Application of machine learning in river water quality management: a review.

Machine learning (ML), a branch of artificial intelligence (AI), has been increasingly used in environmental engineering due to the ability to analyze complex nonlinear problems (such as ones connected with water quality management) through a data-driven approach. This study provides an overview of different ML algorithms applied for monitoring and predicting river water quality. Different parameters could be monitored or predicted, such as dissolved oxygen (DO), biological and chemical oxygen demand (BOD and COD), turbidity levels, the concentration of different ions (such as Mg2+ and Ca2+), heavy metal or other pollutant's concentration, pH, temperature, and many more. Although many algorithms have been investigated for the prediction of river water quality, there are several which are most commonly used in engineering practice. These models mostly include so-called supervised learning algorithms, such as artificial neural network (ANN), support vector machine (SVM), random forest (RF), decision tree (DT), and deep learning (DL). To further enhance prediction power, novel hybrid algorithms, could be used. However, the quality of prediction is not only dependent on the applied algorithm but also on the availability of previously mentioned water quality parameters, their selection, and the combination of input data used to train the ML model.

Chemometric Approach to the Composition of Flavonoid Compounds and Phenolic Acids and Antioxidant Potential of Artemisia Species from Different Habitats.

Four Artemisia species from Serbia were selected for the study: A. annua L., A. absinthium L., A. vulgaris L. and A. scoparia Waldst. et Kit. because of the proven excellent action in treating certain medical conditions and diseases. A. absinthium L., A. vulgaris L., A. annua L. and A. scoparia Waldst. et Kit. collected from different habitats across Serbia (48 samples in total) were studied from the statistical aspect considering the phenolic and flavonoid contents, compositions, and antioxidant activities of methanol extracts in correlation with the soil type. The components were identified using HPLC (High Performance Liquid Chromatography), while antioxidant activities were determined by seven assays (TP (Total phenolic content), TF (Total flavonoid content), DPPH (2,2-diphenyl-1-picrylhydrazyl) radical-based, ABTS (2,2'-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid)) radical cation-based, FRAP (Ferric Reducing Antioxidant Power), TRP (Total Reducing Power), and CUPRAC (Cupric Reducing Antioxidant Capacity). The results were processed using five statistical methods (PCA (Principal Component Analysis), ANOVA (Analysis of Variance), MANOVA (Multivariate analysis of variance), DA (Discriminant analysis), and AHC (Agglomerative Hierarchical Clustering)). Principal component analysis enabled very well separation of the analyzed Artemisia species based on the content of total phenolics, total flavonoids, and the values obtained from antioxidant tests, but not on the individual compounds identified and quantified by HPLC. The MANOVA analyses showed that for A. scoparia and A. annua there was a significant effect of soil type on the total phenolics, total flavonoids, and antioxidant tests. In contrast, for A. vulgaris and A. absinthium, that effect was not significant. Additional MANOVA analyses showed a significant effect of soil type on phenolic and flavonoid compounds in the case of A. vulgaris, A. annua, and A. absinthium. The overall correct classification rate of all samples of four investigated Artemisia species by the discriminant analysis was 81.25 % using the training sample and 72.92 % the cross-validation results based on TP, TF, and antioxidant tests, but a much lower based on selected compounds identified and quantified by HPLC. MANOVA analyses based on particular Artemisia species show that soil is a significant factor affecting the measurable variables.

Less Known but Clinically Relevant Comorbidities of Atrial Fibrillation: A Narrative Review.

BACKGROUND: The important risk factors for atrial fibrillation (AF) in the general population are not always equally important in specific and relatively prevalent diseases. OBJECTIVE: The main goal of this narrative review is to focus attention on the presence and the relationship of AF with several important diseases, such as cancer or sepsis, in order to: 1) stimulate further research in the field, and 2) draw attention to this relationship and search for AF in clinical practice. METHODS: We searched PubMed, SCOPUS, Elsevier, Wiley, Springer, Oxford Journals, Cambridge, SAGE, and Google Scholar for less-known comorbidities of AF. The search was limited to publications in English. No time limits were applied. RESULTS: AF is widely represented in cardiovascular and other important diseases, even in those in which AF is rarely mentioned. In some specific clinical subsets of AF patients (e.g., patients with sepsis or cancer), the general risk factors for AF may not be so important. Patients with new-onset AF have a several-fold increase in relative risk of cancer, deep vein thrombosis, and pulmonary thromboembolism (PTE) during the follow-up. CONCLUSION: AF presence, prognosis, and optimal therapeutic approach are insufficiently recognised in several prevalent diseases, including life-threatening ones. There is a need for a better search for AF in PTE, pulmonary oedema, aortic dissection, sepsis, cancer and several gastrointestinal diseases. Improved AF detection would influence treatment and improve outcomes.

Should Cushing's Syndrome be Considered as a Disease with High Cardiovascular Risk in Relevant Guidelines?

A considerable amount of data supports a 1.8-7.4-fold increased mortality associated with Cushing's syndrome (CS). This is attributed to a high occurrence of several cardiovascular disease (CVD) risk factors in CS [e.g. adiposity, arterial hypertension (AHT), dyslipidaemia and type 2 diabetes mellitus (T2DM)]. Therefore, practically all patients with CS have the metabolic syndrome (MetS), which represents a high CVD risk. Characteristically, despite a relatively young average age, numerous patients with CS display a 'high' or 'very high' CVD risk (i.e. risk of a major CVD event >20% in the following 10 years). Although T2DM is listed as a condition with a high CVD risk, CS is not, despite the fact that a considerable proportion of the CS population will develop T2DM or impaired glucose tolerance. CS is also regarded as a risk factor for aortic dissection in current guidelines. This review considers the evidence supporting listing CS among high CVD risk conditions.

A simple numerical method for snowmelt simulation based on the equation of heat energy.

This paper presents one-dimensional numerical model for snowmelt/accumulation simulations, based on the equation of heat energy. It is assumed that the snow column is homogeneous at the current time step; however, its characteristics such as snow density and thermal conductivity are treated as functions of time. The equation of heat energy for snow column is solved using the implicit finite difference method. The incoming energy at the snow surface includes the following parts: conduction, convection, radiation and the raindrop energy. Along with the snow melting process, the model includes a model for snow accumulation. The Euler method for the numerical integration of the balance equation is utilized in the proposed model. The model applicability is demonstrated at the meteorological station Zlatibor, located in the western region of Serbia at 1,028 meters above sea level (m.a.s.l.) Simulation results of snowmelt/accumulation suggest that the proposed model achieved better agreement with observed data in comparison with the temperature index method. The proposed method may be utilized as part of a deterministic hydrological model in order to improve short and long term predictions of possible flood events.

Effect of two esters of N-methylanthranilic acid from Rutaceae species on impaired kidney morphology and function in rats caused by CCl4.

AIMS: Herein we investigated the potential protective effects of methyl N-methylanthranilate (MA) and isopropyl N-methylanthranilate (IA), two naturally occurring plant constituents from Rutaceae taxa, in a rat model of acute intoxication with carbon tetrachloride (CCl4) by tracking changes in kidney tissue morphology and function. MAIN METHODS: The antioxidant capacity of IA and MA was evaluated using 2,2-diphenyl-1-picrylhydrazyl (DPPH) and 2,2'-azino-bis(3-ethylbenzthiazoline-6-sulphonic acid radical cation (ABTS(+)) assays and superoxide-scavenging test. Wistar rats were treated daily with MA and IA for seven days in a dose of 200mg/kg. Twenty-four hours after a CCl4 injection, rats were sacrificed and blood samples were used for the evaluation of urea and creatinine. Kidney tissue specimens were stained with hematoxylin and eosin, periodic acid-Schiff and Jones stain and evaluated for morphological changes. Quantification of structural changes determined by histological analysis of kidney tissue was assessed by a morphometric analysis of glomeruli using ImageJ software. KEY FINDINGS: IA and MA applied in high doses on their own did not cause any significant damage to kidney tissue. A pretreatment with MA prior to the administration of CCl4 significantly prevented the increase of serum levels of decreased kidney function markers, while that of IA did not. Histopathological evaluation of the kidneys also revealed that MA reduced the incidence of kidney lesions. SIGNIFICANCE: Our experiments showed that methyl-, and not isopropyl-, N-methylanthranilate possesses a protective potential against CCl4-induced kidney damage in rats. The results are of interest due to the presence of natural or synthetic methyl N-methylanthranilate in the human diet and their potent analgesic properties.

New volatile sulfur-containing compounds from wild garlic (Allium ursinum L., Liliaceae).

In many countries, the leaves of Allium ursinum L. (Liliaceae) are a popular substitute for garlic and, for centuries, the herb has been taken internally to treat an array of medical conditions. Herein, we report the chemical composition of 12 different A. ursinum essential-oil samples (five populations; fresh/air-/oven-dried plant material; leaves/inflorescences). GC-MS/GC-FID analyses, quantitative structure-property relationship modeling (simple 0D/1D-descriptors) of retention indices and the synthesis of selected compounds, enabled the identification of >200 different constituents, mainly organo(poly)sulfides. Some of these were new compounds (allyl (methylthio)methyl, (methylthio)methyl (Z)/(E)-1-propenyl and allyl 1-(methylthio)propyl disulfides) or were previously not detected in samples of natural origin (heptyl methyl, methyl octyl, allyl hexyl (1), allyl octyl (2) and propyl (propylthio)methyl sulfides). A multivariate statistical analysis revealed the onset of significant changes in the plant material volatile profile during the drying process.

Exploitation of the antioxidant potential of Geranium macrorrhizum (Geraniaceae): hepatoprotective and antimicrobial activities.

In this study we evaluated in vitro (radical scavenging) and in vivo (hepatoprotective effect) antioxidant activities and antimicrobial properties of the extracts of the above- and underground parts of Geranium macrorrhizum L. (Geraniaceae), an ethnopharmacologically renowned plant species. The antioxidant activity and total phenol and flavonoid contents of four different solvent extracts were evaluated by seven different methods. The methanol extracts, administered i.p. to rats (120-480 mg/kg), were evaluated for hepatoprotective activity in a CCl4-induced hepatotoxicity model. The same extracts were tested for antimicrobial activity against seven bacterial and two fungal species. The administered methanol extracts with the highest antioxidant potential showed a significant dose-dependent hepatoprotective action against CCl4-induced liver damage in both decreasing the levels of liver transaminases and bilirubin and in reducing the extent of morphological malformations of the liver. The leaf methanol extract displayed a very strong antibacterial activity, especially against Staphylococcus aureus, with low minimal inhibitory and bactericidal concentrations. These results justify the frequent use of this plant species in folk medicine. Besides the known astringent effect, one can expect that the observed antimicrobial activity against several human pathogens contributes to the wound healing properties of this plant.

Heavy metal content in different types of smoked meat in Serbia.

Concentrations of Fe, Cu, Ni, Cr, Pb, Mn, Zn and Cd in pork, beef, turkey and chicken samples were determined using inductively coupled plasma-optical emission spectrometry (ICP-OES). The mean concentration ranges in milligrams per 100 g of the studied metals in all samples were 0.6924-1.2154 for Fe, 0.6492-0.9831 for Cu, 0.0012-0.0027 for Pb, 0.041-0.0510 for Ni, 0.1186-0.1481 for Mn, 0.7257-5.2726 for Zn and 0.0042-0.0050 for Cd. The levels of analysed elements were in accordance with European standards for all metals except for manganese in all samples and for nickel in a certain number of samples. Zn level in beef was significantly higher compared to other samples, and Pb and Cd were found in concentrations well below the recommended daily intake.