Cardiovascular disease detection using a new ensemble classifier

One of the biggest problems in mechanical life is the lack of mobility that can cause thousands of problems in human health. In the last decade, along with the life of a machine, many diseases, including cancer and cardiovascular disease, have been common in many societies that kill many people every year. Data mining is based on collected data and existing history to create a model that can be effective in predicting new cases of a disease, whether they are risky or not. The higher the accuracy of the prediction or recognition of a given pattern or model means the higher efficiency of the algorithm. In this study, data on cardiovascular patients collected from the UCI Laboratory is utilized for applying discovery pattern algorithms including Decision tree, Neural Networks, Rough Set, SVM, Naive Bayes, and compare their accuracy and prediction. Finally, we propose a hybrid algorithm to increase the accuracy of these algorithms. Based on the results, the proposed hybrid method achieved an F-measure of 86.8% which outperforms other competing methods.