K062546 · Meridian Bioscience, Inc. · GMZ · Feb 14, 2007 · Microbiology
Device Facts
Record ID
K062546
Device Name
IMMUNOCARD STAT! EHEC, MODEL 751630
Applicant
Meridian Bioscience, Inc.
Product Code
GMZ · Microbiology
Decision Date
Feb 14, 2007
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3255
Device Class
Class 1
Attributes
Pediatric
Indications for Use
ImmunoCard STAT! EHEC is an immunochromatographic rapid test for the qualitative detection of Shiga toxins 1 and 2 (also called Verotoxins) produced by E. coli in cultures derived from clinical stool specimens. ImmunoCard STAT! EHEC is used in conjunction with the patient’s clinical symptoms and other laboratory tests to aid in the diagnosis of diseases caused by enterohemorrhagic E. coli (EHEC) infections.
Device Story
ImmunoCard STAT! EHEC is a rapid, single-use, lateral flow immunochromatographic assay for detecting Shiga toxins 1 and 2 (ST1, ST2) in broth-enriched stool cultures. The device consists of a test strip in a plastic housing. The user applies the sample to a port; the sample migrates through a reaction zone containing gold-labeled monoclonal antibodies specific to ST1 and ST2. If toxins are present, they form complexes with the gold-labeled antibodies, which are then captured by immobilized antibodies in the test window, creating visible red lines. A control line confirms proper flow and reagent activity. The test is performed by laboratory professionals in a clinical setting. Results are interpreted visually by the technician. The output aids clinicians in diagnosing EHEC infections, which can cause life-threatening illness in children, the elderly, and immunocompromised patients. No instruments are required.
Clinical Evidence
Clinical study evaluated 469 samples from US, Canada, and Argentina. Compared ImmunoCard STAT! EHEC against Premier EHEC using GN and MacConkey broths. Mac broth: 93.8% positive agreement (60/64), 99.7% negative agreement (384/385). GN broth: 89.1% positive agreement (57/64), 99.7% negative agreement (380/381). Discrepant samples were negative by reference cytotoxin assay. Analytical sensitivity is 1.25 ng/mL for both toxins. No cross-reactivity observed with 40+ common stool pathogens/flora.
Indicated for the qualitative detection of Shiga toxins 1 and 2 in cultures derived from clinical stool specimens of patients of all ages and genders suspected of having gastroenteritis caused by enterohemorrhagic E. coli (EHEC) infections.
Regulatory Classification
Identification
Escherichia coli serological reagents are devices that consist of antigens and antisera used in serological tests to identify Escherichia coli from cultured isolates derived from clinical specimens. Additionally, some of these reagents consist of Escherichia coli antisera conjugated with a fluorescent dye used to identify Escherichia coli directly from clinical specimens or cultured isolates derived from clinical specimens. The identification aids in the diagnosis of diseases caused by this bacterium belonging to the genus Escherichia, and provides epidemiological information on diseases caused by this microorganism. Although Escherichia coli constitutes the greater part of the microorganisms found in the intestinal tract in humans and is usually nonpathogenic, those strains which are pathogenic may cause urinary tract infections or epidemic diarrheal disease, especially in children.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
K062546
B. Purpose for Submission:
New device clearance
C. Measurand:
Shiga Toxin 1 and Shiga Toxin 2
D. Type of Test:
Immunochromatographic rapid test based on the lateral flow principle
E. Applicant:
Meridian Bioscience, Inc.
F. Proprietary and Established Names:
ImmunoCard STAT! EHEC
G. Regulatory Information:
1. Regulation section: 21 CFR 866.3255
2. Classification: Class I
3. Product code: GMZ
4. Panel: Microbiology (83)
H. Intended Use:
1. Intended use(s):
ImmunoCard STAT! EHEC is an immunochromatographic rapid test for the qualitative detection of Shiga toxins 1 and 2 (also called Verotoxins) produced by *E. coli* in cultures derived from clinical stool specimens. ImmunoCard STAT!
{1}
EHEC is used in conjunction with the patient’s clinical symptoms and other laboratory tests to aid in the diagnosis of diseases caused by enterohemorrhagic *E. coli* (EHEC) infections.
2. **Indication(s) for use:**
Same as Intended Use
3. **Special conditions for use statement(s):**
None
4. **Special instrument requirements:**
None
## I. Device Description:
ImmunoCard STAT! EHEC is an immunochromatographic rapid test utilizing monoclonal antibodies labeled with red-colored gold particles. The test device has a circular sample port and an oval-shaped test (Toxin 1, Toxin 2) and control (Control) window. The maximum number of tests obtained from this test kit is listed on the outer box. The device contents are:
1. ImmunoCard STAT! EHEC Test Devices, containing immobilized monoclonal anti-ST1 and anti-ST2 antibodies. The devices are packaged in individual foil pouches with desiccants.
2. Sample Diluent (Negative Control), a buffered diluent containing 0.094% sodium azide as a preservative. The reagent is supplied in a plastic dropper vial.
3. Positive Control, a solution of formalin-treated ST1 and ST2 toxins in a buffered diluent containing 0.094% sodium azide as a preservative. The reagent is supplied in a plastic dropper vial.
4. 150 µL disposable plastic transfer pipettes
## J. Substantial Equivalence Information:
1. **Predicate device name(s):**
Premier EHEC and Duopath® Verotoxin GLISA
2. **Predicate 510(k) number(s):**
K953362 and K031367, respectively.
{2}
3. Comparison with predicate:
| Characteristics | ImmunoCard STAT! EHEC | Premier EHEC (predicate) | Duopath Verotoxin GLISA (predicate) |
| --- | --- | --- | --- |
| Device Type | | | |
| Technology | Single use, rapid, lateral flow immunoassay | Microwell-based enzyme-linked immunoassay | Single use, rapid, lateral flow immunoassay |
| In vitro diagnostic device | Yes | Yes | Yes |
| Control | Includes external control reagent | Includes external control reagent | No control reagent included |
| Calibrator | No | No | No |
| Assay Features | | | |
| Human factors | No special equipment | EIA-related equipment | No special equipment |
| Sterile device | No | No | No |
| Mechanical safety | Not applicable | Not applicable | Not applicable |
| Environmental safety | Normal medical waste | Normal medical waste | Normal medical waste |
| Chemical hazards | None | None | None |
| Radiation safety | Not applicable | Not applicable | Not applicable |
| Intended Use | | | |
| Detection of Shiga toxins 1 and 2 | Yes | Yes | Yes |
| Differentiation between Shiga toxins 1 and 2 | Yes | No | Yes |
| Screening test | No | No | No |
| Diagnostic test | Yes | Yes | Yes |
| Identification test | Yes | No | Yes |
| Monitoring therapy | No | No | No |
{3}
| Acceptable Samples | ImmunoCard STAT! EHEC | Premier EHEC (predicate) | Duopath Verotoxin GLISA (predicate) |
| --- | --- | --- | --- |
| Stool broth culture | Yes | Yes | No |
| Stool agar culture | Yes | No | Yes |
| Direct stool | No | Yes | No |
| Reagents/Components Provided | | | |
| Test Medium | Test Device with nitrocellulose strip | Antibody-coated microwell | Test Device with nitrocellulose strip |
| Conjugate Reagent | In Test Device | Stand alone reagent | In Test Device |
| Sample Diluent/Negative Control (external) | Yes | Yes | No |
| Substrate Reagent | No | Yes | No |
| Stop Solution | No | Yes | No |
| Procedural/internal control | Yes | No | Yes |
| External positive control | Yes | Yes | No |
| External negative control | Yes | Yes | No |
| Source of Antigens/Antibodies | | | |
| Capture ST1 antibodies | Murine monoclonal | Murine monoclonal | Murine monoclonal |
| Capture ST2 antibodies | Murine monoclonal | Murine monoclonal | Murine monoclonal |
| Detector ST1 Antibodies | Murine monoclonal | Rabbit polyclonal | Murine monoclonal |
| Detector ST2 Antibodies | Murine monoclonal | Rabbit polyclonal | Murine monoclonal |
| Positive Control | Inactivated toxin | Inactivated toxin | None |
| Comparison of assay steps | | | |
| Equipment Required | None | EIA-related | None |
| Level of skill required | Moderately complex | Moderately complex | Moderately complex |
| Assay steps | 5 | 15 | 5 |
| End point | Pink-red band | Yellow color | Pink-red band |
| Interpretation of test result | Pos = color band, Neg = no color | OD ≥ 0.150 (dual wavelength) | Pos = color band, Neg = no color |
{4}
K. Standard/Guidance Document Referenced (if applicable):
Not applicable.
L. Test Principle:
1. The sample is applied to the chromatography paper via the circular sample port (Sample).
2. The sample is absorbed through the pad to the reaction zone containing colloidal, gold-labeled antibodies specific to Shiga toxins.
3. Any Shiga toxin (ST1 and ST2) antigen present complexes with the gold-labeled antibody and migrates through the pad until it encounters the binding zones in the test (Toxin 1, Toxin 2) area.
4. The binding zones (Toxin 1 and Toxin 2) contain another anti-ST1 or -ST2 antibody, which immobilizes any Shiga toxin-antibody complex present. Due to the gold labeling, a distinct red line is then formed.
5. The remainder of the sample continues to migrate to another binding reagent zone within the control zone, and also forms a further distinct red line (positive control). Regardless of whether any Shiga toxin is present or not, a distinct red line should always be formed in the control zone and confirms that the test is working correctly.
M. Performance Characteristics:
1. Analytical performance:
a. Precision/Reproducibility:
Assay precision, intra-assay variability and inter-assay variability were assessed with a reference panel prepared from broths inoculated with ST1 and ST2. Of the 11 samples in the reproducibility panel, 2 were prepared as high positive (HP) samples, four as low positive (LP) samples near the assay limit of detection, 4 as high negative (HN) samples just below the assay limit of detection, and one as a low negative sample (LN). Each clinical site tested the panel twice per day for three consecutive days. The expected results were obtained at each test interval at each site resulting in an assay precision of 100% with no variability.
b. Linearity/assay reportable range:
Not applicable – this is a qualitative test with no numerical output.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Not applicable
{5}
# d. Detection limit:
Method: Diluted broth media was inoculated with defined quantities of Shiga Toxin 1 (ST1) or Shiga Toxin 2 (ST2) toxin, then tested. Results and Conclusions: The results given in Table 12-12 show the analytical sensitivity of the assay is $1.25\mathrm{ng}$ of toxin per mL for both ST 1 and ST 2.
| Toxin | Concentration | Results | | |
| --- | --- | --- | --- | --- |
| | | C | T1 | T2 |
| Shiga Toxin 1 | 20 ng | + | + | - |
| | 10 ng | + | + | - |
| | 5 ng | + | + | - |
| | 2.5 ng | + | + | - |
| | 1.25 ng | + | + | - |
| | 0.625 ng | + | - | - |
| | | | | |
| Shiga Toxin 2 | 20 ng | + | - | + |
| | 10 ng | + | - | + |
| | 5 ng | + | - | + |
| | 2.5 ng | + | - | + |
| | 1.25 ng | + | - | + |
| | 0.625 ng | + | - | - |
Legend: C = Control Line, T1 = Shiga toxin 1 test line, T2 = Shiga toxin 2 test line
# e. Analytical specificity:
Method: Broth media was inoculated with different Shiga toxin-producing strains of $E$ coli, then tested. Results and Conclusions: The following 39 STEC stock cultures were cultivated in GN or MacConkey broth. O157:H7 (32 strains), O157:NM (1), O111:NM (2), O111:H21 (1), O121:H19 (1), O126:H27 (1), O45:H2 (1). All of the isolates produced positive reactions on ImmunoCard STAT! EHEC.
Legend: GN= Gram negative broth, Mac = MacConkey broth, C = Control Line, T1 = Shiga toxin 1 test line, T2 = Shiga toxin 2 test line
| | | | ImmunoCard STAT! EHEC | | |
| --- | --- | --- | --- | --- | --- |
| E. coli strain | Broth | ID | C | T1 | T2 |
| O157:NM | GN | Microbank 95 ATCC 700277 | + | - | + |
| O157:NM | Mac | Microbank 95 ATCC 700277 | + | - | + |
| O157:H7 | GN | Microbank 70 EMDI-67 | + | + | + |
| O157:H7 | Mac | Microbank 70 EMDI-67 | + | + | + |
Table is continued on the next page.
{6}
| | | | ImmunoCard STAT! EHEC | | |
| --- | --- | --- | --- | --- | --- |
| E. coli strain | Broth | ID | C | T1 | T2 |
| O157:H7 | GN | Microbank 92 | + | + | + |
| O157:H7 | Mac | Microbank 92 | + | + | + |
| O45:H2 | GN | Microbank 81 | + | + | — |
| O45:H2 | Mac | Microbank 81 | + | + | — |
| O157:H7 | GN | Microbank 22 EMDI-11 | + | + | — |
| O157:H7 | Mac | Microbank 22 EMDI-11 | + | + | — |
| O157:H7 | GN | Microbank 14 EMDI-46 | + | — | + |
| O157:H7 | Mac | Microbank 14 EMDI-46 | + | — | + |
| O121:H19 | GN | Microbank 23 EMDI-17 | + | — | + |
| O121:H19 | Mac | Microbank 23 EMDI-17 | + | — | + |
| O157:H7 | GN | Microbank 28 Dupont 1450 | + | — | + |
| O157:H7 | Mac | Microbank 28 Dupont 1450 | + | — | + |
| O157:H7 | GN | Microbank 65 EMDI-15 | + | + | + |
| O157:H7 | Mac | Microbank 65 EMDI-15 | + | + | + |
| O157:H7 | GN | Microbank 77 | + | + | + |
| O126:H27 | Mac | Microbank 25 EMDI-32 | + | + | — |
| O157:H7 | GN | Microbank 31 EMDI-55 | + | — | + |
| O157:H7 | Mac | Microbank 31 EMDI-55 | + | — | + |
| O157:H7 | GN | Microbank 34 EMDI-121 | + | — | + |
| O157:H7 | Mac | Microbank 34 EMDI-121 | + | — | + |
| O111:NM | Mac | Microbank 8 EMDI-48 | + | + | + |
| O157:H7 | GN | Microbank 24 EMDI-26 | + | — | + |
| O157:H7 | Mac | Microbank 24 EMDI-26 | + | — | + |
| O157:H7 | GN | Microbank 33 EMDI-52 | + | + | + |
| O157:H7 | Mac | Microbank 33 EMDI-52 | + | + | + |
Table is continued on the next page.
{7}
| | | | ImmunoCard STAT! EHEC | | |
| --- | --- | --- | --- | --- | --- |
| E. coli strain | Broth | ID | C | T1 | T2 |
| O157:H7 | Mac | Microbank 7 EMDI-70 | + | + | + |
| O157:H7 | GN | Microbank 40 EMDI-115 | + | + | + |
| O157:H7 | Mac | Microbank 40 EMDI-115 | + | + | + |
| O157:H7 | GN | Microbank 10 EMDI-19 | + | — | + |
| O157:H7 | Mac | Microbank 10 EMDI-19 | + | — | + |
| O157:H7 | GN | Microbank 18 EMDI-2 | + | + | + |
| O157:H7 | Mac | Microbank 18 EMDI-2 | + | + | + |
| O126:H27 | GN | Microbank 25 EMDI-32 | + | + | — |
| O157:H7 | GN | Microbank 35 EMDI-120 | + | + | + |
| O157:H7 | Mac | Microbank 35 EMDI-120 | + | + | + |
| O111:H21 | GN | Microbank 48 EMDI-82 | + | + | + |
| O111:H21 | Mac | Microbank 48 EMDI-82 | + | + | + |
| O157:H7 | GN | Microbank 62 EMDI-116 | + | + | + |
| O157:H7 | Mac | Microbank 62 EMDI-116 | + | + | + |
| O111:NM | GN | Microbank 52 3007-85 | + | + | + |
| O111:NM | Mac | Microbank 52 3007-85 | + | + | + |
| O157:H7 | GN | Microbank 61 EMDI-50 | + | + | + |
| O157:H7 | Mac | Microbank 61 EMDI-50 | + | + | + |
| O157:H7 | GN | Microbank 39 EMDI-54 | + | + | + |
| O157:H7 | Mac | Microbank 39 EMDI-54 | + | + | + |
| O157:H7 | GN | Microbank 51 EMDI-81 | + | + | + |
| O157:H7 | Mac | Microbank 51 EMDI-81 | + | + | + |
| O157:H7 | GN | Microbank 55 EMDI-118 | + | + | + |
Table is continued on the next page.
{8}
| | | | ImmunoCard STAT! EHEC | | |
| --- | --- | --- | --- | --- | --- |
| E. coli strain | Broth | ID | C | T1 | T2 |
| O157:H7 | Mac | Microbank 55
EMDI-118 | + | + | + |
| O157:H7 | GN | Microbank 60
EMDI-76 | + | + | — |
| O157:H7 | Mac | Microbank 60
EMDI-76 | + | + | — |
| O157:H7 | Mac | Microbank 77 | + | + | + |
| O157:H7 | GN | Microbank 89 | + | — | + |
| O157:H7 | Mac | Microbank 89 | + | — | + |
| O157:H7 | GN | Microbank 94
ATCC 43890 | + | — | + |
| O157:H7 | Mac | Microbank 94
ATCC 43890 | + | — | + |
| O157:NM | GN | Microbank 96
ATCC 700376 | + | + | — |
| O157:NM | Mac | Microbank 96
ATCC 700376 | + | + | — |
| O157:H7 | GN | Microbank 63
EMDI-4 | + | + | + |
| O157:H7 | Mac | Microbank 63
EMDI-4 | + | + | + |
| O157:H7 | GN | Microbank 73
EMDI-71 | + | — | + |
| O157:H7 | Mac | Microbank 73
EMDI-71 | + | — | + |
| O157:H7 | GN | Microbank 88 | + | + | + |
| O157:H7 | Mac | Microbank 88 | + | + | + |
| O157:H7 | GN | Microbank 93
ATCC 43885 | + | — | + |
| O157:H7 | Mac | Microbank 93
ATCC 43885 | + | — | + |
| O157:H7 | Mac | Microbank 27
EMDI-46 | + | — | + |
| O157:H7 | GN | Microbank 91 | + | + | + |
| O157:H7 | Mac | Microbank 91 | + | + | + |
# Cross reactivity:
Method: Stool broth cultures containing low levels of Toxin 1 or Toxin 2 were spiked with bacterial, viral and yeast strains that might be expected to be present in human stool samples either as part of normal flora or from a disease state (TEST). The final concentration of bacteria or yeast in each sample was $\geq 7.5 \times 10^{7}$ organisms/mL. The final concentration of viruses in each sample was $\geq 1.6 \times 10^{5}$
{9}
TCID $_{50}$ /mL. Unspiked samples were tested in parallel to provide a reference against which the reactions with spiked samples could be compared (CONTROL). An organism that diminished a positive reaction by 4 or more grades, that caused a positive to become negative, or that caused the appearance of a positive reaction in a formerly negative sample was considered to be an interfering organism. Results: None of the potential co-contaminants of stool samples affected positive or negative test results. No crossreactivity has been observed with this assay for any of the following organisms crossreacted with the ImmunoCard STAT! EHEC: Aeromonas hydrophila Campylobacter coli, Campylobacter jejuni, Candida albicans, Citrobacter freundii, Clostridium difficile, Clostridium perfringens, Enterobacter cloacae, Enterococcus faecalis, Escherichia coli (2 nontoxigenic strains), Escherichia coli O157:H7 (nontoxigenic strain), Escherichia hermanii, Escherichia fergusonii, Helicobacter pylori, Klebsiella pneumoniae, Proteus vulgaris, Pseudomonas aeruginosa, Pseudomonas fluorescens, Salmonella Group B, Salmonella hiversum, Salmonella minnesota, Salmonella typhimurium, Serratia liquifaciens (2 strains), Shigella boydii, Shigella flexeri, Shigella sonnei, Staphylococcus aureus, Staphylococcus aureus (Cowan), Staphylococcus epidermidis, Yersinia enterocolitica (2 strains), Adenovirus Type 14, Adenovirus Type 2, Adenovirus Type 41, Feline calicivirus, Coxsackie A9, Coxsackie B1, Enterovirus Type 69, Herpes Simplex Virus II, Parainfluenza Type 3, Rotavirus.
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
See Clinical Studies
b. Matrix comparison:
The results of each broth method (Gram Negative (GN) or MacConkey (Mac) broth) are compared to each other in following table.
| | Mac Positive | Mac Negative | Mac No Growth | Total |
| --- | --- | --- | --- | --- |
| GN Positive | 54 | 3 | 1 | 58 |
| GN Negative | 3 | 382 | 5 | 390 |
| GN No growth | 4 | 3 | 14 | 21 |
| Total | 61 | 388 | 20 | 469 |
3. Clinical studies:
a. Clinical Sensitivity and Specificity:
This study was conducted with samples tested fresh or following frozen
{10}
storage. Samples were obtained from patients in the United States, Canada and Argentina. Five US laboratories evaluated 469 samples using Mac and GN broths; 120 of the samples were solid stool specimens obtained from patients assumed to have gastroenteritis. There were 448/469 samples which produced growth in GN broth, while 449 produced growth in Mac broth. Three of the GN broth samples were excluded from evaluation with the comparative device due to insufficient volume. Seven of the 469 samples grew in Mac broth only while another 3 samples grew in GN broth only and 14 failed to grow in either broth. Stool specimens were collected from male and female patients of all ages. Samples producing discrepant results between Premier EHEC and ICS EHEC were further analyzed using cytotoxin assay. These samples generally produced weak reactions (<0.300) in Premier EHEC.
| COMPARATIVE METHOD (Premier EHEC) | | | |
| --- | --- | --- | --- |
| Mac Broth Method | | | |
| ICS EHEC | | | |
| | Positive | Negative | Total |
| Positive | 60 | 1 | 61 |
| Negative | 4* | 384 | 388 |
| Total | 64 | 385 | 449 |
| | | | CI |
| Positive agreement | 60/64 | 93.8% | 84.8% - 98.3% |
| Negative agreement | 384/385 | 99.7% | 98.6% - 100% |
| Overall agreement | 444/449 | 98.9% | 97.4% - 99.6% |
* Two ICS EHEC -, Premier EHEC + samples were negative by a reference cytotoxin method.
| COMPARATIVE METHOD (Premier EHEC) | | | |
| --- | --- | --- | --- |
| GN Broth Method | | | |
| ICS EHEC | | | |
| | Positive | Negative | Total |
| Positive | 57 | 1 | 58 |
| Negative | 7* | 380 | 387 |
| Total | 64 | 381 | 445 |
| | | | CI |
| Positive agreement | 57/64 | 89.1% | 78.8% - 95.5% |
| Negative agreement | 380/381 | 99.7% | 98.5% - 100% |
| Overall agreement | 437/445 | 98.2% | 96.5% - 99.2% |
* Four ICS EHEC -, Premier EHEC + sample were negative by a reference cytotoxin method.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
{11}
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Not applicable - this is a qualitative test with no numerical output.
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.
12
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.