K173217 · Techlab, Inc. · LQP · Jan 22, 2018 · Microbiology
Device Facts
Record ID
K173217
Device Name
CAMPYLOBACTER QUIK CHEK
Applicant
Techlab, Inc.
Product Code
LQP · Microbiology
Decision Date
Jan 22, 2018
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.3110
Device Class
Class 1
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K173217 · Jan 22, 2018
CAMPYLOBACTER QUIK CHEK
Techlab, Inc.
Retrospective clinical specimens
A retrospective study of 30 previously collected, culture-positive clinical specimens was conducted to supplement the prospective clinical performance data.
Retrospective study; Clinical specimens
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Retrospective analysis of clinical specimens
Patients ranging from <11 months to 74 years with Campylobacter spp. culture-positive stool samples; Sample Size: 30
Not applicable for this study
Sensitivity/Correlation with culture and other molecular methods
Indications for Use
The CAMPYLOBACTER QUIK CHEK™ test is a rapid membrane enzyme-linked immunosorbent assay for the qualitative detection of a Campylobacter-specific antigen in human fecal specimens. The CAMPYLOBACTER QUIK CHEK™ test is designed to detect C. jejuni and C. coli from patients with symptoms of gastroenteritis. The test is intended for use with unpreserved human fecal specimens and fecal specimens that are in transport media. Test results should be considered in conjunction with clinical findings and patient history
Device Story
Rapid membrane enzyme-linked immunosorbent assay (ELISA) for qualitative detection of Campylobacter-specific antigens in human stool; utilizes monoclonal/polyclonal antibodies immobilized on membrane cassette; visual interpretation of blue lines in reaction window; 'T' line indicates presence of antigen; 'C' line confirms proper sample migration and reagent activity; performed in clinical microbiology laboratories; results interpreted by healthcare providers alongside clinical findings and patient history; aids in diagnosis of gastroenteritis; provides rapid identification of C. jejuni and C. coli.
Clinical Evidence
Prospective study of 1552 stool specimens across four sites; sensitivity 97.1% (95% CI: 85.5%–99.9%) and specificity 99.1% (95% CI: 98.5%–99.5%) compared to culture. Retrospective study of 30 culture-positive specimens showed 100% correlation with commercial EIA, molecular tests, and sequencing. No performance differences observed based on age or gender.
Indicated for qualitative detection of Campylobacter-specific antigen (C. jejuni and C. coli) in human fecal specimens from patients with signs and symptoms of gastroenteritis.
Regulatory Classification
Identification
Campylobacter fetus serological reagents are devices that consist of antisera conjugated with a fluorescent dye used to identify Campylobacter fetus from clinical specimens or cultured isolates derived from clinical specimens. The identification aids in the diagnosis of diseases caused by this bacterium and provides epidemiological information on these diseases. Campylobacter fetus is a frequent cause of abortion in sheep and cattle and is sometimes responsible for endocarditis (inflammation of certain membranes of the heart) and enteritis (inflammation of the intestines) in humans.
{0}
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
A. 510(k) Number:
K173217
B. Purpose for Submission:
To obtain a substantial equivalence determination for the detection of Campylobacter jejuni and Campylobacter coli antigens in human stool.
C. Measurand:
Campylobacter jejuni and Campylobacter coli antigens
D. Type of Test:
Qualitative membrane enzyme immunoassay
E. Applicant:
TechLab Inc.
F. Proprietary and Established Names:
CAMPYLOBACTER QUIK CHEK
G. Regulatory Information:
1. Regulation section:
21 CFR 866.3110 Camplobacter fetus serological reagents
2. Classification:
I
3. Product code:
LQP
1
{1}
4. Panel:
83 Microbiology
**H. Intended Use:**
1. Intended use(s):
The *CAMPYLOBACTER QUIK CHEK*™ test is a rapid membrane enzyme-linked immunosorbent assay for the qualitative detection of a *Campylobacter*-specific antigen in human fecal specimens. The *CAMPYLOBACTER QUIK CHEK*™ test is designed to detect *C. jejuni* and *C. coli* from patients with symptoms of gastroenteritis. The test is intended for use with unpreserved human fecal specimens and fecal specimens that are in transport media. Test results should be considered in conjunction with clinical findings and patient history
2. Indication(s) for use:
The *CAMPYLOBACTER QUIK CHEK*™ test is a rapid membrane enzyme-linked immunosorbent assay for the qualitative detection of a *Campylobacter*-specific antigen in human fecal specimens. The *CAMPYLOBACTER QUIK CHEK*™ test is designed to detect *C. jejuni* and *C. coli* from patients with symptoms of gastroenteritis. The test is intended for use with unpreserved human fecal specimens and fecal specimens that are in transport media. Test results should be considered in conjunction with clinical findings and patient history
3. Special conditions for use statement(s):
- For prescription use only
- Optimal results with the *CAMPYLOBACTER QUIK CHEK* test are obtained with specimens that are less than 96 hours old. If specimens are not assayed within this time period, they may be frozen.
- Fecal specimens preserved in 10% Formalin, merthiolate formalin, sodium acetate formalin, or polyvinyl alcohol cannot be used.
- The *CAMPYLOBACTER QUIK CHEK* test is qualitative. The intensity of the color should not be interpreted quantitatively.
- No data exists on the effects of colonic washes, barium enemas, laxatives, or bowel preparations on the performance of the *CAMPYLOBACTER QUIK CHEK* test. All of these procedures can result in extensive dilution or the presence of additives that may affect test performance.
4. Special instrument requirements:
None
2
{2}
# I. Device Description:
The CAMPYLOBACTER QUIK CHEK test uses antibodies to Campylobacter specific antigen in human fecal samples. The device contains a reaction window with two vertical lines of immobilized antibodies. The test line (“T”) contains antibodies against Campylobacter specific antigen. The control line (“C”) contains anti-IgG antibodies. The Conjugate consists of antibodies to a Campylobacter-specific antigen coupled to horseradish peroxidase. The “T” reaction is examined visually for the appearance of a vertical blue line on the “T” side of the Reaction Window. A blue line indicates a positive test. A positive “C” reaction, indicated by a vertical blue line on the “C” side of the reaction window, monitors/confirms that the sample and reagents were added correctly, the reagents were active at the time of performing the assay, and that the sample migrated properly through the membrane device. A positive “C” reaction also confirms the reactivity of the other reagents associated with the assay.
# J. Substantial Equivalence Information:
1. Predicate device name(s):
IMMUNOCARD STAT CAMPY
2. Predicate 510(k) number(s):
K090700
3. Comparison with predicate:
Table 1. Comparison of the CAMPYLOBACTER CHECK to IMMUNOCARD STAT CAMPY
| Similarities | | |
| --- | --- | --- |
| Item | Device K173217 | Predicate K090700 |
| Indications for use | The CAMPYLOBACTER QUIK CHEK™ test is a rapid membrane enzyme-linked immunosorbent assay for the qualitative detection of a Campylobacter-specific antigen in human fecal specimens. The CAMPYLOBACTER QUIK CHEK test is designed to detect C. jejuni and C. coli from patients with symptoms of gastroenteritis. The test is intended for use with unpreserved human fecal specimens and fecal specimens that are in transport media. Test results should be considered in conjunction with clinical findings and patient history. | ImmunoCard STAT! CAMPY is an immunochromatographic rapid test for the qualitative detection of specific Campylobacter antigens in human stool. ImmunoCard STAT! CAMPY detects C. jejuni and C. coli in human stool, where stool may be either unpreserved or preserved in Cary-Blair-based transport media. Test results are to be used in conjunction with information available from the patient clinical evaluation and other diagnostic procedures. |
| Measured analyte | Detection of Campylobacter-specific antigens (C. jejuni and C. coli) | Detection of Campylobacter-specific antigens (C. jejuni and C. coli) |
3
{3}
| Similarities | | |
| --- | --- | --- |
| Item | Device K173217 | Predicate K090700 |
| Type of Test | Qualitative | Same |
| Controls | Positive and negative control included in the kit Internal “C” Control line | Same |
| Format | Single Use Membrane Cassette | Same |
| Target Population | Persons suspected of having *Campylobacter* infection | Same |
| Storage | Refrigerated (2°C – 8°C) | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device K173217 | Predicate K090700 |
| Specimen Type | Fecal specimens in Cary-Blair and C&S Transport Media | Fecal specimens in Cary-Blair Transport Media |
| Time to Result | <30 minutes | < 25 minutes |
| Antibody Format | Monoclonal/Polyclonal | Monoclonal/Monoclonal |
# **K. Standard/Guidance Document Referenced (if applicable):**
CLSI EP07-A2 Interference Testing In Clinical Chemistry; Approved Guideline - Second Edition
CLSI EP15-A3 User Verification of Precision And Estimation Of Bias; Approved Guideline - Third Edition
CLSI EP17-A2 Evaluation Of Detection Capability For Clinical Laboratory Measurement Procedures; Approved Guideline - Second Edition
# **L. Test Principle:**
Lateral flow immunochromatographic assay
# **M. Performance Characteristics (if/when applicable):**
# 1. Analytical performance:
# a. *Precision/Reproducibility:*
The reproducibility of the *CAMPYLOBACTER QUIK CHEK* test was determined using an eight member masked fecal specimen panel. The panel consisted of 2 negative, 2 high negative (just below C5), 2 low positive (just above LoD), and 2 moderate positive (2-3x higher than the C95) specimens. Each fecal specimen was spiked using a known concentration of *C. jejuni* whole organism to achieve the desired level. Testing was performed at 2 independent laboratories and on-site at TECHLAB, Inc. The Specimens were tested twice a day in triplicate over a five day
4
{4}
period by multiple technicians at each site using two different kit lots. Positive and negative controls were run with each sample panel of masked specimens. The result from each laboratory were submitted to TECHLAB Inc. and compared. The results were consistent among all three locations with 100% reproducibility for all test panels.
# b. *Linearity/assay reportable range:*
Not applicable
# c. *Traceability, Stability, Expected values (controls, calibrators, or methods):*
The effect of specimen storage on antigen stability was evaluated for both fresh samples and samples in transport media. For the analysis, a total of 20 fecal specimens were tested with the *CAMPYLOBACTER QUIK CHEK* test. The fecal specimens consisted 10 *C. jejuni* low positive fecal samples (1-2 times C95 for whole organisms), 5 *C. jejuni* moderate positive fecal samples (2-3 times C95 for whole organism), and 5 *C. jejuni* high positive fecal samples (4-5 times C95 for whole organism). Both fresh samples and samples stored in Cary Blair and C&S transport media were tested.
For fresh samples, samples were stored between 2°C and 8°C and tested at 24 hour intervals for 120 hours. At the same time positive and negative controls were tested. The following transport media were used for the study: Thermo Scientific *Protocol* Cary Blair media and Meridian Bioscience Inc., *Para-Pak* C&S. As recommended in the package insert, Cary Blair and C&S samples were stored between 20°C and 30°C. Samples stored in transport media were tested at 24 hour intervals for 120 hours.
Positive samples remained positive throughout the study. Storage in transport media did not affect the stability of the samples. Based on these results, the recommended storage time for fresh samples is up to 120 hours between 2°C and 8°C, Cary Blair transport media is up to 96 hours between 20°C and 30°C and C&S transport media is up to 120 hours between 20°C-30°C based on the data and the package insert recommendation.
Freeze/Thaw:
Freeze/Thaw stability for raw specimens was demonstrated for six freeze/thaw cycle over a nine day period. A panel consisting of 20 masked raw stool samples were prepared and tested in duplicates; three true negative, two high negative (1-2 times below C5 (whole organisms)), five low positives (1-2 times C95 (whole organisms)), six moderate positives (2-3 times C95 (whole organisms)) and four high positives (4-5 x LoD (whole organisms)) were tested in raw stool. Based on the data submitted, none of the specimens converted from positive-to-negative or negative-to-positive after any of the freeze/thaw cycles. After six cycles freeze/thawing neither enhances nor impairs the performance of the *CAMPYLOBACTER QUIK CHEK* test.
5
{5}
#### d. Detection limit:
The limit of detection (LoD) for the CAMPYLOBACTER QUIK CHEK test was determined visually using whole organisms of both C. jejuni and C. coli spiked into unpreserved (raw stool) and preserved (Cary Blair and C&S media). The concentrations were calculated in colony forming units per milliliter (CFU/mL) and their equivalent in CFU/test by factoring in the dilutions and the final volume used in the assay. The LoD is the concentrations of organisms that yields a positive result 95% of the time and a negative result 5% of the time. See the LoDs in Table 2 listed by organisms and by stool (unpreserved and preserved).
Table 2. LoD for C. jejuni and C. coli
| C. jejuni | | C. coli | |
| --- | --- | --- | --- |
| CFU/mL | CFU/test | CFU/mL | CFU/test |
| Fecal Matrix | | | |
| \( 8.4 \times 10^{4} \) | 1,300 | \( 7.7 \times 10^{5} \) | 11,700 |
| Cary Blair | | | |
| \( 1.8 \times 10^{5} \) | 2,800 | \( 2.2 \times 10^{6} \) | 34,700 |
| C & S | | | |
| \( 7.2 \times 10^{4} \) | 1,100 | \( 1.6 \times 10^{6} \) | 24,400 |
#### e. Analytical specificity:
The CAMPYLOBACTER QUIK CHEK test was evaluated for cross-reactivity with the bacteria and viruses listed below. C. helveticus (strain 54661) was found to be positive at \( 3.08 \times 10^{6} \) CFU/mL (4 x LoD of C. coli). C. lari (strain 23947) was found to be positive at \( 3.08 \times 10^{6} \) CFU/mL (4 x LoD of C. coli). C. upsaliensis (strain 14913) was found to be positive at \( 1.54 \times 10^{6} \) CFU/mL (2 x LoD of C. coli). All other strains were shown to not interfere with the performance of the CAMPYLOBACTER QUIK CHEK test. Bacteria was spiked at concentration of \( >10^{8} \) CFU/mL and viruses at a range from \( 10^{3.3} \) to \( 10^{8.75} \) TCID \( _{50} \) units per 0.2 mL.
Acinetobacter baumannii
Aeromonas hydrophila
Bacillus subtilis
Campylobacter concisus
Campylobacter hyointestinalis
Candida albicans
Clostridium bifermentans
Clostridium perfringens
Enterobacter cloacae
Escherichia coli
Escherichia coli EPEC
Escherichia coli O157:H7 (non-
Bacillus cereus
Bacteroides fragilis
Campylobacter fetus
Campylobacterhelveticus
Citrobacter freundii
Clostridium difficile
Edwardsiella tarda
Enterococcus faecalis
Escherichia coli EIEC
Escherichia coli ETEC
Escherichia coli O157:H7 (toxigenic)
6
{6}
toxigenic)
Escherichia fergusonii
Helicobacter pylori
Lactobacillus acidophilus
Listeria monocytogenes
Plesiomonas shigelloides
Proteus vulgaris
Pseudomonas areuginosa
Salmonella enterica typhimurium
Shigella dysenteriae
Shigella sonnei
Staphylococcus aureus (Cowan's)
Streptococcus agalactiae
Yersinia enterocolitica
Escherichia hermanii
Klebsiella pneumoniae
Lactococcus lactis
Peptostreptococcus anaerobius
Prophyromonas asaccharolytica
Prevotella melaninogenica
Pseudomonas fluorescens
Serratia marcescens
Shigella flexneri
Staphylococcus aureus
Staphylococcus epidermidis
Vibrio parahaemolyticus
Adenovirus, 1, 2, 3, 5, 40, 41
Coxsackievirus B2, B3, B4, B5
Enterovirus 68, 69, 70, 71
Human Rotavirus
Coronavirus
Echovirus 9, 11, 18, 22, 33
Norovirus
The CAMPYLOBACTER QUIK CHEK test was evaluated for interfering substances with the substances and concentrations listed in Table 3. None of the substances where shown to interfere with the performance of the CAMPYLOBACTER QUIK CHEK test.
Table 3. Interfering Substances
| Barium sulfate (5% w/v) | Benzalkonium Chloride (1% w/v) |
| --- | --- |
| Ciprofloxacin (0.25% w/v) | Hog gastric mucin (3.5% w/v) |
| Human blood (40% v/v) | Imodium® (5% v/v), |
| Kaopectate® (5% v/v) | Maalox® Advanced (5% v/v) |
| Mesalazine (10% w/v) | Metronidazole (0.25% w/v) |
| Mylanta® (4.2 mg/mL) | Naproxen Sodium (5% w/v) |
| Nonoxynol-9 (40% w/v) | Palmitic Acid/Fecal Fat (40% w/v) |
| Pepto-Bismol® (5% v/v) | Phenylephrine (1% w/v) |
| Priolsec OTC® (5 μg/mL) | Sennosides (1% w/v) |
| Simethicone (10% w/v) | Tagamet® (5 μg/mL) (40%w/v) |
| Tagamet® (5 μg/mL) | TUMS (50 μg/mL) |
| Human Urine (5% v/v) | Vancomycin (0.25% w/v) |
# Strain Reactivity Study
The sponsor tested the reactivity of the following Campylobacter stock cultures from different sources at 2x, 4x, and 8x the LoD of each species: C. coli strains 11283, 10956, 17755, 36994, 53138 and C. jejuni strains 11284, 6951, 12081, 29411, 38106, and 24567. All results were positive except for C. coli strain 53138 and 10956 which
7
{7}
was negative at 2x LoD and 4xLOD but positive at 8x LoD. C. coli strain 11283 was negative at 2x LoD but positive at 4x LOD and 8x LoD.
f. Assay cut-off:
Not applicable
g. Prozone:
The purpose of this study was to demonstrate that a high concentration of Camplobacter (antigen) does not interfere with a positive reaction in the CAMPYLOBACTER QUIK CHEK test. High samples were prepared by spiking a negative fecal pool with 5 X 10⁷ whole organisms of C. jejuni and 2.4 X 10⁸ whole organisms of C. coli. A total of 5 different dilutions of C. jejuni and C. coli whole organisms, were prepared and tested. Testing was performed in triplicate according to the Package Insert instructions. The results demonstrated that there was no overall hook affect, and that elevated levels of whole organism did not affect the detection or Campylobacter.
2. Comparison studies:
a. Method comparison with predicate device:
Not applicable
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Prospective Study
The performance of the CAMPYLOBACTER QUIK CHEK test was evaluated at four independent sites. The sensitivity and specificity for the CAMPYLOBACTER QUIK CHEK device was compared directly to culture results at all three sites. Prospective testing consisted of 1552 stool specimens tested in clinical microbiology laboratories at the Medical College of Wisconsin, Penn State Milton S. Hershey Medical Center, TriCore Reference Laboratories and Techlab, Inc.
The ages of patients ranged from less than 1 year to 100 Years with, 15.7% of the specimens coming from patients that were ≤ 18 years. Of the 1552 patients tested 38.7% were female and 61.3% were male. No difference in test performance was observed based on patient age or gender.
8
{8}
Table 4. shows a summary of the clinical performance of the CAMPYLOBACTER QUIK CHEK test for all 4 sites combined. The results of the study show that the CAMPYLOBACTER QUIK CHEK test exhibited a sensitivity of 97.1%, and a specificity of 99.1% with culture.
Table 4. Clinical Performance of the CAMPYLOBACTER QUIK CHEK
| | Culture Positive | Culture Negative |
| --- | --- | --- |
| CAMPYLOBACTER QUIK CHEK Positive | 34 | 13* |
| CAMPYLOBACTER QUIK CHEK Negative | 1** | 1504 |
| Sensitivity (95% C.I.) | 97.1% (85.5% - 99.9%) |
| --- | --- |
| Specificity (95% C.I.) | 99.1%(98.5% - 99.5%) |
* Nine of the specimens were confirmed to be positive for C. jejuni with all test methods. Two of the specimens were confirmed to be positive with the commercial EIA, in-house PCR, and bidirectional sequencing. One of the specimens was confirmed to be positive with an FDA-cleared commercial molecular test, in-house PCR and bidirectional sequencing. One of the specimen was confirmed to be positive for C. upsaliensis by species-specific PCR and sequencing.
** The one specimen was confirmed to be negative for C. jejuni or C. coli with all test methods.
### Retrospective Study
Additional testing was performed on 30 retrospective positive specimens. The patient ages ranged from less than 11 months to 74 years. All retrospective specimens were Campylobacter spp. culture positive and were further characterized as Campylobacter spp. positive by an FDA-cleared commercial Microassay well EIA, an FDA-cleared commercial molecular test, in-house PCR (detecting the 16s rRNA gene of Campylobacter spp., and species-specific identification), and bidirectional sequencing. These specimens were then tested by the CAMPYLOBACTER QUIK CHEK test. All 30 specimens tested positive for Campylobacter spp. by all methods, yielding 100% correlation with all test methods.
#### b. Clinical specificity:
See section M3a. above.
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable.
### 4. Clinical cut-off:
Not applicable.
9
{9}
# 5. Expected values/Reference range:
Not applicable.
# N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Parts 809.10
# O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
10
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.