number | 21 CFR 866.3983 | Same |
| Regulatory Class | II | Same |
| Product Code | QVP | Same |
| Analyte | Total anti-SARS-CoV-2 antibodies | Total anti-SARS-CoV-2 antibodies |
| Technology | CLIA | ECLIA, similar chemiluminescence detection as CLIA with difference in light signal generation. |
| Streptavidin/ Biotin Technology | Yes | Same |
| Sample Type/ Matrix | Serum, Li-Heparin, K2-EDTA, K3-EDTA | Serum, Li-Heparin, K2-EDTA, K3-EDTA Sodium Citrate |
| Controls(s) | 1 non-reactive, 1 reactive | 1 non-reactive, 1 reactive |
| Analyte Detection | Qualitative detection of total antibodies to SARS-CoV-2 | Quantitative detection of total antibodies to SARS-CoV-2 |
| Test principle | Two-stage immunometric technique with HRP-labeled antigen | Double-antigen sandwich with ruthenium complex |
| Assay Duration | 37 min incubation, 48 min to first result | 18 minutes total |
| Sample Volume | 80 μL | 12 μL |
K252280 - Page 6 of 20
{6}
| Interpretation of Results | S/C < 1.0: Non-reactive S/C ≥ 1.0: Reactive | < 0.40 BAU/mL: Negative. Result below the lower limit of quantitation (LLOQ) of the method. Numerical result is reported outside the laboratory indicating that the result is below 0.40 BAU/mL. ≥ 0.40 – < 0.80 BAU/mL: Negative. Result above the LLOQ but below the assay cutoff. Numerical result is reported outside the laboratory, with numeric value within the analytical measuring interval (AMI). ≥ 0.80 BAU/mL – ≤ 250 BAU/mL BAU/mL: Positive. Numerical result is reported outside the laboratory, with numeric value within the analytical measuring interval (AMI) > 250 BAU/mL – ≤ 100000 BAU/mL: Positive. Numerical result is reported outside the laboratory, with numeric value within the extended measuring interval (EMI, specimen requires dilution per IFU) > 100000 BAU/mL: Positive. Report outside the laboratory indicates that the result is above 100000 BAU/mL |
| --- | --- | --- |
| Platform | VITROS ECi/ECiQ/3600/5600/XT 7600 Systems | **cobas e 801** analyzer |
| Calibrators | 2 calibrators (positive and negative) | 2 positive calibrators: CalSet with 2 concentration ranges (Cal1, Cal2) |
| Reagent Components | - Coated wells with SARS-CoV-2 antigen - HRP-labeled conjugate - Assay reagent buffer | - Streptavidin-coated microparticles - Biotinylated RBD antigen - Ruthenium-labeled RBD antigen |
K252280 - Page 7 of 20
{7}
## VI Standards/Guidance Documents Referenced:
- CLSI EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved
- Guideline - Third Edition
- CLSI EP06 Evaluation of the Linearity of Quantitative Measurement Procedures- Second Edition
- CLSI EP07 Interference testing in Clinical Chemistry- Third Edition
- CLSI EP12-A2 User Protocol for Evaluation of Qualitative Test Performance; Approved Guideline - Second Edition
- ISO 17511 Second edition 2020-04 In vitro diagnostic medical devices – Requirements for establishing metrological traceability of values assigned to calibrators trueness control materials and human samples.
## VII Performance Characteristics (if/when applicable):
### A Analytical Performance:
#### 1. Precision/Reproducibility:
Within-Laboratory Precision: A within-laboratory precision study was performed using 2 lots of the Elecsys Anti-SARS-CoV-2 S reagent packs, 2 lots of the CalSet Anti-SARS-CoV-2 S calibrators, and one cobas e 801 analyzer. One PreciControl PC ACOV2S2 (Positive Control, PC) and 6 human serum pools were tested in 3 replicates 2 separate times per day on 5 days using 4 reagent pack lot/calibrator lot combinations. The within-laboratory precision data are summarized below in Table 2.
Table 2. Elecsys Anti-SARS-CoV-2 S assay Within-Laboratory Precision
| Sample | Mean (BAU/mL) | N | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Calibrator Lot | | Between-Reagent Lot | | Overall, Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| 1 | 0.708 | 120 | 0.0141 | 1.99 | 0.00752 | 1.06 | 0.0018 | 0.255 | 0.00274 | 0.387 | 0.0214 | 3.02 | 0.0269 | 3.8 |
| 2 | 0.904 | 120 | 0.012 | 1.33 | 0.0147 | 1.62 | 0 | 0 | 0.00207 | 0.229 | 0.00421 | 0.466 | 0.0195 | 2.16 |
| 3 | 13.2 | 120 | 0.106 | 0.805 | 0.0832 | 0.63 | 0.0877 | 0.663 | 0 | 0 | 0.199 | 1.51 | 0.256 | 1.94 |
| 4 | 122 | 120 | 1.17 | 0.958 | 0 | 0 | 0.765 | 0.628 | 0 | 0 | 0.357 | 0.293 | 1.44 | 1.18 |
| 5 | 206 | 120 | 1.50 | 0.731 | 0.558 | 0.272 | 1.31 | 0.64 | 0 | 0 | 0 | 0 | 2.07 | 1.01 |
| 6 | 231 | 120 | 2.29 | 0.988 | 1.41 | 0.611 | 0.372 | 0.161 | 0 | 0 | 2.60 | 1.13 | 3.76 | 1.63 |
| PC | 9.16 | 120 | 0.078 | 0.852 | 0.0959 | 1.05 | 0.0463 | 0.506 | 0 | 0 | 0.0347 | 0.347 | 0.136 | 1.48 |
Reproducibility Study (multi-site precision): A 5-day reproducibility study was conducted at 3 sites (two external and one internal site), using 7 human serum pool samples (1 negative and 6 positive) and 2 control samples (1 negative and 1 positive) in cobas e 801 analyzers. Three aliquots per sample were evaluated in 2 runs per day over 5 days using one lot of reagent packs, calibrators, and controls per site.
K252280 - Page 8 of 20
{8}
Table 3. Elecsys Anti-SARS-CoV-2 S assay Reproducibility
| Sample | Mean (BAU/mL) | N | Repeatability | | Between-Run | | Between-Day | | Between-Site | | Reproducibility | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | % CV | SD | % CV | SD | % CV | SD | % CV | SD | % CV |
| 1 | 0.727 | 90 | 0.0441 | 6.06 | 0 | 0 | 0 | 0 | 0 | 0 | 0.0441 | 6.06 |
| 2 | 0.913 | 90 | 0.0152 | 1.67 | 0.00333 | 0.364 | 0.00844 | 0.924 | 0.0102 | 1.12 | 0.0205 | 2.24 |
| 3 | 13.1 | 90 | 0.14 | 1.06 | 0.0578 | 0.441 | 0.0696 | 0.531 | 0.101 | 0.769 | 0.194 | 1.48 |
| 4 | 123 | 90 | 1.43 | 1.16 | 0.741 | 0.6 | 0.678 | 0.549 | 1.01 | 0.82 | 2.02 | 1.63 |
| 5 | 207 | 90 | 2.06 | 0.992 | 1.13 | 0.544 | 1.23 | 0.591 | 1.9 | 0.918 | 3.26 | 1.57 |
| 6 | 235 | 90 | 2.43 | 1.03 | 1.35 | 0.574 | 1.2 | 0.511 | 1.75 | 0.743 | 3.5 | 1.49 |
| PC | 9.23 | 90 | 0.11 | 1.19 | 0.0643 | 0.696 | 0.072 | 0.78 | 0.0165 | 0.179 | 0.147 | 1.59 |
*Reproducibility metrics (SD, CV) were not calculated for the negative samples, as their concentrations fell below the assay's quantifiable range.
# 2. Linearity:
A linearity study was conducted to establish the analytical measuring interval (AMI) of the Elecsys Anti-SARS-CoV-2 assay. Six high concentration native samples (3 sodium citrate plasma, 3 serum) were serially diluted with their respective negative matrix to create 15 dilutions spanning the concentration range from ~0.2 BAU/mL to ~280-300 BAU/mL (Serum samples were diluted with negative serum, and plasma samples were diluted with negative plasma). Each sample dilution was measured in one run with four replicates using one reagent/calibrator lot combination. Linearity was assessed by calculating deviations from the best-fitted straight line for each dilution level. The study employed weighted least squares regression to generate the best fitted straight line, with deviations calculated as the difference between measured mean values and predicted values from this regression line.
The linearity for the Elecsys Anti-SARS-CoV-2 S assay was demonstrated across the analytical measuring range of 0.4 BAU/mL to 250 BAU/mL using both serum and plasma samples.
# 3. Analytical Specificity/Interference:
# a. Potential Cross-Reactivity:
The Elecsys Anti-SARS-CoV-2 S assay was evaluated for potential cross-reactivity by testing 1582 human serum and plasma samples collected before October 2019 from individuals with antibodies to other microorganisms or autoimmune disorders. Testing was performed on cobas e 801 analyzers in single determination. The summary of the data is shown in the following table.
K252280 - Page 9 of 20
{9}
Table 4. Elecsys Anti-SARS-CoV-2 S assay Cross-Reactivity study
| Disease/Infectious agent Positive Sera | Number of Samples Tested (n) | Elecsys Anti-SARS-CoV-2 S Results | |
| --- | --- | --- | --- |
| | | Non-reactive | Reactive |
| **SARS-CoV-2 related:** | | | |
| MERS CoV (anti-S1 IgG+) | 51 | 51 | 0 |
| Common Corona virus panels^{a} | 151 | 151 | 0 |
| SARS-CoV-1 IgG | 10 | 10 | 0 |
| **Infectious respiratory diseases:** | | | |
| Bordetella pertussis | 39 | 39 | 0 |
| Chlamydia pneumonia | 36 | 36 | 0 |
| Common cold panel | 21 | 21 | 0 |
| Enterovirus (IgG+ IgM+) | 35 | 35 | 0 |
| Haemophilus influenzae B | 75 | 75 | 0 |
| Influenza A (IgM+ IgG+ IgA+) | 40 | 40 | 0 |
| Influenza B (IgG+ IgM+ IgA+) | 45 | 45 | 0 |
| Influenza vaccines | 25 | 25 | 0 |
| Metapneumovirus (MPV) | 15 | 14 | 1** |
| Mycobacterium tuberculosis (IgG) | 15 | 15 | 0 |
| Mycoplasma pneumoniae (IgG+ IgM+) | 46 | 46 | 0 |
| Parainfluenza | 82 | 82 | 0 |
| Pneumocystis jirovecii IgG | 14 | 14 | 0 |
| Pseudomonas aeruginosa | 15 | 15 | 0 |
| Respiratory syncytial virus | 51 | 51 | 0 |
| Streptococcus pneumoniae | 15 | 15 | 0 |
| **Other infectious diseases:** | | | |
| Adenovirus | 25 | 25 | 0 |
| Borrellia | 6 | 6 | 0 |
| Candida albicans | 13 | 13 | 0 |
| Chlamydia trachomatis | 12 | 12 | 0 |
| CMV acute (IgM+ IgG+) | 86 | 86 | 0 |
| E. coli (anti-E. coli reactive) | 10 | 10 | 0 |
| EBV acute (IgM+ VCA IgG+) | 106 | 106 | 0 |
K252280 - Page 10 of 20
{10}
| Disease/Infectious agent Positive Sera | Number of Samples Tested (n) | Elecsys Anti-SARS-CoV-2 S Results | |
| --- | --- | --- | --- |
| | | Non-reactive | Reactive |
| Gonorrhea (Tripper) | 5 | 5 | 0 |
| HAV acute (IgM+) | 10 | 10 | 0 |
| HAV late (IgG+) | 15 | 15 | 0 |
| HAV vaccinees | 15 | 15 | 0 |
| HBV acute | 12 | 12 | 0 |
| HBV chronic | 12 | 12 | 0 |
| HBV vaccinees | 15 | 15 | 0 |
| HCV | 50 | 50 | 0 |
| HEV | 12 | 12 | 0 |
| HIV infection | 10 | 10 | 0 |
| HSV acute (IgM+) | 24 | 24 | 0 |
| HTLV | 6 | 6 | 0 |
| Legionella (IgGAM+) | 7 | 7 | 0 |
| Listeria | 6 | 6 | 0 |
| Measles | 10 | 10 | 0 |
| Mumps | 14 | 14 | 0 |
| Parvovirus B19 | 30 | 30 | 0 |
| Plasmodium falciparum (Malaria) | 8 | 8 | 0 |
| Rubella acute (IgM+, IgG+) | 12 | 12 | 0 |
| Staphylococcus epidermis | 15 | 15 | 0 |
| Streptococcus pyogenes | 15 | 15 | 0 |
| Toxoplasma gondii (IgM+, IgG+) | 8 | 8 | 0 |
| Treponema pallidum (Syphilis) | 62 | 62 | 0 |
| VZV (Varicella zoster) | 30 | 30 | 0 |
| **Auto-immune diseases:** | | | |
| AMA (anti-mitochondrial antibodies) | 30 | 30 | 0 |
| ANA (anti-nuclear antibodies) | 17 | 17 | 0 |
| Hemophiliacs | 15 | 15 | 0 |
| RA (rheumatoid arthritis) | 10 | 10 | 0 |
| SLE (systemic lupus erythematosus) | 10 | 10 | 0 |
K252280 - Page 11 of 20
{11}
| Disease/Infectious agent Positive Sera | Number of Samples Tested (n) | Elecsys Anti-SARS-CoV-2 S Results | |
| --- | --- | --- | --- |
| | | Non-reactive | Reactive |
| **Hepatic diseases:** | | | |
| Alcohol induced hepatitis/cirrhosis | 13 | 13 | 0 |
| Drug induced hepatitis/cirrhosis | 10 | 10 | 0 |
| Fatty liver | 10 | 10 | 0 |
| Liver cancer | 10 | 10 | 0 |
| Non-viral liver disease | 15 | 15 | 0 |
| **Total** | **1582** | **1581** | **1** |
*One out of 15 samples with human metapneumovirus showed a false positive result
aCommon Coronavirus panel includes pre-pandemic samples, which showed serologic reactivity to at least 1 of the endemic Coronavirus HKU1, NL63, 229E, or OC43.
Cross-reactivity with antibodies to Rhinovirus has not been evaluated, and the potential for false positive results in this population is unknown.
# b. Potentially Endogenous Interfering Substances:
The Elecsys Anti-SARS-CoV-2 S assay was evaluated for potential interference caused by endogenous substances using serum and K2-EDTA plasma samples with the following SARS-CoV-2 antibodies concentrations: one positive sample (>50.0 BAU/mL), one low positive sample (between 0.8 and 5.0 BAU/mL), and one negative sample (<0.8 BAU/mL).
No interference was observed for the following potential endogenous substances at the following concentrations.
Table 5. Endogenous Interfering Substances Evaluated
| Substance | Concentrations Tested |
| --- | --- |
| Biotin | 1200 ng/mL |
| Intralipid | 2000 mg/dL |
| Bilirubin | 66.0 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Rheumatoid Factors | 1200 IU/mL |
| Human IgG | 70.0 mg/mL |
| Human IgM | 10.0 mg/mL |
| Human IgA | 16.0 mg/mL |
| Human Serum Albumin | 70.0 mg/mL |
| Cholesterol | 400.0 mg/dL |
K252280 - Page 12 of 20
{12}
| Triglycerides | 2000 mg/dL |
| --- | --- |
| Anti-Nuclear Antibody (ANA) | 1:1280 titer |
# c. Potentially Exogenous Interfering Substances:
The Elecsys Anti-SARS-CoV-2 S assay was evaluated for potential interference caused by exogenous substances using one negative sample and one low positive sample. The acceptance criterion was recovery within 100 ±10% of reference. No significant interference was observed for the substances at the concentrations listed in the table below, except for Itraconazole and Ritonavir which showed interference above indicated concentrations.
Table 6. Exogenous Interfering Substances and Concentrations with NO Interference in assay performance
| Substance | Concentrations Tested |
| --- | --- |
| Acetylcysteine | 150 mg/L |
| Acetylsalicylic acid | 30 mg/L |
| Ampicillin | 75 mg/L |
| Ascorbic acid | 52.5 mg/L |
| Cefoxitin | 750 mg/L |
| Doxycycline | 18 mg/L |
| Heparin | 3300 IU/L |
| Levodopa | 7.5 mg/L |
| Methyldopa | 22.5 mg/L |
| Metronidazole | 123 mg/L |
| Rifampicin | 48 mg/L |
| Acetaminophen | 156 mg/L |
| Cyclosporine | 1.8 mg/L |
| Ibuprofen | 219 mg/L |
| Theophylline | 60 mg/L |
| Phenylbutazone | 321 mg/L |
| Itraconazole | 15 mg/L |
| Special Drugs Tested: | |
| Zanamivir | 0.006 mg/mL |
| Oseltamivir | 0.090 mg/mL |
| Ceftriaxone | 2.40 mg/mL |
| Levofloxacin | 0.300 mg/mL |
| Meropenem | 3.60 mg/mL |
| Ribavirin | 0.720 mg/mL |
| Azithromycin | 0.300 mg/mL |
| Lopinavir | 0.720 mg/mL |
| α-interferon 2b | 3000 IU/mL |
K252280 - Page 13 of 20
{13}
| Peramivir | 0.360 mg/mL |
| --- | --- |
| Tobramycin | 0.360 mg/mL |
| Histamine Dihydrochloride | 0.0006 mg/mL |
| Tocilizumab | 0.384 mg/mL |
| α-interferon 2a | 43200 IU/mL |
| Hydroxychloroquinsulfate | 0.240 mg/mL |
| Remdesivir | 0.120 mg/mL |
| Ritonavir | 0.160 mg/mL |
#### 4. Assay Reportable Range:
The Elecsys Anti-SARS-CoV-2 S assay has the following ranges:
• AMI (Analytical Measuring Interval): 0.40 to 250 BAU/mL
• EMI (Extended Measuring Interval): 250 to 100,000 BAU/mL
• Reportable Interval: 0.40 to 100,000 BAU/mL
The analytical measuring interval was validated through comprehensive studies including establishing the limit of quantitation, and demonstrating precision, linearity using clinical samples, and accuracy studies using certified reference material traceable to the First International Standard for anti-SARS-CoV-2 immunoglobulin (NIBSC code: 20/136).
The assay's EMI (Extended measuring interval) is 250-100,000 BAU/mL based on automated dilutions (1:30 initial, 1:400 for high samples).
#### 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Calibrator Traceability:
The Elecsys Anti-SARS-CoV-2 S assay was standardized against the First International Standard Material for anti-SARS-CoV-2 immunoglobulin (NIBSC 20/136) with results reported in BAU/mL units.
Specimen Stability:
Specimen stability was evaluated in serum and plasma matrices (K2-EDTA, lithium heparin and sodium citrate) using the Elecsys Anti-SARS-CoV-2 S assay on the cobas e 801 analyzer. Storage conditions tested included room temperature (15-25°C), refrigerated (2-8°C), frozen ( \( \leq \) -20°C), and freeze-thaw cycles.
Native negative samples and low positive samples prepared by spiking with specimens containing high-concentrations of anti-SARS-CoV-2 antibodies were used to achieve target concentrations across the analytical range. Percent difference to baseline was calculated for each storage condition.
K252280 - Page 14 of 20
{14}
Results support specimen stability for
○ 14 days at 15-25°C and 2-8°C,
○ 3 months at -20°C (±5°C),
○ 3 freeze-thaw cycles
# 6. Detection Limit:
The limit of blank (LoB), limit of detection (LoD), and Lower Limit of Quantitation (LLoQ) for the
Elecsys Anti-SARS-CoV-2 S assay were evaluated using 3 lots of Elecsys Anti-SARS-CoV-2 S reagent packs on one cobas e 801 analyzer over three days.
Table 7. Elecsys Anti-SARS-CoV-2 S assay Detection Limits
| Parameter | BAU/mL |
| --- | --- |
| LoB^{a} | 0.30 |
| LoD^{b} | 0.35 |
| LLoQ^{c} | 0.40 |
$^{a}$The LoB represents the 95th percentile value from n ≥ 60 measurements of analyte-free samples over several independent series, defined as the concentration at which there is a 95% probability that a sample is analyte-free.
$^{b}$The LoD represents the concentration at which there is a 95% probability that a sample contains analyte, determined based on the LoB and the standard deviation of low concentration samples using the formula: LoD = LoB + 1.645 × SD total.
$^{c}$The LLoQ is defined as the lowest amount of analyte in a sample that can be accurately quantified with a maximum allowable total error of 20%, considering the CV of result precision and systematic bias to the First International Standard for anti-SARS-CoV-2 immunoglobulin (NIBSC code: 20/136). The The LLoQ has been determined using low concentration of anti-SARS-CoV-2 samples.
# 7. Assay Cut-Off:
The Elecsys Anti-SARS-CoV-2 S assay cutoff was established using 899 clinical samples: 727 pre-pandemic negative samples (collected before October 2019) and 172 positive samples collected from hospitalized patients with prior PCR-confirmed SARS-CoV-2 infection (collected 0-29 days post-PCR confirmation). Receiver Operating Characteristic (ROC) analysis was performed to determine the optimal assay cutoff value that maximized both sensitivity and specificity. The resulting ROC curve demonstrated high sensitivity and specificity for the Elecsys Anti-SARS-CoV-2 S assay at the established cutoff of 0.8 BAU/mL.
K252280 - Page 15 of 20
{15}
## 8. Hook Effect:
A study was performed to demonstrate that the Elecsys Anti-SARS-CoV-2 S assay is not susceptible to high dose hook effect, a phenomenon in which excessively high antibody levels form immune complexes that saturate the assay and produce false non-reactive results. Four plasma samples with high titer for the analyte (analyte concentrations between 1200 and 1500 BAU/mL) were each serially diluted with an anti-SARS-CoV-2 antibody negative plasma sample to generate a 12-member dilution series. Each dilution was tested in duplicate with one kit lot of the Elecsys Anti-SARS-CoV-2 S assay on the **cobas e 801** analyzer. The results demonstrate the absence of high-dose hook effect for the Elecsys Anti-SARS-CoV-2 S assay across the tested concentration range.
## 9. Accuracy:
An analytical accuracy study was conducted to evaluate the recovery and linearity of the Elecsys Anti-SARS-CoV-2 S assay using the closest calibrator material to the certified reference material (CCRM) in Roche's metrological traceability calibration hierarchy.
The CCRM was serially diluted in anti-SARS-CoV-2 negative serum to create 10 dilution levels spanning 0.286 to 278 BAU/mL (covering the entire AMI from 5-20% below the lower limit of quantitation, the LLoQ, to 5-20% above the upper limit of quantitation, the ULoQ). The study was conducted using one reagent pack lot with two calibrator lots across two **cobas e 801** analyzers, generating four reagent/calibrator/analyzer combinations. Each dilution level was tested with 6 replicates.
**Table 8.** Elecsys Anti-SARS-CoV-2 S Accuracy Study Summary
| Combination | Recovery Range | Linearity Deviation Range | Slope | Pearson's r | R^{2} |
| --- | --- | --- | --- | --- | --- |
| 1 | 96 – 100% | -4.9% to 6.2% | 1.041 | 1.00 | 0.999 |
| 2 | 96 – 100% | -5.0% to 9.9% | 1.049 | 1.00 | 1.00 |
| 3 | 96 – 100% | -5.0% to 6.1% | 1.059 | 1.00 | 0.999 |
| 4 | 96 – 100% | -3.8% to 8.2% | 1.061 | 1.00 | 0.999 |
The accuracy study confirms that the Elecsys Anti-SARS-CoV-2 S assay provides accurate quantitative results traceable to the First International Standard for anti-SARS-CoV-2 immunoglobulin (NIBSC code: 20/136) across the entire analytical measuring interval.
## 10. Carry-Over:
N/A
K252280 - Page 16 of 20
{16}
## B Comparison Studies:
### 1. Method Comparison:
The clinical performance of the Elecsys Anti-SARS-CoV-2 S assay was evaluated at three testing sites using 614 unique specimens retrospectively collected from two populations. Population 1 consisted of 124 specimens collected from individuals with prior confirmed SARS-CoV-2 infection based on positive RT-PCR results using highly sensitive FDA-cleared or authorized assays. These specimens were collected in the United States between April 17, 2020, to August 27, 2020. Population 2 consisted of 490 specimens collected prior to January 18, 2020 (before the widespread outbreak of COVID-19 in the US).
Of the 124 specimens in Population 1, 1 specimen was collected 0–7 days from symptom onset, 5 specimens were collected 8–14 days from symptom onset, and 118 specimens were collected ≥15 days from symptom onset.
Both populations demonstrated diverse representation across age groups (21-79 years), sex distribution (population 1: 38.7% male, 61.3% female; population 2: 42.2% male, 57.8% female), and varied racial/ethnic backgrounds.
**Table 9.** Demographic Characteristics by Days Post Symptom Onset: Population 1 (n=124)
| Characteristic | 0-7 days (n=1) | 8-14 days (n=5) | ≥15 days (n=118) | Total (n=124) |
| --- | --- | --- | --- | --- |
| **Race, n (%)** | | | | |
| White | 1 (100.0) | 4 (80.0) | 30 (25.42) | 35 (28.23) |
| Black or African American | 0 (0.0) | 0 (0.0) | 20 (16.95) | 20 (16.13) |
| Asian | 0 (0.0) | 0 (0.0) | 1 (0.85) | 1 (0.81) |
| Other | 0 (0.0) | 0 (0.0) | 2 (1.69) | 2 (1.61) |
| Unknown | 0 (0.0) | 1 (20.0) | 65 (55.08) | 66 (53.23) |
| **Ethnicity, n (%)** | | | | |
| Not Hispanic or Latino | 0 (0.0) | 0 (0.0) | 13 (11.02) | 13 (10.48) |
| Hispanic or Latino | 1 (100.0) | 5 (100.0) | 82 (69.49) | 88 (70.97) |
| Unknown | 0 (0.0) | 0 (0.0) | 23 (19.49) | 22 (18.55) |
| **Sex, n (%)** | | | | |
| Male | 1 (100.00) | 2 (40.00) | 45 (38.14) | 48 (38.71) |
| Female | 0 (0.00) | 3 (60.00) | 73 (61.86) | 76 (61.29) |
| **Age** | | | | |
| Mean (SD) | N/A | 30.20 (12.52) | 43.04 (11.74) | 42.44 (11.97) |
| Median | N/A | 27 | 43 | 42 |
| Range | N/A | 21-52 | 22-77 | 21-77 |
| 25th - 75th Percentile | N/A | 23-28 | 35-50 | 32-50 |
**Note:** All samples were plasma matrix. SD = Standard Deviation; N/A = Not applicable for single observation.
K252280 - Page 17 of 20
{17}
Clinical performance was evaluated by comparing the Elecsys Anti-SARS-CoV-2 S assay results to a composite comparator method comprising three SARS-CoV-2 serology assays. SARS-CoV-2 seropositivity was determined using majority rule ($\geq 2$ out of 3 positive results) from the composite comparator. Positive percent agreement (PPA) and negative percent agreement (NPA) with respective 95% confidence intervals were calculated.
The following tables present the PPA and NPA of the Elecsys Anti-SARS-CoV-2 S assay compared to the composite comparator method.
**Table 10.** Performance of Elecsys Anti-SARS-CoV-2 S - Population 1
| Days Post Symptom Onset | Elecsys Anti- SARS- CoV-2 S | Composite Comparator | | PPA [%] (95% CI) | NPA [%] (95% CI) |
| --- | --- | --- | --- | --- | --- |
| | | Reactive | Non-Reactive | | |
| 0-7 days | Reactive | 0 | 0 | - | 100.00% (1/1) (20.65% - 100.00%) |
| | Non-Reactive | 0 | 1 | | |
| | **Total** | 0 | 1 | | |
| 8-14 days | Reactive | 3 | 1 | 100.00% (3/3) (43.85% - 100.00%) | 50.00% (1/2) (9.45% - 90.55%) |
| | Non-Reactive | 0 | 1 | | |
| | **Total** | 3 | 2 | | |
| $\geq 15$ days | Reactive | 116 | 0 | 100.00% (116/116) (96.79% - 100.00%) | 100.00% (2/2) (34.24% - 100.00%) |
| | Non-Reactive | 0 | 2 | | |
| | **Total** | 116 | 2 | | |
**Table 11.** Performance of Elecsys Anti-SARS-CoV-2 S - Population 2
| | Elecsys Anti- SARS-CoV-2 S | Composite Comparator | | PPA [%] (95% CI) | NPA [%] (95% CI) |
| --- | --- | --- | --- | --- | --- |
| | | Reactive | Non-Reactive | | |
| | Reactive | 0 | 0 | NA | 100.00% (489/489) (99.25%-100.00%) |
| | Non-Reactive | 1 | 489 | | |
| | **Total** | 1 | 489 | | |
#### Additional Clinical Performance Evaluation:
In addition to the studies above, the Negative Percent Agreement (NPA) was also evaluated in a separate study using 3,612 samples (Population 3) collected before October 2019 (and presumed negative for SARS-CoV-2 antibodies). One false positive sample was detected, resulting in an NPA of 99.97% (95% CI lower limit of 99.84%).
K252280 - Page 18 of 20
{18}
**Table 12.** Performance of Elecsys Anti-SARS-CoV-2 S - Population 3
| Cohort | N | Non-Reactive | Reactive | NPA, % (95% CI) |
| --- | --- | --- | --- | --- |
| Diagnostic Routine (Europe) | 2528 | 2528 | 0 | 100.00% (99.85%–100.00%) |
| Blood donors (US) | 1084 | 1083 | 1 | 99.91% (99.48%–99.98%) |
| **Overall** | **3612** | **3611** | **1** | 99.97% (99.84%–100.00%) |
## 2. Matrix Comparison:
Matrix comparison study was performed to verify the types of blood collection tubes that can be used with the Elecsys Anti-SARS-CoV-2 assay. Specimens were obtained in matched serum and plasma collection tubes. The number of donors varied slightly for each comparison: 70 donors for the K3-EDTA plasma comparison, 67 donors for the Sodium Citrate plasma comparison, and 66 donors for both the Lithium Heparin and K2-EDTA plasma comparisons. Serum was used as the control (reference) tube type. Data was analyzed using comparing concentrations of all matrices to serum. All blood collection tube types tested are acceptable for use with the Elecsys Anti-SARS-CoV-2 assay. Statistical evaluation data are summarized below.
**Table 13.** Elecsys Anti-SARS-CoV-2 S Matrix Equivalency Statistical Results Summary
| Collection Tube | Slope (Passing-Bablok) | Correlation (Pearson r) | Bias at assay cutoff of 0.8 BAU/mL, Based on Passing-Bablok |
| --- | --- | --- | --- |
| **Li-Heparin** | 0.988 | 0.999 | -1.2 |
| **K2-EDTA** | 1.008 | 0.999 | 0.8 |
| **K3-EDTA** | 1.009 | 1.000 | 0.9 |
| **Na-Citrate** | 0.997 | 0.998 | -0.3 |
Intercept (Constrained to Zero)
## C Clinical Studies:
### 1. Clinical Sensitivity:
Not applicable.
### 2. Clinical Specificity:
Not applicable.
### 3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
K252280 - Page 19 of 20
{19}
# **D Clinical Cut-Off:**
Not applicable
# **E Expected Values/Reference Range:**
Not applicable
# **F Other Supportive Instrument Performance Characteristics Data:**
Not applicable
# **VIII Proposed Labeling:**
The labeling supports the finding of substantial equivalence for this device.
# **IX Conclusion:**
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K252280 - Page 20 of 20
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.