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.

Recent studies have demonstrated that the matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) could be used to detect superbugs, such as methicillin-resistant Staphylococcus aureus (MRSA). Due to an increasingly clinical need to classify between MRSA and methicillin-sensitive Staphylococcus aureus (MSSA) efficiently and effectively, we were motivated to develop a systematic pipeline based on a large-scale dataset of MS spectra. However, the shifting problem of peaks in MS spectra induced a low effectiveness in the classification between MRSA and MSSA isolates. Unlike previous works emphasizing on specific peaks, this study employs a binning method to cluster MS shifting ions into several representative peaks. A variety of bin sizes were evaluated to coalesce drifted or shifted MS peaks to a well-defined structured data. Then, various machine learning methods were performed to carry out the classification between MRSA and MSSA samples. Totally 4858 MS spectra of unique S. aureus isolates, including 2500 MRSA and 2358 MSSA instances, were collected by Chang Gung Memorial Hospitals, at Linkou and Kaohsiung branches, Taiwan. Based on the evaluation of Pearson correlation coefficients and the strategy of forward feature selection, a total of 200 peaks (with the bin size of 10 Da) were identified as the marker attributes for the construction of predictive models. These selected peaks, such as bins 2410-2419, 2450-2459 and 6590-6599 Da, have indicated remarkable differences between MRSA and MSSA, which were effective in the prediction of MRSA. The independent testing has revealed that the random forest model can provide a promising prediction with the area under the receiver operating characteristic curve (AUC) at 0.8450. When comparing to previous works conducted with hundreds of MS spectra, the proposed scheme demonstrates that incorporating machine learning method with a large-scale dataset of clinical MS spectra may be a feasible means for clinical physicians on the administration of correct antibiotics in shorter turn-around-time, which could reduce mortality, avoid drug resistance and shorten length of stay in hospital in the future.

Machine Learning-Based Method for Obesity Risk Evaluation Using Single-Nucleotide Polymorphisms Derived from Next-Generation Sequencing.

Obesity is a major risk factor for many metabolic diseases. To understand the genetic characteristics of obese individuals, single-nucleotide polymorphisms (SNPs) derived from next-generation sequencing (NGS) provide comprehensive insight into genome-wide genetic investigation. However, interpretation of these SNP data for clinical application is difficult given the high complexity of NGS data. Hence, in this study, obesity risk prediction models based on SNPs were designed using machine learning (ML) methods, namely support vector machine (SVM), k-nearest neighbor, and decision tree (DT). This investigation obtained clinicopathological features, including 130 SNPs, sex, and age, from 139 eligible individuals. Various feature selection methods, such as stepwise multivariate linear regression (MLR), DT, and genetic algorithms, were applied to select informative features for generating obesity prediction models. Multivariate logistic regression was used to evaluate the importance of the selected features. The models trained from various features evaluated their predictive performances based on fivefold cross-validation. Three measures, namely accuracy, sensitivity, and specificity, were used to examine and compare the predictive power among various models. To design obesity prediction models using ML methods, nine SNPs, including rs10501087, rs17700144, rs2287019, rs534870, rs660339, rs7081678, rs718314, rs9816226, and rs984222, were selected based on stepwise MLR. In evaluation of model performance, the SVM model significantly outperformed other classifiers based on the same training features. The SVM model exhibits 70.77% accuracy, 80.09% sensitivity, and 63.02% specificity. This investigation has demonstrated that the selected SNPs were effective in the detection of obesity risk. Additionally, the ML-based method provides a feasible mean for conducting preliminary analyses of genetic characteristics of obesity.

Accelerated Arterial Stiffening Change in Early Years of Spinal Cord Injury.

Patients with spinal cord injury (SCI) possess higher arterial stiffness index (SI) than the healthy population. This study aimed to clarify the effect of post-morbid duration on arterial stiffening change among SCI sufferers. Seventy-one SCI patients were recruited. The demographic data including age, gender, level of injury, body mass index, American Spinal Cord Injury Association Impairment Scale, and post-morbid duration were collected. The age was 36.4 ± 11.7 years and the duration was 87.5 ± 106.4 months. SI was assessed with digital volume pulse analysis. Correlation matrix demonstrated that age is the most significant determinant of SI (R = 0.503). The scatter plot of duration versus SI showed that they were correlated significantly, but in a logarithmic rather than linear trend. Partial correlation showed that the natural log of duration (Lnduration) has higher adjusted correlation coefficient (0.357) than duration when the effect of age and other factors were eliminated. Multiple linear regression modeling also exhibited that Lnduration is the only factor that significantly increases the explanation of SI by age. In conclusion, Lnduration is an independent determinant of SI. SCI accelerates vascular aging especially in the early several years. Therefore, there should be emphasis on primary prevention of cardiovascular disorders during early years of SCI.