Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been widely used in microbial identification. This study evaluated the performance of MALDI-TOF MS and investigated the economic and medical impact of MALDI-TOF MS implementation. A total of 12,202 clinical isolates collected from April to September 2013 were identified using MALDI-TOF MS, and the success rates in identifying isolates were analyzed. The differences in the processing time, cost of consumables, weight of waste, and clinical impact between MALDI-TOF MS and biochemical reaction were compared. MALDI-TOF MS successfully identified 96% of 12,202 isolates, including 96.8% of 10,502 aerobes, 90.5% of 1481 anaerobes, 93.8% of 81 yeasts, and 90.6% of 138 nontuberculous mycobacteria at the genus level. By using MALDI-TOF MS, the processing time for aerobes decreased from 32.5 hours to 4.1 hours, and that for anaerobes decreased from 71.5 hours to 46 hours. For detection of aerobes and anaerobes, the cost of consumables was estimated to decrease by US$0.9 per isolate, thus saving US$94,500 in total annual isolation. Furthermore, the weight of waste decreased six-fold, resulting in a reduction of 350 kg/month or 4.2 tons/year. MALDI-TOF MS also increased the percentage of correct antibiotics treatment for Escherichia coli and Klebsiella pneumonia from 56.1% to 75% and shortened the initiation time of the correct antibiotic action from 3.3 hours to 2.5 hours. MALDI-TOF MS is a rapid, reliable, economical, and environmentally friendly method for routine microbial identification and may contribute to early appropriate antibiotic treatment in clinical settings.

Staphylococcus aureus causes a variety of severe infections such as bacteremia and sepsis. At present, 60–80% of S. aureus isolates from Taiwan are methicillin resistant (MRSA). It has been shown that certain MRSA clones circulate worldwide. The goals of this study were to identify MRSA clones in Taiwan and to correlate the molecular types of isolates with their phenotypes. A total of 157 MRSA isolates from bacteremic patients were collected from nine medical centers. They were typed based on polymorphisms in agr, SCCmec, MLST, spa, and dru. Phenotypes characterized included Panton-Valentine leucocidin (pvl), inducible macrolide-lincosamide-streptogramin B resistance (MLSBi), vancomycin (VA) and daptomycin (DAP) minimal inhibitory concentrations (MIC), and superantigenic toxin gene profiles. Difference between two consecutive samples was determined by Mann-Whitney-U test, and difference between two categorical variables was determined by Fisher's exact test. Four major MRSA clone complexes CC1, CC5, CC8, and CC59 were found, including 4 CC1, 9 CC5, 111 CC8, and 28 CC59 isolates. These clones had the following molecular types: CC1: SCCmecIV and ST573; CC5: SCCmecII and ST5; CC8: SCCmecIII, ST239, and ST241, and CC59: SCCmecIV, SCCmecV_T, ST59, and ST338. The toxin gene profiles of these clones were CC1: sec-seg-(sei)-sell-selm-(seln)-selo; CC5: sec-seg-sei-sell-selm-(seln)-selp-tst1; CC8: sea-selk-selq, and CC59: seb-selk-selq. Most isolates with SCCmecV_T, ST59, spat437, and dru11 types were pvl⁺ (13 isolates), while multidrug resistance (≥4 antimicrobials) were associated with SCCmecIII, ST239, spa t037, agrI, and dru14 (119 isolates) (p<0.001). One hundred and twenty four isolates with the following molecular types had higher VA MIC: SCCmecII and SCCmecIII; ST5, ST239, and ST241; spa t002, t037, and t421; dru4, dru10, dru12, dru13, and dru14 (p<0.05). No particular molecular types were found to be associated with MLSBi phenotype. Four major MRSA clone complexes were found in Taiwan. Further studies are needed to delineate the evolution of MRSA isolates.

Methicillin-resistant Staphylococcus aureus (MRSA), one of the most important clinical pathogens, conducts an increasing number of morbidity and mortality in the world. Rapid and accurate strain typing of bacteria would facilitate epidemiological investigation and infection control in near real time. Matrix-assisted laser desorption ionization-time of flight (MALDI-TOF) mass spectrometry is a rapid and cost-effective tool for presumptive strain typing. To develop robust method for strain typing based on MALDI-TOF spectrum, machine learning (ML) is a promising algorithm for the construction of predictive model. In this study, a strategy of building templates of specific types was used to facilitate generating predictive models of methicillin-resistant Staphylococcus aureus (MRSA) strain typing through various ML methods. The strain types of the isolates were determined through multilocus sequence typing (MLST). The area under the receiver operating characteristic curve (AUC) and the predictive accuracy of the models were compared. ST5, ST59, and ST239 were the major MLST types, and ST45 was the minor type. For binary classification, the AUC values of various ML methods ranged from 0.76 to 0.99 for ST5, ST59, and ST239 types. In multiclass classification, the predictive accuracy of all generated models was more than 0.83. This study has demonstrated that ML methods can serve as a cost-effective and promising tool that provides preliminary strain typing information about major MRSA lineages on the basis of MALDI-TOF spectra.

Heterogeneous vancomycin-intermediate Staphylococcus aureus (hVISA) is an emerging superbug with implicit drug resistance to vancomycin. Detecting hVISA can guide the correct administration of antibiotics. However, hVISA cannot be detected in most clinical microbiology laboratories because the required diagnostic tools are either expensive, time consuming, or labor intensive. By contrast, matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) is a cost-effective and rapid tool that has potential for providing antibiotics resistance information. To analyze complex MALDI-TOF mass spectra, machine learning (ML) algorithms can be used to generate robust hVISA detection models. In this study, MALDI-TOF mass spectra were obtained from 35 hVISA/vancomycin-intermediate S. aureus (VISA) and 90 vancomycin-susceptible S. aureus isolates. The vancomycin susceptibility of the isolates was determined using an Etest and modified population analysis profile–area under the curve. ML algorithms, namely a decision tree, k-nearest neighbors, random forest, and a support vector machine (SVM), were trained and validated using nested cross-validation to provide unbiased validation results. The area under the curve of the models ranged from 0.67 to 0.79, and the SVM-derived model outperformed those of the other algorithms. The peaks at m/z 1132, 2895, 3176, and 6591 were noted as informative peaks for detecting hVISA/VISA. We demonstrated that hVISA/VISA could be detected by analyzing MALDI-TOF mass spectra using ML. Moreover, the results are particularly robust due to a strict validation method. The ML models in this study can provide rapid and accurate reports regarding hVISA/VISA and thus guide the correct administration of antibiotics in treatment of S. aureus infection.

Analytic measurement of serum tumour markers is one of commonly used methods for cancer risk management in certain areas of the world (e.g. Taiwan). Recently, cancer screening based on multiple serum tumour markers has been frequently discussed. However, the risk–benefit outcomes appear to be unfavourable for patients because of the low sensitivity and specificity. In this study, cancer screening models based on multiple serum tumour markers were designed using machine learning methods, namely support vector machine (SVM), k-nearest neighbour (KNN), and logistic regression, to improve the screening performance for multiple cancers in a large asymptomatic population. AFP, CEA, CA19-9, CYFRA21-1, and SCC were determined for 20 696 eligible individuals. PSA was measured in men and CA15-3 and CA125 in women. A variable selection process was applied to select robust variables from these serum tumour markers to design cancer detection models. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, area under the curve, and Youden index of the models based on single tumour markers, combined test, and machine learning methods were compared. Moreover, relative risk reduction, absolute risk reduction (ARR), and absolute risk increase (ARI) were evaluated. To design cancer detection models using machine learning methods, CYFRA21-1 and SCC were selected for women, and all tumour markers were selected for men. SVM and KNN models significantly outperformed the single tumour markers and the combined test for men. All 3 studied machine learning methods outperformed single tumour markers and the combined test for women. For either men or women, the ARRs were between 0.003–0.008; the ARIs were between 0.119–0.306. Machine learning methods outperformed the combined test in analysing multiple tumour markers for cancer detection. However, cancer screening based solely on the application of multiple tumour markers remains unfavourable because of the inadequate PPV, ARR, and ARI, even when machine learning methods were incorporated into the analysis.

Graves’ disease (GD) is a systemic autoimmune disease characterized by hyperthyroidism. Evidence suggests that alterations to the gut microbiota may be involved in the development of autoimmune disorders. The aim of this study was to characterize the composition of gut microbiota in GD patients. Fecal samples were collected from 55 GD patients and 48 healthy controls. Using 16S rRNA gene amplification and sequencing, the overall bacterial richness and diversity were found to be similar between GD patients and healthy controls. However, principal coordinate analysis and partial least squares-discriminant analysis showed that the overall gut microbiota composition was significantly different (ANOSIM; p < 0.001). The linear discriminant analysis effect size revealed that Firmicutes phylum decreased in GD patients, with a corresponding increase in Bacteroidetes phylum compared to healthy controls. In addition, the families Prevotellaceae, and Veillonellaceae and the genus Prevotella_9 were closely associated with GD patients, while the families Lachnospiraceae and Ruminococcaceae and the genera Faecalibacterium, Lachnospira, and Lachnospiraceae NK4A136 were associated with healthy controls. Metagenomic profiles analysis yielded 22 statistically significant bacterial taxa: 18 taxa were increased and 4 taxa were decreased. Key bacterial taxa with different abundances between the two groups were strongly correlated with GD-associated clinical parameters using Spearman’s correlation analysis. Importantly, the discriminant model based on predominant microbiota could effectively distinguish GD patients from healthy controls (AUC = 0.825). Thus, the gut microbiota composition between GD patients and healthy controls is significantly difference, indicating that gut microbiota may play a role in the pathogenesis of GD. Further studies are needed to fully elucidate the role of gut microbiota in the development of GD.