Early Prediction in Classification of Cardiovascular Diseases with Machine Learning, Neuro-Fuzzy and Statistical Methods.

Timely and accurate detection of cardiovascular diseases (CVDs) is critically important to minimize the risk of a myocardial infarction. Relations between factors of CVDs are complex, ill-defined and nonlinear, justifying the use of artificial intelligence tools. These tools aid in predicting and classifying CVDs. In this article, we propose a methodology using machine learning (ML) approaches to predict, classify and improve the diagnostic accuracy of CVDs, including support vector regression (SVR), multivariate adaptive regression splines, the M5Tree model and neural networks for the training process. Moreover, adaptive neuro-fuzzy and statistical approaches, nearest neighbor/naive Bayes classifiers and adaptive neuro-fuzzy inference system (ANFIS) are used to predict seventeen CVD risk factors. Mixed-data transformation and classification methods are employed for categorical and continuous variables predicting CVD risk. We compare our hybrid models and existing ML techniques on a CVD real dataset collected from a hospital. A sensitivity analysis is performed to determine the influence and exhibit the essential variables with regard to CVDs, such as the patient's age, cholesterol level and glucose level. Our results report that the proposed methodology outperformed well known statistical and ML approaches, showing their versatility and utility in CVD classification. Our investigation indicates that the prediction accuracy of ANFIS for the training process is 96.56%, followed by SVR with 91.95% prediction accuracy. Our study includes a comprehensive comparison of results obtained for the mentioned methods.

The role of vitamin D deficiency on COVID-19: a systematic review and meta-analysis of observational studies.

OBJECTIVES: Although vaccination has started, coronavirus disease 2019 (COVID-19) poses a continuing threat to public health. Therefore, in addition to vaccination, the use of supplements to support the immune system may be important. The purpose of this study was to synthesize evidence on the possible effect of low serum vitamin D levels (25[OH]D<20 ng/mL or 50 nmol/L) on COVID-19 infection and outcomes. METHODS: We searched Google Scholar, PubMed, Scopus, Web of Science, and ScienceDirect without any language restrictions for articles published between January 1 and December 15, 2020. We performed 3 meta-analyses (called vitamin D and COVID-19 infection meta-analysis [D-CIMA], vitamin D and COVID-19 severity meta-analysis [D-CSMA], and vitamin D and COV ID-19 mortality meta-analysis [D-CMMA] for COVID-19 infection, severity, and mortality, respectively) to combine odds ratio values according to laboratory measurement units for vitamin D and the measured serum 25(OH)D level. RESULTS: Twenty-one eligible studies were found to be relevant to the relationship between vitamin D and COVID-19 infection/outcomes (n=205,869). The D-CIMA meta-analysis showed that individuals with low serum vitamin D levels were 1.64 times (95% confidence interval [CI], 1.32 to 2.04; p<0.001) more likely to contract COVID-19. The D-CSMA meta-analysis showed that people with serum 25(OH)D levels below 20 ng/mL or 50 nmol/L were 2.42 times (95% CI, 1.13 to 5.18; p=0.022) more likely to have severe COVID-19. The D-CMMA meta-analysis showed that low vitamin D levels had no effect on COVID-19 mortality (OR, 1.64; 95% CI, 0.53 to 5.06, p=0.390). CONCLUSIONS: According to our results, vitamin D deficiency may increase the risk of COVID-19 infection and the likelihood of severe disease. Therefore, we recommend vitamin D supplementation to prevent COVID-19 and its negative outcomes.

Histopathological evaluation of autopsy cases with isolated pulmonary fat embolism (IPFE): is cardiopulmonary resuscitation a main cause of death in IPFE?

Background: Fat embolism (FE) may develop following many traumatic and atraumatic clinical conditions; however, fewer data exist regarding the occurrence of isolated pulmonary FE (IPFE). Cardiopulmonary resuscitation (CPR) is an emergency procedure for maintaining blood circulation and oxygenation during cardiac arrest. In this study, we aimed to evaluate the association of CPR with IPFE in autopsy cases. Methods: A total 402 cases among 4,118 autopsies were diagnosed with IPFE, and the medical background of these cases was retrospectively evaluated. Diagnosis of FE and FE grading were performed with histopathological examinations of postmortem tissue samples, and injury-severity scores of traumatic cases were assessed. Data of traumatic and atraumatic cases were statistically compared. Results: Of the IPFE cases, 298 (741%) were male and 104 (25.9%) female, with overall mean age 53.7 (2-99) years. Causes of death of studied subjects were traumatic for 302 (75.1%) and atraumatic reasons for 100 (24.9%) cases. CPR was performed for 277 cases of which 177 (63.9%) were traumatic and 100 (36.1%) were non-traumatic. In comparison to traumatic cases, significantly higher CPR frequency was determined in atraumatic IPFE (P=0.001). High grade FE in the traumatic cases, and mild-moderate grade of FE in the nontraumatic cases were found statistically significant (P=0.001). Conclusion: This study indicates that CPR may be one of the leading factors in the development of IPFE in atraumatic conditions, and this procedure was related to mild-moderate IPFE manifestations. Regardless of whether conditions were traumatic or atraumatic, in patients who survive following CPR for manifest ventilation/perfusion problems, it should be remembered that IPFE may have developed due to CPR.

Cytoprotective effects of molsidomine against methotrexate-induced hepatotoxicity: an experimental rat study.

INTRODUCTION AND AIM: Methotrexate (Mtx) is an antineoplastic and immunosuppressive drug that may cause hepatotoxicity, whereas molsidomine (Mol) is a vasodilating and antioxidant agent. This study aimed to investigate the potential protective effects of Mol in Mtx-induced liver toxicity in rats. MATERIALS AND METHODS: Forty Wistar albino rats were equally divided into five groups: control, Mol, Mtx, Mol-Mtx, and Mtx-Mol. Following treatment, the animals were sacrificed, and liver tissue samples were histopathologically evaluated using Roening grading and Bcl-2 antibody staining. Tissue oxidants, antioxidants, and serum transaminases were measured and statistically compared across all groups. RESULTS: No hepatic fibrosis or steatosis was observed in any of the groups. In the Mtx group, grade 2 liver injury and score 2 Bcl-2 antibody staining were observed; however, in the Mol-Mtx group, these were lower (grade 1, score 1). There were no statistically significant differences in serum transaminase levels among groups. Malondialdehyde levels were higher in all rats that received Mtx, but no differences in myeloperoxidase levels were observed among the groups. Levels of tissue antioxidants, including superoxide dismutase, glutathione (GSH) peroxidase (GSH-Px), and reduced GSH, were significantly higher in the Mol-treated and Mol pre-treated groups. Catalase (CAT) levels were elevated in all Mol-treated groups, but only in that group were CAT levels statistically significantly higher than in the control group. CONCLUSION: Our results suggest that some oxidant levels could increase following Mtx administration in the liver, possibly contributing to liver damage, whereas Mol could mitigate the histopathological and biochemical effects of hepatotoxicity. However, molecular studies are required to understand the exact mechanisms of these alterations.

A novel hybrid dimension reduction technique for undersized high dimensional gene expression data sets using information complexity criterion for cancer classification.

Gene expression data typically are large, complex, and highly noisy. Their dimension is high with several thousand genes (i.e., features) but with only a limited number of observations (i.e., samples). Although the classical principal component analysis (PCA) method is widely used as a first standard step in dimension reduction and in supervised and unsupervised classification, it suffers from several shortcomings in the case of data sets involving undersized samples, since the sample covariance matrix degenerates and becomes singular. In this paper we address these limitations within the context of probabilistic PCA (PPCA) by introducing and developing a new and novel approach using maximum entropy covariance matrix and its hybridized smoothed covariance estimators. To reduce the dimensionality of the data and to choose the number of probabilistic PCs (PPCs) to be retained, we further introduce and develop celebrated Akaike's information criterion (AIC), consistent Akaike's information criterion (CAIC), and the information theoretic measure of complexity (ICOMP) criterion of Bozdogan. Six publicly available undersized benchmark data sets were analyzed to show the utility, flexibility, and versatility of our approach with hybridized smoothed covariance matrix estimators, which do not degenerate to perform the PPCA to reduce the dimension and to carry out supervised classification of cancer groups in high dimensions.