Database of results for over 1,400 characterized sera/plasma from patients with systemic autoimmune diseases and healthy individuals.
—
Clinical trial of 1,130 patients.
—
Indications for Use
The BioPlex™ 2200 ANA Screen is intended for the qualitative screening of specific antinuclear antibodies (ANA), the quantitative detection of antibody to dsDNA, and the semi-quantitative detection of ten (10) separate antibody assays (Chromatin, Ribosomal Protein, SS-A, SS-B, Sm, SmRNP, RNP, Scl-70, Jo-1, and Centromere B) in human serum and/or EDTA or heparinized plasma. The test system is used as an aid in the diagnosis of systemic autoimmune diseases. The ANA Screen is intended for use with the Bio-Rad BioPlex 2200 System. The BioPlex 2200 Medical Decision Support Software (MDSS), used in conjunction with the ANA Screen, is an optional laboratory tool that associates patient antibody results with predefined MDSS profiles that have been correlated with the following systemic autoimmune diseases: Systemic Lupus Erythematosus (SLE), Mixed Connective Tissue Disease (MCTD), Sjögren's Syndrome (SS), Scleroderma (Systemic Sclerosis) and Polymyositis.
Device Story
The BioPlex 2200 MDSS is a software-based pattern recognition tool used in clinical laboratories to assist physicians in the differential diagnosis of systemic autoimmune diseases. It takes as input the quantitative/semi-quantitative results of 11 individual antibody assays from the BioPlex 2200 Multi-Analyte Detection System. The software uses a k-nearest neighbor (kNN) statistical algorithm to compare the patient's antibody profile against a database of over 1,400 characterized samples. The output is a classification of the patient's results as 'Negative', 'No Association', or an 'Association with Disease' (proposing up to two disease classifications). This output is intended to aid clinicians in interpreting complex serological data and determining the need for further autoimmune testing. By providing automated pattern matching, the device helps clinicians navigate the diagnostic complexity of autoimmune conditions, where referring and final diagnoses often show low agreement.
Clinical Evidence
Clinical performance was evaluated using 908 prospective samples from rheumatology clinic patients and 222 normal blood donors (total N=1,130). The study compared MDSS outputs against clinical diagnoses based on ACR, literature, or established medical criteria. Primary endpoints included disease agreement and likelihood ratios. Results showed MDSS associations for SLE (85.3% agreement in positive antibody patients), Primary Sjögren's (86.7%), Scleroderma (51.6%), MCTD (81.3%), and Polymyositis (33.3%). The study also reported positive/negative likelihood ratios and odds ratios for each disease association. No clinical data was excluded; performance metrics were calculated for both targeted and non-targeted disease populations.
Technological Characteristics
The MDSS is a software-based data processing module. It utilizes a k-nearest neighbor (kNN) statistical algorithm to analyze 11 antibody assay inputs. The system operates on the BioPlex 2200 Multi-Analyte Detection System platform. It is a standalone software tool that functions as an optional add-on to the primary detection system. No specific hardware materials are described for the software itself; it relies on a pre-established medical database of 1,400 characterized samples for pattern matching.
Indications for Use
Indicated for use as an optional laboratory tool to associate patient antibody results with predefined profiles correlated to systemic autoimmune diseases (SLE, MCTD, SS, Scleroderma, Polymyositis) in patients undergoing ANA Screen testing.
Regulatory Classification
Identification
An amphetamine test system is a device intended to measure amphetamine, a central nervous system stimulating drug, in plasma and urine. Measurements obtained by this device are used in the diagnosis and treatment of amphetamine use or overdose and in monitoring levels of amphetamine to ensure appropriate therapy.
Special Controls
*Classification.* Class II (special controls). An amphetamine test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (*e.g.,* programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).
Predicate Devices
Remedi HS™ Drug Profiling System (k941596)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k043341
B. Purpose for Submission:
This is a new device.
C. Manufacturer and Instrument Name:
Bio-Rad Laboratories
BioPlex 2200 Medical Decision Support Software (MDSS) on the BioPlex 2200 Multi-Analyte Detection System.
D. Type of Test or Tests Performed:
The BioPlex™ 2200 Medical Decision Support Software (MDSS) is a separate informatics software module for use with the BioPlex™ 2200 ANA Screen on the BioPlex 2200 Multi-Analyte Detection System
E. System Descriptions:
1. Device Description:
The BioPlex 2200 Medical Decision Support Software (MDSS) is a pattern recognition algorithm that can enhance the performance of the ANA Screen by identifying associated diagnostic patterns among its multiple assay results. The MDSS can suggest one or more possible disease associations after identifying patterns from the eleven (11) individual antibody results. The MDSS is based on the principles of the "k-nearest neighbor" (kNN) statistical techniques. Each "unknown" is compared to a pre-established database that contains the results for over 1,400 characterized sera/plasma. Results of MDSS analysis fall into one of the following general outcomes; Negative, No Association, or Association with Disease. When the results of the MDSS analysis fall into the Association with Disease category, the MDSS software will propose a maximum of two disease classifications based upon the similarity of the current analysis to the stored results. The MDSS output can also aid in determining appropriate additional autoimmune serological testing. All possible MDSS disease associations with corresponding definitions are listed in the following table. Note: MDSS outputs 9 through 15 were not observed in the clinical trial.
{1}
Table: MDSS Output
| # | MDSS Text Output | Internal Output Abbreviations |
| --- | --- | --- |
| 1 | All antibody levels for systemic autoimmune disease are below pre-established cutoffs. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Negative |
| 2 | Antibody levels show no association with MDSS profiles for systemic autoimmune diseases. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | No Association (NA) |
| 3 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider SLE. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | SLE |
| 4 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider SLE or Sjogren's syndrome. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | SS / SLE |
| 5 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Polymyositis. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Polymyositis |
| 6 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Scleroderma. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Scleroderma |
| 7 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider MCTD or SLE. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | MCTD / SLE |
| 8 | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider SLE or Scleroderma. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | SLE / Scleroderma |
{2}
| # | MDSS Text Output | Internal Output Abbreviations |
| --- | --- | --- |
| 9* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Polymyositis or SLE. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Polymyositis / SLE |
| 10* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Polymyositis or MCTD. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Polymyositis / MCTD |
| 11* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Polymyositis or Sjogren’s syndrome. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Polymyositis / SS |
| 12* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Polymyositis or Scleroderma. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Polymyositis / Scleroderma |
| 13* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider MCTD or Sjogren’s syndrome. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | MCTD / SS |
| 14* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider MCTD or Scleroderma. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | MCTD / Scleroderma |
| 15* | Antibody levels show association with MDSS profiles for systemic autoimmune disease. Consider Scleroderma or Sjogren’s syndrome. MDSS outputs of “Negative” or “No Association” do not rule out autoimmune disease. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS, thus MDSS associations from patients with RA should be interpreted with caution. | Scleroderma / SS |
*Note: these MDSS outputs were not observed in the clinical trial
The MDSS is not, in and of itself, diagnostic for the targeted diseases associations and must be considered in conjunction with other laboratory test results and the clinical presentation of the patient.
{3}
4
2. Principles of Operation:
When the MDSS module is activated, the autoantibody results are compared to the MDSS database that contain results for over 1,400 sera/plasma, representing test results from patients with systemic autoimmune diseases and from healthy individuals. If one or more results are obtained from a serum or plasma sample, the results are associated with the most appropriate MDSS profiles.
When the MDSS result is positive, the MDSS produces two outputs that BioPlex 2200 can display in its User Interface. The first output is a text result containing the specific disease association(s) results. The second output is a graph of the specific disease association(s) and the patient's analyte results.
3. Modes of Operation:
The MDSS module interacts with the BioPlex 2200 Instrument software (BPX), which runs on a PC running the Windows operating system. MDSS activates the kNN algorithm which runs queries on a database of serum and plasma results from over 1,000 previously-diagnosed systemic autoimmune patients. This database is stored within the BPX database. Using XML (Extensible Markup Language) strings, BPX sends patient analyte data to the MDSS module and retrieves resultant disease associations from the MDSS module.
4. Specimen Identification:
Refer to k041658 (BioPlex 2200 ANA Screen on the BioPlex 2200 Multi-Analyte Detection System)
5. Specimen Sampling and Handling:
Refer to k041658 (BioPlex 2200 ANA Screen on the BioPlex 2200 Multi-Analyte Detection System)
6. Calibration:
Refer to k041658 (BioPlex 2200 ANA Screen on the BioPlex 2200 Multi-Analyte Detection System)
7. Quality Control:
Refer to k041658 (BioPlex 2200 ANA Screen on the BioPlex 2200 Multi-Analyte Detection System)
8. Software:
FDA has reviewed applicant's Hazard Analysis and Software Development processes for this line of product types:
Yes ☑ or No ☐
F. Regulatory Information:
1. Regulation section:
21 CFR § 862.3100 Amphetamine Test System
{4}
2. Classification:
Class II
3 Product code:
NVI, Diagnostic software, k-nearest neighbor algorithm, autoimmune disease
4. Panel:
91 Clinical Toxicology
G. Intended Use:
1. Indication(s) for Use:
The BioPlex 2200 Medical Decision Support Software (MDSS), used in conjunction with the ANA Screen, is an optional laboratory tool that associates patient antibody results with predefined MDSS profiles that have been correlated with the following systemic autoimmune diseases: Systemic Lupus Erythematosus (SLE), Mixed Connective Tissue Disease (MCTD), Sjögren's Syndrome (SS), Scleroderma (Systemic Sclerosis) and Polymyositis
2. Special Conditions for Use Statement(s):
For use with the BioPlex 2200 ANA Screen Assay on the BioPlex 2200 Multi-Analyte Detection System. (k041658)
H. Substantial Equivalence Information:
1. Predicate Device Name(s) and 510(k) numbers:
Remedi HS™ Drug Profiling System (k941596)
2. Comparison with Predicate Device:
Table 1 (a): Similarities between data processing modules
| | BioPlex 2200 Medical Decision Support Software | Remedi HS Drug Profiling System |
| --- | --- | --- |
| Input | Library or training set data on test results from 1,130 patients. | Library of known drug spectra stored in memory |
| Function | Data processing module for association of patient specific information with the current condition of patient | Same |
| Technology | Computer based, software driven, data driven algorithm. | Sophisticated computer algorithm. |
| | Test results as compared to training set | |
{5}
Table 1 (b): Differences between data processing modules
| | BioPlex 2200 Medical Decision | Remedi HS Drug Profiling System |
| --- | --- | --- |
| Input | Results from serological analysis of patient serum or plasma for specific autoantibodies | Results from chromatographic analysis of patient urine or serum for drugs |
| Modules | Identification of possible disease associations | Identification of possible drugs in the biological specimen |
| Algorithm Technology | k-Nearest Neighbor data analysis algorithm and pre-established medical database. | Peak Identification for comparison of unknown to spectral library of drugs. |
| Output | List of test results in IU/ml and AI (antibody index). | List of test results in the form of a Chromatogram. |
# I. Special Control/Guidance Document Referenced (if applicable):
None referenced.
# J. Performance Characteristics:
# 1. Analytical Performance:
Performance testing in this section is limited to additional clinical concordance and MDSS related claims. Clinical performance testing relating to BioPlex ANA Screen on the BioPlex 2200 ANA Screen was presented on prior (k041658) application.
# a. Accuracy:
The following table presents %disease agreement of the MDSS output with the diagnosis provided by a physician. Data is presented as % disease agreement for patients with one or more positive antibodies and for patients with a targeted connective tissue disease (TCTD) classification, regardless of antibody response. The difference between disease agreements is the inclusion of negative results for all antibodies in the TCTD patients. MDSS does not provide an association with a patient with negative test results for all antibodies.
{6}
MDSS vs. Disease Classification (n = 1130)
| Disease Classification By Criteria** | (N) | MDSS Output | | | | | | | | % Disease Agreement | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | Negative for all antibodies | Positive for one or more antibody (P) | No Association | Any SLE Association | Any Sjogren's syndrome Association | Any SclCR Association | Any MCTD Association | Any Polymyositis Association | Patients with Positive Antibody Only | Patients with TCTD Classification |
| *Systemic Lupus Erythematosus (SLE) | 16 | 1 | 15 | 0 | 15 | 13 | 0 | 0 | 0 | 86.7%
13/15 | 81.3%
13/16 |
| *Primary Sjogren's Syndrome | 16 | 1 | 15 | 0 | 15 | 13 | 0 | 0 | 0 | 86.7%
13/15 | 81.3%
13/16 |
| * Scleroderma | 44 | 13 | 31 | 3 | 19 | 1 | 16 | 3 | 0 | 51.6%
16/31 | 36.4%
16/44 |
| *MCTD | 16 | 0 | 16 | 0 | 15 | 0 | 1 | 13 | 0 | 81.3%
13/16 | 81.3%
13/16 |
| *Polymyositis | 12 | 6 | 6 | 0 | 4 | 0 | 0 | 1 | 2** | 33.3%
2/6 | 16.7%
2/12 |
* Targeted Connective Tissue Disease (TCTD)
** For these patients, the MDSS outputs suggesting Polymyositis referenced the disorder alone and not in combination with another TCTD
The table below presents the % agreement of the MDSS output when a specific positive antibody result is present and the diagnosis provided by the physician is consistent with the presence of that antibody.
MDSS Assignments in Patients with TCTD and a Positive Antibody Result
| Positive Antibody Test Results | Disease by Established Medical Criteria* | MDSS Output** | % Agreement | 95% Confidence Interval |
| --- | --- | --- | --- | --- |
| dsDNA (N = 119) | SLE (N = 92) | Any SLE (N = 87) | 87/92 or 95% | 89-100% |
| Chromatin (N = 168) | SLE (N = 122) | Any SLE (N = 112) | 112/122 or 92% | 86-97% |
| Ribosomal Protein (N = 37) | SLE (N = 30) | Any SLE (N = 29) | 29/30 or 97% | 83-99% |
| SSA (N = 173) | SS (N = 15) | SS or SLE (N = 13) | 13/15 or 87% | 62-96% |
| | SLE (N = 111) | Any SLE (N = 106) | 106/111 or 96% | 91-100% |
| SSB (N = 76) | SS (N = 13) | SS or SLE (N = 13) | 13/13 or 100% | 83-100% |
| Sm (N = 60) | SLE (N = 49) | Any SLE (N = 49) | 49/49 or 100% | 99-100% |
| SmRNP (N = 103) | MCTD (N = 15) | MCTD or SLE (N = 13) | 13/15 or 87% | 62-96% |
| RNP (N = 112) | MCTD (N = 15) | MCTD or SLE (N = 13) | 13/15 or 87% | 62-96% |
{7}
Since some MDSS outputs contain more disease associations with other diseases than the disease association under consideration, the results in the first table were calculated by excluding patients with other diseases listed in the output. The second table presents results where these patients were not excluded. Not all patients with a targeted connective tissue disease produce antibodies that may be detected with the BioPlex 2200 ANA Screen
MDSS Agreement with Disease Classification (excluding patients with other MDSS associations)
| Disease Classification by Criteria | Systemic Lupus Erythematosus (SLE) (N = 332) | Primary Sjögren's Syndrome (N = 16) | Scleroderma (N = 44) | Mixed Connective Tissue Disease (N = 16) | Polymyositis (N = 12) |
| --- | --- | --- | --- | --- | --- |
| Positive Antibody Test(s) | 218 | 15 | 31 | 16 | 6 |
| MDSS Associations | 186 | 13 | 16 | 13 | 2 |
| Odds Ratio (OR) | 12.8 | 479.8 | 22.1 | 481 | 223.4 |
| OR 95% Confidence Interval | 9.1 -17.8 | 111.4 -2065.6 | 10.3 -47.5 | 111.7 -2071.9 | 11.9 -2667.6 |
| Positive Likelihood Ratio (PLR) | 6.17 | 90.8 | 14.4 | 91.0 | 186.3 |
| (PLR) 95% Confidence Interval | 4.8 -7.9 | 41.8 -196.9 | 7.9 -26.1 | 41.95 -197.35 | 18.1 -1919.2 |
| Negative Likelihood Ratio (NLR) | 0.48 | 0.19 | 0.65 | 0.19 | 0.83 |
| NLR 95% Confidence Interval | 0.43 -0.54 | 0.07 -0.52 | 0.52 -0.81 | 0.07 -0.52 | 0.65 -1.07 |
| Total N after exclusions | 1059 | 798 | 798 | 800 | 1130 |
{8}
MDSS Agreement with Disease Classification (including patients with multiple MDSS associations)
| Disease Classification by Criteria | Systemic Lupus Erythematosus (SLE) (N = 332) | Primary Sjögren’s Syndrome (N = 16) | Scleroderma (N = 44) | Mixed Connective Tissue Disease (N = 16) | Polymyositis (N = 12) |
| --- | --- | --- | --- | --- | --- |
| Positive Antibody Test(s) | 218 | 15 | 31 | 16 | 6 |
| MDSS Associations | 186 | 13 | 16 | 13 | 2 |
| Odds Ratio (OR) | 7.9 | 162.1 | 23.3 | 196.8 | 223.4 |
| OR 95% Confidence Interval | 5.9 -10.6 | 43.8 -599.6 | 11.3 -48.2 | 52.6 -735.4 | 11.9 -2667.6 |
| Positive Likelihood Ratio (PLR) | 4.03 | 31.21 | 15.19 | 37.71 | 186.3 |
| (PLR) 95% Confidence Interval | 3.3 -4.9 | 20.3 -47.9 | 8.8 -26.2 | 23.8 -59.8 | 18.1 -1919.2 |
| Negative Likelihood Ratio (NLR) | 0.51 | 0.19 | 0.65 | 0.19 | 0.83 |
| NLR 95% Confidence Interval | 0.45 -0.57 | 0.07 -0.53 | 0.52 -0.81 | 0.07 -0.53 | 0.65 -1.07 |
| Total N | 1130 | 1130 | 1130 | 1130 | 1130 |
Some of the Clinical Disease Classifications encountered do not have an associated MDSS output. These non-targeted connective tissue diseases should be classified as either Negative or No Association by MDSS. The table below presents MDSS results incorrectly associated with a targeted connective tissue disease (% Incorrect Association).
MDSS vs. Non-targeted Connective Tissue Diseases
| Clinical Disease Classification | | (N) | Negative or No MDSS Associations | Incorrect MDSS Associations | % Incorrect Association |
| --- | --- | --- | --- | --- | --- |
| Non TCTD | Dermatomyositis-only | 15 | 12 | 3 | 20% (3/15) |
| | Rheumatoid Arthritis-only | 341 | 310 | 31* | 9% (31/341) |
| | Other CTD-only | 45 | 36 | 9 | 20% (9/45) |
| No CTD | | 77 | 77 | 61 | 16 |
| Blood Donor Samples | | 222 | 222 | 214 | 8** |
* Of the 31 patients with only rheumatoid arthritis, 27 were associated with SLE by MDSS. Patients with Rheumatoid Arthritis may result in an SLE association from MDSS. Additionally, patients with Rheumatoid Arthritis who are receiving anti-TNF $\alpha$ blockers as part of their therapy have been reported to produce antibodies against both dsDNA and Chromatin. For these reasons, MDSS associations from patients with Rheumatoid Arthritis should be interpreted with caution.
{9}
** The clinical status of blood donors tested in this study was not known.
The following tables present % correctness in conjunction with the following prevalence of diseases: study: SLE 29% (332/1130), Sjögren's Syndrome 1.4% (16/1130), Scleroderma 3.9% (44/1130), Mixed Connective Tissue Disease 1.4% (16/1130), Polymyositis 1.1% (12/1130), Other Connective Tissue Disease 36.9% (417/1130), and
No Connective Tissue Disease 6.8% (77/1130). Note: the Correct Association values presented in the following tables may change in different patient populations. The % correctness is defined as the number of patients with given MDSS association who also have that disease by ACR, literature, or established medical criteria
Correct Association without any Targeted Disease Classification
| MDSS Output | # by MDSS | # Without any Targeted Disease | Correct Association | 95% Confidence Interval |
| --- | --- | --- | --- | --- |
| Negative | 719 | 585 | 81.4% (585/719) | 78.4 -84.3% |
| No Association | 89 | 57 | 64% (57/89) | 53.3 -74.8 |
Correct Association with Targeted Disease Classification
| MDSS Output | # by MDSS | # by Clinical Diagnosis | Correct Association | 95% Confidence Interval |
| --- | --- | --- | --- | --- |
| SLE only | 198 | 142 | 71.7% (142/198) | 65.1 -78.3% |
| SLE or SS | 42 | 35 | 83.3% (35/42) | 70.2 -96.5% |
| MCTD or SLE | 37 | 30 | 81.1% (30/37) | 66.3 -95.9% |
| Scleroderma | 22 | 9 | 40.9% (9/22) | 23.3 -61.3% |
| SLE or Scleroderma | 20 | 11 | 55% (11/20) | 34.2 -74.2% |
| Polymyositis only | 3* | 2 | 66.7% (2/3) | 20.8 -93.9% |
* One of these 3 patients was diagnosed with Dermatomyositis.
# b. Precision/Reproducibility:
Reproducibility testing was performed at three (3) US testing facilities on a total of three (3) lots of the ANA Screen. Each testing facility evaluated reproducibility using one (1) kit lot of the ANA Screen. The eleven (11) panel members consisted of ten (10) positive panel members prepared by combining one (1) or more antibody positive patient samples for one (1) or more of the 13 analytes contained in the ANA Screen (dsDNA, Chromatin, SS-A 52, SS-A 60, SS-B, Sm, RNP 68, RNP A, Sm/RNP, Centromere, Ribosomal Protein, Scl-70, and Jo-1. Five of the 10 members had higher levels of the antibodies and five had antibody levels near the cut-off. One panel member was negative for all 13 analytes. In addition, three lots of the ANA Screen Control set positive control (antibody positive for all 13 analytes), 1 diluted positive control and a negative control (negative for all 13 analytes) were also tested.
{10}
Each of the eleven (11) panel members and the Autoimmune Control Set was tested in duplicate (x2) on two (2) runs per day (morning and afternoon) for ten (10) days using one (1) lot of ANA Screen Reagent Pack and one (1) lot of ANA Screen. Calibrator Set at each of three (3) sites. [2 times x 2 runs x 10 days = 40 replicates per panel member per site. Total replicates at 3 sites = 120 replicates per panel member.] The data were then analyzed for intra-assay and inter-assay reproducibility according to the National Committee for Clinical Laboratory Standards (NCCLS EP5-A, Vol. 19, No. 2, p7, Eq. (1) and p8 Eq. (4)). The mean Antibody Index (AI), standard deviation (SD), and percent coefficient of variation (%CV) for each panel member is presented. For dsDNA, the mean International Units per ml (IU/mL), standard deviation (SD), and percent coefficient of variation (%CV) for each panel member is presented. Results for Positive Control, High Positive Panel, and Low Positive Panel can be found in the following tables.
Intra-assay- Site 1
| Clinical Site 1, Lot 1 | ANA Screen - Intra-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Sel-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 45.6 | 2.7 | 2.4 | 4.1 | 3.4 | 3.6 | 3.3 | 4.0 | 4.1 | 3.8 | 3.3 | 3.9 | 3.7 |
| | SD* | 0.89 | 0.08 | 0.07 | 0.19 | 0.07 | 0.07 | 0.09 | 0.08 | 0.10 | 0.13 | 0.08 | 0.10 | 0.08 |
| | % CV | 2.0% | 2.9% | 2.7% | 4.6% | 1.9% | 2.0% | 2.9% | 2.0% | 2.4% | 3.5% | 2.4% | 2.5% | 2.2% |
| | N= | 40 | 40 | 40 | 36 | 36 | 36 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 17.0 | 1.3 | 1.2 | 2.2 | 1.8 | 1.7 | 1.5 | 2.2 | 1.9 | 1.8 | 1.9 | 1.9 | 2.0 |
| | SD* | 0.05 | 0.06 | 0.04 | 0.17 | 0.07 | 0.05 | 0.05 | 0.06 | 0.05 | 0.09 | 0.06 | 0.09 | 0.05 |
| | % CV | 2.9% | 4.4% | 3.9% | 7.9% | 3.9% | 3.1% | 3.2% | 2.6% | 2.6% | 4.9% | 2.9% | 5.0% | 2.7% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 36 | 40 | 40 |
| Positive Control | Mean | 23.2 | 2.5 | 1.7 | 3.1 | 2.5 | 2.7 | 2.8 | 3.0 | 2.7 | 2.5 | 2.7 | 2.7 | 2.8 |
| | SD* | 0.62 | 0.10 | 0.04 | 0.16 | 0.04 | 0.07 | 0.07 | 0.07 | 0.08 | 0.16 | 0.06 | 0.08 | 0.05 |
| | % CV | 2.7% | 4.0% | 2.6% | 5.1% | 1.7% | 2.6% | 2.4% | 2.2% | 3.0% | 6.6% | 2.0% | 2.9% | 1.9% |
| | N= | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 36 |
{11}
Intra-assay Site 2
| Clinical Site 2, Lot 2 | ANA Screen - Intra-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Scl-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 44.9 | 2.9 | 2.7 | 3.8 | 3.6 | 3.5 | 3.9 | 3.4 | 3.8 | 3.9 | 3.2 | 3.1 | 2.9 |
| | SD* | 1.06 | 0.09 | 0.07 | 0.09 | 0.09 | 0.07 | 0.11 | 0.12 | 0.10 | 0.16 | 0.10 | 0.12 | 0.10 |
| | % CV | 2.4% | 3.2% | 2.8% | 2.4% | 2.6% | 2.1% | 2.9% | 3.4% | 2.7% | 4.2% | 3.3% | 4.0% | 3.3% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 18.2 | 1.5 | 1.6 | 2.2 | 1.9 | 1.6 | 1.7 | 1.9 | 1.8 | 1.8 | 1.8 | 1.4 | 1.6 |
| | SD* | 0.52 | 0.09 | 0.07 | 0.09 | 0.07 | 0.05 | 0.15 | 0.07 | 0.08 | 0.09 | 0.13 | 0.07 | 0.08 |
| | % CV | 2.9% | 5.5% | 4.4% | 4.3% | 3.9% | 3.1% | 8.6% | 3.5% | 4.3% | 5.2% | 7.1% | 5.1% | 5.2% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Positive Control | Mean | 24.7 | 2.3 | 2.7 | 2.8 | 2.8 | 3.8 | 3.0 | 2.7 | 2.9 | 3.4 | 2.4 | 3.6 | 2.4 |
| | SD* | 0.72 | 0.09 | 0.07 | 0.13 | 0.10 | 0.12 | 0.09 | 0.07 | 0.11 | 0.14 | 0.08 | 0.14 | 0.09 |
| | % CV | 2.9% | 4.1% | 2.5% | 4.7% | 3.5% | 3.1% | 3.0% | 2.5% | 3.8% | 4.2% | 3.2% | 3.8% | 3.7% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
Intra-Assay Site-3
| Clinical Site 3, Lot 3 | ANA Screen - Intra-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Scl-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 52.8 | 2.8 | 2.6 | 4.7 | 4.2 | 4.0 | 3.7 | 3.7 | 4.7 | 4.3 | 3.8 | 3.9 | 4.2 |
| | SD* | 1.16 | 0.11 | 0.07 | 0.41 | 0.11 | 0.10 | 0.09 | 0.11 | 0.13 | 0.16 | 0.09 | 0.13 | 0.09 |
| | % CV | 2.2% | 3.9% | 2.9% | 8.7% | 2.6% | 2.4% | 2.3% | 3.0% | 2.7% | 3.8% | 2.5% | 3.4% | 2.1% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 19.9 | 1.4 | 1.3 | 2.8 | 2.2 | 2.1 | 1.8 | 1.9 | 2.2 | 2.3 | 2.3 | 2.0 | 2.5 |
| | SD* | 0.72 | 0.07 | 0.05 | 0.25 | 0.10 | 0.08 | 0.05 | 0.05 | 0.07 | 0.10 | 0.06 | 0.10 | 0.08 |
| | % CV | 3.6% | 4.7% | 3.5% | 9.1% | 4.4% | 3.7% | 3.0% | 2.8% | 3.1% | 4.5% | 2.7% | 4.8% | 3.0% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Positive Control | Mean | 26.1 | 2.7 | 2.5 | 3.4 | 3.1 | 3.1 | 2.7 | 3.4 | 3.5 | 2.8 | 2.9 | 3.1 | 2.9 |
| | SD* | 0.60 | 0.07 | 0.08 | 0.38 | 0.08 | 0.08 | 0.07 | 0.07 | 0.10 | 0.09 | 0.07 | 0.11 | 0.09 |
| | % CV | 2.3% | 2.7% | 3.1% | 11.1% | 2.8% | 2.5% | 2.5% | 2.2% | 3.0% | 3.4% | 2.5% | 3.6% | 3.1% |
| | N= | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 36 |
{12}
Inter-Assay Site 1
| Clinical Site 1, Lot 1 | ANA Screen - Inter-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Scl-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 45.6 | 2.7 | 2.4 | 4.1 | 3.4 | 3.6 | 3.3 | 4.0 | 4.1 | 3.8 | 3.3 | 3.9 | 3.7 |
| | SD* | 1.82 | 0.13 | 0.16 | 0.28 | 0.20 | 0.21 | 0.10 | 0.14 | 0.14 | 0.20 | 0.12 | 0.20 | 0.10 |
| | % CV | 4.0% | 4.8% | 6.7% | 6.8% | 5.8% | 5.8% | 3.2% | 3.5% | 3.5% | 5.4% | 3.7% | 5.0% | 2.8% |
| | N= | 40 | 40 | 40 | 36 | 36 | 36 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 17.0 | 1.3 | 1.2 | 2.2 | 1.8 | 1.7 | 1.5 | 2.2 | 1.9 | 1.8 | 1.9 | 1.9 | 2.0 |
| | SD* | 0.60 | 0.08 | 0.06 | 0.21 | 0.08 | 0.08 | 0.07 | 0.09 | 0.08 | 0.12 | 0.12 | 0.12 | 0.11 |
| | % CV | 3.5% | 6.1% | 5.6% | 9.7% | 4.6% | 5.0% | 5.0% | 4.0% | 4.0% | 6.3% | 6.3% | 6.2% | 5.3% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 36 | 40 | 40 |
| Positive Control | Mean | 23.2 | 2.5 | 1.7 | 3.1 | 2.5 | 2.7 | 2.8 | 3.0 | 2.7 | 2.5 | 2.7 | 2.7 | 2.8 |
| | SD* | 2.09 | 0.29 | 0.10 | 0.39 | 0.25 | 0.29 | 0.26 | 0.10 | 0.26 | 0.29 | 0.28 | 0.27 | 0.27 |
| | % CV | 9.0% | 11.7% | 5.8% | 12.8% | 10.0% | 10.7% | 9.5% | 3.2% | 9.7% | 11.6% | 10.5% | 10.1% | 9.8% |
| | N= | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 36 |
Inter-Assay Site 2
| Clinical Site 2, Lot 2 | ANA Screen - Inter-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Scl-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 44.9 | 2.9 | 2.7 | 3.8 | 3.6 | 3.5 | 3.9 | 3.4 | 3.8 | 3.9 | 3.2 | 3.1 | 2.9 |
| | SD* | 3.40 | 0.25 | 0.19 | 0.28 | 0.24 | 0.30 | 0.22 | 0.25 | 0.24 | 0.28 | 0.21 | 0.28 | 0.18 |
| | % CV | 7.6% | 8.8% | 7.2% | 7.4% | 6.8% | 8.4% | 5.8% | 7.2% | 6.3% | 7.2% | 6.5% | 9.0% | 6.2% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 18.2 | 1.5 | 1.6 | 2.2 | 1.9 | 1.6 | 1.7 | 1.9 | 1.8 | 1.8 | 1.8 | 1.4 | 1.6 |
| | SD* | 1.15 | 0.16 | 0.10 | 0.19 | 0.15 | 0.14 | 0.20 | 0.13 | 0.15 | 0.18 | 0.17 | 0.12 | 0.17 |
| | % CV | 6.3% | 10.2% | 6.6% | 8.4% | 8.1% | 8.8% | 11.9% | 6.8% | 8.7% | 10.2% | 9.5% | 9.0% | 10.6% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Positive Control | Mean | 24.7 | 2.3 | 2.7 | 2.8 | 2.8 | 3.8 | 3.0 | 2.7 | 2.9 | 3.4 | 2.4 | 3.6 | 2.4 |
| | SD* | 1.71 | 0.19 | 0.19 | 0.24 | 0.21 | 0.32 | 0.23 | 0.18 | 0.24 | 0.29 | 0.18 | 0.30 | 0.20 |
| | % CV | 7.0% | 8.3% | 7.1% | 8.6% | 7.3% | 8.4% | 7.8% | 6.8% | 8.4% | 8.6% | 7.3% | 8.2% | 8.6% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
{13}
Inter-Assay Site 3
| Clinical Site 3, Lot 3 | ANA Screen - Inter-assay | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | dsDNA (IU/mL) | Chromatin (AI) | RibosomalProtein (AI) | SS-A 52 (AI) | SS-A 60 (AI) | SS-B (AI) | Sm (AI) | SmRNP (AI) | RNP A (AI) | RNP 68 (AI) | Scl-70 (AI) | Jo-1 (AI) | Centromere B (AI) |
| High Positive Panel | Mean | 52.8 | 2.8 | 2.6 | 4.7 | 4.2 | 4.0 | 3.7 | 3.7 | 4.7 | 4.3 | 3.8 | 3.9 | 4.2 |
| | SD* | 2.05 | 0.16 | 0.15 | 0.47 | 0.21 | 0.20 | 0.17 | 0.18 | 0.20 | 0.23 | 0.16 | 0.24 | 0.15 |
| | % CV | 3.9% | 5.6% | 5.9% | 9.8% | 5.1% | 5.0% | 4.5% | 5.1% | 4.2% | 5.5% | 4.3% | 6.0% | 3.6% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Low Positive Panel | Mean | 19.9 | 1.4 | 1.3 | 2.8 | 2.2 | 2.1 | 1.8 | 1.9 | 2.2 | 2.3 | 2.3 | 2.0 | 2.5 |
| | SD* | 1.29 | 0.11 | 0.09 | 0.28 | 0.15 | 0.15 | 0.10 | 0.11 | 0.13 | 0.13 | 0.13 | 0.15 | 0.14 |
| | % CV | 6.5% | 7.9% | 7.0% | 10.0% | 6.8% | 7.2% | 5.5% | 5.8% | 5.6% | 5.9% | 5.7% | 7.2% | 5.5% |
| | N= | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
| Positive Control | Mean | 26.1 | 2.7 | 2.5 | 3.4 | 3.1 | 3.1 | 2.7 | 3.4 | 3.5 | 2.8 | 2.9 | 3.1 | 2.9 |
| | SD* | 1.06 | 0.15 | 0.23 | 0.41 | 0.15 | 0.14 | 0.12 | 0.25 | 0.16 | 0.18 | 0.13 | 0.19 | 0.14 |
| | % CV | 4.1% | 5.6% | 9.5% | 12.0% | 5.0% | 4.5% | 4.5% | 7.5% | 4.6% | 6.4% | 4.4% | 6.0% | 4.8% |
| | N= | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 40 | 36 | 36 | 36 | 36 | 36 |
c. Linearity:
Refer to k041658
d. Carryover:
Refer to k041658
e. Interfering Substances:
Refer to k041658
2. Other Supportive Instrument Performance Data Not Covered Above:
None
K. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
L. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence determination.
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.