The Sensititre 18-24 hour MIC or Breakpoint Susceptibility System with Ceftazidime/Avibactam in the dilutions range of 0.015/4 - 32/4 ug/mL
Applicant
Thermo Fisher Scientific
Product Code
JWY · Microbiology
Decision Date
Dec 21, 2015
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.1640
Device Class
Class 2
Indications for Use
The Sensititre MIC and Breakpoint Susceptibility system is an in vitro diagnostic product for clinical susceptibility testing of non-fastidious Gram negative isolates, comprising of Enterobacteriaceae, Pseudomonas aeruginosa, and other non-Enterobacteriaceae and of non-fastidious Gram positive isolates, comprising of Staphylococcus spp., Enterococcus spp., and Beta haemolytic Streptococci other than S. pneumoniae.
Device Story
Sensititre MIC Susceptibility plates are multi-well micro-titer plates containing dried, stabilized antimicrobials; used for quantitative/qualitative antimicrobial susceptibility testing (AST). Plates are inoculated with bacterial samples using the Sensititre AIM autoinoculator, sealed, and incubated at 34-36°C for 18-24 hours. Bacterial growth is detected via fluorescence technology (OptiRead/Autoreader) or visual inspection (Vizion). Fluorescence is generated when bacterial surface enzymes cleave a non-fluorescent substrate. The Minimum Inhibitory Concentration (MIC) is determined by the lowest dilution of antimicrobial inhibiting growth. Results are used by clinicians to guide antibiotic therapy for non-fastidious Gram-negative and Gram-positive infections. The system provides MIC values and interpretive criteria (S, R) to inform clinical decision-making.
Clinical Evidence
No clinical data provided; substantial equivalence is based on bench testing of the antimicrobial susceptibility test system performance.
Technological Characteristics
Multi-well plastic micro-titer plates; dried, stabilized antimicrobial agents. Sensing principle: fluorogenic substrate cleavage by bacterial surface enzymes. Energy source: electrical (for readers/incubators). Connectivity: standalone or networked (OptiRead/Vizion). Software: automated reading/interpretation. Sterilization: not specified.
Indications for Use
Indicated for clinical susceptibility testing of non-fastidious Gram-negative organisms (Enterobacter cloacae, E. coli, K. oxytoca, K. pneumoniae, P. mirabilis, C. freundii, C. koseri, E. aerogenes, Proteus spp., P. aeruginosa) using Ceftazidime/Avibactam in the dilution range of 0.015/4-32/4 µg/mL.
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.
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
K152774
B. Purpose for Submission:
Addition of Ceftazidime/Avibactam to the Sensititre 18-24 hours MIC or Breakpoint Susceptibility System for non-fastidious gram negative organisms.
C. Measurand:
Ceftazidime/Avibactam 0.015/4 – 32/4 µg/mL
D. Type of Test:
Quantitative Antimicrobial Susceptibility Test (AST) growth based
E. Applicant:
ThermoFisher Scientific
F. Proprietary and Established Names:
Sensititre Susceptibility plates
G. Regulatory Information:
1. Regulation section:
866.1640 Antimicrobial Susceptibility Test Powder
2. Classification:
Class II
3. Product code:
JWY – Manual Antimicrobial Susceptibility Test System
LRG – Instrument for Auto Reader and Instrumentation of Overnight Susceptibility Systems.
{1}
LTT - Panels, Test, Susceptibility, Antimicrobial
4. Panel: Microbiology
H. Intended Use:
1. Intended use(s):
The Sensititre MIC and Breakpoint Susceptibility system is an in vitro diagnostic product for clinical susceptibility testing of non-fastidious Gram negative isolates, comprising of Enterobacteriaceae, Pseudomonas aeruginosa, and other non-Enterobacteriaceae and of non-fastidious Gram positive isolates, comprising of Staphylococcus spp., Enterococcus spp., and Beta haemolytic Streptococci other than S. pneumoniae.
2. Indication(s) for use:
The Sensititre 18-24 hours MIC or Breakpoint Susceptibility System is an in vitro diagnostic product for clinical susceptibility testing for non-fastidious isolates.
This 510(k) is for Ceftazidime/Avibactam the dilution range of 0.015/4 – 32/4 µg/mL for testing non-fastidious gram negative organisms on the Sensititre 18-24 hour MIC panel.
The approved primary “Indications for Use” and clinical significance for non-fastidious gram negative isolates:
Enterobacter cloacae
Escherichia coli
Klebsiella oxytoca
Klebsiella pneumoniae
Proteus mirabilis
Citrobacter freundii
Citrobacter koseri
Enterobacter aerogenes
Proteus spp.
Pseudomonas aeruginosa
3. Special conditions for use statement(s):
For prescription use only
The performance of Ceftazidime/avibactam with Enterobacteriaceae and Pseudomonas aeruginosa was established using the Autoinoculator/AIM autoinoculator. The use of an alternative inoculation system when testing Ceftazidime/avibactam has not been evaluated.
2
{2}
The ability of the Sensititre system to detect isolates that are resistant to Ceftazidime/Avibactam is unknown because a sufficient number of resistant isolates was not available at the time of the comparative testing. If such isolates are observed, they should be submitted to a reference lab.
Enzyme group characterization was not available for all organisms at the time of comparative testing, and therefore the performance of the Sensititre Ceftazidime/Avibactam for non-fastidious gram negative isolates is unknown for the following: Enterobacteriaceae (OXA) and Pseudomonas aeruginosa [AmpC, and loss of outer membrane porin (OprD)].
4. Special instrument requirements:
Sensititre AIM for device inoculation
Sensititre Vizion or OptiRead for device reading
I. Device Description:
Sensititre MIC Susceptibility plate MIC panels are multi-well plastic micro-titer plates, dosed with dried, stabilized antimicrobials. It is a micro-version of the classic broth dilution methods and can provide both qualitative and quantitative susceptibility results. After inoculation, plates are sealed with an adhesive seal, incubated at 34-36°C for 18-24 hours and examined for bacterial growth.
Antimicrobial susceptibility test results can be read manually by visual reading of growth or automatically on an OptiRead®/Autoreader® using fluorescence.
J. Substantial Equivalence Information:
1. Predicate device name(s):
MicroScan Dried Gram-Negative and Gram-Positive MIC/Combo Panels
2. Predicate 510(k) number(s):
K010159
{3}
# 3. Comparison with predicate:
Table 1. Comparison with Predicate Device
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended Use | The Sensititre MIC and Breakpoint Susceptibility System is an in vitro diagnostic product for clinical susceptibility testing of non-fastidious Gram negative isolates, comprising of Enterobacteriaceae, Pseudomonas aeruginosa, and other non-Enterobacteriaceae and of non-fastidious Gram positive isolates, comprising of Staphylococcus spp., Enterococcus spp., and Beta haemolytic Streptococci other than S. pneumoniae | MicroScan Dried Gram-Negative and Gram-Positive MIC/Combo Panel is used to determine quantitative and/or qualitative antimicrobial susceptibility of colonies grown on solid media of rapidly growing aerobic and facultative Gram-Negative bacilli and Gram-Positive cocci |
| Test Panel | 96-well plate dosed with selected antimicrobial agents then dried | Same |
| Test Organism | Non-fastidious gram negative isolates | Same |
| Results Reported | Report results as Minimum Inhibitory Concentration (MIC) and interpretive criteria (S, I, R) | Same |
| Read Method | Automated and Manual | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Reading Method | Results can be read by the following methods:1) Automatically - with the AutoReader/OptiRead (fluorogenic substrate technology)2) On the Vizion - Digital Viewing Device3) Manually - using a manual viewer via visual interpretation of growth | Organism growth/turbidity based reading and interpretation via manual read or MicroScan instrumentation (Walkaway, AutoScan-4) |
| Antimicrobial | Ceftazidime/Avibactam | Gatifloxacin |
| Incubation | 18-24 hours | 16-20 hours |
{4}
5
K. Standard/Guidance Document Referenced:
1. Guidance for Industry and FDA - Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems – August 28, 2009.
2. CLSI M100-S025: Performance Standards for Antimicrobial Susceptibility Testing; Twenty-fifth Informational Supplement
3. CLSI M7-A9: Methods for Dilution Antimicrobial Susceptibility Tests for Bacteria that Grow Aerobically; Approved Standard – Ninth Edition
L. Test Principle:
The Sensititre 18-24 hour MIC or Breakpoint Susceptibility System are multi-well plastic microtitre plates that contain doubled dilution of antibacterial agents. Each plate includes antimicrobial agents at appropriate dilutions. Results can be read manually by visual reading of growth or by use of an automated reader.
The Sensititre autoreader systems (OptiRead®, Autoreader®) utilize fluorescence technology to read the microbroth dilution plates after 18 to 24 hours incubation. The technology involves the detection of bacterial growth by monitoring the activity of specific surface enzymes produced by the test organism. Growth is determined by generating a fluorescent product from a fluorogenic substrate. The non-fluorescent substrate is prepared by conjugating a fluorescent compound to the specific enzyme substrates with a bond which prevents fluorescence. The enzymatic action of the bacterial surface enzymes on the bound non-fluorescent substrate cleaves the bond releasing fluorescence. The amount of fluorescence detected is directly related to the activity of bacterial growth. The MIC is determined by observing the lowest dilution of antimicrobial agent that inhibits growth of the organism. The non-fluorescent (fluorogenic) substrate can be added to the inoculum broth which is dispensed into the test plate at the same time as the test organism, or, the plates can be prepared with the substrate already added to each micro-well.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
A reproducibility study was performed using 25 isolates of non-fastidious gram negative rods (5 E.coli, 4 K. pneumoniae, 3 K. oxytoca, 2 E. cloacae, 2 E. aerogenes, 2 C. koseri, 3 Citrobacter freundii, 2 P. mirabilis, 1 Proteus spp., and 1 P. aeruginosa). The Sensititre AIM was used for plate inoculation. The isolates were tested one time at each of three sites for each reading method (Vizion, OptiRead). The mode MIC value was determined and the reproducibility was calculated based on MICs falling within $\pm 1$ dilution of the mode MIC value. The testing resulted in the overall "best-case" reproducibility results of greater than $95\%$ for both the manual and
{5}
autoreader methods.
b. Linearity/assay reportable range:
Not Applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Organisms recommended by both FDA (CDER) and The CLSI, namely Escherichia coli ATCC 25922, Escherichia coli ATCC 35218, Klebsiella pneumoniae ATCC 700603, and Pseudomonas aeruginosa ATCC 27853, were tested against Ceftazidime/Avibactam. Quality control testing was performed at all study sites using the Sensititre AIM for inoculation, read by the Sensititre Vizion and the Sensititre OptiRead. The following table represents the frequency of the results. All results were within acceptable range.
Table 2. Quality Control Results – Ceftazidime/Avibactam
| ORGANISM | Conc.^{a} (μg/mL) | Reference Panel | Sensititre OptiRead | Sensititre Vizion |
| --- | --- | --- | --- | --- |
| | | | | |
| Escherichia coli
ATCC 25922
(0.06-0.5 μg/mL) | 0.03 | 0 | 0 | 0 |
| | 0.06 | 8 | 9 | 13 |
| | 0.12 | 35 | 34 | 33 |
| | 0.25 | 17 | 17 | 14 |
| | 0.5 | 0 | 0 | 0 |
| | 1 | 0 | 0 | 0 |
| | | | | |
| Escherichia coli
ATCC 35218
(0.03-0.12 μg/m L) | 0.015 | 0 | 0 | 0 |
| | 0.03 | 1 | 10 | 5 |
| | 0.06 | 56 | 48 | 50 |
| | 0.12 | 3 | 2 | 5 |
| | 0.25 | 0 | 0 | 0 |
| | | | | |
| Pseudomonas aeruginosa
ATCC 27853
(0.5-4 μg/mL) | 0.25 | 0 | 0 | 0 |
| | 0.5 | 1 | 16 | 10 |
| | 1 | 49 | 44 | 42 |
| | 2 | 9 | 0 | 8 |
| | 4 | 1 | 0 | 0 |
| | 8 | 0 | 0 | 0 |
| | | | | |
| Klebsiella pneumoniae
ATCC 700603
(0.25-2 μg/mL) | 0.12 | 0 | 0 | 0 |
| | 0.25 | 0 | 9 | 8 |
| | 0.5 | 49 | 46 | 48 |
| | 1 | 11 | 5 | 4 |
| | 2 | 0 | 0 | 0 |
| | 4 | 0 | 0 | 0 |
| | | | | |
{6}
| Klebsiella pneumoniae^{b}
ATCC 700603
(>16 µg/mL) | <16 | 0 | 0 | 0 |
| --- | --- | --- | --- | --- |
| | >16 | 60 | 60 | 60 |
a MIC for ceftazidime in the presence of a fixed concentration of 4 mg/L of avibactam.
b K. pneumoniae ATCC 700603 should be tested against ceftazidime and avibactam and ceftazidime alone to confirm the activity of avibactam in the combination and to ensure that the plasmid encoding the beta-lactamase has not been lost in this strain. The acceptable range for ceftazidime alone is greater than 16 mg/L.
The inoculum density of the quality control organisms tested was determined each day of testing. A total of 214 inoculum density checks were performed. The average colony counts of each quality control organism at each site were within acceptable range.
d. Detection limit:
Not Applicable
e. Analytical specificity:
Not Applicable
f. Assay cut-off:
Not Applicable
2. Comparison studies:
a. Method comparison with predicate device:
The CLSI microbroth dilution panel was prepared according to the CLSI recommendation and used as the reference method. During the course of the clinical trial, all Sensititre dried MIC panels were inoculated using the Sensititre Autoinoculator (AIM).
Clinical testing was conducted at three sites using 269 non-fastidious gram negative rods of the Enterobacteriaceae family (60 E. coli, 30 K. pneumoniae, 30 K. oxytoca, 30 E. cloacae, 29 E. aerogenes, 15 C. koseri, 30 C. freundii, 30 P. mirabilis, and 15 Proteus spp.) and 60 isolates of P. aeruginosa totaling 329 fresh clinical isolates tested. Additional testing of challenge isolates was conducted at one study site. Challenge testing was conducted using 88 non-fastidious gram negative rods of the Enterobacteriaceae family (15 E. coli, 18 K. pneumoniae, 14 K. oxytoca, 5 E. cloacae, 5 E. aerogenes, 5 C. koseri, 10 C. freundii, 11 P. mirabilis, and 5 Proteus spp.) and 5 isolates of P. aeruginosa totaling 93 stock challenge isolates tested.
{7}
The growth rates for the Vizion and OptiRead methods were both greater than 90%. Table 3 and Table 4 below illustrate performance based on essential agreement and category agreement of clinical and challenge isolates for both P. aeruginosa and the Enterobacteriaceae family. Table 3 illustrates performance using the Vizion and Table 4 illustrates performance using the OptiRead.
Table 3. Performance Summary of Gram Negative Organisms - Read by Vizion
| Ceftazidime /Avibactam | Tot | EA N | %EA Total | Total Eval | EA Eval | %EA Eval | CA N | %CA | #R | maj (%) | vmj (%) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Enterobacteriaceae | | | | | | | | | | | |
| Clinical | 269 | 269 | 100 | 262 | 262 | 100 | 268 | 99.6 | 1 | 0 | 1 (100%) |
| Challenge | 88 | 88 | 100 | 84 | 84 | 100 | 88 | 100 | 0 | 0 | 0 |
| Combined | 357 | 357 | 100 | 346 | 346 | 100 | 356 | 99.7 | 1 | 0 | 1(100%) |
| Pseudomonas aeruginosa | | | | | | | | | | | |
| Clinical | 60 | 60 | 100 | 59 | 59 | 100 | 59 | 98.3 | 2 | 0 | 1 (50%) |
| Challenge | 5 | 5 | 100 | 4 | 4 | 100 | 5 | 100 | 1 | 0 | 0 |
| Combined | 65 | 65 | 100 | 63 | 63 | 100 | 64 | 98.5 | 3 | 0 | 1 (33%) |
| Combined Total | | | | | | | | | | | |
| TOTAL | 422 | 422 | 100 | 409 | 409 | 100 | 420 | 99.5 | 4 | 0 | 2 (50%) |
Table 4. Performance Summary of Gram Negative Organisms - Read by OptiRead
| Ceftazidime /Avibactam | Tot | EA N | %EA Total | Total Eval | EA Eval | %EA Eval | CA N | %CA | #R | maj (%) | vmj (%) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Enterobacteriaceae | | | | | | | | | | | |
| Clinical | 269 | 269 | 100 | 259 | 259 | 100 | 268 | 99.6 | 1 | 0 | 1 (100%) |
| Challenge | 88 | 88 | 100 | 84 | 84 | 100 | 87 | 98.9 | 0 | 1 (1.1%) | 0 |
| Combined | 357 | 357 | 100 | 343 | 343 | 100 | 355 | 99.4 | 1 | 1 (0.3%) | 1 (100%) |
| Pseudomonas aeruginosa | | | | | | | | | | | |
| Clinical | 60 | 60 | 100 | 59 | 59 | 100 | 59 | 98.3 | 2 | 0 | 1 (50%) |
| Challenge | 5 | 5 | 100 | 4 | 4 | 100 | 5 | 100 | 1 | 0 | 0 |
| Combined | 65 | 65 | 100 | 63 | 63 | 100 | 64 | 98.5 | 3 | 0 | 1 (33%) |
| Combined Total | | | | | | | | | | | |
| TOTAL | 422 | 422 | 100 | 406 | 406 | 100 | 419 | 99.3 | 4 | 1 (0.2%) | 2 (50%) |
EA - Essential Agreement
CA - Category Agreement
R - resistant isolates
maj - major discrepancies
vmj - very major discrepancies
Note: There are no minor error calculations due to lack of intermediate interpretive criteria
Evaluable results are those that are on-scale for both the reference panel and the Sensititre panel. Essential agreement (EA) occurs when there is agreement between the MIC result of the reference method and that of Sensititre panel within plus or minus one serial two-fold dilution of the antibiotic. Category (CA) occurs when the interpretation of the result of the reference method agrees exactly with the interpretation of the Sensititre panel result.
In each instance, both the percent CA and percent EA consistently fell above 90%, and are therefore acceptable as described in the Class II Special Controls Guidance Document:
{8}
Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA, August 2009. A comparative evaluation of performance data of the manual and autoread methods revealed very little difference.
Two very major discrepancies were observed with the Vizion read method (involving one resistant isolate of K. pneumoniae and one resistant isolate of P. aeruginosa). However taking into consideration the lack of an intermediate breakpoint for ceftazidime/avibactam, FDA examined the MIC data associated with those discrepancies to determine if the values fall within essential agreement compared to reference. The data showed that both very major discrepancies fall within essential agreement of the reference method MIC result, and FDA considers these findings acceptable.
Similarly, two very major discrepancies and one major discrepancy were observed with the OptiRead method (involving one resistant isolate of P. aeruginosa, one resistant isolate of K. pneumoniae, and one susceptible isolate of E. coli, respectively). However taking into consideration the lack of an intermediate breakpoint for ceftazidime/avibactam and the fact that all discrepancies fall within essential agreement of the reference method MIC result, FDA considers these findings acceptable.
Ceftazidime/avibactam performance data was also evaluated for any signs of MIC result trends as illustrated in Table 5 below.
Table 5. Summary of Evaluation of MIC Trends (combined clinical and challenge data)
| Ceftazidime/ Avibactam | Total | 2 dil. lower | 1 dil. lower | Exact | 1 dil. higher | 2 dil. higher |
| --- | --- | --- | --- | --- | --- | --- |
| | Enterobacteriaceae | | | | | |
| Vizion | 357 | 0 | 16.5% (59/357) | 50.4% (180/357) | 33.1% (118/357) | 0 |
| OptiRead | 357 | 0 | 20.7% (74/357) | 46.2% (165/357) | 33.1% (118/357) | 0 |
| | Pseudomonas aeruginosa | | | | | |
| Vizion | 65 | 0 | 30.8% (20/65) | 61.5% (40/65) | 7.7% (5/65) | 0 |
| OptiRead | 65 | 0 | 33.8% (22/65) | 55.4% (36/65) | 10.8% (7/65) | 0 |
As illustrated in Table 5, there was no marked difference in device performance between Vizion and OptiRead methods. However, a difference between organism groups is apparent. The data for the Enterobacteriaceae group demonstrates an upward trend of one doubling dilution in the MIC of ceftazidime/avibactam on the Sensititre panel as compared to that of the reference method $33.1\%$ of the time, for both Vizion and OptiRead methods. This upward trend resulted in only one major discrepancy since the majority of the organisms tested had MIC values which fell well below the susceptible MIC breakpoint of $8/4~\mu \mathrm{g/mL}$ .
Moreover, the data for Pseudomonas aeruginosa demonstrates a downward trend of one doubling dilution in the MIC of ceftazidime/avibactam on the Sensititre panel as
{9}
compared to that of the reference method 30.8% and 33.8% of the time, for Vizion and OptiRead methods respectively. This downward trend resulted in only one very major discrepancy since the majority of the organisms tested had MIC values which fell well below the susceptible MIC breakpoint of 8/4 µg/mL.
The following footnote was added to the device performance table in the package insert to inform end users of observed trending:
Sensititre ceftazidime/avibactam MIC values for non-fastidious Enterobacteriaceae isolates tended to trend upward one doubling dilution compared to the reference broth microdilution method. Sensititre ceftazidime/avibactam MIC values for Pseudomonas aeruginosa isolates tended to trend downward one doubling dilution as compared to the reference broth microdilution method. The trending was observed with the use of both OptiRead and Vizion read methods.
b. Matrix comparison:
Not Applicable
3. Clinical studies:
a. Clinical Sensitivity:
Not Applicable
b. Clinical specificity:
Not Applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not Applicable
4. Clinical cut-off:
Not Applicable
5. Expected values/Reference range:
The FDA susceptibility interpretive criteria (ug/mL) for susceptible(S) and resistant (R) as listed below were used to evaluate all performance data.
Enterobacteriaceae S ≤ 8/4, R ≥ 16/4
Pseudomonas aeruginosa S ≤ 8/4, R ≥ 16/4
10
{10}
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.
11
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.