Rapid Identification of Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF MS and Machine Learning from over 20,000 Clinical Isolates

Yu, Jiaxin; Tien, Ni; Liu, Yu-Ching; Cho, Der Yang; Chen, Jia-Wen; Tsai, Yin-Tai; Huang, Yu-Chen; Chao, Huei-Jen; Chen, Chao‐Jung

doi:10.1128/spectrum.00483-22

Cited by 23 publications

(15 citation statements)

References 21 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early and rapid detection of CRKP in clinical isolates can help physicians in providing appropriate empiric antibiotics to patients. In studies identifying bacteria with AMR, ML models based on MALDI-TOF MS data have been widely used, and the most discussed bacteria was Staphylococcus aureus [ 18 – 20 ]. However, only a few studies using ML models have focused on CRKP; There were two studies about CRKP identification based on MALDI-TOF MS and ML techniques published on February 2020 and July 2022 [ 21 , 22 ].…”

Section: Discussionmentioning

confidence: 99%

Rapid identification of carbapenem-resistant Klebsiella pneumoniae based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry and an artificial neural network model

et al. 2023

View full text Add to dashboard Cite

Background Carbapenem-resistant Klebsiella pneumoniae (CRKP) is a clinically critical pathogen that causes severe infection. Due to improper antibiotic administration, the prevalence of CRKP infection has been increasing considerably. In recent years, the utilization of matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) has enabled the identification of bacterial isolates at the families and species level. Moreover, machine learning (ML) classifiers based on MALDI-TOF MS have been recently considered a novel method to detect clinical antimicrobial-resistant pathogens. Methods A total of 2683 isolates (369 CRKP cases and 2314 carbapenem-susceptible Klebsiella pneumoniae [CSKP]) collected in the clinical laboratories of Taipei Medical University Hospital (TMUH) were included in this study, and 80% of data was split into the training data set that were submitted for the ML model. The remaining 20% of data was used as the independent data set for external validation. In this study, we established an artificial neural network (ANN) model to analyze all potential peaks on mass spectrum simultaneously. Results Our artificial neural network model for detecting CRKP isolates showed the best performance of area under the receiver operating characteristic curve (AUROC = 0.91) and of area under precision–recall curve (AUPRC = 0.90). Furthermore, we proposed the top 15 potential biomarkers in probable CRKP isolates at 2480, 4967, 12,362, 12,506, 12,855, 14,790, 15,730, 16,176, 16,218, 16,758, 16,919, 17,091, 18,142, 18,998, and 19,095 Da. Conclusions Compared with the prior MALDI-TOF and machine learning studies of CRKP, the amount of data in our study was more sufficient and allowing us to conduct external validation. With better generalization abilities, our artificial neural network model can serve as a reliable screening tool for CRKP isolates in clinical practice. Integrating our model into the current workflow of clinical laboratories can assist the rapid identification of CRKP before the completion of traditional antimicrobial susceptibility testing. The combination of MADLI-TOF MS and machine learning techniques can support physicians in selecting suitable antibiotics, which has the potential to enhance the patients’ outcomes and lower the prevalence of antimicrobial resistance.

show abstract

Section: Discussionmentioning

confidence: 99%

Rapid identification of carbapenem-resistant Klebsiella pneumoniae based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry and an artificial neural network model

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In addition, the sensitivity of our model was higher than that reported by other studies. In a study of five clinics with over 20,000 clinical MSSA and MRSA isolates, Yu et al [ 34 ] reported that the ranges of sensitivity and specificity were 72–83% and 65–88%, respectively. Tang et al [ 35 ] reported a sensitivity of 88.2%, specificity of 90.0%, and accuracy of 88.9% for a total of 224 strains of MRSA and MSSA.…”

Section: Discussionmentioning

confidence: 99%

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

Jeon

Kim

Rho³

et al. 2022

Microorganisms

View full text Add to dashboard Cite

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.

show abstract

“…22,23 Besides m/z 3006, there are still several important peaks that would be interesting for the investigation of resistance mechanisms (Table S1). The peak at m/z 6593 was identi ed as the UPF0337 protein, SACOL1680 24 . However, the identi cation of the important peaks is labor-intensive, thus requiring the efforts of the entire research community.…”

Section: Discussionmentioning

confidence: 99%

Effect of an Artificial Intelligence-assisted Antibiotic Susceptibility Test on Reducing the Mortality Rate of and Antibiotics Use in Patients with Bacteremia: A Prospective Observational Cohort Study

Wang

Chung

Tseng

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

No mass spectrometry-based antibiotic susceptibility test (AST) AI system has been robustly validated and truly deployed in real-world settings. In the study, an AI-assisted AST prediction system XBugHunter was extensively validated and deployed. A total of 90,064 consecutive patients were included in the models development. During the deployment, 155 consecutive patients with Staphylococcus aureus bacteremia (SAB) was analyzed, whereas the historical control cohort included 455 patients. The predictive sensitivity and specificity for S. aureus (oxacillin) were 0.95 and 0.97, respectively. The reduction on AST turnaround time was 34.06 h. Death within 28 days was 13.55% for the SAB patients in the XBugHunter intervention group, which was significantly lower than 17.58% in the historical control cohort. Totally, 114.77 defined daily doses of inappropriate antibiotics were avoided by deploying XBugHunter. This work showed that XBugHunter can prevent inappropriate antibiotic use, and the adjustment in antibiotic treatment can yield a lower mortality rate.

show abstract

Rapid Identification of Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF MS and Machine Learning from over 20,000 Clinical Isolates

Abstract: Over 20,000 clinical MSSA and MRSA isolates were collected to build a machine learning (ML) model to identify MSSA/MRSA and their markers. This model was tested across four external clinical sites to ensure the model’s usability.

Cited by 23 publications

References 21 publications

Rapid identification of carbapenem-resistant Klebsiella pneumoniae based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry and an artificial neural network model

Rapid identification of carbapenem-resistant Klebsiella pneumoniae based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry and an artificial neural network model

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

Effect of an Artificial Intelligence-assisted Antibiotic Susceptibility Test on Reducing the Mortality Rate of and Antibiotics Use in Patients with Bacteremia: A Prospective Observational Cohort Study

Contact Info

Product

Resources

About