Heart Disease Prediction Based on the Embedded Feature Selection Method and Deep Neural Network.

In recent decades, heart disease threatens people's health seriously because of its prevalence and high risk of death. Therefore, predicting heart disease through some simple physical indicators obtained from the regular physical examination at an early stage has become a valuable subject. Clinically, it is essential to be sensitive to these indicators related to heart disease to make predictions and provide a reliable basis for further diagnosis. However, the large amount of data makes manual analysis and prediction taxing and arduous. Our research aims to predict heart disease both accurately and quickly through various indicators of the body. In this paper, a novel heart disease prediction model is given. We propose a heart disease prediction algorithm that combines the embedded feature selection method and deep neural networks. This embedded feature selection method is based on the LinearSVC algorithm, using the L1 norm as a penalty item to choose a subset of features significantly associated with heart disease. These features are fed into the deep neural network we built. The weight of the network is initialized with the He initializer to prevent gradient varnishing or explosion so that the predictor can have a better performance. Our model is tested on the heart disease dataset obtained from Kaggle. Some indicators including accuracy, recall, precision, and F1-score are calculated to evaluate the predictor, and the results show that our model achieves 98.56%, 99.35%, 97.84%, and 0.983, respectively, and the average AUC score of the model reaches 0.983, confirming that the method we proposed is efficient and reliable for predicting heart disease.

Vascular endothelial growth factor A polymorphisms are associated with increased risk of coronary heart disease: a meta-analysis.

Coronary heart disease (CHD) is a common complex disease resulting from the interaction of multiple environmental and genetic factors. To assess the potential relationship of vascular endothelial growth factor (VEGFA) rs699947 C>A, rs3025039 C>T and rs2010963 G>C polymorphisms with CHD risk, a comprehensive meta-analysis was conducted. A systematic search of EMBASE and PubMed online database for publications on VEGFA polymorphisms and risk of CHD was carried out. Crude Odds ratios (ORs) with their 95% confidence intervals (CIs) were calculated to determine the association. A total of ten publications including 22 trails involving 2097 cases and 2867 controls were included in our pooled analysis. Overall, results of the present meta-analysis demonstrated a significant association between VEGFA rs699947 C>A polymorphism and an increased risk of CHD. After stratifying by ethnicity and CHD type, the association was also obtained. A significant association between VEGFA rs3025039 C>T polymorphism and risk of CHD was also found. For VEGFA rs2010963 G>C polymorphism, the polymorphism was associated with MI risk. In conclusion, our findings suggest that VEGFA rs699947 C>A, rs3025039 C>T and rs2010963 G>C polymorphisms are risk factors for CHD. In the future, large sample size and well-designed epidemiologic studies are needed to confirm these conclusions.