ETEST® is a quantitative technique for determination of antimicrobial susceptibility of nonfastidious Gram-negative and Gram-positive aerobic bacteria such as Enterobacteriaceae, Pseudomonas, Staphylococcus, and Enterococcus species and fastidious bacteria, such as anaerobes, N. gonorrhoeae, S. pneumoniae, Streptococcus and Haemophilus species. The system comprises a predefined antibiotic gradient which is used to determine the Minimum Inhibitory Concentration (MIC), in ug/mL, of different antimicrobial agents against microorganisms as tested on agar media using overnight incubation. Telavancin has been shown to be active against the Gram positive aerobic microorganisms listed below, according to the FDA label for this antimicrobial agent. Active both in vitro and in clinical infections: Staphylococcus aureus (including methicillin resistant isolates) Enterococcus faecalis (vancomycin susceptible isolates only)
Device Story
ETEST is a thin, inert, non-porous plastic strip with a predefined antibiotic gradient on one side and an MIC reading scale on the other. Used in clinical microbiology laboratories; applied to inoculated agar surfaces. Antibiotic gradient transfers into agar, forming a stable, continuous, exponential concentration gradient. Following overnight incubation, bacterial growth forms a symmetrical inhibition ellipse. The MIC value is determined by visual inspection where the ellipse intersects the strip. Provides quantitative susceptibility data to assist clinicians in selecting appropriate antimicrobial therapy for patients with bacterial infections.
Clinical Evidence
Performance evaluated by comparing ETEST® Telavancin against CLSI broth microdilution reference method using fresh/stock clinical isolates and challenge strains. Results for S. aureus: 98.4% Essential Agreement (EA), 97.9% Category Agreement (CA). Results for E. faecalis: 91.6% EA, 97.6% CA. Reproducibility and quality control demonstrated acceptable results.
Indicated for determination of antimicrobial susceptibility of Staphylococcus aureus (including MRSA) and Enterococcus faecalis (vancomycin-susceptible only) to telavancin.
Regulatory Classification
Identification
An antimicrobial susceptibility test powder is a device that consists of an antimicrobial drug powder packaged in vials in specified amounts and intended for use in clinical laboratories for determining in vitro susceptibility of bacterial pathogens to these therapeutic agents. Test results are used to determine the antimicrobial agent of choice in the treatment of bacterial diseases.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K180936
B. Purpose for Submission:
To obtain a substantial equivalence determination for telavancin at concentrations of 0.002 – 32 µg/mL for susceptibility testing of Gram positive aerobic microorganisms with ETEST.
C. Measurand:
Telavancin 0.002 – 32 µg/mL
D. Type of Test:
Quantitative AST growth-based detection
E. Applicant:
bioMérieux, Inc.
F. Proprietary and Established Names:
ETEST Telavancin (TLA) (0.002 – 32 µg/mL)
G. Regulatory Information:
1. Regulation section:
866.1640 Antimicrobial Susceptibility Test Powder
2. Classification:
II
3. Product code:
JWY – Manual Antimicrobial Test Systems
4. Panel:
83 – Microbiology
{1}
H. Intended Use:
1. Intended use(s):
ETEST is a quantitative technique for determination of antimicrobial susceptibility of non-fastidious Gram-negative and Gram-positive aerobic bacteria such as Enterobacteriaceae, Pseudomonas, Staphylococcus, and Enterococcus species and fastidious bacteria, such as anaerobes, N. gonorrhoeae, S. pneumoniae, Streptococcus and Haemophilus species. The system comprises a predefined antibiotic gradient which is used to determine the Minimum Inhibitory Concentration (MIC), in $\mu \mathrm{g} / \mathrm{mL}$, of different antimicrobial agents against microorganisms as tested on agar media using overnight incubation.
Telavancin has been shown to be active against the Gram positive aerobic microorganisms listed below according to the FDA label for this antimicrobial agent.
Active both in vitro and in clinical infections:
Staphylococcus aureus (including methicillin-resistant isolates)
Enterococcus faecalis (vancomycin-susceptible isolates only)
2. Indication(s) for use:
Same as the Intended Use
3. Special conditions for use statement(s):
For prescription use only
Limitations:
- Due to the lack of an intermediate category and the observed trending for Telavancin, testing of S. aureus and E. faecalis have resulted in major discrepancies for isolates that are otherwise within essential agreement with the reference method. If critical to patient care, testing should be repeated using an alternative testing/reference method prior to reporting results for S. aureus when the ETEST TLA MIC is $0.25\mu \mathrm{g} / \mathrm{mL}$ and $0.5\mu \mathrm{g} / \mathrm{mL}$ for E. faecalis.
4. Special instrument requirements:
N/A
I. Device Description:
ETEST consists of a thin, inert and non-porous plastic strip $5\mathrm{mm}$ wide and $60~\mathrm{mm}$ long. One side of the strip carries a three letter code designating the identity of the antibiotic and is calibrated with MIC values in terms of $\mu \mathrm{g} / \mathrm{mL}$. On the reverse, a predefined exponential gradient of the dried and stabilized antibiotic covers a continuous concentration range across
{2}
15 two-fold dilutions of a conventional MIC method.
J. Substantial Equivalence Information:
1. Predicate device name(s):
ETEST Ceftaroline
2. Predicate 510(k) number(s):
K151873
3. Comparison with predicate:
3
{3}
Table 1. Comparison with the Predicate Device
| Similarities | | |
| --- | --- | --- |
| Item | Device K180936 ETEST Telavancin | Predicate K151873 ETEST Ceftaroline |
| Intended Use | ETEST is a quantitative technique for determination of antimicrobial susceptibility of non-fastidious Gram-negative and Gram-positive aerobic bacteria such as Enterobacteriaceae, Pseudomonas, Staphylococcus, and Enterococcus species and fastidious bacteria, such as anaerobes, N. gonorrhoeae, S. pneumoniae, Streptococcus and Haemophilus species. The system comprises a predefined antibiotic gradient which is used to determine the Minimum Inhibitory Concentration (MIC), in μg/mL, of different antimicrobial agents against microorganism as tested on agar media using overnight incubation. | Same |
| Antimicrobial Concentration Range | 0.002 – 32 μg/mL | Same |
| Test Design | A predefined exponential gradient of the dried and stabilized antibiotic covers a continuous concentration range across 15 two-fold dilutions of a conventional MIC method. | Same |
| Inoculation | Isolated colonies from culture | Same |
| Result | MIC | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device K180936 ETEST Telavancin | Predicate K151873 ETEST Ceftaroline |
| Claimed organisms | S. aureus (including MRSA), E. faecalis (vancomycin-susceptible only) | S. agalactiae, S. pneumoniae, H. influenza |
| Antimicrobial Agent | Telavancin | Ceftaroline |
| Incubation | 35°±2°C for 16–20 hours | 35°±2°C for 20–24 hours |
{4}
5
K. Standard/Guidance Document Referenced (if applicable):
Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA
CLSI M07-A10, Method for Dilution Antimicrobial Susceptibility Tests for Bacteria That Grow Aerobically; Approved Standard, January 2015.
CLSI M100-S26, Performance Standards for Antimicrobial Susceptibility Testing; Volume 36, No. 1, January 2016.
L. Test Principle:
The ETEST consists of a thin, inert, nonporous plastic strip that is used to determine the antimicrobial susceptibility of bacteria. One side of the strip carries the minimum inhibitory concentration (MIC) reading scale expressed in $\mu \mathrm{g} / \mathrm{mL}$. The other side of the strip contains a predefined continuous gradient of antibiotic concentrations.
When the strip is applied to an inoculated agar surface, the preformed antibiotic gradient immediately transfers into the agar matrix, then forming a stable, continuous and exponential gradient of antibiotic concentrations directly underneath the strip. Bacteria growth becomes visible during incubation, and a symmetrical inhibition ellipse centered along the strip appears. After incubation, the MIC value is read from the scale in terms of $\mu \mathrm{g} / \mathrm{mL}$ at complete inhibition of bacterial growth, where the pointed end of the ellipse intersects the strip. Since ETEST generates MIC values which fall between two-fold dilutions for interpretation, the MIC value read must be recorded to the next two-fold dilution.
The MIC gradient on ETEST Telavancin ranges from 0.002 to $32~\mu \mathrm{g / mL}$.
M. Performance Characteristics:
1. Analytical performance:
a. Precision/Reproducibility:
A reproducibility study was conducted at three external sites using 10 isolates of Gram positive organisms that were consistent with the intended use. Testing was performed on three separate days and in triplicate for a total of 270 data points among the sites. The isolates tested included five S. aureus and five E. faecalis isolates.
The mode MIC was determined and the reproducibility was calculated based on MIC values that fell within $\pm$ one doubling dilution from the mode MIC value. All results were on-scale and within $\pm 1$ doubling dilution of the mode MIC value for telavancin. The overall reproducibility was $100.0\%$.
b. Linearity/assay reportable range:
{5}
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Inoculum Density Check. Inoculum density checks were performed for all quality control and reproducibility organism suspensions and for 10% of the suspensions prepared for susceptibility testing of the fresh clinical isolates. The mean inoculum density was acceptable at 4.40 X 10⁵ CFU/mL.
Purity Check. All clinical, challenge and reproducibility test suspensions were subcultured to assure purity.
Growth or Device Failure. There were no growth or device failures during the course of the study.
Quality Control Testing. Organisms recommended by both FDA and the CLSI were tested with telavancin at three sites. The QC organisms tested included S. aureus ATCC 29213 and E. faecalis ATCC 29212. These QC strains were tested a minimum of 20 times per site by both the ETEST and the reference method. The results demonstrate that the telavancin ETEST can produce quality control results in the recommended range >95% of the time. See Table 2 below for a summary of the QC results.
Table 2. Quality Control Data for Telavancin
| QC organism | Telavancin expected range (μg/mL) | Concentration (μg/mL) | Reference | ETEST |
| --- | --- | --- | --- | --- |
| S. aureus ATCC 29213 | 0.03 – 0.12 | 0.016 | - | - |
| | | 0.03 | 60 | 6 |
| | | 0.06 | 20 | 71 |
| | | 0.12 | 1 | 4 |
| | | 0.25 | - | - |
| | | | | |
| E. faecalis ATCC 29212 | 0.03 – 0.12 | 0.016 | - | - |
| | | 0.03 | - | - |
| | | 0.06 | 75 | 41 |
| | | 0.12 | 6 | 40 |
| | | 0.25 | - | - |
d. Detection limit:
Not applicable
e. Analytical specificity:
Not applicable
{6}
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
Results obtained with ETEST telavancin were compared to results obtained with the CLSI broth microdilution reference panel. The CLSI panel was prepared and interpreted in accordance with the CLSI Standard: CLSI Document M07-A10, Methods for Dilution Antimicrobial Susceptibility Tests for Bacteria that Grow Aerobically; Approved Standard – Tenth Edition, Vol. 35, No. 2; January 2015. The testing conditions for the reference method consisted of the following:
- Medium – Cation-adjusted Mueller Hinton Broth with appropriate dilutions of antimicrobial solution added
- Inoculum – Direct colony suspension to achieve a turbidity equivalent to a 0.5 McFarland standard
- Incubation 35 °C in ambient air; 16-20 hours for all organisms
Clinical testing was performed at three sites using a total of 561 clinical isolates (31 vancomycin-resistant *E. faecalis* isolates, 228 vancomycin-susceptible *E. faecalis* isolates, and 302 *S. aureus* isolates). Of the clinical isolates, 462 were fresh isolates (82.4%) and 99 were stock isolates (17.6%). Clinical isolates were tested using both ETEST and the reference method.
A total of 104 challenge isolates were also tested by ETEST and the reference method (seven vancomycin-resistant *E. faecalis* isolates, 23 vancomycin-susceptible *E. faecalis* isolates, and 74 *S. aureus* isolates). Testing of challenge isolates was conducted at a single site.
Combined clinical and challenge isolates (665 including vancomycin-resistant *E. faecalis*) included: 38 vancomycin-resistant *E. faecalis* isolates, 251 vancomycin-susceptible *E. faecalis* isolates, and 376 *S. aureus* isolates. Of the 376 *S. aureus* isolates tested, 181 isolates were methicillin-resistant (MRSA) and 189 were methicillin-susceptible. Of the 376 *S. aureus* isolates tested, the methicillin-resistance status was unavailable at the time of testing for 6 isolates.
For *S. aureus*, the combined results from clinical and challenge testing demonstrated a combined EA of 98.4% and CA of 97.9% (Table 3). Eight major errors were identified resulting in an overall major error rate of 2.2%. There were no very major errors. Results were acceptable.
For vancomycin-susceptible *E. faecalis*, the combined results from clinical and challenge testing demonstrated a combined EA of 91.6% and CA of 97.6% (Table 3).
7
{7}
Six major errors were identified resulting in an overall major error rate of $2.4\%$ . There were no very major errors. Results were acceptable. The 31 vancomycin-resistant E. faecalis isolates that were tested were also identified as non-susceptible to telavancin by the ETEST. This organism is not an indication for telavancin, however, they were included in the study to evaluate the ability of the ETEST to evaluate resistance.
The overall EA and CA of the Telavancin ETEST was acceptable. However, given the lack of an intermediate interpretive criteria breakpoint and the observed trending (see below) towards higher MIC value by ETEST compared to the reference method, the following limitation was included in the labeling to instruct users to retest using an alternative method for S. aureus isolates that result with an MIC of $0.25\mu \mathrm{g / mL}$ and $0.5\mu \mathrm{g / mL}$ for E. faecalis.
Due to the lack of an intermediate category and the observed trending for Telavancin, testing of S. aureus and E. faecalis have resulted in major discrepancies for isolates that are otherwise within essential agreement with the reference method. If critical to patient care, testing should be repeated using an alternative testing/reference method prior to reporting results for S. aureus when the ETEST® TLA MIC is $0.25\mu \mathrm{g / mL}$ and $0.5\mu \mathrm{g / mL}$ for E. faecalis.
Table 3 . Performance of Clinical and Challenge Isolates, Telavancin ETEST.
| | Tot | No. EA | EA % | Eval Tot | No. Eval EA | Eval EA % | No. CA | CA % | No. NS | min | maj | vmj |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| S. aureus (MSSA) | | | | | | | | | | | | |
| Clinical | 163 | 160 | 98.2 | 163 | 160 | 98.2 | 163 | 100 | 0 | NA | 0 | 0 |
| Challenge | 26 | 25 | 96.2 | 26 | 25 | 96.2 | 25 | 96.2 | 0 | NA | 1 | 0 |
| Combined | 189 | 185 | 97.9 | 189 | 185 | 97.9 | 188 | 99.5 | 0 | NA | 1 | 0 |
| S. aureus (MRSA) | | | | | | | | | | | | |
| Clinical | 139 | 137 | 98.6 | 139 | 137 | 98.6 | 137 | 98.6 | 3 | NA | 2 | 0 |
| Challenge | 42 | 42 | 100 | 42 | 42 | 100 | 41 | 97.6 | 2 | NA | 1 | 0 |
| Combined | 181 | 179 | 98.9 | 181 | 179 | 98.9 | 178 | 98.3 | 5 | NA | 3 | 0 |
| S. aureus (all) | | | | | | | | | | | | |
| Clinical | 302 | 297 | 98.3 | 302 | 297 | 98.3 | 300 | 99.3 | 3 | NA | 2 | 0 |
| Challenge | 74 | 73 | 98.6 | 74 | 73 | 98.6 | 68 | 91.9 | 2 | NA | 6 | 0 |
| Combined | 376 | 370 | 98.4 | 376 | 370 | 98.4 | 368 | 97.9 | 5 | NA | 8 | 0 |
| E. faecalis (vancomycin-susceptible) | | | | | | | | | | | | |
| Clinical | 228 | 208 | 91.2 | 228 | 208 | 91.6 | 245 | 97.6 | 0 | NA | 5 | 0 |
| Challenge | 23 | 22 | 95.7 | 23 | 22 | 95.7 | 22 | 95.7 | 0 | NA | 1 | 0 |
| Combined | 251 | 230 | 91.6 | 251 | 230 | 91.6 | 245 | 97.6 | 0 | NA | 6 | 0 |
| E. faecalis (vancomycin-resistant) | | | | | | | | | | | | |
| Clinical | 31 | 31 | 100 | 12 | 12 | 100 | 31 | 100 | 31 | NA | 0 | 0 |
| Challenge | 7 | 7 | 100 | 0 | 0 | NA | 7 | 100 | 7 | NA | 0 | 0 |
| Combined | 38 | 38 | 100 | 12 | 12 | 100 | 38 | 100 | 38 | NA | 0 | 0 |
| E. faecalis (all) | | | | | | | | | | | | |
| Clinical | 259 | 239 | 92.3 | 240 | 220 | 91.7 | 254 | 98.1 | 31 | NA | 5 | 0 |
{8}
| Challenge | 30 | 29 | 96.7 | 23 | 22 | 95.7 | 29 | 96.7 | 7 | NA | 1 | 0 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Combined | 289 | 268 | 92.7 | 263 | 242 | 92 | 283 | 97.9 | 38 | NA | 6 | 0 |
| All organisms (excluding vancomycin-resistant E. faecalis) | | | | | | | | | | | | |
| Clinical | 530 | 505 | 95.3 | 530 | 505 | 95.3 | 523 | 98.7 | 3 | NA | 7 | 0 |
| Challenge | 97 | 95 | 97.9 | 97 | 95 | 97.9 | 90 | 92.8 | 2 | NA | 7 | 0 |
| Combined | 627 | 600 | 95.7 | 627 | 600 | 95.7 | 613 | 97.8 | 5 | NA | 14 | 0 |
| All organisms (including vancomycin-resistant E. faecalis) | | | | | | | | | | | | |
| Clinical | 561 | 536 | 95.5 | 542 | 517 | 95.4 | 554 | 98.8 | 34 | NA | 7 | 0 |
| Challenge | 104 | 102 | 98.1 | 97 | 95 | 97.9 | 97 | 93.3 | 9 | NA | 7 | 0 |
| Combined | 665 | 638 | 95.9 | 639 | 612 | 95.8 | 651 | 97.9 | 43 | NA | 14 | 0 |
EA - Essential Agreement (+/- 1 dilution)
min - minor discrepancies
CA - Category Agreement
maj - major discrepancies
EVAL - Evaluable isolates
vmj - very major discrepancies
R - Resistant isolates
Essential Agreement (EA) occurs when the result of the reference method and that of ETEST Telavancin are within plus or minus one serial two-fold dilution of the antibiotic. Evaluable results are those that are on scale for both ETEST Telavancin and the reference method. Category Agreement (CA) occurs when the interpretation of the result of the reference method agrees exactly with the interpretation of ETEST Telavancin.
## MIC Trending
An analysis was conducted to evaluate trending in MIC values. Trending was observed (Table 4) for each species tested for both S. aureus and E. faecalis tending to be in exact agreement or higher when compared to the reference method. The difference between higher and lower dilutions for E. faecalis was 72.11% and 63.83% for S. aureus. The following footnotes were included in the labeling to indicate this trending:
ETEST Telavancin MIC values tended to be in exact agreement or one doubling dilution higher when testing Staphylococcus aureus compared to the reference broth microdilution method.
ETEST Telavancin MIC values tended to be one doubling dilution higher when testing Enterococcus faecalis compared to the reference broth microdilution method.
Table 4. Trending for S. aureus and E. faecalis (vancomycin-susceptible)
| Total | ≥2 dil. lower | 1 dil. lower | Exact | 1 dil. higher | ≥2 dil. higher |
| --- | --- | --- | --- | --- | --- |
| E. faecalis^{a} (vancomycin-susceptible) | | | | | |
| 251 | 0 | 3 | 64 | 163 | 21 |
| | (1.2%) | | (25.5%) | (73.31%) | |
| S. aureus^{b} (MSSA + MRSA) | | | | | |
| 376 | 0 | 3 | 130 | 237 | 6 |
| | (0.8%) | | (34.57%) | (64.63%) | |
aDifference between the higher and lower dilutions for vancomycin-susceptible E. faecalis is: 72.11%; 95% C.I. (65.89% to 77.26%).
bDifference between the higher and lower dilutions for S. aureus (MSSA + MRSA) is: 63.83%; 95% C.I. (58.64% to 68.52%).
{9}
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):
No applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Table 5. Interpretive Criteria (Breakpoints) for Telavancin
| Organism | Interpretive Criteria for Telavancin (MIC, μg/mL) | | |
| --- | --- | --- | --- |
| | S | I | R |
| S. aureus (including MRSA) | ≤0.12 | NA | NA |
| E. faecalis (vancomycin-susceptible only) | ≤0.25 | NA | NA |
N. Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
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.