A large-scale investigation and identification of methicillin-resistant Staphylococcus aureus based on peaks binning of matrix-assisted laser desorption ionization-time of flight MS spectra

Impact of the implementation of the Intelligent Antimicrobial System (iAMS) on clinical outcomes among patients with bacteraemia caused by methicillin-resistant Staphylococcus aureus

OBJECTIVES

This study aimed to investigate the clinical impact of the Intelligent Antimicrobial System (iAMS) on patients with bacteraemia due to methicillin-resistant (MRSA) and methicillin-susceptible Staphylococcus aureus (MSSA).

METHODS

A total of 1008 patients with suspected SA infection were enrolled before and after the implementation of iAMS. Among them, 252 with bacteraemia caused by SA, including 118 in the iAMS and 134 in the non-iAMS groups, were evaluated.

RESULTS

The iAMS group exhibited a 5.2% (from 55.2% to 50.0%; P = 0.96) increase in the 1-year survival rate. For patients with MRSA and MSSA compared to the non-iAMS group, the 1-year survival rate increased by 17.6% (from 70.9% to 53.3%; P = 0.41) and 7.0% (from 52.3% to 45.3%; P = 0.57), respectively, both surpassing the rate of the non-iAMS group. The iAMS intervention resulted in a higher long-term survival rate (from 70.9% to 52.3%; P = 0.984) for MRSA patients than for MSSA patients. MRSA patients experienced a reduced length of hospital stay (from 23.3% to 35.6%; P = 0.038), and the 45-day discharge rate increased by 20.4% (P = 0.064). Furthermore, the intervention resulted in a significant 97.3% relative decrease in near miss medication incidents reported by pharmacists (P = 0.013).

CONCLUSIONS

Implementation of iAMS platform improved long-term survival rates, discharge rates, hospitalization days, and medical cost (although no significant differences were observed) among patients with MRSA bacteraemia. Additionally, it demonstrated significant benefits in ensuring drug safety.

Distinguishing methicillin-resistant Staphylococcus aureus from methicillin-sensitive strains by combining Fe3O4 magnetic nanoparticle-based affinity mass spectrometry with a machine learning strategy

Pathogenic bacteria, including drug-resistant variants such as methicillin-resistant Staphylococcus aureus (MRSA), can cause severe infections in the human body. Early detection of MRSA is essential for clinical diagnosis and proper treatment, considering the distinct therapeutic strategies for methicillin-sensitive S. aureus (MSSA) and MRSA infections. However, the similarities between MRSA and MSSA properties present a challenge in promptly and accurately distinguishing between them. This work introduces an approach to differentiate MRSA from MSSA utilizing matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS) in conjunction with a neural network-based classification model. Four distinct strains of S. aureus were utilized, comprising three MSSA strains and one MRSA strain. The classification accuracy of our model ranges from ~ 92 to ~ 97% for each strain. We used deep SHapley Additive exPlanations to reveal the unique feature peaks for each bacterial strain. Furthermore, Fe3O4 MNPs were used as affinity probes for sample enrichment to eliminate the overnight culture and reduce the time in sample preparation. The limit of detection of the MNP-based affinity approach toward S. aureus combined with our machine learning strategy was as low as ~ 8 × 103 CFU mL-1. The feasibility of using the current approach for the identification of S. aureus in juice samples was also demonstrated.

Using Protein Fingerprinting for Identifying and Discriminating Methicillin Resistant Staphylococcus aureus Isolates from Inpatient and Outpatient Clinics

In hospitals and other clinical settings, Methicillin-resistant Staphylococcus aureus (MRSA) is a particularly dangerous pathogen that can cause serious or even fatal infections. Thus, the detection and differentiation of MRSA has become an urgent matter in order to provide appropriate treatment and timely intervention in infection control. To ensure this, laboratories must have access to the most up-to-date testing methods and technology available. This study was conducted to determine whether protein fingerprinting technology could be used to identify and distinguish MRSA recovered from both inpatients and outpatients. A total of 326 S. aureus isolates were obtained from 2800 in- and outpatient samples collected from King Faisal Specialist Hospital and Research Centre in Riyadh, Saudi Arabia, from October 2018 to March 2021. For the phenotypic identification of 326 probable S. aureus cultures, microscopic analysis, Gram staining, a tube coagulase test, a Staph ID 32 API system, and a Vitek 2 Compact system were used. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), referred to as protein fingerprinting, was performed on each bacterial isolate to determine its proteomic composition. As part of the analysis, Principal Component Analysis (PCA) and a single-peak analysis of MALDI-TOF MS software were also used to distinguish between Methicillin-sensitive Staphylococcus aureus (MSSA) and MRSA. According to the results, S. aureus isolates constituted 326 out of 2800 (11.64%) based on the culture technique. The Staph ID 32 API system and Vitek 2 Compact System were able to correctly identify 262 (80.7%) and 281 (86.2%) S. aureus strains, respectively. Based on the Oxacillin Disc Diffusion Method, 197 (62.23%) of 326 isolates of S. aureus exhibited a cefoxitin inhibition zone of less than 21 mm and an oxacillin inhibition zone of less than 10 mm, and were classified as MRSA under Clinical Laboratory Standards Institute guidelines. MALDI-TOF MS was able to correctly identify 100% of all S. aureus isolates with a score value equal to or greater than 2.00. In addition, a close relationship was found between S. aureus isolates and higher peak intensities in the mass ranges of 3990 Da, 4120 Da, and 5850 Da, which were found in MRSA isolates but absent in MSSA isolates. Therefore, protein fingerprinting has the potential to be used in clinical settings to rapidly detect and differentiate MRSA isolates, allowing for more targeted treatments and improved patient outcomes.

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data

In clinical microbiology, matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) is frequently employed for rapid microbial identification. However, rapid identification of antimicrobial resistance (AMR) in Escherichia coli based on a large amount of MALDI-TOF MS data has not yet been reported. This may be because building a prediction model to cover all E. coli isolates would be challenging given the high diversity of the E. coli population. This study aimed to develop a MALDI-TOF MS-based, data-driven, two-stage framework for characterizing different AMRs in E. coli. Specifically, amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM) were used. In the first stage, we split the data into two groups based on informative peaks according to the importance of the random forest. In the second stage, prediction models were constructed using four different machine learning algorithms-logistic regression, support vector machine, random forest, and extreme gradient boosting (XGBoost). The findings demonstrate that XGBoost outperformed the other four machine learning models. The values of the area under the receiver operating characteristic curve were 0.62, 0.72, 0.87, 0.72, and 0.72 for AMC, CAZ, CIP, CRO, and CXM, respectively. This implies that a data-driven, two-stage framework could improve accuracy by approximately 2.8%. As a result, we developed AMR prediction models for E. coli using a data-driven two-stage framework, which is promising for assisting physicians in making decisions. Further, the analysis of informative peaks in future studies could potentially reveal new insights. IMPORTANCE Based on a large amount of matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) clinical data, comprising 37,918 Escherichia coli isolates, a data-driven two-stage framework was established to evaluate the antimicrobial resistance of E. coli. Five antibiotics, including amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM), were considered for the two-stage model training, and the values of the area under the receiver operating characteristic curve (AUC) were 0.62 for AMC, 0.72 for CAZ, 0.87 for CIP, 0.72 for CRO, and 0.72 for CXM. Further investigations revealed that the informative peak m/z 9714 appeared with some important peaks at m/z 6809, m/z 7650, m/z 10534, and m/z 11783 for CIP and at m/z 6809, m/z 10475, and m/z 8447 for CAZ, CRO, and CXM. This framework has the potential to improve the accuracy by approximately 2.8%, indicating a promising potential for further research.

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

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.

Cas12a/Guide RNA-Based Platforms for Rapidly and Accurately Identifying Staphylococcus aureus and Methicillin-Resistant S. aureus

In order to ensure the prevention and control of methicillin-resistant Staphylococcus aureus (MRSA) infection, rapid and accurate detection of pathogens and their resistance phenotypes is a must. Therefore, this study aimed to develop a fast and precise nucleic acid detection platform for identifying S. aureus and MRSA. We initially constructed a CRISPR-Cas12a detection system by designing single guide RNAs (sgRNAs) specifically targeting the thermonuclease (nuc) and mecA genes. To increase the sensitivity of the CRISPR-Cas12a system, we incorporated PCR, loop-mediated isothermal amplification (LAMP), and recombinase polymerase amplification (RPA). Subsequently, we compared the sensitivity and specificity of the three amplification methods paired with the CRISPR-Cas12a system. Finally, the clinical performance of the methods was tested by analyzing the fluorescence readout of 111 clinical isolates. In order to visualize the results, lateral-flow test strip technology, which enables point-of-care testing, was also utilized. After comparing the sensitivity and specificity of three different methods, we determined that the nuc-LAMP-Cas12a and mecA-LAMP-Cas12a methods were the optimal detection methods. The nuc-LAMP-Cas12a platform showed a limit of detection (LOD) of 10 aM (~6 copies μL-1), while the mecA-LAMP-Cas12a platform demonstrated a LOD of 1 aM (~1 copy μL-1). The LOD of both platforms reached 4 × 103 fg/μL of genomic DNA. Critical evaluation of their efficiencies on 111 clinical bacterial isolates showed that they were 100% specific and 100% sensitive with both the fluorescence readout and the lateral-flow readout. Total detection time for the present assay was approximately 80 min (based on fluorescence readout) or 85 min (based on strip readout). These results indicated that the nuc-LAMP-Cas12a and mecA-LAMP-Cas12a platforms are promising tools for the rapid and accurate identification of S. aureus and MRSA. IMPORTANCE The spread of methicillin-resistant Staphylococcus aureus (MRSA) poses a major threat to global health. Isothermal amplification combined with the trans-cleavage activity of Cas12a has been exploited to generate diagnostic platforms for pathogen detection. Here, we describe the design and clinical evaluation of two highly sensitive and specific platforms, nuc-LAMP-Cas12a and mecA-LAMP-Cas12a, for the detection of S. aureus and MRSA in 111 clinical bacterial isolates. With a limit of detection (LOD) of 4 × 103 fg/μL of genomic DNA and a turnaround time of 80 to 85 min, the present assay was 100% specific and 100% sensitive using either fluorescence or the lateral-flow readout. The present assay promises clinical application for rapid and accurate identification of S. aureus and MRSA in limited-resource settings or at the point of care. Beyond S. aureus and MRSA, similar CRISPR diagnostic platforms will find widespread use in the detection of various infectious diseases, malignancies, pharmacogenetics, food contamination, and gene mutations.

Antibiotic Resistance Diagnosis in ESKAPE Pathogens-A Review on Proteomic Perspective

Antibiotic resistance has emerged as an imminent pandemic. Rapid diagnostic assays distinguish bacterial infections from other diseases and aid antimicrobial stewardship, therapy optimization, and epidemiological surveillance. Traditional methods typically have longer turn-around times for definitive results. On the other hand, proteomic studies have progressed constantly and improved both in qualitative and quantitative analysis. With a wide range of data sets made available in the public domain, the ability to interpret the data has considerably reduced the error rates. This review gives an insight on state-of-the-art proteomic techniques in diagnosing antibiotic resistance in ESKAPE pathogens with a future outlook for evading the "imminent pandemic".

Towards Accurate Identification of Antibiotic-Resistant Pathogens through the Ensemble of Multiple Preprocessing Methods Based on MALDI-TOF Spectra

Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has been used to identify microorganisms and predict antibiotic resistance. The preprocessing method for the MS spectrum is key to extracting critical information from complicated MS spectral data. Different preprocessing methods yield different data, and the optimal approach is unclear. In this study, we adopted an ensemble of multiple preprocessing methods--FlexAnalysis, MALDIquant, and continuous wavelet transform-based methods--to detect peaks and build machine learning classifiers, including logistic regressions, naïve Bayes classifiers, random forests, and a support vector machine. The aim was to identify antibiotic resistance in Acinetobacter baumannii, Acinetobacter nosocomialis, Enterococcus faecium, and Group B Streptococci (GBS) based on MALDI-TOF MS spectra collected from two branches of a referral tertiary medical center. The ensemble method was compared with the individual methods. Random forest models built with the data preprocessed by the ensemble method outperformed individual preprocessing methods and achieved the highest accuracy, with values of 84.37% (A. baumannii), 90.96% (A. nosocomialis), 78.54% (E. faecium), and 70.12% (GBS) on independent testing datasets. Through feature selection, important peaks related to antibiotic resistance could be detected from integrated information. The prediction model can provide an opinion for clinicians. The discriminative peaks enabling better prediction performance can provide a reference for further investigation of the resistance mechanism.

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

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.

Discrimination of Methicillin-resistant Staphylococcus aureus by MALDI-TOF Mass Spectrometry with Machine Learning Techniques in Patients with Staphylococcus aureus Bacteremia

Early administration of proper antibiotics is considered to improve the clinical outcomes of Staphylococcus aureus bacteremia (SAB), but routine clinical antimicrobial susceptibility testing takes an additional 24 h after species identification. Recent studies elucidated matrix-assisted laser desorption/ionization time-of-flight mass spectra to discriminate methicillin-resistant strains (MRSA) or even incorporated with machine learning (ML) techniques. However, no universally applicable mass peaks were revealed, which means that the discrimination model might need to be established or calibrated by local strains’ data. Here, a clinically feasible workflow was provided. We collected mass spectra from SAB patients over an 8-month duration and preprocessed by binning with reference peaks. Machine learning models were trained and tested by samples independently of the first six months and the following two months, respectively. The ML models were optimized by genetic algorithm (GA). The accuracy, sensitivity, specificity, and AUC of the independent testing of the best model, i.e., SVM, under the optimal parameters were 87%, 75%, 95%, and 87%, respectively. In summary, almost all resistant results were truly resistant, implying that physicians might escalate antibiotics for MRSA 24 h earlier. This report presents an attainable method for clinical laboratories to build an MRSA model and boost the performance using their local data.

Differentiation of Bacillus cereus and Bacillus thuringiensis Using Genome-Guided MALDI-TOF MS Based on Variations in Ribosomal Proteins

Bacillus cereus and B. thuringiensis are closely related species that are relevant to foodborne diseases and biopesticides, respectively. Unambiguous differentiation of these two species is crucial for bacterial taxonomy. As genome analysis offers an objective but time-consuming classification of B. cereus and B. thuringiensis, in the present study, matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) was used to accelerate this process. By combining in silico genome analysis and MALDI-TOF MS measurements, four species-specific peaks of B. cereus and B. thuringiensis were screened and identified. The species-specific peaks of B. cereus were m/z 3211, 6427, 9188, and 9214, and the species-specific peaks of B. thuringiensis were m/z 3218, 6441, 9160, and 9229. All the above peaks represent ribosomal proteins, which are conserved and consistent with the phylogenetic relationship between B. cereus and B. thuringiensis. The specificity of the peaks was robustly verified using common foodborne pathogens. Thus, we concluded that genome-guided MALDI-TOF MS allows high-throughput differentiation of B. cereus and B. thuringiensis and provides a framework for differentiating other closely related species.

Methodology Establishment and Application of VITEK Mass Spectrometry to Detect Carbapenemase-Producing Klebsiella pneumoniae

The ability of VITEK mass spectrometry (MS) in detection of bacterial resistance is currently under exploration and evaluation. In this study, we developed and validated a VITEK MS method to rapidly test carbapenemase-producing Klebsiella pneumoniae (CPKP). Solvents, antibiotic concentrations, crystal conditions and times, centrifugation speeds, and other factors were optimized to design a rapid sample pretreatment process for CPKP detection by VITEK MS. The related parameters of the mass spectrum were adjusted on the instrument to establish an CPKP detection mode. 133 clinically isolated strains of CPKP in the microbiology laboratory at the Shenzhen People’s Hospital from 2004 to 2017 were selected for accuracy evaluation. The fresh suspected strains from the microbiology laboratory in 2020 were used to complete the clinical verification. Two antibiotics, meropenem (MEM) and imipenem (IPM), were used as substrates. These two substrates were incubated with suspected CPKP, and the results were obtained by VITEK MS detection. Using this method, different types of CPKP showed different detection results and all the CPKP strains producing KPC-2 and IMP-4 carbapenemase were detected by VITEK MS. Thus, VITEK MS can be used for rapid detection of CPKP, especially for some common types of CPKP. This method provides high accuracy and speed of detection. Combined with its cost advantages, it can be intensely valuable in clinical microbiology laboratories after the standard operating procedures are determined.

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance

The combination of Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) spectra data and artificial intelligence (AI) has been introduced for rapid prediction on antibiotic susceptibility testing (AST) of Staphylococcus aureus. Based on the AI predictive probability, cases with probabilities between the low and high cut-offs are defined as being in the “grey zone”. We aimed to investigate the underlying reasons of unconfident (grey zone) or wrong predictive AST. In total, 479 S. aureus isolates were collected and analyzed by MALDI-TOF, and AST prediction and standard AST were obtained in a tertiary medical center. The predictions were categorized as correct-prediction group, wrong-prediction group, and grey-zone group. We analyzed the association between the predictive results and the demographic data, spectral data, and strain types. For methicillin-resistant S. aureus (MRSA), a larger cefoxitin zone size was found in the wrong-prediction group. Multilocus sequence typing of the MRSA isolates in the grey-zone group revealed that uncommon strain types comprised 80%. Of the methicillin-susceptible S. aureus (MSSA) isolates in the grey-zone group, the majority (60%) comprised over 10 different strain types. In predicting AST based on MALDI-TOF AI, uncommon strains and high diversity contribute to suboptimal predictive performance.

Energy Efficiency of Inference Algorithms for Clinical Laboratory Data Sets: Green Artificial Intelligence Study

Background

The use of artificial intelligence (AI) in the medical domain has attracted considerable research interest. Inference applications in the medical domain require energy-efficient AI models. In contrast to other types of data in visual AI, data from medical laboratories usually comprise features with strong signals. Numerous energy optimization techniques have been developed to relieve the burden on the hardware required to deploy a complex learning model. However, the energy efficiency levels of different AI models used for medical applications have not been studied.

Objective

The aim of this study was to explore and compare the energy efficiency levels of commonly used machine learning algorithms—logistic regression (LR), k-nearest neighbor, support vector machine, random forest (RF), and extreme gradient boosting (XGB) algorithms, as well as four different variants of neural network (NN) algorithms—when applied to clinical laboratory datasets.

Methods

We applied the aforementioned algorithms to two distinct clinical laboratory data sets: a mass spectrometry data set regarding Staphylococcus aureus for predicting methicillin resistance (3338 cases; 268 features) and a urinalysis data set for predicting Trichomonas vaginalis infection (839,164 cases; 9 features). We compared the performance of the nine inference algorithms in terms of accuracy, area under the receiver operating characteristic curve (AUROC), time consumption, and power consumption. The time and power consumption levels were determined using performance counter data from Intel Power Gadget 3.5.

Results

The experimental results indicated that the RF and XGB algorithms achieved the two highest AUROC values for both data sets (84.7% and 83.9%, respectively, for the mass spectrometry data set; 91.1% and 91.4%, respectively, for the urinalysis data set). The XGB and LR algorithms exhibited the shortest inference time for both data sets (0.47 milliseconds for both in the mass spectrometry data set; 0.39 and 0.47 milliseconds, respectively, for the urinalysis data set). Compared with the RF algorithm, the XGB and LR algorithms exhibited a 45% and 53%-60% reduction in inference time for the mass spectrometry and urinalysis data sets, respectively. In terms of energy efficiency, the XGB algorithm exhibited the lowest power consumption for the mass spectrometry data set (9.42 Watts) and the LR algorithm exhibited the lowest power consumption for the urinalysis data set (9.98 Watts). Compared with a five-hidden-layer NN, the XGB and LR algorithms achieved 16%-24% and 9%-13% lower power consumption levels for the mass spectrometry and urinalysis data sets, respectively. In all experiments, the XGB algorithm exhibited the best performance in terms of accuracy, run time, and energy efficiency.

Conclusions

The XGB algorithm achieved balanced performance levels in terms of AUROC, run time, and energy efficiency for the two clinical laboratory data sets. Considering the energy constraints in real-world scenarios, the XGB algorithm is ideal for medical AI applications.

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

Early use of effective antimicrobial treatments is critical for the outcome of infections and the prevention of treatment resistance. Antimicrobial resistance testing enables the selection of optimal antibiotic treatments, but current culture-based techniques can take up to 72 hours to generate results. We have developed a novel machine learning approach to predict antimicrobial resistance directly from matrix-assisted laser desorption/ionization-time of flight (MALDI-TOF) mass spectra profiles of clinical isolates. We trained calibrated classifiers on a newly created publicly available database of mass spectra profiles from the clinically most relevant isolates with linked antimicrobial susceptibility phenotypes. This dataset combines more than 300,000 mass spectra with more than 750,000 antimicrobial resistance phenotypes from four medical institutions. Validation on a panel of clinically important pathogens, including Staphylococcus aureus, Escherichia coli and Klebsiella pneumoniae, resulting in areas under the receiver operating characteristic curve of 0.80, 0.74 and 0.74, respectively, demonstrated the potential of using machine learning to substantially accelerate antimicrobial resistance determination and change of clinical management. Furthermore, a retrospective clinical case study of 63 patients found that implementing this approach would have changed the clinical treatment in nine cases, which would have been beneficial in eight cases (89%). MALDI-TOF mass spectra-based machine learning may thus be an important new tool for treatment optimization and antibiotic stewardship.

MDRSA: A Web Based-Tool for Rapid Identification of Multidrug Resistant Staphylococcus aureus Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry

As antibiotics resistance on superbugs has risen, more and more studies have focused on developing rapid antibiotics susceptibility tests (AST). Meanwhile, identification of multiple antibiotics resistance on Staphylococcus aureus provides instant information which can assist clinicians in administrating the appropriate prescriptions. In recent years, matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) has emerged as a powerful tool in clinical microbiology laboratories for the rapid identification of bacterial species. Yet, lack of study devoted on providing efficient methods to deal with the MS shifting problem, not to mention to providing tools incorporating the MALDI-TOF MS for the clinical use which deliver the instant administration of antibiotics to the clinicians. In this study, we developed a web tool, MDRSA, for the rapid identification of oxacillin-, clindamycin-, and erythromycin-resistant Staphylococcus aureus. Specifically, the kernel density estimation (KDE) was adopted to deal with the peak shifting problem, which is critical to analyze mass spectra data, and machine learning methods, including decision trees, random forests, and support vector machines, which were used to construct the classifiers to identify the antibiotic resistance. The areas under the receiver operating the characteristic curve attained 0.8 on the internal (10-fold cross validation) and external (independent testing) validation. The promising results can provide more confidence to apply these prediction models in the real world. Briefly, this study provides a web-based tool to provide rapid predictions for the resistance of antibiotics on Staphylococcus aureus based on the MALDI-TOF MS data. The web tool is available at: http://fdblab.csie.ncu.edu.tw/mdrsa/.

MALDI-TOF Mass Spectrometry Technology as a Tool for the Rapid Diagnosis of Antimicrobial Resistance in Bacteria

Species identification by using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a routine diagnostic process for infectious diseases in current clinical settings. The rapid, low-cost, and simple to conduct methodology is expanding its application in clinical microbiology laboratories to diagnose the antimicrobial resistance (AMR) in microorganisms. Primarily, antimicrobial susceptibility testing is able to be carried out either by comparing the area under curve of MALDI spectra of bacteria grown in media with antimicrobial drugs or by identifying the shift peaks of bacteria grown in media including ¹³C isotope with antimicrobial drugs. Secondly, the antimicrobial resistance is able to be determined through identifying (i) the antimicrobial-resistant clonal groups based on the fingerprints of the clone, (ii) the shift peak of the modified antimicrobial drug, which is inactivated by the resistance determinant, (iii) the shift peak of the modified antimicrobial target, (iv) the peak specific for the antimicrobial determinant, and (v) the biomarkers that are coproduced proteins with AMR determinants. This review aims to present the current usage of the MALDI-TOF MS technique for diagnosing antimicrobial resistance in bacteria, varied approaches for AMR diagnostics using the methodology, and the future applications of the methods for the accurate and rapid identification of AMR in infection-causing bacterial pathogens.