Performance of a Machine Learning-Based Methicillin Resistance of Staphylococcus aureus Identification System Using MALDI-TOF MS and Comparison of the Accuracy according to SCCmec Types

Abstract

The prompt presumptive identification of methicillin-resistant Staphylococcus aureus (MRSA) using matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) can aid in early clinical management and infection control during routine bacterial identification procedures. This study applied a machine learning approach to MALDI-TOF peaks for the presumptive identification of MRSA and compared the accuracy according to staphylococcal cassette chromosome mec (SCCmec) types. We analyzed 194 S. aureus clinical isolates to evaluate the machine learning-based identification system (AMRQuest software, v.2.1, ASTA: Suwon, Korea), which was constructed with 359 S. aureus clinical isolates for the learning dataset. This system showed a sensitivity of 91.8%, specificity of 83.3%, and accuracy of 87.6% in distinguishing MRSA. For SCCmec II and IVA types, common MRSA types in a hospital context, the accuracy was 95.4% and 96.1%, respectively, while for the SCCmec IV type, it was 21.4%. The accuracy was 90.9% for methicillin-susceptible S. aureus. This presumptive MRSA identification system may be helpful for the management of patients before the performance of routine antimicrobial resistance testing. Further optimization of the machine learning model with more datasets could help achieve rapid identification of MRSA with less effort in routine clinical procedures using MALDI-TOF MS as an identification method.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

“…Interestingly, a more recent study by Jeon et al has also explored the use of MALDI-TOF spectral data combined with ML for the identification of MRSA using the MALDI-TOF MS technique. In this study, the authors were able to diagnose MRSA with a sensitivity, specificity and accuracy of 91.8%, 83.3% and 87.6%, respectively [ 97 ].…”

Tackling the Antimicrobial Resistance “Pandemic” with Machine Learning Tools: A Summary of Available Evidence

“…Machine learning techniques were adopted to support research into bacterial resistance to a panel of antimicrobials using whole-genome sequence data of Pseudomonas aeruginosa, with more than 95% accuracy [49] (Table 1). Furthermore, a similar system was used for the identification of methicillin resistance of Staphylococcus aureus, with an accuracy of 87.6%, sensitivity of 91.8%, and specificity of 83.3% [50] (Table 1). In other research, machine learning models were able to predict the minimum inhibitory concentrations of ten different antimicrobial agents for Staphylococcus aureus [51] (Table 1).…”

Mass Spectral Imaging to Map Plant–Microbe Interactions

“…This finding indicates that using ML techniques in tandem with MALDI-MS can provide fast and accurate methods to classify and identify biological products under different thermal treatment conditions [ 38 ]. ML techniques have also been used in antimicrobial resistance screening for Campylobacter and Staphylococcus bacterial strains by MALDI [ 121 , 122 ]. Both experiments yielded high accuracy and precision, and the methods could be used for rapid antimicrobial resistance screening.…”