Use of multivariate analysis to compare antimicrobial agents on the basis of in vitro activity data

Abstract

PCA and factor analysis assist in the identification of the interrelationships of multiple variables, all acting simultaneously. Multivariate methods handle large volumes of data resulting from the interactions of multiple variables and identify principal components or factors that link some of the variables and that unlink others. There are as many components or factors identified as there are variables studied. The information provided by the factors is not identical; the first factors reflect links of a greater strength and influence on the context than do the last factors. The graphic, three-dimensional representation of the principal components helps to provide a better understanding of the interrelations among variables. These relationships can be extrapolated qualitatively to generate postulates or to reveal trends, making multivariate techniques useful hypothesis-generating tools.These analyses can be useful for comparing new antimicrobial agents with existing ones. Microbiological activity influences the interest in a new antimicrobial agent in its early development stages. In the present study, multivariate analysis techniques were used to investigate the interrelationships of * Corresponding author. Mailing address: Clinical Investigation

Identifying patient-level risk factors associated with non-β-lactam resistance outcomes in invasive MRSA infections in the United States using chain graphs

“…One previous study applied principal component analysis and factor analysis to identify groups of antibiotics with similar trends in MIC from 15 groups of microbes from 17 studies. 17 Rotated principal components correspond to dense subregions in PGMs. 15 The PGMs give a more detailed picture of how the variables are correlated in a way that is visually interpretable and more detailed and that requires fewer assumptions.…”

“…The MIC values were log 2 transformed so that a unit change corresponded to a single 2-fold dilution. 14 , 17 …”

Identifying patient-level risk factors associated with non-β-lactam resistance outcomes in invasive methicillin-resistant Staphylococcus aureus infections in the United States using chain graphs

“…There have been a few previous studies that have approached AMR as a multivariate problem, but they have not applied a chain graph or comparable approach. One previous study applied principal component analysis and factor analysis to identify groups of antibiotics with similar trends in MIC from 15 groups of microbes from 17 studies (Hernandez and Conforti 1994). Rotated principal components correspond to dense subregions in probabilistic graphical models, i .…”

“…HO (n = 1927) and HACO (n = 5201) isolates were both classified as healthcare-acquired. The minimum inhibitory concentration (MIC) values were log 2 transformed so that a one unit change in the transformed value would correspond to a change of one two-fold dilution as used in microbroth dilution plates (Love et al 2016; Hernandez and Conforti 1994). Susceptibility results which exceeded the highest tested concentration were increased by one dilution, e.g., MIC > 16 ug/mL was re-coded MIC = 32 ug/mL with log 2 (MIC) = 5.…”

Analysis of phenotypic antibiotic resistance profile of Staphylococcus aureus from community settings of a university campus

“…The ability of multivariate methods to portray the impact of antibiotic usage on resistance patterns has been suggested before [12,13]. Applying multivariate techniques, those investigators found a high degree of correlation between the activities of OXA, CLI/ERY and CTR against isolates of S aureus and postulated that this species underwent similar evolutionary resistance pressures for these antibiotics.…”