K142826 · Siemens Healthcare Diagnostics, Inc. · LGD · Dec 22, 2015 · Microbiology
Device Facts
Record ID
K142826
Device Name
ADVIA Centaur Toxoplasma M (Toxo M)
Applicant
Siemens Healthcare Diagnostics, Inc.
Product Code
LGD · Microbiology
Decision Date
Dec 22, 2015
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3780
Device Class
Class 2
Indications for Use
The ADVIA Centaur Toxoplasma M (Toxo M) assay is an IgM antibody capture microparticle direct chemiluminometric in vitro diagnostic immunoassay intended for the qualitative detection of IgM antibodies to Toxoplasma gondii in serum or plasma (EDTA, heparin) using the ADVIA Centaur and ADVIA Centaur XP systems. The ADVIA Centaur Toxo M assay is used to measure IgM antibody against T. gondii which is presumptive of an acute, recent, or reactivated toxoplasma infection. Any measurement of IgM antibody to T. gondii must be performed in conjunction with the determination of IgG antibody to T. gondii.
Device Story
The ADVIA Centaur Toxo M assay is an automated in vitro diagnostic immunoassay for detecting IgM antibodies to Toxoplasma gondii. It uses an immunoglobulin class-capture sandwich principle on ADVIA Centaur and ADVIA Centaur XP systems. The system dispenses 10 µL of patient sample and 340 µL of paramagnetic particles coated with mouse anti-human IgM; after incubation, it adds a tracer reagent containing T. gondii antigen complexed with acridinium-ester-labeled anti-p30 monoclonal antibody. Following further incubation and wash steps, acid and base reagents are added to trigger a chemiluminescent reaction. The system measures relative light units (RLUs) to determine an Index Value, classifying samples as reactive, equivocal, or nonreactive. The assay is performed in clinical laboratories by trained personnel. Results assist clinicians in identifying acute or reactivated toxoplasmosis when interpreted alongside IgG antibody status.
Clinical Evidence
Bench testing only. Method comparison study of 1,111 specimens (985 patient, 126 panel) compared the modified assay to the predicate. Patient specimens showed 99.4% positive percent agreement (PPA) and 99.8% negative percent agreement (NPA). Panel specimens showed 98.1% PPA and 100.0% NPA. Precision met acceptance criteria (≤15% total CV). Cross-reactivity and endogenous interference studies showed no significant impact on assay performance.
Technological Characteristics
Immunoglobulin class-capture sandwich immunoassay; chemiluminometric detection. Components: paramagnetic particles coated with mouse anti-human IgM; Lite Reagent with T. gondii antigen and acridinium-labeled mouse anti-p30 F(ab)2 fragment. Buffer systems: Tricine (pH 8.0) with Tween-20, sm-BSA, and mouse IgG. Automated on ADVIA Centaur/XP systems. Standards: CLSI EP05-A2, CLSI EP07-A2, EN 13640, ANSI/AAMI/ISO 14971.
Indications for Use
Indicated for qualitative detection of IgM antibodies to Toxoplasma gondii in serum or plasma (EDTA, heparin) to aid in the presumptive diagnosis of acute, recent, or reactivated toxoplasma infection. Must be used in conjunction with IgG antibody testing. Not for blood, plasma, or tissue donor screening.
Regulatory Classification
Identification
Toxoplasma gondii serological reagents are devices that consist of antigens and antisera used in serological tests to identify antibodies to Toxoplasma gondii in serum. Additionally, some of these reagents consist of antisera conjugated with a fluorescent dye (immunofluorescent reagents) used to identify Toxoplasma gondii from clinical specimens. The identification aids in the diagnosis of toxoplasmosis caused by the parasitic protozoan Toxoplasma gondii and provides epidemiological information on this disease. Congenital toxoplasmosis is characterized by lesions of the central nervous system, which if undetected and untreated may lead to brain defects, blindness, and death of an unborn fetus. The disease is characterized in children by inflammation of the brain and spinal cord.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K142826
B. Purpose for Submission:
To seek clearance for modification of the ADVIA Centaur Toxoplasma M (Toxo M) assay
C. Measurand:
Toxoplasma IgM antibodies
D. Type of Test:
Immunoglobulin Class-Capture Chemiluminescence Immunoassay
E. Applicant:
Siemens Healthcare Diagnostic, Inc.
F. Proprietary and Established Names:
ADVIA Centaur Toxoplasma M (Toxo M)
G. Regulatory Information:
1. Regulation section:
21CFR 866.3780; Toxoplasma gondii Serological Reagents
2. Classification:
Class II
3. Product code:
LGD; Enzyme Linked Immunosorbent Assay, Toxoplasma gondii
4. Panel:
83, Microbiology
{1}
H. Intended Use:
1. Intended use(s):
The ADVIA Centaur Toxoplasma M (Toxo M) assay is an IgM antibody capture microparticle direct chemiluminometric in vitro diagnostic immunoassay intended for the qualitative detection of IgM antibodies to *Toxoplasma gondii* in serum or plasma (EDTA, heparin) using the ADVIA Centaur and ADVIA Centaur XP systems.
The ADVIA Centaur Toxo M assay is used to measure IgM antibody against *T. gondii* which is presumptive of an acute, recent, or reactivated toxoplasma infection. Any measurement of IgM antibody to *T. gondii* must be performed in conjunction with the determination of IgG antibody to *T. gondii*.
2. Indication(s) for use:
The ADVIA Centaur Toxoplasma M (Toxo M) assay is an IgM antibody capture microparticle direct chemiluminometric in vitro diagnostic immunoassay intended for the qualitative detection of IgM antibodies to *Toxoplasma gondii* in serum or plasma (EDTA, heparin) using the ADVIA Centaur and ADVIA Centaur XP systems.
The ADVIA Centaur Toxo M assay is used to measure IgM antibody against *T. gondii* which is presumptive of an acute, recent, or reactivated toxoplasma infection. Any measurement of IgM antibody to *T. gondii* must be performed in conjunction with the determination of IgG antibody to *T. gondii*.
3. Special conditions for use statement(s):
The detection of toxoplasma IgM in a given specimen, as determined by assays from different manufacturers, can vary due to differences in assay methods and reagent specificity. The results reported by the laboratory to the physician must include the identity of the toxoplasma IgM assay used. Values obtained with different assay methods cannot be used interchangeably. The reported IgM level cannot be correlated to an endpoint titer.
This assay is not intended for use in screening blood, plasma, or tissue donors. The effectiveness of this assay for use in screening blood, plasma, or tissue donors has not been established.
4. Special instrument requirements:
ADVIA Centaur and ADVIA Centaur XP
I. Device Description:
The modified ADVIA Centaur Toxo M Assay is comprised of the following:
{2}
- ADVIA Centaur Toxo M Lite Reagent (10.0mL/pack)
- Partially purified T. gondii antigen (~3 µg/mL) complexed with a mouse anti-T. gondii p30 monoclonal antibody (F(ab)2 fragment) labeled with acridinium ester in protein buffer with surfactant and preservatives
- ADVIA Centaur Toxo M Solid Phase (17.0mL/pack)
- Mouse anti-human IgMμ monoclonal antibody (~24 µg/mL) covalently coupled to paramagnetic particles in protein buffer with surfactant and preservatives
- ADVIA Centaur Toxo M calibrators (600 µL/vial)
- Defibrinated recalcified processed human plasma positive for toxoplasma IgM antibodies with preservatives.
- ADVIA Centaur Toxo M Controls (1.5mL/vial)
- Defibrinated recalcified processed human plasma negative and positive for toxoplasma IgM antibodies with preservatives.
J. Substantial Equivalence Information:
1. Predicate device name(s):
ADVIA Centaur Toxoplasma M (Toxo M)
2. Predicate 510(k) number(s):
K010755
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device: ADVIA Centaur Toxoplasma M | Predicate: ADVIA Centaur Toxoplasma M |
| | K142826 | K010755 |
| Intended Use | The ADVIA Centaur Toxoplasma M (Toxo M) assay is an IgM antibody capture microparticle direct chemiluminometric in vitro diagnostic immunoassay intended for the qualitative detection of IgM antibodies to Toxoplasma gondii in serum or plasma (EDTA, heparin) using the ADVIA Centaur and ADVIA Centaur XP systems. The ADVIA Centaur Toxo M assay is used to measure IgM antibody against T. gondii which is presumptive of an acute, recent, or reactivated toxoplasma infection. Any measurement of | Same |
{3}
| Similarities | | |
| --- | --- | --- |
| Item | Device: ADVIA Centaur Toxoplasma M | Predicate: ADVIA Centaur Toxoplasma M |
| | K142826 | K010755 |
| | IgM antibody to T. gondii must be performed in conjunction with the determination of IgG antibody to T. gondii. | |
| Sample Type | Serum or plasma (EDTA, heparin) | Same |
| Sample Volume | 10 μL | Same |
| Instrument platforms | ADVIA Centaur
ADVIA Centaur XP | Same |
| Calibration | 2-point calibration using Toxo M Calibrators | Same |
| Capture Antibody (Solid Phase) | Mouse anti-human IgMμ monoclonal antibody | Same |
| Tracer (Lite Reagent) | Toxoplasma p30 antigen bound to acridinium ester (via mouse anti-T. gondii p30 monoclonal antibody) | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | K142826 | K010755 |
| Toxoplasma IgM Source (Calibrators, Controls) | Cell culture supernatant of human anti-toxoplasma IgM monoclonal antibody-producing cells | Toxoplasma IgM positive human plasma pools |
| Particle Resuspension | Particle re-suspension with Wash 1 (phosphate buffered saline) | Particle re-suspension with water |
| Lite Reagent Conjugate | Ab format = F(ab): fragment
Ab Concentration = 12.5 ng/mL
Conjugate Loading Ratio = 18:1 | Ab format = Whole IgG
Ab Concentration = 30 ng/mL
Conjugate Loading Ratio = 30:1 |
| Solid Phase Buffer | Buffer: Tricine (pH = 8.0)
NaCl: 300 mM
Surfactant: Tween-20 = 2.2g/L
Blocker: sm-BSA = 10.0 g/L
Mouse IgG: 100 mg/L
EDTA: 0.7 g/L | Buffer: Tris (pH =8.0)
NaCl: 150 mM
Surfactant: CHAPS = 0.1 g/L
Blocker: Gelatin = 22.2 g/L
Mouse IgG: 25 mg/L
EDTA: none |
| Claimed Measuring Range | 0.10–10.00 Index | 0.10–40.00 Index |
K. Standard/Guidance Document Referenced (if applicable):
The following recognized standards from Clinical Laboratory Standards Institute (CLSI) were used as a basis of the study procedures described in this submission:
{4}
- Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline– Second Edition (CLSI EP05-A2, 2004; Recognition No. 7-110)
- Interference Testing in Clinical Chemistry; Approved Guideline – Second Edition (CLSI EP07-A2, 2005; Recognition No. 7-127)
- Stability testing of in vitro diagnostic reagents (European Committee for Standardization EN 13640:2002; Recognition No. 7-84)
- Medical devices – Application of risk management to medical devices (ANSI/AAMI/ISO 14971:2007/(R)2010; Recognition No. 5-70)
## L. Test Principle:
The ADVIA Centaur Toxo M assay is an immunoglobulin class-capture sandwich immunoassay using direct, chemiluminometric technology. The anti-human IgM monoclonal antibody is covalently coupled to paramagnetic particles in the Solid Phase. In the Lite Reagent, the *T. gondii* antigen is complexed with an anti-p30 monoclonal antibody (F(ab)2 fragment) labeled with acridinium ester. Antibody-antigen complexes will form if toxoplasma IgM is present in the sample.
ADVIA Centaur systems automatically perform the following steps for the Toxo M assay:
- Dispenses 10 µL of sample into a cuvette.
- Dispenses 340 µL of Solid Phase and incubates the mixture for 18 minutes at 37°C.
- Separates the Solid Phase from the mixture and aspirates the unbound reagent.
- Washes the cuvette with Wash 1.
- Dispenses 200 µL Lite Reagent and incubates the mixture for 18 minutes at 37°C.
- Separates the Solid Phase from the mixture and aspirates the unbound reagent.
- Washes the cuvette with Wash 1.
- Dispenses 300 µL each of Acid Reagent and Base Reagent to initiate the chemiluminescent reaction.
- Reports results according to the selected option, as described in the system operating instructions or in the online help system
A direct relationship exists between the amount of toxoplasma IgM activity present in the patient sample and the amount of relative light units (RLUs) detected by the system. A result of reactive (positive) or nonreactive (negative) is automatically determined using an Index Value.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
Precision of the modified ADVIA Centaur Toxo M assay was evaluated according to CLSI EP05-A2. The study was conducted for 20 days with 2 runs per day using 1 lot of reagents and 2 instruments. The materials tested consisted of lot-specific
{5}
calibrators, one lot of controls, and four patient samples (low positive, moderate positive, high positive). For each run, samples were tested in duplicate. Within-run CV and total CV were calculated. The predetermined acceptance criteria of ≤ 10% (with in run CV) and ≤ 15% (total CV) for specimens ranging from 0.4 to 0.9 Index and ≤ 8% (with in run CV) and ≤ 12% (total CV) for specimens ≥ 1.0 index. The within-run and total precision obtained with the modified ADVIA Centaur Toxo M reagents on the ADVIA Centaur (XP) system meets acceptance criteria.
b. Linearity/assay reportable range:
The modified ADVIA Centaur Toxo M assay is a qualitative assay. Linearity studies are not applicable. The assay reportable range is 0.10–10.00 Index.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Stability:
Stability studies were performed to establish the in-use stability claims (onboard stability and calibration interval) for modified ADVIA Centaur Toxo M reagents kept onboard the ADVIA Centaur (XP) system. The onboard stability of the ADVIA Centaur Toxo M reagents is 28 days with a calibration interval of 14 days. The reagents and calibrators are stable until the date printed on the box label when stored at 2-8°C. The claimed shelf-life of the modified ADVIA Centaur Toxo M reagents and calibrators are 14 months.
The predetermined acceptance criteria were met and the results claim the 28-day on board stability claim with the 14 day calibration interval for the for modified ADVIA Centaur Toxo M reagents on the ADVIA Centaur (XP) system.
d. Detection limit:
Not applicable
e. Analytical specificity:
Cross-Reactivity:
The performance of the modified ADVIA Centaur Toxo M assay was evaluated in the presence of 204 potentially cross-reacting substances using two lots of reagent. The results are summarized in Table 1 below.
6
{6}
Table 1. Summary of Results from Cross-Reactivity Study
| Sample Type | Lot 1 | | | | Lot 2 | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | N | Neg | Equivocal | Pos | Neg | Equivocal | Pos |
| Anti-mitochondrial antibody (AMA) | 15 | 15 | 0 | 0 | 15 | 0 | 0 |
| Anti-nuclear antibody (ANA) | 19 | 19 | 0 | 0 | 19 | 0 | 0 |
| Human anti-mouse antibody (HAMA) | 25 | 24 | 1 | 0 | 24 | 1 | 0 |
| Rheumatoid factor (RF) | 29 | 29 | 0 | 0 | 29 | 0 | 0 |
| Multiple Myeloma IgM | 13 | 13 | 0 | 0 | 13 | 0 | 0 |
| anti-Cytomegalovirus (CMV) IgM | 14 | 14 | 0 | 0 | 14 | 0 | 0 |
| anti-Epstein Barr (EBV) IgM | 16 | 16 | 0 | 0 | 16 | 0 | 0 |
| anti-Herpes Simplex (HSV) IgM | 20 | 20 | 0 | 0 | 20 | 0 | 0 |
| anti-Measles (Rubeola) IgM | 10 | 10 | 0 | 0 | 10 | 0 | 0 |
| anti-Parvovirus B19 IgM | 10 | 10 | 0 | 0 | 10 | 0 | 0 |
| anti-Syphilis IgM | 12 | 12 | 0 | 0 | 12 | 0 | 0 |
| anti-Varicella Zoster (VZV) IgM | 21 | 21 | 0 | 0 | 21 | 0 | 0 |
| Total | 204 | 203 | 1* | 0 | 203 | 1* | 0 |
*This sample was equivocal in lot 1 and lot 2 when tested with the modified ADVIA Centaur Toxo M assay and negative when tested with the unmodified predicate ADVIA Centaur Toxo M assay.
The predetermined acceptance criteria were no false positive results with any interfering disease states tested. The results demonstrated no false positives results found, the results of the cross reactivity study were acceptable.
# Endogenous Interference:
The performance of the modified ADVIA Centaur Toxo M assay was evaluated according to CLSI EP07-A2 in the presence of low and high levels of endogenous substances (hemoglobin, conjugated and unconjugated bilirubin, triglycerides (intralipids), and total protein). Samples in 3 matrices (serum, LiHep plasma, and EDTA plasma) from 3 donors were spiked with toxoplasma IgM at three levels (negative, low positive and high positive), then the potentially-interfering endogenous substance were added. The results are pooled and summarized in Table 2 below.
The bias was calculated as follows for the low positive and high positive samples:
$$
\%Bias = \frac{\text{Index of Interferent-Spiked Sample} - \text{Index of Diluent-Spiked Sample}}{\text{Index of Diluent-Spiked Sample}}
$$
Table 2. Toxo IgM Results in the Presence of Endogenous Substance at the Indicated Levels
| Endogenous Substance | Endogenous Substance Levels | | Bias | |
| --- | --- | --- | --- | --- |
| | | Negative Toxo IgM | Low Positive Toxo IgM | High Positive Toxo IgM |
| Hemoglobin | 250 mg/dL, 500 mg/dL | Negative | <10% | <10% |
| Triglycerides (Intralipid) | 500 mg/dL, 1000 mg/dL | Negative | <10% | <10% |
| Unconjugated Bilirubin | 20 mg/dL, 40 mg/dL | Negative | <10% | <10% |
| Conjugated Bilirubin | 30 mg/dL, 60 mg/dL | Negative | <10% | <10% |
| Protein | 3 g/dL, 12 g/dL | Negative | <10% | <10% |
{7}
For nonreactive specimens, all samples (serum, LiHep plasma, and EDTA plasma) remained negative in the presence of interferents at the levels tested. For both low positive and high positive toxoplasma IgM spiking levels in each matrix (serum, LiHep plasma, and EDTA plasma) and across matrices, the calculated bias was below 10% for all interferents: therefore the predefined acceptance criteria of nonreactive samples must remain nonreactive in the presence of interferents and for reactive samples, the grand mean % difference in Index (across all 3 matrices) must be less than 10% were met.
f. Assay cut-off:
The modifications to the ADVIA Centaur Toxo M assay did not alter the cutoff (as reported in K010755).
- Samples with a calculated value of less than 0.9 Index are considered nonreactive (negative).
- Samples with a calculated value between 0.9 and 0.99 Index are considered equivocal.
- Samples with a calculated value greater than or equal to 1.0 Index are considered reactive (positive).
2. Comparison studies:
a. Method comparison with predicate device:
The method comparison study was conducted by assaying 1111 clinical specimens. The testing included: 1) Panel specimens (n = 126) containing well characterized clinical specimens and 2) Patient specimens (n = 985) consisting of prenatal specimens, prospective, and characterized specimens with known clinical status from various locations, including the US and France.
Specimens were assayed in single replicate on ADVIA Centaur (XP) with the modified ADVIA Centaur Toxo M assay and the unmodified predicate ADVIA Centaur Toxo M assay.
Table 3 shows results obtained for the 985 patient specimens. The composition of the patient specimens is as follows:
- 98 prenatal specimens (Source: US)
- 164 prenatal specimens (Source: France)
- 507 prospective (Source: US)
- 187 characterized (Source: US)
- 25 characterized (Source: France)
- 4 characterized (Source: in-house)
8
{8}
Table 3. Percent Agreement (Modified vs Unmodified Toxo M): Patient specimens
| | Unmodified Predicate
ADVIA Centaur Toxo M | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Reactive | Equivocal | Nonreactive | Total |
| Modified
ADVIA Centaur Toxo M | Reactive | 163 | 0 | 2 | 165 |
| | Equivocal | 1 | 0 | 1 | 2 |
| | Nonreactive | 1 | 0 | 817 | 818 |
| | Total | 165 | 0 | 820 | 985 |
The two specimens that produced equivocal results in the modified ADVIA Centaur Toxo M assay were removed from the analysis. Therefore the total numbers of reactive and non-reactive specimens were 164 and 819, respectively. The positive percent agreement was 99.4% (163/164) with a 95% confidence interval (CI) of 96.65%–99.98%, and the negative percent agreement was 99.8% (817/819) with 95% CI of 99.12%–99.97%.
Table 4 shows the results obtained for panel specimens. The composition of the panel specimens is as follows:
- 100 members of the CDC Toxoplasma performance panel (includes 35 positives)
- 22 members of a Toxoplasma performance panel (Source: Germany)
- 4 members of the Toxo M QC panel (Source: in-house)
Table 4. Percent Agreement (Modified vs Unmodified Toxo M): Panel Specimens
| | Unmodified Predicate
ADVIA Centaur Toxo M | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Reactive | Equivocal | Nonreactive | Total |
| Modified
ADVIA Centaur Toxo M | Reactive | 53 | 1 | 0 | 54 |
| | Equivocal | 1 | 0 | 0 | 1 |
| | Nonreactive | 1 | 0 | 70 | 71 |
| | Total | 55 | 1 | 70 | 126 |
The two specimens that produced equivocal results (one specimen each by the modified and unmodified assay) were removed from the analysis. Therefore the total number of reactive specimens was 54. The number of non-reactive specimens was not affected. The positive percent agreement was 98.1% (53/54) with 95% CI of 90.11%–99.95%, and the negative percent agreement was 100.0% (70/70) with 95% CI of 94.87%–100.00%.
The acceptance criteria as defined by the sponsor, for the modified ADVIA Centaur Toxo M assay compared to the unmodified predicate ADVIA Centaur Toxo M assay was as follows:
- Positive Percent Agreement ≥97.21%
- Negative Percent Agreement ≥98.56%
{9}
These results met the acceptance criteria for both patient specimens and panel specimens.
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
The unmodified predicate ADVIA Centaur Toxo M assay was designed to have a positive cutoff of 1.00 Index. The cutoff for the unmodified predicate ADVIA Centaur Toxo M assay was originally established by running a known population of 1295 samples using the unmodified predicate ADVIA Centaur Toxo M assay and adjusting the cutoff Index value between known positives and non-positives to 1.0.
The modifications to the current modified ADVIA Centaur Toxo M assay did not alter the cutoff.
Expected values/Reference range:
The incidence of toxoplasmosis varies considerably by the geographic location and age of patient as indicated in Table 5.
10
{10}
Table 5. Toxoplasmosis Incidence As Reported in Literature
| Location | Seroprevalence Rate |
| --- | --- |
| France, Italy | 50–85%, by region |
| Germany | 20–72%, by region |
| United Kingdom | 20% |
| Japan | 24% |
| Africa | 20–65%, by country |
| S. America | 36–82%, by country |
| N. America | 8–38%, by region |
# N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
# O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.