This study investigates the potential of using principal component analysis and other multivariate analysis techniques to evaluate water quality data gathered from natural watercourses. With this goal in mind, a comprehensive water quality data set was used for the analysis, gathered on a reach of the Danube River in 2011. The considered measurements included physical, chemical, and biological parameters. The data were collected within seven data ranges (cross-sections) of the Danube River. Each cross-section had five verticals, each of which had five sampling points distributed over the water column. The gathered water quality data was then subjected to several multivariate analysis techniques. However, the most attention was attributed to the principal component analysis since it can provide an insight into possible grouping tendencies within verticals, cross-sections, or the entire considered reach. It has been concluded that there is no stratification in any of the analyzed water columns. However, there was an unambiguous clustering of sampling points with respect to their cross-sections. Even though one can attribute these phenomena to the unsteady flow in rivers, additional considerations suggest that the position of a cross-section can have a significant impact on the measured water quality parameters. Furthermore, the presented results indicate that these measurements, combined with several multivariate analysis methods, especially the principal component analysis, may be a promising approach for investigating the water quality tendencies of alluvial rivers.

In order to limit the spread of the novel betacoronavirus (SARS-CoV-2), it is necessary to detect positive cases as soon as possible and isolate them. For this purpose, machine-learning algorithms, as a field of artificial intelligence, have been recognized as a promising tool. The aim of this study was to assess the utility of the most common machine-learning algorithms in the rapid triage of children with suspected COVID-19 using easily accessible and inexpensive laboratory parameters. A cross-sectional study was conducted on 566 children treated for respiratory diseases: 280 children with PCR-confirmed SARS-CoV-2 infection and 286 children with respiratory symptoms who were SARS-CoV-2 PCR-negative (control group). Six machine-learning algorithms, based on the blood laboratory data, were tested: random forest, support vector machine, linear discriminant analysis, artificial neural network, k-nearest neighbors, and decision tree. The training set was validated through stratified cross-validation, while the performance of each algorithm was confirmed by an independent test set. Random forest and support vector machine models demonstrated the highest accuracy of 85% and 82.1%, respectively. The models demonstrated better sensitivity than specificity and better negative predictive value than positive predictive value. The F1 score was higher for the random forest than for the support vector machine model, 85.2% and 82.3%, respectively. This study might have significant clinical applications, helping healthcare providers identify children with COVID-19 in the early stage, prior to PCR and/or antigen testing. Additionally, machine-learning algorithms could improve overall testing efficiency with no extra costs for the healthcare facility.