Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning

Weis, Caroline; Cuénod, Aline; Rieck, Bastian; Dubuis, Olivier; Graf, Susanne; Lang, Claudia; Oberle, Michael; Brackmann, Maximilian; Søgaard, Kirstine Kobberøe; Osthoff, Michael; Borgwardt, Karsten; Egli, Adrian

doi:10.1038/s41591-021-01619-9

Cited by 78 publications

(106 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AUC for oxacillin susceptibility prediction under XGBoost is 0.93, while it is only 0.86 for the model applying LR. The performance for oxacillin resistance prediction got improved compared with the AUC of 0.80 from DRIAMS ( Weis et al, 2022 ) as well. Meanwhile, the AUC of clindamycin susceptibility prediction gets increased from 0.85 to 0.89 by turning LR into XGBoost.…”

Section: Resultsmentioning

confidence: 99%

“…The crucial consideration from both patients and doctors is that the computational model on the basis of the cohort representation and assumption lacks quality guarantee for individuals, which can be solved and ensured largely in the antibiotics susceptibility test. Specifically, the consideration is getting mitigated with a novel resistance information database called DRIAMS with huge-scale data, which collects at least 300,000 mass spectra with more than 750,000 antimicrobial resistances ( Weis et al, 2022 ). Another limitation is that each existing classification model only refers to a specific type of antibiotic, which is not suitable and applicable for the multidrug-resistant S. aureus with the widespread multidrug-resistant phenotype, referring to being resistant to at least three classes of antibiotic mechanisms or three antibiotics based on the gene level ( Schwarz et al, 2010 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid Antibiotic Resistance Serial Prediction in Staphylococcus aureus Based on Large-Scale MALDI-TOF Data by Applying XGBoost in Multi-Label Learning

Zhang

Wang

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

Multidrug resistance has become a phenotype that commonly exists among Staphylococcus aureus and is a serious concern for infection treatment. Nowadays, to detect the antibiotic susceptibility, antibiotic testing is generated based on the level of genomic for cure decision consuming huge of time and labor, while matrix-assisted laser desorption-ionization (MALDI) time-of-flight mass spectrometry (TOF/MS) shows its possibility in high-speed and effective detection on the level of proteomic. In this study, on the basis of MALDI-TOF spectra data of discovery cohort with 26,852 samples and replication cohort with 4,963 samples from Taiwan area and their corresponding susceptibilities to oxacillin and clindamycin, a multi-label prediction model against double resistance using Lowest Power set ensemble with XGBoost is constructed for rapid susceptibility prediction. With the output of serial susceptibility prediction, the model performance can realize 77% of accuracy for the serial prediction, the area under the receiver characteristic curve of 0.93 for oxacillin susceptibility prediction, and the area under the receiver characteristic curve of 0.89 for clindamycin susceptibility prediction. The generated multi-label prediction model provides serial antibiotic resistance, such as the susceptibilities of oxacillin and clindamycin in this study, for S. aureus-infected patients based on MALDI-TOF, which will provide guidance in antibiotic usage during the treatment taking the advantage of speed and efficiency.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Rapid Antibiotic Resistance Serial Prediction in Staphylococcus aureus Based on Large-Scale MALDI-TOF Data by Applying XGBoost in Multi-Label Learning

Zhang

Wang

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

show abstract

“…Moreover, single peaks' presence or absence rather than the whole pattern of the peaks were used for classifying AST. In the past few years, some studies have harnessed artificial intelligence (AI) algorithms to analyze the MALDI-TOF MS peaks pattern for classifying specific bacterial strains (Wang et al, 2019(Wang et al, , 2020bWeis et al, 2022). Most of the works studied Staphylococcus aureus (Weis et al, 2022), group B Streptococcus (Wang et al, 2019), and Enterobacteriaceae (Weis et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…In the past few years, some studies have harnessed artificial intelligence (AI) algorithms to analyze the MALDI-TOF MS peaks pattern for classifying specific bacterial strains (Wang et al, 2019(Wang et al, , 2020bWeis et al, 2022). Most of the works studied Staphylococcus aureus (Weis et al, 2022), group B Streptococcus (Wang et al, 2019), and Enterobacteriaceae (Weis et al, 2022). By contrast, Enterococcus faecium is also a superbug with rising clinical importance (Ahmed and Baptiste, 2018), only a few studies have been reported for rapid detection of vancomycinresistant Enterococcus faecium (VREfm) by using MALDI-TOF MS and machine learning approaches (Griffin et al, 2012;.…”

Section: Introductionmentioning

confidence: 99%

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Wang

Hsieh²,

Chung

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

Matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has recently become a useful analytical approach for microbial identification. The presence and absence of specific peaks on MS spectra are commonly used to identify the bacterial species and predict antibiotic-resistant strains. However, the conventional approach using few single peaks would result in insufficient prediction power without using complete information of whole MS spectra. In the past few years, machine learning algorithms have been successfully applied to analyze the MALDI-TOF MS peaks pattern for rapid strain typing. In this study, we developed a convolutional neural network (CNN) method to deal with the complete information of MALDI-TOF MS spectra for detecting Enterococcus faecium, which is one of the leading pathogens in the world. We developed a CNN model to rapidly and accurately predict vancomycin-resistant Enterococcus faecium (VREfm) samples from the whole mass spectra profiles of clinical samples. The CNN models demonstrated good classification performances with the average area under the receiver operating characteristic curve (AUROC) of 0.887 when using external validation data independently. Additionally, we employed the score-class activation mapping (CAM) method to identify the important features of our CNN models and found some discriminative signals that can substantially contribute to detecting the ion of resistance. This study not only utilized the complete information of MALTI-TOF MS data directly but also provided a practical means for rapid detection of VREfm using a deep learning algorithm.

show abstract

“…The most widespread explainable techniques comprise SHapley Additive exPlanation (SHAP) [12] and Local Interpretable Model-Agnostic Explanations (LIME). These new interpretable methods have been successfully applied to explain the ML models related to mortality prediction in acute gastrointestinal bleeding [13] and sepsis [14] , prediction of antimicrobial resistance [15] and the occurrence of AKI following cardiac surgery [16] .…”

Section: Introductionmentioning

confidence: 99%

Application of interpretable machine learning for early prediction of prognosis in acute kidney injury

Tan

Zhang

et al. 2022

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning

Cited by 78 publications

References 46 publications

Rapid Antibiotic Resistance Serial Prediction in Staphylococcus aureus Based on Large-Scale MALDI-TOF Data by Applying XGBoost in Multi-Label Learning

Rapid Antibiotic Resistance Serial Prediction in Staphylococcus aureus Based on Large-Scale MALDI-TOF Data by Applying XGBoost in Multi-Label Learning

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Application of interpretable machine learning for early prediction of prognosis in acute kidney injury

Contact Info

Product

Resources

About