Large-Scale Samples Based Rapid Detection of Ciprofloxacin Resistance in Klebsiella pneumoniae Using Machine Learning Methods

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.

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.

Rapid and Accurate Discrimination of Mycobacterium abscessus Subspecies Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Spectrum and Machine Learning Algorithms

Mycobacterium abscessus complex (MABC) has been reported to cause complicated infections. Subspecies identification of MABC is crucial for adequate treatment due to different antimicrobial resistance properties amid subspecies. However, long incubation days are needed for the traditional antibiotic susceptibility testing (AST). Delayed effective antibiotics administration often causes unfavorable outcomes. Thus, we proposed a novel approach to identify subspecies and potential antibiotic resistance, guiding early and accurate treatment. Subspecies of MABC isolates were determined by secA1, rpoB, and hsp65. Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) spectra were analyzed, and informative peaks were detected by random forest (RF) importance. Machine learning (ML) algorithms were used to build models for classifying MABC subspecies based on spectrum. The models were validated by repeated five-fold cross-validation to avoid over-fitting. In total, 102 MABC isolates (52 subspecies abscessus and 50 subspecies massiliense) were analyzed. Top informative peaks including m/z 6715, 4739, etc. were identified. RF model attained AUROC of 0.9166 (95% CI: 0.9072-0.9196) and outperformed other algorithms in discriminating abscessus from massiliense. We developed a MALDI-TOF based ML model for rapid and accurate MABC subspecies identification. Due to the significant correlation between subspecies and corresponding antibiotics resistance, this diagnostic tool guides a more precise and timelier MABC subspecies-specific treatment.