Clinical performance evaluation: 404 clinical isolates and 75 challenge isolates
—
Indications for Use
VITEK® 2 AST- Gram Positive Clindamycin Resistance is designed for antimicrobial susceptibility testing of Staphylococcus aureus, Staphylococcus lugdunensis, and Coagulase Negative Staphylococcus spp. VITEK® 2 AST- Gram Positive Inducible Clindamycin Resistance is a qualitative test. It is intended for use with the VITEK® 2 and VITEK® 2 Compact Systems as a laboratory aid in the determination of in vitro susceptibility to antimicrobial agents. The VITEK® 2 Antimicrobial Susceptibility Test (AST) is intended to be used with the VITEK® 2 Systems for the automated quantitative or qualitative susceptibility testing of isolated colonies for the most clinically significant aerobic Gram-negative bacilli, Staphylococcus spp., Enterococcus spp., Streptococcus spp. and yeast.
Device Story
VITEK 2 AST-GP Inducible Clindamycin Resistance (ICR) card; miniaturized, automated doubling dilution technique. Inputs: isolated bacterial colonies in saline suspension. Operation: VITEK 2 system automatically fills, seals, and incubates card; optical scanner monitors growth via light attenuation in 64 micro-wells containing clindamycin or clindamycin/erythromycin. Outputs: qualitative result (Positive/Negative for ICR) and MIC values. Used in clinical laboratories; operated by technicians. Output informs clinicians of inducible clindamycin resistance, guiding antibiotic selection for Staphylococcus infections.
Clinical Evidence
External evaluation conducted using fresh and stock clinical isolates and challenge strains. Performance compared against CLSI broth microdilution reference method (16-20 hours incubation). Results demonstrated 97.7% categorical agreement (CA), 1.5% very major error (VME), and 2.4% minor error (mE). Reproducibility and quality control testing yielded acceptable results.
Technological Characteristics
Miniaturized broth microdilution cards; automated filling, sealing, and incubation/reading system. Compatible with VITEK 2 and VITEK 2 Compact platforms. Operates via optical growth monitoring of wells over time. No specific material standards cited.
Indications for Use
Indicated for antimicrobial susceptibility testing of Staphylococcus aureus, Staphylococcus lugdunensis, and Coagulase Negative Staphylococcus spp. in clinical laboratory settings using VITEK 2 or VITEK 2 Compact systems.
Regulatory Classification
Identification
A fully automated short-term incubation cycle antimicrobial susceptibility system is a device that incorporates concentrations of antimicrobial agents into a system for the purpose of determining in vitro susceptibility of bacterial pathogens isolated from clinical specimens. Test results obtained from short-term (less than 16 hours) incubation are used to determine the antimicrobial agent of choice to treat bacterial diseases.
Special Controls
*Classification.* Class II (special controls). The special control for this device is FDA's guidance document entitled “Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA.”
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
K181766
B. Purpose for Submission:
To obtain a substantial equivalence determination for a modification of Inducible Clindamycin Resistance (ICR) for testing *Staphylococcus aureus*, *Staphylococcus lugdunensis*, and Coagulase Negative *Staphylococcus* spp. (CNS) on the VITEK 2 and VITEK 2 Compact Antimicrobial Susceptibility Test (AST) Systems
C. Measurand:
The VITEK2 AST-GP Inducible Clindamycin Resistance has the following concentrations in the card: Clindamycin 1.5 µg/mL, Clindamycin/Erythromycin at 0.5/2.5 µg/mL.
D. Type of Test:
Automated qualitative test for detection of ICR from *Staphylococcus aureus*, *Staphylococcus lugdunensis*, and Coagulase Negative *Staphylococcus* spp.
E. Applicant:
bioMérieux, Inc.
F. Proprietary and Established Names:
VITEK 2 AST- Gram Positive Inducible Clindamycin Resistance
G. Regulatory Information:
1. Regulation section:
21 CFR 866.1645: Fully Automated Short-Term Incubation Cycle Antimicrobial Susceptibility System
2. Classification:
Class II
3. Product code:
{1}
LON – Fully automated short-term incubation cycle antimicrobial susceptibility system
LTW – Susceptibility Test Cards, Antimicrobial
LTT – Panels, Test, Susceptibility, Antimicrobial
4. Panel:
83- Microbiology
H. Intended Use:
1. Intended use(s):
The VITEK 2 Antimicrobial Susceptibility Test (AST) is intended to be used with the VITEK 2 Systems for the automated quantitative or qualitative susceptibility testing of isolated colonies for the most clinically significant aerobic gram-negative bacilli, Staphylococcus spp., Enterococcus spp., Streptococcus spp. and clinically significant yeast.
2. Indication(s) for use:
VITEK 2 AST-Gram Positive Inducible Clindamycin Resistance is designed for antimicrobial susceptibility testing of Staphylococcus aureus, Staphylococcus lugdunensis, and Coagulase Negative Staphylococcus spp.. VITEK 2 AST- Gram Positive Inducible Clindamycin Resistance is a qualitative test. It is intended for use with the VITEK 2 and VITEK 2 Compact Systems as a laboratory aid in the determination of in vitro susceptibility to antimicrobial agents.
The VITEK 2 Antimicrobial Susceptibility Test (AST) is intended to be used with the VITEK 2 Systems for the automated quantitative or qualitative susceptibility testing of isolated colonies for the most clinically significant aerobic gram-negative bacilli, Staphylococcus spp., Enterococcus spp., Streptococcus spp. and clinically significant yeast.
3. Special conditions for use statement(s):
For Prescription Use Only
Perform an alternative method of testing prior to reporting of results when a Positive (+) result is obtained with the following antibiotic/organism combination(s):
- Inducible Clindamycin Resistance (icr03n): Staphylococcus haemolyticus
4. Special instrument requirements:
VITEK 2 Systems 9.02 (PC version) for all VITEK 2 Systems and VITEK 2 Compact Systems
{2}
I. Device Description:
The VITEK 2 AST card is a miniaturized, abbreviated and automated version of the doubling dilution technique for determining the minimum inhibitory concentration (MIC). Each VITEK 2 AST card contains 64 wells. A control well(s) which contain only nutrient medium is resident on all cards. The remaining wells contain premeasured portions of antimicrobials combined with the nutrient media. The isolate to be tested is diluted to a standardized concentration with 0.45% to 0.50% saline before being used to rehydrate the antimicrobial medium within the card. The VITEK 2 System will automatically dilute the bacterial suspension to prepare an inoculum for susceptibility cards. Then the VITEK 2 will fill, seal and place the card into the incubator/reader. The VITEK 2 Compact has a manual filling, sealing and loading operation. The VITEK 2 Systems monitor the growth of each well in the card over a defined period of time (up to 24 hours for Streptococcus species). The analysis program determines when a well demonstrates growth based on attenuation of light measured by an optical scanner. This data is used to determine the minimum inhibitory concentration or "MIC" values for the anti-microbial agent. At the completion of the incubation cycle, a report is generated that contains the MIC value along with the interpretive category result for each antimicrobial contained on the card.
VITEK2 AST-Gram Positive Inducible Clindamycin Resistance has the following concentrations in the card: Clindamycin 1.5 µg/mL, Clindamycin/Erythromycin at 0.5/2.5 µg/mL (equivalent standard method concentration by efficacy in µg/mL). Results of the VITEK2 AST-Gram Positive Inducible Clindamycin Resistance are reported as Positive (inducible resistance to clindamycin) or Negative (no inducible resistance to clindamycin).
J. Substantial Equivalence Information:
1. Predicate device name(s): VITEK 2 AST-ST Inducible Clindamycin Resistance
2. Predicate 510(k) number(s): K111909
3. Comparison with predicate:
{3}
Table 1: Comparison with Predicate Device
| Similarities | | |
| --- | --- | --- |
| Item | Device VITEK 2 AST- Gram Positive Inducible Clindamycin Resistance K181766 | Predicate VITEK 2 AST- ST Inducible Clindamycin Resistance K111909 |
| Intended Use | The VITEK 2 Antimicrobial Susceptibility Test (AST) is intended to be used with the VITEK 2 Systems for the automated quantitative or qualitative susceptibility testing of isolated colonies for the most clinically significant aerobic gram-negative bacilli, Staphylococcus spp., Enterococcus spp. and clinically significant yeast. | Same |
| Test Method | Automated qualitative antimicrobial susceptibility test for use with the VITEK 2 and VITEK 2 Compact Systems to determine the in vitro susceptibility of microorganisms | Same |
| Inoculum | Standardized saline suspension of test organism | Same |
| Instrument | VITEK 2 and VITEK 2 Compact Systems | Same |
| Antimicrobial Agents | Clindamycin Clindamycin/Erythromycin | Same |
| Analysis Algorithm | Discriminate analysis | Same |
| Differences | | |
| Antimicrobial Concentration | Clindamycin 1.5 μg/mL Clindamycin/Erythromycin 0.5/2.5 μg/mL | Clindamycin 0.5 μg/mL Clindamycin/Erythromycin 0.25/0.5 μg/mL |
| Test Card | AST- Gram Positive (GP) | AST- Streptococcus (ST) |
# K. Standard/Guidance Document Referenced (if applicable):
FDA Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA (Issued August 28, 2009)
- CLSI M07-A10, "Methods for Dilution Antimicrobial Susceptibility Tests for Bacteria that Grow Aerobically; Approved Standard- Tenth Edition" Vol. 35 No. 2 (January 2015)
- CLSI M02-A12, "Methods Standards for Antimicrobial Disk Susceptibility Tests; Approved Standard- Twelfth Edition" Vol. 35 No. 1 (January 2015)
- CLSI M100-S27, "Performance Standards for Antimicrobial Susceptibility Testing"; Twenty-Fourth Informational Supplement, Vol. 37 No. 1 (January 2017)
{4}
L. Test Principle:
The VITEK 2 and VITEK 2 Compact Systems utilize automated growth-based detection using attenuation of light measured by an optical scanner. The optics in the systems uses visible light to directly measure organism growth within each of the 64 micro-wells. Transmittance optics is based on an initial light reading of a well before significant growth has begun. Every 15 minutes throughout the incubation cycle (defined period of time based on the VITEK 2 card), light transmittance readings of each well measures organism growth by the amount of light that is prevented from passing through the well. At the completion of the incubation period, the MIC values and their associated interpretive category results for each antimicrobial on the test card are displayed in an automatically generated report.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A reproducibility study for the VITEK 2 AST-Gram Positive Inducible Clindamycin Resistance card with Clindamycin and Clindamycin/Erythromycin was conducted at three external clinical sites using ten isolates of Staphylococcus spp. consistent with the Intended Use. The isolates tested in the reproducibility study included six Staphylococcus aureus, two Staphylococcus epidermidis, and one each for Staphylococcus haemolyticus and Staphylococcus saprophyticus. The reproducibility set included three S. aureus positive for ICR, three S. aureus negative for ICR, and four coagulase-negative Staphylococcus spp. negative for ICR. Inocula were prepared using both the auto-dilution and manual dilution methods for testing in the VITEK 2 System. Inocula were prepared by the manual dilution method only for use with the VITEK 2 Compact. Testing of ech isolate was performed on three separate days and in triplicate for a total of 270 data points. As a qualitative test, results were evaluated by comparing the VITEK 2 or VITEK 2 Compact results to the expected result for each isolate.
The reproducibility was 100% for VITEK 2 and VITEK 2 Compact for each dilution method.
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Inoculum Density Control
The DensiCHEK Plus was used to standardize the inoculum to a 0.5 McFarland standard. The instrument was standardized daily with all results recorded at each site. Calibration values were within the expected range.
5
{5}
6
# Purity Check
A purity check of all organisms was performed on the dilution tube used to prepare the VITEK 2 card inoculum. Only those cultures that were pure were evaluated in the study.
# Growth Failure Rate
A total of 404 isolates were tested in the clinical study and 75 challenge isolates tested at one external site. All isolates grew.
# Quality Control (QC) Testing
The CLSI recommended QC organisms (Staphylococcus aureus ATCC BAA-976 as negative control and S. aureus ATCC BAA-977 as positive control for ICR) were tested using both the VITEK 2 card and the reference method at each site. Both the automatic dilution and manual dilution methods were used for the VITEK 2 and the manual dilution method was used for the VITEK 2 Compact.
As shown in Table 2 both the auto-dilution and the manual dilution methods for VITEK 2 and the manual dilution for VITEK 2 Compact gave the expected QC result (positive/negative) >95% of the time.
Table 2: Quality Control Summary Results for VITEK 2 (Auto-Dilution and Manual Dilution Methods) and VITEK 2 Compact (Manual Dilution Method)
| Inducible Clindamycin Resistance | VITEK 2 | | | | VITEK 2 Compact | |
| --- | --- | --- | --- | --- | --- | --- |
| | Auto-Dilution | | Manual Dilution | | Manual Dilution | |
| QC Organisms | Reference | Test | Reference | Test | Reference | Test |
| S. aureus
ATCC BAA-976
Expected Result: Negative | 87/87
(100) | 86/87
(98.9) | 87/87
(100) | 87/87
(100) | 86/86
(100) | 86/86
(100) |
| S. aureus
ATCC BAA-977
Expected Result: Positive | 88/88
(100) | 86/88
(97.7) | 88/88
(100) | 86/88
(97.7) | 87/87
(100) | 85/87
(97.7) |
d. Detection limit:
Not applicable
e. Analytical specificity:
Not applicable
f. Assay cut-off:
Not applicable
{6}
# 2. Comparison studies:
The VITEK 2 AST- Gram Positive ICR was compared to the CLSI D-zone reference method using standard disk diffusion procedure. The conditions were:
Medium: Mueller Hinton agar with Clindamycin (CM) $2\mu \mathrm{g}$ disk and Erythromycin (E) $15\mu \mathrm{g}$ disk
Inoculum: Direct colony suspension
- Incubation: $35^{\circ}\mathrm{C}$ in ambient air for 16-18 hours
A $15 - \mu \mathrm{g}$ erythromycin disk was positioned $15\mathrm{mm}$ (edge to edge) from a $2 - \mu \mathrm{g}$ clindamycin disk. After incubation, flattening of the clindamycin zone adjacent to the erythromycin disk (D-zone) indicates inducible clindamycin resistance.
The VITEK 2 ICR test consists of two wells, Clindamycin at concentration of $1.5\mu \mathrm{g / mL}$ and Clindamycin/Erythromycin at concentration of $0.5 / 2.5~\mu \mathrm{g / mL}$ . The VITEK 2 ICR interpretation is shown in Table 3 below. The VITEK 2 ICR results were compared to the reference D-zone results tested at the testing sites and the comparative result is shown in Table 4 below.
Table 3: Interpretation of VITEK 2 AST- GP ICR
| Clindamycin 1.5 μg/mL | Clindamycin/Erythromycin 0.5/2.5 μg/mL | VITEK 2/VITEK 2 Compact ICR Interpretation |
| --- | --- | --- |
| No Growth | No Growth | Negative |
| No Growth | Growth | Positive* |
| Growth | No Growth | Negative |
| Growth | Growth | Negative |
*For conformity with the current CLSI M100 recommendation, a VITEK 2 ICR-positive result has the following comment message in the laboratory report with the 9.02 software release: "This isolate is presumed to be resistant based on detection of inducible clindamycin resistance"
Table 4: ICR Performance * Summary of S. aureus, S. lugdunensis, and CNS
| | Total | CA | %CA | Neg | Pos | maj | vmj |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Staphylococcus aureus | | | | | | | |
| Clinical | 150 | 148 | 98.7 | 128 | 22 | 1 | 1 |
| Challenge | 56 | 56 | 100 | 41 | 15 | 0 | 0 |
| Combined | 206 | 204 | 99.0 | 169 | 37 | 1 (0.6%) | 1 (2.7%)a |
| Staphylococcus lugdunensis | | | | | | | |
| Clinical | 20 | 20 | 100 | 19 | 1 | 0 | 0 |
| Coagulase negative Staphylococcus spp. (CNS)b | | | | | | | |
| Clinical | 234 | 225 | 96.2 | 208 | 26 | 9 | 0 |
| Challenge | 19 | 19 | 100 | 17 | 2 | 0 | 0 |
| Combined | 253 | 244 | 96.4 | 225 | 28 | 9 (6.8%) | 0 |
| All Staphylococcus spp. Combined | | | | | | | |
| Clinical | 404 | 393 | 97.3 | 355 | 49 | 10 | 1 |
| Challenge | 75 | 75 | 100 | 58 | 17 | 0 | 0 |
| Combined | 479 | 468 | 97.7 | 413 | 66 | 10 (2.4%) | 1 (1.5%) |
{7}
a One very major error (vmj) was observed for Staphylococcus aureus during the VITEK 2 AST-Gram Positive Inducible Clindamycin Resistance clinical performance evaluation. Further testing confirms this isolate was constitutively resistant to clindamycin, and therefore the isolate is ICR-negative.
b Staphylococcus epidermidis (68), S. haemolyticus (20), S. hominis (16), S. simulans (14), S. capitis (13), S. saprophyticus (78), S. warneri (41), S. auricularis (1), S. intermedius (1), and S. lentus (1)
# CA-Category Agreement
vmj- very major discrepancies (false ICR-negative)
maj- major discrepancies (false ICR-positive)
CA is when interpretation of the VITEK 2 results agrees exactly with the interpretation of the reference D test
Staphylococcus aureus: One vmj (i.e., false negative) error was observed with S. aureus. The vmj error rate was 2.7%. It was determined to be constitutively resistant to clindamycin upon further analysis. This strain is ICR-negative in accordance with the interpretation noted in Table 3 above.
As a result, the footnote below is included for S. aureus:
"One very major error (vmj) was observed for Staphylococcus aureus during the VITEK 2 AST-GP Inducible Clindamycin Resistance clinical performance evaluation. Further testing confirms this isolate was constitutively resistant to clindamycin, and therefore the isolate is ICR-negative."
# Coagulase Negative Staphylococcus spp. (CNS):
Because of the broad claim for CNS, multiple species were tested and all species were combined for analysis but also was evaluated for each by species. It was noted that the CNS group performance did not meet the acceptance criteria with a maj error rate of $6.8\%$ (9/132). An additional study of 100 CNS was conducted. This study included 67 S. saprophyticus and 33 S. warneri. With the combined data obtained by testing 253 CNS isolates, the CNS maj error rate was $4.0\%$ as demonstrated in Table 5 below.
Table 5: Performance Summary of CNS
| | Total | CA | %CA | Neg | Pos | maj | vmj |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Original Study | | | | | | | |
| Clinical | 134 | 125 | 93.3 | 115 | 19 | 9 | 0 |
| Challenge | 19 | 19 | 100 | 17 | 2 | 0 | 0 |
| Combined | 153 | 144 | 94.1 | 132 | 21 | 9 (6.8%) | 0 |
| Combined (Original plus Additional) | | | | | | | |
| Clinical | 234 | 225 | 96.2 | 208 | 26 | 9 | 0 |
| Challenge | 19 | 19 | 100 | 17 | 2 | 0 | 0 |
| Combined | 253 | 244 | 96.4 | 225 | 28 | 9 (4.0%) | 0 |
Of the nine maj errors, four maj (i.e., false positive) errors were observed with the S. haemolyticus isolates. The maj error rate was $23.5\%$ (4/17). As a result, a limitation for ICR (i.e. icr03n) is included in the limitation section of the package insert:
"Perform an alternative method of testing prior to reporting of results when
{8}
a Positive (+) result is obtained with the following antibiotic/organism combination(s):
- Inducible Clindamycin Resistance (icr03n): Staphylococcus haemolyticus
## All Staphylococcus spp. combined
With the additional testing, the performance of data from 479 Staphylococcus spp. isolates combined is 97.7% CA, 1.5% vmj rate, and 2.4% maj rate; the performance is acceptable.
In addition, for consistency with the current CLSI M100 recommendation, a VITEK 2 ICR-positive result has the following comment message in the laboratory report with the 9.02 software release:
“This isolate is presumed to be resistant based on detection of inducible clindamycin resistance”
## Challenge
A challenge study was performed utilizing auto-dilution and manual dilution for VITEK2 and VITEK 2 Compact on 75 isolates at one external site. No differences observed between these two dilution methods with VITEK 2 and VITEK 2 Compact. Results are shown in Table 6 below.
Table 6: Challenge Isolates Performance Summary
| | Total | CA | CA% | Neg | Pos | Maj | Vmj |
| --- | --- | --- | --- | --- | --- | --- | --- |
| VITEK 2 | | | | | | | |
| Auto | 75 | 75 | 100 | 58 | 17 | 0 | 0 |
| Manual | 75 | 75 | 100 | 58 | 17 | 0 | 0 |
| VITEK 2 Compact | | | | | | | |
| Manual | 75 | 75 | 100 | 58 | 17 | 0 | 0 |
a. Method comparison with predicate device:
Not applicable
b. Matrix comparison:
Not applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
{9}
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Positive: Inducible resistance to clindamycin
Negative: No inducible resistance to clindamycin
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.
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.