Diagnosis of Heart Disease Based on Meta Heuristic Algorithms and Clustering Methods

Data analysis in cardiovascular diseases is difficult due to large massive of information. All of the features are not impressive in the final results. So, it is very important to identify more effective features. In this study, the method of feature selection with binary cuckoo optimization algorithm is implemented to reduce property. According to the results, the most appropriate classification for support vector machine is featured diagnoses heart disease. The main purpose of this article is feature reduction and providing a more precise diagnosis of the disease. The performance of the proposed method is evaluated using three measures: accuracy, sensitivity and specificity. For comparison, a data set of Machine Learning Repository database including information about 303 people with 14 features was used. In addition to the high accuracy of current methods, they are expensive and time-consuming. The results indicate that the proposed method is superior to the other algorithms in terms of performance, accuracy and run time.

Keywords:

Heart disease , Support vector machine , Binary cuckoo optimization , Algorithm , Features selection