Comparison of machine learning algorithms for clinical event prediction (risk of coronary heart disease).

AIM: The aim of this study is to compare the utility of several supervised machine learning (ML) algorithms for predicting clinical events in terms of their internal validity and accuracy. The results, which were obtained using two statistical software platforms, were also compared. MATERIALS AND METHODS: The data used in this research come from the open database of the Framingham Heart Study, which originated in 1948 in Framingham, Massachusetts as a prospective study of risk factors for cardiovascular disease. Through data mining processes, three data models were elaborated and a comparative methodological study between the different ML algorithms - decision tree, random forest, support vector machines, neural networks, and logistic regression - was carried out. The global selection criterium for choosing the right set of hyperparameters and the type of data manipulation was the area under a curve (AUC). The software tools used to analyze the data were R-Studio® and RapidMiner®. RESULTS: The Framingham study open database contains 4240 observations. The algorithm that yielded the greatest AUC when analyzing the data in R-Studio was neural network applied to a model that excluded all observations in which there was at least one missing value (AUC = 0.71); when analyzing the data in RapidMiner and applying the same model, the best algorithm was support vector machines (AUC = 0.75). CONCLUSIONS: ML algorithms can reinforce the diagnostic and prognostic capacity of traditional regression techniques. Differences between the applicability of those algorithms and the results obtained with them were a function of the software platforms used in the data analysis.

Antioxidant Effect of the Ethyl Acetate Extract of Potentilla indica on Kidney Mitochondria of Streptozotocin-Induced Diabetic Rats.

Diabetes mellitus (DM) is a metabolic disorder characterized by persistent hyperglycemia. This state may lead to an increase in oxidative stress, which contributes to the development of diabetes complications, including diabetic kidney disease. Potentilla indica is a traditional medicinal herb in Asia, employed in the treatment of several diseases, including DM. In this study, we investigated the antioxidant effect of the ethyl acetate extract of Potentilla indica both in vitro and on kidneys of streptozotocin-induced diabetic male rats. Firstly, phytochemicals were identified via UPLC-MS/MS, and their in vitro antioxidant capabilities were evaluated. Subsequently, male Wistar rats were assigned into four groups: normoglycemic control, diabetic control, normoglycemic treated with the extract, and diabetic treated with the extract. At the end of the treatment, fasting blood glucose (FBG) levels, creatinine, blood urea nitrogen (BUN), and uric acid were estimated. Furthermore, the kidneys were removed and utilized for the determination of mitochondrial reactive oxygen species (ROS) production, mitochondrial respiratory chain complex activities, mitochondrial lipid peroxidation, glutathione peroxidase (GSH-Px), superoxide dismutase (SOD), and catalase (CAT) activities. The in vitro findings showed that the major phytochemicals present in the extract were phenolic compounds, which exhibited a potent antioxidant activity. Moreover, the administration of the P. indica extract reduced creatinine and BUN levels, ROS production, and lipid peroxidation and improved mitochondrial respiratory chain complex activity and GSH-Px, SODk, and CAT activities when compared to the diabetic control group. In conclusion, our data suggest that the ethyl acetate extract of Potentilla indica possesses renoprotective effects by reducing oxidative stress on the kidneys of streptozotocin-induced diabetic male rats.

An Ethyl Acetate Extract of Eryngium carlinae Inflorescences Attenuates Oxidative Stress and Inflammation in the Liver of Streptozotocin-Induced Diabetic Rats.

Secondary metabolites such as flavonoids are promising in the treatment of non-alcoholic fatty liver disease (NAFLD), which is one of the complications of diabetes due to oxidative stress and inflammation. Some plants, such as Eryngium carlinae, have been investigated regarding their medicinal properties in in vitro and in vivo assays, showing favorable results for the treatment of various diseases such as diabetes and obesity. The present study examined the antioxidant and anti-inflammatory effects of the phenolic compounds present in an ethyl acetate extract of the inflorescences of Eryngium carlinae on liver homogenates and mitochondria from streptozotocin (STZ)-induced diabetic rats. Phenolic compounds were identified and quantified by UHPLC-MS. In vitro assays were carried out to discover the antioxidant potential of the extract. Male Wistar rats were administered with a single intraperitoneal injection of STZ (45 mg/kg) and were given the ethyl acetate extract at a level of 30 mg/kg for 60 days. Phytochemical assays showed that the major constituents of the extract were flavonoids; in addition, the in vitro antioxidant activity was dose dependent with IC50 = 57.97 mg/mL and IC50 = 30.90 mg/mL in the DPPH and FRAP assays, respectively. Moreover, the oral administration of the ethyl acetate extract improved the effects of NAFLD, decreasing serum and liver triacylglycerides (TG) levels and oxidative stress markers and increasing the activity of the antioxidant enzymes. Likewise, it attenuated liver damage by decreasing the expression of NF-κB and iNOS, which lead to inflammation and liver damage. We hypothesize that solvent polarity and consequently chemical composition of the ethyl acetate extract of E. carlinae, exert the beneficial effects due to phenolic compounds. These results suggest that the phenolic compounds of the ethyl acetate extract of E. carlinae have antioxidant, anti-inflammatory, hypolipidemic, and hepatoprotective activity.