K253367 · Phadia AB · LLL · Jun 25, 2026 · Immunology
Device Facts
Record ID
K253367
Device Name
EliA CTD 13 Screen
Applicant
Phadia AB
Product Code
LLL · Immunology
Decision Date
Jun 25, 2026
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.5100
Device Class
Class 2
Indications for Use
EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method.
Device Story
EliA CTD 13 Screen is an automated, qualitative solid-phase fluoroenzymeimmunoassay for detecting IgG autoantibodies against 13 specific antigens (dsDNA, SmD3, Rib-P, SS-A/Ro 60/52, SS-B/La, Scl-70, Centromere B, RNA Pol III, Jo-1, U1RNP-A/C, RNP70). Used on Phadia 250 instrument; patient serum samples are incubated in antigen-coated wells. Bound antibodies are detected via enzyme-labeled anti-IgG conjugate and a development solution; fluorescence intensity is measured. Results are reported as a ratio compared to calibrators. Used in clinical laboratories to aid diagnosis of systemic autoimmune rheumatic diseases. Benefits include standardized, automated screening for multiple autoantibodies simultaneously, facilitating clinical decision-making.
Clinical Evidence
Clinical study evaluated 1027 serum samples (575 target disease, 452 disease controls). Sensitivity 86.8% (95% CI: 83.7-89.4) and specificity 81.2% (95% CI: 77.3-84.7) when equivocal results are negative. Sensitivity 90.4% (95% CI: 87.7-92.7) and specificity 72.6% (95% CI: 68.2-76.6) when equivocal results are positive. Analytical performance included precision (CLSI EP05-A3), interference testing, and CDC ANA reference panel validation.
Technological Characteristics
Solid-phase fluoroenzymeimmunoassay. Polystyrene wells coated with native purified dsDNA, synthetic SmD3 peptide, and human recombinant proteins (Rib-P, SS-A/Ro60, SS-A/Ro52, SS-B/La, Scl-70, Centromere B, RNA Pol III, Jo-1, RNP70, U1RNP-A, U1RNP-C). Detection via β-Galactosidase-labeled anti-human IgG conjugate and 4-Methylumbelliferyl-β-D-galactoside substrate. Fluorescence-based detection. Automated on Phadia 250 instrument. 37°C controlled reaction temperature.
Indications for Use
Indicated for in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of SLE, SS, SSc, PM, DM, and MCTD in conjunction with other clinical findings. 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}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY
# I Background Information:
A 510(k) Number
K253367
B Applicant
Phadia AB
C Proprietary and Established Names
EliA CTD 13 Screen
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| LLL | Class II | 21 CFR 866.5100 – Antinuclear Antibody Immunological Test System | IM - Immunology |
# II Submission/Device Overview:
A Purpose for Submission:
New assay
B Measurand:
Human IgG autoantibodies to U1RNP-A, U1RNP-C, RNP-70, SS-A/Ro 52, SS-A/Ro 60, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm, and dsDNA
C Type of Test:
Automated qualitative solid phase fluoroenzymeimmunoassay
# III Intended Use/Indications for Use:
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
# **A Intended Use(s):**
See Indications for Use below
# **B Indication(s) for Use:**
EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method.
# **C Special Conditions for Use Statement(s):**
Rx – For Prescription Use Only
# **D Special Instrument Requirements:**
For use on the Phadia 250 instrument
# **IV Device/System Characteristics:**
# **A Device Description:**
The EliA CTD 13 Screen test system is a fully integrated and automated system which comprises of assay-specific reagents, EliA method-specific reagents, and general reagents.
# *Assay-specific reagents:*
- EliA CTD 13 Screen Well, coated with native purified dsDNA, synthetic SmD₃ peptide and human recombinant Rib-P, SS-A/Ro (60 kDa, 52 kDa), SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1, U1RNP-A, U1RNP-C, and RNP70, proteins – 4 carriers (16 Wells each), sufficient for 64 determinations, ready for use
- EliA ANA Positive Control 250: Human blood preparation and monoclonal antibodies containing IgG antibodies against dsDNA, RNP, Sm, Ro, La, Scl-70, CENP, and Jo-1, in PBS containing BSA, detergent and sodium azide (0.095% (w/v)) – 6 single-use vials, 0.3 mL each, sufficient for two determinations per vial, ready for use
- EliA IgG/IgM/IgA Negative Control 250: Human blood preparation in PBS containing BSA, detergent and sodium azide (0.095% (w/v)) – 6 single-use vials, 0.3 mL each, ready for use.
# *EliA Method-specific reagents:*
- EliA Sample Diluent: PBS containing BSA, detergent and sodium azide (0.095% (w/v)) – 6 bottles, 48 mL each, ready for use
- EliA IgG Conjugate 50 or 200: β-Galactosidase anti-IgG (mouse monoclonal antibodies) in PBS containing BSA and sodium azide (0.06% (w/v)) – 6 wedge-shaped bottles, 5 mL
K253367 - Page 2 of 15
{2}
each (Conjugate 50), ready to use; 6 wedge-shaped bottles, 19 mL each (Conjugate 200), ready for use.
- EliA IgG Calibrator Strips: Human IgG (0, 4, 10, 20, 100, 600 μg/L); in PBS containing BSA, detergent and sodium azide (0.095% (w/v)) – 5 strips, 6 single-use vials per strip, 0.3 mL each, ready for use.
- EliA IgG Curve Control Strips: Human IgG (20 μg/L); in PBS containing BSA, detergent and sodium azide (0.095% (w/v)) – 5 strips, 6 single-use vials per strip, 0.3 mL each, ready for use.
- EliA IgG Calibrator Well: Coated with mouse monoclonal antibodies – 4 carriers (12 wells each), ready for use.
# General Reagents:
- Development Solution: 0.01% 4-Methylumbelliferyl-β-D-galactoside, <0.0010% preservative – 6 bottles (11 mL or 17 mL each), ready for use.
- Stop Solution: 4% Sodium Carbonate – 6 bottles (65 mL or 119 mL each), ready for use.
- Dilution Plates: MicroWell™ plates with 96 wells, 0.5 mL each – 100 plates/package, ready for use.
- Washing Solution:
- Washing Solution Additive: detergent, preservative <0.13% – 6 x 17.2 mL or 2 x 86mL.
- Washing Solution Concentrate: phosphate buffer, preservative <0.0015% – 6 x 80 mL or 2 x 400 mL.
# B Principle of Operation:
The EliA CTD 13 Screen Wells are coated with native purified dsDNA, synthetic SmD₃ peptide and human recombinant Rib-P, SS-A/Ro 60, SS-A/Ro 52, SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1 and U1RNP-A, U1RNP-C, and RNP70 proteins. If present in the patient's specimen, antibodies to the antigens bind to their specific antigen.
After washing away non-bound antibodies, enzyme-labeled antibodies against human IgG antibodies (EliA IgG Conjugate) are added to form an antibody-conjugate complex. After incubation, non-bound conjugate is washed away, and the bound complex is incubated with a Development Solution. After stopping the reaction, the fluorescence in the reaction mixture is measured. The assay directly measures the amount of antibody of interest bound to the antigen coating the EliA Well, therefore the higher the value of fluorescent signal detected by the instrument, the higher the amount of antibody bound and detected in the sample tested. To evaluate test results, the response for patient samples is compared directly to the response for calibrators.
# V Substantial Equivalence Information:
# A Predicate Device Name(s):
EliA Symphonyˢ, EliA dsDNA, EliA Rib-P, and EliA RNA Pol III
K253367 - Page 3 of 15
{3}
# **B Predicate 510(k) Number(s):**
K190710, K072939, K202540, and K202541
# **C Comparison with Predicate(s):**
| Device & Predicate Device(s): | K251440 (Candidate) | K190710 (Predicate) |
| --- | --- | --- |
| Device Trade Name | EliA CTD 13 Screen | EliA Symphony^{S} |
| **General Device Characteristic Similarities** | | |
| Sample Matrix | Serum | Serum and Plasma |
| Detection | Qualitative | Same |
| Technology | Enzyme Linked Immunosorbent Assay (ELISA) | Same |
| Result Reporting | Ratio | Same |
| Cut-off | 1.0 | Same |
| Interpretation | Negative: < 0.7 Ratio Equivocal: 0.7-1.0 Ratio Positive: > 1.0 Ratio | Same |
| **General Device Characteristic Differences** | | |
| Intended Use/ Indications For Use | EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method. | EliA Symphony^{S} is intended for the in vitro, qualitative measurement of antinuclear IgG antibodies in human serum and plasma (Li-heparin, EDTA). EliA Symphony^{S} is based on human recombinant U1RNP (RNP 70, A, C), SS-A/Ro (60 kDa, 52 kDa), SS-B/La, Centromere B, Scl-70, Jo-1 proteins and a synthetic SmD3 peptide as antigen and is useful as an aid in the clinical diagnosis of patients with systemic lupus erythematosus (SLE), mixed connective tissue disease (MCTD), Sjögren's syndrome, scleroderma and polymyositis/dermatomyositis, in conjunction with other laboratory and clinical findings. EliA Symphony^{S} uses the EliA IgG method. |
| Antigens | Native purified dsDNA, synthetic SmD3 peptide and human recombinant Rib-P, SS-A/Ro 60 SSA-A/Ro 52, SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1 and U1RNP-A, U1RNP-C, and RNP70 proteins | Human recombinant U1RNP (RNP70, A, C), SS-A/Ro (60 kDa, 52 kDa), SS-B/La, Centromere B, Scl-70 and Jo-1 proteins, synthetic SmD3 peptide |
K253367 - Page 4 of 15
{4}
| Device & Predicate Device(s): | K251440 (Candidate) | K072939 (Predicate) |
| --- | --- | --- |
| Device Trade Name | EliA CTD 13 Screen | EliA dsDNA |
| **General Device Characteristic Similarities** | | |
| Technology | Enzyme Linked Immunosorbent Assay (ELISA) | Same |
| **General Device Characteristic Differences** | | |
| Sample Matrix | Serum | Serum and Plasma |
| Intended Use/ Indications For Use | EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method. | EliA dsDNA is intended for the in vitro quantitative measurement of IgG antibodies directed to dsDNA in human serum and plasma (Li-heparin, EDTA) as an aid in the clinical diagnosis of systemic lupus erythematosus (SLE) in conjunction with other laboratory and clinical findings. EliA dsDNA uses the EliA IgG method. |
| Detection | Qualitative | Quantitative |
| Result Reporting | Ratio | IU/mL |
| Antigens | Native purified dsDNA, synthetic SmD3 peptide and human recombinant Rib-P, SS-A/Ro 60 SSA-A/Ro 52, SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1 and U1RNP-A, U1RNP-C, and RNP70 proteins | dsDNA |
| Cut-off | 1.0 | 15 IU/mL |
| Interpretation | Negative: < 0.7 Ratio Equivocal: 0.7-1.0 Ratio Positive: > 1.0 Ratio | Negative: < 10 IU/mL Equivocal: 10-15 IU/mL Positive: > 15 IU/mL |
K253367 - Page 5 of 15
{5}
| Device & Predicate Device(s): | K251440 (Candidate) | K202540 (Predicate) |
| --- | --- | --- |
| Device Trade Name | EliA CTD 13 Screen | EliA Rib-P |
| General Device Characteristic Similarities | | |
| Sample Matrix | Serum | Same |
| Technology | Enzyme Linked Immunosorbent Assay (ELISA) | Same |
| General Device Characteristic Differences | | |
| Intended Use/ Indications For Use | EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method. | EliA Rib-P is intended for the in vitro semi-quantitative measurement of IgG antibodies directed to Rib-P in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE) in conjunction with other laboratory and clinical findings. EliA Rib-P uses the EliA IgG method. |
| Detection | Qualitative | Semi-quantitative |
| Result Reporting | Ratio | EliA U/mL (arbitrary) |
| Cut-off | 1.0 | 10 U/mL |
| Antigens | Native purified dsDNA, synthetic SmD3 peptide and human recombinant Rib-P, SS-A/Ro 60 SSA-A/Ro 52, SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1 and U1RNP-A, U1RNP-C, and RNP70 proteins | Rib-P |
| Interpretation | Negative: < 0.7 Ratio Equivocal: 0.7-1.0 Ratio Positive: > 1.0 Ratio | Negative: < 7 EliA U/mL Equivocal: 7-10 EliA U/mL Positive: > 10 EliA U/mL |
K253367 - Page 6 of 15
{6}
| Device & Predicate Device(s): | K251440 (Candidate) | K202541 (Predicate) |
| --- | --- | --- |
| Device Trade Name | EliA CTD 13 Screen | EliA RNA Pol III |
| General Device Characteristic Similarities | | |
| Sample Matrix | Serum | Same |
| Technology | Enzyme Linked Immunosorbent Assay (ELISA) | Same |
| General Device Characteristic Differences | | |
| Intended Use/Indications For Use | EliA CTD 13 Screen is intended for the in vitro qualitative detection of antinuclear IgG antibodies in human serum as an aid in the diagnosis of systemic lupus erythematosus (SLE), Sjögren's syndrome (SS), systemic sclerosis (SSc), polymyositis (PM), dermatomyositis (DM) and mixed connective tissue disease (MCTD), in conjunction with other laboratory and clinical findings. EliA CTD 13 Screen detects antibodies against RNP70, U1RNP-A, U1RNP-C, SS-A/Ro60, SS-A/Ro52, SS-B/La, Centromere B, Scl-70, Jo-1, RNA Pol III, Rib-P, Sm and dsDNA. EliA CTD 13 Screen uses the EliA IgG method. | EliA RNA Pol III is intended for the in vitro semi-quantitative measurement of antinuclear IgG antibodies directed to RNA polymerase III (RNA Pol III) in human serum as an aid in the diagnosis of systemic sclerosis (diffuse form) in conjunction with other laboratory and clinical findings. EliA RNA Pol III uses the EliA IgG method. |
| Detection | Qualitative | Semi-quantitative |
| Result Reporting | Ratio | EliA U/mL (arbitrary) |
| Cut-off | 1.0 | 10 U/mL |
| Antigens | Native purified dsDNA, synthetic SmD3 peptide and human recombinant Rib-P, SS-A/Ro 60 SSA-A/Ro 52, SS-B/La, Scl-70, Centromere B, RNA Polymerase III, Jo-1 and U1RNP-A, U1RNP-C, and RNP70 proteins | |
| Interpretation | Negative: < 0.7 Ratio Equivocal: 0.7-1.0 Ratio Positive: > 1.0 Ratio | Negative: < 7 EliA U/mL Equivocal: 7-10 EliA U/mL Positive: > 10 EliA U/mL |
## VI Standards/Guidance Documents Referenced:
The following Clinical and Laboratory Standards Institute (CLSI) guidelines were used:
- CLSI EP07, Interference Testing in Clinical Chemistry, 3rd Edition,
K253367 - Page 7 of 15
{7}
- CLSI EP12-Ed3, Evaluation of Qualitative, Binary Output Examination Performance, 3rd Edition,
- CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures, 2nd Edition
- CLSI EP28-A3c, Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory, 3rd Edition
- CLSI EP34, Establishing and Verifying an Extended Measuring Interval Through Specimen Dilution and Spiking, 1st Edition
- CLSI EP37, Supplemental Tables for Interference Testing in Clinical Chemistry, 1st Edition
- CLSI GP44-A4, Procedures for the handling and processing of blood specimens for common laboratory tests, 4th Edition
# VII Performance Characteristics (if/when applicable):
# A Analytical Performance:
# 1. Precision/Reproducibility:
Precision and reproducibility of EliA CTD 13 Screen were evaluated in accordance with the CLSI guideline EP12-Ed3.
# Single-site precision
To evaluate the within-laboratory precision of the EliA CTD Screen, 10 samples were prepared by diluting positive native serum samples with negative serum samples. The prepared samples, containing various concentrations of autoantibodies, were assayed in duplicate, twice a day, for 20 or 21 days, using one reagent lot, one instrument, and one operator, for a total of 80 or 84 measurements per sample.
| Sample | Mean Ratio (interpretation) | Range of Ratio | N# of Positive/Equivocal/Negative | % of Positive/Equivocal/Negative |
| --- | --- | --- | --- | --- |
| 1 | 0.3 (negative) | 0.2 – 0.3 | 0/0/84 | 0/0/100 |
| 2 | 0.3 (negative) | 0.3 – 0.4 | 0/0/84 | 0/0/100 |
| 3 | 0.5 (negative) | 0.4 – 0.6 | 0/0/80 | 0/0/100 |
| 4 | 0.8 (equivocal) | 0.7 – 0.9 | 0/78*/5 | 0/94/6 |
| 5 | 1.0 (positive) | 0.8 – 1.2 | 48/36/0 | 57/43/0 |
| 6 | 1.2 (positive) | 1.0 – 1.4 | 84/0/0 | 100/0/0 |
| 7 | 4.5 (positive) | 3.8 – 5.8 | 84/0/0 | 100/0/0 |
| 8 | 5.3 (positive) | 4.4 – 6.0 | 84/0/0 | 100/0/0 |
| 9 | 23 (positive) | 19 – 28.1 | 81**/0/0 | 100/0/0 |
| 10 | 26 (positive) | 22 – >31 | 84*/0/0 | 100/0/0 |
* Result for one replicate was not reported due to instrument error
** Results for three replicates were not reported due to instrument error in 3 separate runs (1 rep/run)
K253367 - Page 8 of 15
{8}
# Site-to-site reproducibility
The reproducibility of the EliA CTD Screen was evaluated by assaying 10 samples prepared by diluting positive native serum samples with negative serum samples. The prepared samples, containing various concentrations of autoantibodies, were assayed in quintuplicate, once a day, for five days, using one reagent lot at each site, on three instruments for a total of 75 measurements per sample. The instrument and operator variables were nested within the multiple site component. The resulting data are summarized in the following table:
| Sample | Mean Ratio (Result Interpretation) | Range of Ratio | N of Positive/ Equivocal/ Negative | % of Positive/ Equivocal/ Negative | Instrument 1 | | Instrument 2 | | Instrument 3 | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative |
| 1 | 0.6 (negative) | 0.5 - 0.6 | 0/0/75 | 0/0/100 | 0/0/25 | 0/0/100 | 0/0/25 | 0/0/100 | 0/0/25 | 0/0/100 |
| 2 | 0.6 (negative) | 0.6 - 0.7 | 0/1/74 | 0/1/99 | 0/0/25 | 0/0/100 | 0/0/25 | 0/0/100 | 0/1/24 | 0/4/96 |
| 3 | 0.7 (equivocal) | 0.6 - 0.8 | 0/34/41 | 0/45/55 | 0/18/7 | 0/72/28 | 0/7/18 | 0/28/72 | 0/9/16 | 0/36/64 |
| 4 | 0.8 (equivocal) | 0.7 - 0.9 | 0/74/1 | 0/99/1 | 0/25/0 | 0/100/0 | 0/24/1 | 0/96/4 | 0/25/0 | 0/100/0 |
| 5 | 0.9 (equivocal) | 0.8 - 1.0 | 0/75/0 | 0/100/0 | 0/25/0 | 0/100/0 | 0/25/0 | 0/100/0 | 0/25/0 | 0/100/0 |
| 6 | 1.1 (positive) | 0.9 - 1.4 | 70/5/0 | 93/7/0 | 22/3/0 | 88/12/0 | 25/0/0 | 100/0/0 | 23/2/0 | 92/8/0 |
| 7 | 3.6 (positive) | 3.3 - 3.9 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 8 | 4.8 (positive) | 4.2 - 5.3 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 9 | 23 (positive) | 20 - 25 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 10 | 30 (positive) | 25 - >31 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
# Between-lot imprecision
Between-lot imprecision of EliA CTD 13 Screen was evaluated by assaying 10 samples prepared by diluting positive native serum samples with negative serum samples. The prepared samples were tested in quintuplicate once a day for five days with 3 reagent lots on one instrument, for a total of 75 replicates per sample.
| Sample | Mean Ratio (Result Interpretation) | Range of Ratio | N of Positive/ Equivocal/ Negative | % of Positive/ Equivocal/ Negative | Lot 1 | | Lot 2 | | Lot 3 | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative | Positive/ Equivocal/ Negative | %Positive/ Equivocal/ Negative |
| 1 | 0.6 (negative) | 0.6 - 0.7 | 0/4/71 | 0/5/95 | 0/1/24 | 0/4/96 | 0/3/22 | 0/12/88 | 0/0/25 | 0/0/100 |
| 2 | 0.6 (negative) | 0.5 - 0.6 | 0/0/75 | 0/0/100 | 0/0/25 | 0/0/100 | 0/0/25 | 0/0/100 | 0/0/25 | 0/0/100 |
| 3 | 0.7 (equivocal) | 0.6 - 0.8 | 0/30/45 | 0/40/60 | 0/9/16 | 0/36/64 | 0/9/16 | 0/36/64 | 0/12/13 | 0/48/52 |
| 4 | 0.8 (equivocal) | 0.6 - 0.9 | 0/65/10 | 0/87/13 | 0/25/0 | 0/100/0 | 0/25/0 | 0/100/0 | 0/15/10 | 0/60/40 |
| 5 | 0.9 (equivocal) | 0.8 - 1.0 | 0/75/0 | 0/100/0 | 0/25/0 | 0/100/0 | 0/25/0 | 0/100/0 | 0/25/0 | 0/100/0 |
| 6 | 1.2 (positive) | 0.9 - 1.4 | 68/7/0 | 91/9/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 18/7/0 | 72/28/0 |
| 7 | 3.7 (positive) | 3.3 - 4.1 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 8 | 4.8 (positive) | 4.0 - 5.6 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 9 | 23 (positive) | 20 - 28 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
| 10 | 30 (positive) | 25 - >31 | 75/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 | 25/0/0 | 100/0/0 |
K253367 - Page 9 of 15
{9}
# 2. Linearity:
Not applicable
# 3. Analytical Specificity/Interference:
# Endogenous and exogenous interference
Four serum samples (including a negative, equivocal and positive sample) were prediluted in EliA Sample Diluent and spiked with different interfering substances or blank solution. Six replicates were measured for all test samples and control samples. The aliquots (test and control) of each sample were assayed in the same run. A calibration and curve controls were included in each run. None of the interferents changed the expected result at the indicated testing concentrations as shown in the table below.
| Endogenous Substances | |
| --- | --- |
| Potential interfering substance | Concentration |
| Albumin | 6000 mg/dL |
| Bilirubin, unconjugated | 40 mg/dL |
| Bilirubin, conjugated | 40 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Rheumatoid factor IgM | 500 IU/mL |
| Exogenous Substances | |
| --- | --- |
| Potential interfering substance | Concentration |
| Triglycerides | 2000 mg/dL |
| Alendronate | 0.0034 mg/dL |
| Amlodipine | 0.0075 mg/dL |
| Amoxicillin | 12.9 mg/dL |
| Atorvastatin | 0.075 mg/dL |
| Azathioprine | 0.26 mg/dL |
| Belimumab | 94.0 mg/dL |
| Cyclophosphamide | 54.9 mg/dL |
| Diltiazem | 0.09 mg/dL |
| Enalapril | 0.0819 mg/dL |
| Erythromycin | 13.8 mg/dL |
| Hydroxychloroquine | 0.36 mg/dL |
| Ibuprofen | 21.9 mg/dL |
| Infliximab | 90 mg/dL |
| Losartan | 0.09 mg/dL |
| Methotrexate | 205.0 mg/dL |
| Mycophenolic acid | 33.0 mg/dL |
| Omeprazole | 0.84 mg/dL |
K253367 - Page 10 of 15
{10}
| Exogenous Substances | |
| --- | --- |
| Potential interfering substance | Concentration |
| Prednisone | 0.01 mg/dL |
| Ranitidine | 1.05 mg/dL |
| Rituximab | 114.3 mg/dL |
| Simvastatin | 0.168 mg/dL |
# Reference Sera:
Selected Antinuclear Antibodies(ANA) IUIS Reference Standards samples, previously known as the CDC (Center for Disease Controls and Prevention) ANA Reference Panel, were tested in singlicate using one reagent lot of the EliA CTD 13 Screen to illustrate the analytical specificity of the assay. The results are outlined below.
| Sample | Description/Assigned Specificity | EliA CTD Screen Result |
| --- | --- | --- |
| CDC ANA #1 | Homogeneous Rim Pattern in FANA test due to antibodies to dsDNA | Positive |
| CDC ANA #2 | Speckled pattern in FANA test due to antibodies to SS-B/La | Positive |
| CDC ANA #3 | Speckled pattern in FANA due to antibodies to U1-RNP, SS-B/La and SS-A/Ro | Positive |
| CDC ANA #4 | High levels of antibodies to U1-RNP | Positive |
| CDC ANA #5 | High levels of antibodies to Sm | Positive |
| CDC ANA #6 | Nucleolar pattern in FANA test (due antibodies to U3-RNP) | Negative |
| CDC ANA #7 | High levels of antibodies to SS-A/Ro | Positive |
| CDC ANA #8 | Centromere pattern in FANA test | Positive |
| CDC ANA #9 | High levels of antibodies to Scl-70 | Positive |
| CDC ANA #10 | High levels of antibodies to Jo-1 | Positive |
| CDC ANA #11 | High levels of antibodies to PM/Scl | Negative |
| CDC ANA #12 | High levels of antibodies to Ribosomal P | Positive |
FANA= Fluorescent Antinuclear Antibody
# 4. Detection Limit and Assay Reportable Range:
Not applicable
# 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
# Traceability
This EliA test uses EliA IgG Calibrators. EliA IgG Calibrators are traceable to an internal reference material which is based on the WHO International Standard Immunoglobulins A, G and M, Human Serum (NIBSC code: 67/086).
# Reagent stability:
Shelf-life: The stability of the EliA CTD 13 Screen wells was evaluated with a real-time study on the Phadia 250 instrument. Three lots of EliA CTD 13 Screen wells were stored
K253367 - Page 11 of 15
{11}
under recommended conditions at 2 – 8°C and tested at different timepoints using 10 positive, nine (9) negative, and two (2) equivocal samples. The results support a shelf-life of 9 months at 2 – 8°C for EliA CTD 13 Screen.
Transport stability: Transport stability was evaluated on the Phadia 250 instrument with real-time stability study. EliA CTD 13 Screen wells were incubated under two different transport stress conditions (24 hours at -20°C and 5 days at 35°C) and tested using 10 positive, nine (9) negative, and two (2) equivocal samples after stress. The results support a claim that transport conditions like heat (35°C) and cold (-20°C) or storage for up to 5 days at up to 35°C are possible without any impact on the shelf-life up to 12 weeks.
On-board (storage chamber) stability: The on-board stability of EliA CTD 13 Screen Well carriers was evaluated at 80% humidity and at 11°C for 15, 29 and 43 days in the Phadia 250 carrier storage tray using eight (8) positive serum samples, two (2) equivocal serum samples, two (2) negative serum samples and a positive control. The on-board stability in the storage chamber of the Phadia 250 instrument was determined to be 28 days under operating conditions at 2– 8°C.
On-board (loading tray) stability: The on-board stability of EliA CTD 13 Screen Well carriers was evaluated on the loading tray of the Phadia 250 instrument at 32°C and 80% relative humidity (RH). The wells were stored on a loading tray in a climate chamber for 12 hours, 24 hours, 25 hours and 72 hours and tested with eight (8) positive serum samples, two (2) equivocal serum samples, nine (9) negative serum samples and positive control. The on-board stability of EliA CTD 13 Screen Well on the loading tray of the Phadia 250 instrument was determined to be 24 hours.
In-use stability: For evaluation of Stability after first opening, foil bags containing the EliA CTD 13 Screen wells in carriers (stored under standard conditions, at 2 – 8 °C) were opened. The process of opening and sealing of the foil bags was repeated multiple times over the study duration exposing the wells to 11°C and 80% RH. Ten (10) positive serum samples (including one high- and one low-positive), two (2) equivocal serum samples and three (3) negative serum samples were tested. The in-use stability after first opening of EliA CTD 13 Screen Well was determined to be 12 weeks at 2 – 8°C.
Sample Stability: The sample stability was evaluated to support the stability of samples, when stored frozen for 27 months from blood draw using 10 serum samples (across the reportable range of EliA CTD 13 Screen) were included in this study. Four (4) positive serum samples, four (4) equivocal serum samples and two (2) negative serum samples were tested at 7 weeks, 5 months, 8 months, 14 months, 16 months, 24 months, 24.5 months and 27 months timepoints. All tested serum samples fulfilled the study specifications, when stored frozen up to 27 months and supported the sample stability claim of 24.5 months.
# 6. Assay Cut-Off:
To define the cut-off, a study was performed using a cohort consisting of 70 apparently healthy blood donors, four (4) serum samples from MCTD patients, eight (8) serum samples from IIM patients, seven (7) serum samples from systemic sclerosis patients, six (6) serum
K253367 - Page 12 of 15
{12}
samples from SLE patients and five (5) serum samples from Sjögren's syndrome patients. The samples were measured on a Phadia 250 instrument.
The cut-off was set as follows for EliA CTD 13 Screen:
| | Negative | Equivocal | Positive |
| --- | --- | --- | --- |
| Result [Ratio] | <0.7 | 0.7 – 1.0 | >1.0 |
In case of equivocal results, the manufacturer recommends retesting the patient after 8–12 weeks.
### B Comparison Studies:
#### 1. Method Comparison with Predicate Device:
A total of 1082 serum samples were tested with EliA CTD 13 Screen and compared to the combination of the predicate devices EliA SymphonyS, EliA dsDNA, EliA Rib-P and EliA RNA Pol III assays. The tests were run in single determination and evaluated according to the Directions for Use of both assays. The results are summarized in the tables below:
| n=1082 | Combination of Predicate Devices | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Positive | Equivocal | Negative | Total |
| EliA CTD 13 Screen | Positive <0.7 | 572 | 35 | 24 | 631 |
| | Equivocal 0.7 – 1.0 | 3 | 4 | 55 | 62 |
| | Negative >1.0 | 7 | 14 | 386 | 389 |
| | Total | 582 | 53 | 447 | 1082 |
| Equivocal results considered negative | Agreement (%) | 95% CI |
| --- | --- | --- |
| Positive Percent Agreement | 98.3 | 96.9–99.2 |
| Negative Percent Agreement | 88.2 | 85.0–90.9 |
| Total Percent Agreement | 93.6 | 92.0–95.0 |
| Equivocal results considered positive | Agreement (%) | 95% CI |
| --- | --- | --- |
| Positive Percent Agreement | 96.7 | 95.0–97.9 |
| Negative Percent Agreement | 82.3 | 78.5–85.8 |
| Total Percent Agreement | 90.8 | 88.9–92.4 |
#### 2. Matrix Comparison:
Not applicable.
### C Clinical Studies:
#### Clinical Sensitivity and Specificity:
A cohort of 1027 clinically defined serum samples were used to determine sensitivity and specificity of the assay. Samples with a diagnosis of polymyositis (PM), dermatomyositis (DM),
K253367 - Page 13 of 15
{13}
mixed connective tissue disease (MCTD), Raynaud's phenomenon, Sjögren's syndrome (SS), systemic lupus erythematosus (SLE) (including lupus nephritis) and systemic sclerosis (SSc) (including limited systemic sclerosis (ISSc) represented the diagnostic group (target disease group, n=575). Samples with various autoimmune and infectious disease diagnosis represent the disease control group (n=452).
The distribution of the cohort and the EliA CTD 13 Screen positivity rate for each clinical subgroup is summarized in the following table.
| Disease | N | N# of Positive^{a} | % of Positive^{a} | 95% CI |
| --- | --- | --- | --- | --- |
| **Target Disease** | | | | |
| Systemic Lupus Erythematosus (SLE) | 200 | 200 | 100 | 98.2 – 100.0 |
| Lupus Nephritis | 11 | 11 | 100 | 71.5 – 100.0 |
| Polymyositis (PM) | 45 | 31 | 68.9 | 53.4 – 81.8 |
| Dermatomyositis (DM) | 51 | 24 | 47.1 | 32.9 – 61.5 |
| Mixed Connective Tissue Disease (MCTD) | 53 | 29 | 54.7 | 40.4 – 68.4 |
| Sjögren's Syndrome (SS) | 97 | 97 | 100 | 96.3 – 100.0 |
| Systemic Sclerosis (SSc) | 57 | 50 | 87.7 | 76.3 – 94.9 |
| Limited Systemic Sclerosis (ISSc) | 22 | 21 | 95.5 | 77.2 – 99.9 |
| Raynaud's Phenomenon | 39 | 36 | 92.3 | 79.1 – 98.4 |
| **Disease Controls** | | | | |
| Antiphospholipid Syndrome (pAPS+sAPS)^{b} | 47 | 27 | 57.4 | 42.2 – 71.7 |
| Autoimmune Hepatitis (AIH) | 20 | 18 | 90 | 68.3 – 98.8 |
| Bacterial Infection | 35 | 5 | 14.3 | 4.8 – 30.3 |
| Celiac Disease | 28 | 4 | 14.3 | 4.0 – 32.7 |
| Crohn's Disease | 21 | 0 | 0 | 0.0 – 16.1 |
| Graves' Disease | 27 | 0 | 0 | 0.0 – 12.8 |
| HIV | 24 | 0 | 0 | 0.0 – 14.2 |
| Hashimoto's Thyroiditis | 10 | 0 | 0 | 0.0 – 30.8 |
| Hepatitis C | 19 | 0 | 0 | 0.0 – 17.6 |
| Leukemia | 20 | 0 | 0 | 0.0 – 16.8 |
| Lymphoma | 20 | 0 | 0 | 0.0 – 16.8 |
| Polymyalgia Rheumatica | 25 | 0 | 0 | 0.0 – 13.7 |
| Primary Biliary Cholangitis (PBC) | 20 | 2 | 10 | 1.2 – 31.7 |
| Primary Sclerosing Cholangitis (PSC) | 24 | 0 | 0 | 0.0 – 14.2 |
| Rheumatoid Arthritis (RA) | 40 | 25 | 62.5 | 45.8 – 77.3 |
| Ulcerative Colitis | 22 | 1 | 4.5 | 0.1 – 22.8 |
| Vasculitis | 32 | 3 | 9.4 | 2.0 – 25.0 |
| Other Viral Infections (EBV, HBV etc.) | 18 | 0 | 0 | 0.0 – 18.5 |
$^{a}$ Equivocal results were considered as negative in this evaluation.
$^{b}$ Primary Antiphospholipid Syndrome (pAPS) = 27; Antiphospholipid Syndrome associated with SLE (sAPS) = 20.
K253367 - Page 14 of 15
{14}
Clinical sensitivity and specificity of EliA CTD 13 Screen are summarized in the tables below.
| n= 1027 | Clinical Diagnosis | | | |
| --- | --- | --- | --- | --- |
| | | Target Diseases | Disease Controls | Total |
| EliA CTD 13 Screen | Positive <0.7 | 499 | 84 | 583 |
| | Equivocal 0.7 – 1.0 | 21 | 40 | 61 |
| | Negative >1.0 | 55 | 328 | 383 |
| | Total | 575 | 452 | 1027 |
| Equivocal results are considered negative | | |
| --- | --- | --- |
| Sensitivity | 86.8% | 95% CI: 83.7 - 89.4 |
| Specificity | 81.2% | 95% CI: 77.3 – 84.7 |
| Equivocal results are considered positive | | |
| --- | --- | --- |
| Sensitivity | 90.4% | 87.7 - 92.7 |
| Specificity | 72.6% | 68.2 - 76.6 |
### D Expected Values/Reference Range:
The frequency distribution for antinuclear antibodies was investigated in 330 apparently healthy subjects equally distributed by age and gender, using blood bank sera reflecting the ethnical distribution of the United States. The results of the cohort are depicted in the table below:
| EliA CTD 13 Screen | Ratio |
| --- | --- |
| Median | 0.1 |
| Mean | 0.3 |
| Minimum | 0.0 |
| Maximum | 26.1 |
| 95th percentile | 0.5 |
| 97th percentile | 0.8 |
### 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.
K253367 - Page 15 of 15
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.