Liofilchem MIC Test Strip (MTS)- Ceftolozane/Tazobactam 0.016/4 - 256/4 mcg/mL
Applicant
Liofilchem s.r.l.
Product Code
JWY · Microbiology
Decision Date
Jul 12, 2016
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 866.1640
Device Class
Class 2
Indications for Use
The Liofilchem MIC Test Strip (MTS) is a quantitative method intended for the in vitro determination of antimicrobial susceptibility of non-fastidious Gram negative and Gram positive aerobic bacteria (for example, Enterobacteriaceae, Pseudomonas, Enterococcus and Staphylococus species) and fastidious bacteria (for example, anaerobes, Haemophilus and Streptococcus species and N. gonorhoeae). MTS consists of specialized paper impregnated with a pre-defined concentration gradient of an antimicrobial agent, which is used to determine the minimum inhibitory concentration (MIC) in ug/mL of antimicrobial agents against bacteria as tested on agar media using overnight incubation and manual reading procedures. The purpose of this 510(k) is specifically for the ceftolozane/tazobactam MTS at concentrations of 0.016/4 - 256/4 mcg/mL. Ceftolozane/azobactam has been shown to be active against the following bacteria, both clinically and in vitro according to the FDA label: Enterobacter cloacae Escherichia coli Klebsiella oxytoca Klebsiella pneumoniae Proteus mirabilis Pseudomonas aeruginosa
Device Story
Liofilchem MIC Test Strip (MTS) is a quantitative in vitro diagnostic device for determining antimicrobial susceptibility. Device consists of specialized paper strips impregnated with a predefined concentration gradient of ceftolozane/tazobactam. Used in clinical microbiology laboratories by trained personnel. Procedure involves placing the strip on inoculated agar media, followed by overnight incubation. The MIC is determined by manual visual inspection of the inhibition ellipse intersection with the strip. Results provide clinicians with quantitative susceptibility data to guide antibiotic therapy selection for bacterial infections. Benefits include standardized, reliable MIC determination for specific pathogens.
Clinical Evidence
Performance evaluated via clinical and challenge studies (n=401 isolates). Combined results showed 95.7% Essential Agreement (EA) and 93.8% Category Agreement (CA) across all isolates. Pseudomonas aeruginosa showed 92.6% EA and 91.6% CA; Enterobacteriaceae showed 97.6% EA and 95.3% CA. Trending analysis indicated a slight bias toward higher MIC values compared to reference broth microdilution. Reproducibility >95%.
Technological Characteristics
Specialized paper strip impregnated with predefined exponential concentration gradient of ceftolozane/tazobactam (15 two-fold dilutions). Manual application to Mueller Hinton agar. Manual reading of inhibition ellipse. No electronic components or software algorithms.
Indications for Use
Indicated for in vitro susceptibility testing of Enterobacter cloacae, E. coli, Klebsiella oxytoca, Klebsiella pneumoniae, Proteus mirabilis, and Pseudomonas aeruginosa to ceftolozane/tazobactam (0.016/4 - 256/4 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}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION MEMORANDUM
A. 510(k) Number:
K161175
B. Purpose for Submission:
To obtain a substantial equivalence determination for the Liofilchem MIC Test Strip (MTS) containing ceftolozane/tazobactam at concentrations of 0.016/4 -256/4 µg/mL for susceptibility testing of Enterobacter cloacae, E. coli, Klebsiella oxytoca, Klebsiella pneumoniae, Proteus mirabilis, and Pseudomonas aeruginosa
C. Measurand:
Ceftolozane/tazobactam 0.016/4 -256/4 µg/mL
D. Type of Test:
Quantitative AST growth based detection
E. Applicant:
Liofilchem s.r.l.
F. Proprietary and Established Names:
Liofilchem MIC Test Strip (MTS) Ceftolozane/Tazobactam 0.016/4 – 256/4 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:
{1}
83 – Microbiology
H. Intended Use:
1. Intended use(s):
The Liofilchem MIC Test Strip (MTS) is a quantitative method intended for the in vitro determination of antimicrobial susceptibility of non-fastidious Gram negative and Gram positive aerobic bacteria (for example, Enterobacteriaceae, Pseudomonas, Enterococcus and Staphylococcus species) and fastidious bacteria (for example, anaerobes, Haemophilus and Streptococcus species and N. gonorrhoeae). MTS consists of specialized paper impregnated with a pre-defined concentration gradient of an antimicrobial agent, which is used to determine the minimum inhibitory concentration (MIC) in $\mu \mathrm{g} / \mathrm{mL}$ of antimicrobial agents against bacteria as tested on agar media using overnight incubation and manual reading procedures.
2. Indication(s) for use:
The Liofilchem MIC Test Strip (MTS) is a quantitative method intended for the in vitro determination of antimicrobial susceptibility of non-fastidious Gram negative and Gram positive aerobic bacteria (for example, Enterobacteriaceae, Pseudomonas, Enterococcus and Staphylococcus species) and fastidious bacteria (for example, anaerobes, Haemophilus and Streptococcus species and N. gonorrhoeae). MTS consists of specialized paper impregnated with a pre-defined concentration gradient of an antimicrobial agent, which is used to determine the minimum inhibitory concentration (MIC) in $\mu \mathrm{g} / \mathrm{mL}$ of antimicrobial agents against bacteria as tested on agar media using overnight incubation and manual reading procedures.
The purpose of this 510(k) is specifically for the ceftolozane/tazobactam MTS at concentrations of $0.016/4 - 256/4\ \mu \mathrm{g/mL}$ interpreted after 16-20 hours of incubation.
Ceftolozane/tazobactam has been shown to be active against the following bacteria, both clinically and in vitro according to the FDA label:
Enterobacter cloacae
Escherichia coli
Klebsiella oxytoca
Klebsiella pneumoniae
Proteus mirabilis
Pseudomonas aeruginosa
3. Special conditions for use statement(s):
For prescription use
{2}
The following limitations are included in the Liofilchem Ceftolozane/Tazobactam MIC Test Strip (MTS) package insert supplement:
1. Enzyme group characterization was not available for organisms at the time of comparative testing, and therefore the performance of Liofilchem MIC Test Strip Ceftolozane/Tazobactam for non-fastidious gram negative bacilli is unknown for the following: Enterobacteriaceae (ESBL, TEM, SHV, CTX-M, and OXA); Pseudomonas aeruginosa (chromosomal AmpC, loss of OprD, up-regulation of MexXY, and MexAB).
2. Ceftolozane/Tazobactam is not active against bacteria that produce serine carbapenemases [K. pneumoniae carbapenemase (KPC)] and metallo-beta lactamases.
4. Special instrument requirements:
Manual reading only
I. Device Description:
The ceftolozane/tazobactam MIC Test Strip (MTS) consists of specialized paper impregnated with a predefined concentration gradient of ceftolozane/tazobactam across 15 two-fold dilutions like those of a conventional MIC method. One side of the strip is labelled with the ceftolozane/tazobactam code (C/T) and the MIC reading scale in $\mu \mathrm{g} / \mathrm{mL}$. When the MIC Test Strip is applied onto an inoculated agar surface, the preformed exponential gradient of antimicrobial agent is immediately transferred to the agar matrix. After 16-20 hours incubation, a symmetrical inhibition ellipse centered along the strip is formed. The MIC is read directly from the scale in terms of $\mu \mathrm{g} / \mathrm{mL}$ at the point where the edge of the inhibition ellipse intersects the MIC Test Strip.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Liofilchem MTS, Vancomycin
2. Predicate $510(\mathbf{k})$ number(s):
K153687
{3}
# 3. Comparison with predicate:
Table 1: Comparison with the Predicate Device
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate K153687 |
| Intended Use | Quantitative susceptibility to antimicrobial agents | Same |
| Media | Mueller Hinton agar | Same |
| Inoculation | Isolated colonies from culture in suspension equivalent to 0.5 McFarland. Inoculum is applied manually using the manual plate inoculation method or plate rotator for even distribution of inoculum | Same |
| Reading | Manual; the point where the edge of inhibition ellipse intersects the MIC Test Strip | Same |
| Result | MIC | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Antibiotic | Ceftolozane/tazobactam | Vancomycin |
| Incubation | 35 ± 2°C for 16- 20hrs | 35 ± 2°C for 24hrs |
# K. Standard/Guidance Document Referenced:
"Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA"
CLSI M07-A10 "Methods for Dilution Antimicrobial Susceptibility Tests for Bacteria That Grow Aerobically; Approved Standard, Tenth Edition January 2015"
CLSI M100-S26 "Performance Standards for Antimicrobial Susceptibility Testing; Twenty-Fifth Informational Supplement, January 2016"
# L. Test Principle:
MTS are made of specialized paper impregnated with a predefined concentration gradient of antibiotic, across 15 two-fold dilutions like those of a conventional MIC method. When the MIC Test Strip is applied onto an inoculated agar surface, the preformed exponential gradient of antimicrobial agent is immediately transferred to the agar matrix. After 16-20 hours incubation, a symmetrical inhibition ellipse centered along the strip is formed. The MIC is read directly from the scale in terms of $\mu \mathrm{g} / \mathrm{mL}$ at the point where the edge of the inhibition ellipse intersects the strip MIC Test Strip.
Growth along the entire gradient (i.e. no inhibition ellipse) indicates that the MIC value is
{4}
greater than or equal to $(\geq)$ the highest value on the scale. An inhibition ellipse that intersects below the lower end of the scale is read as less than $(<)$ the lowest value. An MIC of $0.125\mu \mathrm{g / mL}$ is considered to be the same as $0.12\mu \mathrm{g / mL}$ for reporting purposes.
An MTS MIC value which falls between standard two-fold dilutions must be rounded up to the next standard upper two fold value before categorization.
# M. Performance Characteristics (if/when applicable):
# a. Precision/Reproducibility:
Reproducibility testing was performed using six Pseudomonas aeruginosa isolates and four Enterobacteriaceae isolates (two $E.$ coli, one $K.$ pneumoniae, and one Enterobacter cloacae). These ten organisms were tested at three sites in triplicates on three days. The mode of MIC value was determined and the reproducibility was calculated based on the number of MIC values that fell within $\pm 1$ doubling dilution of the mode. The testing resulted in overall reproducibility of greater than $95\%$ . The results were acceptable.
# b. Linearity/assay reportable range:
Not applicable
# c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The recommended QC isolates were tested a sufficient number of times at all three sites with acceptable results in comparison to the reference method. All results were within the expected range greater than $95\%$ of the time. The results are summarized in Table 2 below.
Table 2: Ceftolozane/tazobactam MTS QC results
| Organism | Concentration (μg/mL) | Reference | MTS |
| --- | --- | --- | --- |
| E. coli | 0.06/4 | | |
| ATCC 25922 | 0.12/4 | | |
| Expected Results | 0.25/4 | 39 | 11 |
| 0.12/4 - 0.5/4μg/mL | 0.5/4 | 21 | 49 |
| | 1/4 | | |
| | | | |
| K. pneumoniae | 0.5/4 | 1 | |
| ATCC 700603 | 1/4 | 37 | 10 |
| Expected Results | 2/4 | 22 | 49 |
| 0.5/4 - 2/4 μg/mL | 4/4 | | 1 |
| | | | |
| P. aeruginosa | 0.12/4 | | |
| ATCC 27853 | 0.25/4 | 1 | 1 |
| Expected Results | 0.5/4 | 37 | 4 |
| 0.25/4 - 1/4 μg/mL | 1/4 | 22 | 53 |
| | 2/4 | | 2 |
{5}
The inoculum density of the quality control organisms was determined each day of testing. A total of 180 inoculum density checks were performed; the average colony counts of each QC strain were within the recommended range of approximately $1 \times 10^{8}$ CFU/mL.
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:
Clinical testing was conducted at three sites (two U.S. sites and one outside the U.S.). A total of 401 organisms were tested and all organisms grew in the studies. There were 338 $(84.3\%)$ isolates that were tested within seven days of collection and 63 $(15.7\%)$ isolates that were tested within one year of collection. The study included 296 Enterobacteriaceae and 190 Pseudomonas aeruginosa. The Enterobacteriaceae tested were Enterobacter cloacae, Esherichia coli, Klebsiella oxytoca, Klebsiella pneumoniae, and Proteus mirabilis. The performance is listed in Table 3 below:
Table 3: Performance of Enterobacteriaceae and Pseudomonas aeruginosa isolates*
| Ceftolozane/Tazobactam | EA Tot | EA N | EA % | Eval. EA Tot | Eval. EA N | Eval. EA % | CA N | CA % | #R | min | maj | vmj |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Enterobacteriaceae (≤2/4, 4/4, ≥8/4)** | | | | | | | | | | | |
| E. cloacae | | | | | | | | | | | | |
| Clinical | 30 | 29 | 96.7 | 30 | 29 | 96.7 | 28 | 93.3 | 8 | 2 | 0 | 0 |
| Challenge | 9 | 9 | 100 | 9 | 9 | 100 | 9 | 100 | 8 | 0 | 0 | 0 |
| Combined | 39 | 38 | 97.4 | 39 | 38 | 97.4 | 37 | 94.9 | 16 | 2 | 0 | 0 |
| E. coli | | | | | | | | | | | | |
| Clinical | 104 | 104 | 100 | 90 | 90 | 100 | 104 | 100 | 16 | 0 | 0 | 0 |
| Challenge | 15 | 14 | 93.3 | 15 | 14 | 93.3 | 7 | 46.7 | 4 | 8 | 0 | 0 |
| Combined | 119 | 118 | 99.2 | 105 | 104 | 99.0 | 111 | 93.2 | 20 | 8 | 0 | 0 |
| K. oxytoca | | | | | | | | | | | | |
| Clinical | 29 | 28 | 96.6 | 29 | 28 | 96.6 | 27 | 93.1 | 1 | 2 | 0 | 0 |
| Challenge | 3 | 3 | 100 | 3 | 3 | 100 | 3 | 100 | 2 | 0 | 0 | 0 |
| Combined | 32 | 31 | 96.9 | 32 | 31 | 96.9 | 30 | 93.8 | 3 | 2 | 0 | 0 |
{6}
| Ceftolozane/Tazobactam | EA Tot | EA N | EA % | Eval. EA Tot | Eval. EA N | Eval. EA% | CA N | CA% | #R | min | maj | vmj |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| K. pneumoniae | | | | | | | | | | | | |
| Clinical | 59 | 57 | 96.6 | 49 | 47 | 95.9 | 58 | 98.3 | 10 | 1 | 0 | 0 |
| Challenge | 14 | 13 | 92.9 | 12 | 12 | 100 | 13 | 92.9 | 11 | 1 | 0 | 0 |
| Combined | 73 | 70 | 95.9 | 61 | 59 | 96.7 | 71 | 97.3 | 21 | 2 | 0 | 0 |
| P. mirabilis | | | | | | | | | | | | |
| Clinical | 31 | 30 | 96.8 | 30 | 29 | 96.7 | 31 | 100 | 4 | 0 | 0 | 0 |
| Challenge | 2 | 2 | 100 | 2 | 2 | 100 | 2 | 100 | 1 | 0 | 0 | 0 |
| Combined | 33 | 32 | 97.0 | 32 | 31 | 96.9 | 33 | 100 | 5 | 0 | 0 | 0 |
| Total Enterobacteriaceae | 296 | 289 | 97.6 | 269 | 263 | 97.8 | 282 | 95.3 | 65 | 14 | 0 | 0 |
| Pseudomonas aeruginosa (≤4/4, 8/4, ≥16/4)** | | | | | | | | | | | | |
| Clinical | 148 | 140 | 94.6 | 124 | 116 | 93.5 | 141 | 95.3 | 32 | 7 | 0 | 0 |
| Challenge | 42 | 36 | 85.7 | 40 | 34 | 85.0 | 33 | 78.6 | 27 | 8 | 1 | 0 |
| Combined | 190 | 176 | 92.6 | 164 | 150 | 91.5 | 174 | 91.6 | 59 | 15 | 1 | 0 |
| All Isolates | 486 | 465 | 95.7 | 423 | 413 | 97.6 | 456 | 93.8 | 124 | 29 | 1 | 0 |
* EA - Essential Agreement maj - major discrepancies
CA - Category Agreement vmj- very major discrepancies
R- resistant isolates min- minor discrepancies
Essential Agreement (EA) is when the Liofilchem MIC Test Strip (MST) results agree exactly or within one doubling dilution of the reference broth microdilution results. Category Agreement (CA) is when the Liofilchem MIC Test Strip (MST) result interpretation agrees exactly with the reference broth microdilution result interpretation.
** Parenthesis show the ceftolozane/tazobactam MIC values that correspond to the interpretive categories of S/I/R
In the challenge study, low CA was observed for $E$ coli (46.7%, 7/15) and Pseudomonas aeruginosa (78.6%, 33/42); low EA (85.7%, 36/42) was also noted for Pseudomonas aeruginosa.
E. coli: There were eight minor discrepancies, seven of which were within $\pm$ one doubling dilution. The challenge set included six susceptible, five intermediate, and four resistant isolates. The CA was $100\%$ in the clinical study which included 88 susceptible and 16 resistant isolates; there was no intermediate isolates. The resistant isolates were in exact agreement with the reference and the susceptible isolates were all within EA. The combined clinical + challenge E. coli CA was $93.2\%$ meeting the acceptance criterion.
Pseudomonas aeruginosa: Forty-two isolates were tested in the challenge study. The challenge set included eight susceptible, seven intermediate and 27 resistant isolates. The low CA was caused by minor (19.0%, 8/42) and major (12.5%, 1/8) discrepancies. The major discrepancy rate was high at 12.5% because of the low number of susceptible isolates tested. The EA was also low at 85.7% in the challenge study. However, there were no major or very major discrepancies in the clinical study which resulted in a CA of 95.3% and EA of 94.6%. The overall performance of $P$ . aeruginosa was acceptable, with an EA of 92.6%, a CA of 91.6%, and a major discrepancy rate of 0.82%.
{7}
The combined clinical and challenge on-scale data of the Enterobacteriaceae and Pseudomonas aeruginosa were further analyzed for trending as presented in Table 4 below:
Table 4: Trending Summary of on-scale Clinical and Challenge Isolate Results
| Ceftolozane/Tazobactam | Total | Difference in MIC as Compared to the CLSI Reference Method | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | >2 dil. lower | 2 dil. lower | 1 dil. lower | Exact | 1 dil. higher | 2 dil. higher | >2 dil. higher |
| Enterobacteriaceae | 296 | 0.3% (1/296) | 0.7% (2/296) | 14.9% (44/296) | 54.7% (162/296) | 28.0% (83/296) | 1% (3/296) | 0.3% (1/296) |
| P. aeruginosa | 190 | 0 | 0 | 6.8% (13/190) | 45.8% (87/190) | 40.0% (76/190) | 1.6% (3/190) | 5.8% (11/190) |
The trending analysis indicated that the MTS MIC results tended to be higher than the reference method. For Pseudomonas aeruginosa, 40.0% of the MTS MIC results were one doubling dilution higher than the reference method results, while 45.8% of the MTS MIC results matched the reference method exactly. For the Enterobacteriaceae, 28.0% of the MTS results were one doubling dilution higher than the reference method results, while 54.7% of the MTS results matched the reference method exactly. Only one major discrepancy was observed from Pseudomonas aeruginosa, and no major discrepancies were observed from Enterobacteriaceae. The MIC trends were noted as the following footnotes to the Performance Characteristics Table in the ceftolozane/tazobactam MTS package insert supplement:
- The Liofilchem MIC Test Strip (MST) ceftolozane/tazobactam MIC values tended to be one doubling dilution higher when testing Enterobacteriaceae compared to the reference broth microdilution (out of 296 Enterobacteriaceae isolates tested, 0.3% were >2 dilutions lower, 0.7% were 2 dilutions lower, 14.9% were 1 dilution lower, 54.7% were equivalent, 28.0% were 1 dilution higher, 1.0% were 2 dilutions higher, 0.3% were >2 dilutions higher compared to the CLSI broth microdilution results).
- The Liofilchem MIC Test Strip (MST) ceftolozane/tazobactam MIC values tended to be one doubling dilution higher when testing P. aeruginosa compared to the reference broth microdilution (out of 190 P. aeruginosa isolates tested, 6.8% were 1 dilution lower, 45.8% were equivalent, 40.0% were 1 dilution higher, 1.6% were 2 dilutions higher, 5.8% were >2 dilutions higher compared to the CLSI broth microdilution results).
## Enzyme group characterization
The FDA approved pharmaceutical antimicrobial agent package insert provides a detailed description of enzyme groups for organisms tested in the drug study. However, this information was not available at the time when the device comparative study was conducted. The Liofilchem MST ceftolozane/tazobactam study included 220 susceptible, 11 intermediate and 65 resistant isolates for Enterobacteriaceae; 122
{8}
susceptible, 9 intermediate and 59 resistant Pseudomonas aeruginosa. The enzyme group characterization has not been evaluated. This information is noted in the limitation section of ceftolozane/tazobactam package insert supplement:
1. Enzyme group characterization was not available for organisms at the time of comparative testing, and therefore the performance of Liofilchem MIC Test Strip Ceftolozane/Tazobactam for non-fastidious gram negative bacilli is unknown for the following: Enterobacteriaceae (ESBL, TEM, SHV, CTX-M, and OXA); Pseudomonas aeruginosa (chromosomal AmpC, loss of OprD, up-regulation of MexXY, and MexAB).
2. Ceftolozane/Tazobactam is not active against bacteria that produce serine carbapenemases [K. pneumoniae carbapenemase (KPC)] and metallo-beta lactamases.
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:
Table 5: FDA Interpretive Criteria for Ceftolozane/Tazobactam (μg/mL)
| Organisms | S | I | R |
| --- | --- | --- | --- |
| Enterobacteriaceae | ≤2/4 | 4/4 | ≥8/4 |
| Pseudomonas aeruginosa | ≤4/4 | 8/4 | ≥16/4 |
{9}
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.
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.