Feature selection using heuristic approaches for heart disease classification

Abstract

This research is designed in alignment with recent reports published by World Health Organization (WHO) on Cardio vascular diseases (CVD) the most common heart problem and the possible detection methods. Recent estimates show that 27.1 million individuals are suffering from CVD in 2018 out of which 69% of them suffer death as an average in the world every year due to cardiac trauma. Third world countries with low and moderate incomes are affected adversely at 82% of death caused by CVD occurs in these countries out of the world total numbers irrespective of gender. It is estimated to be about 23,600,000 in 2030 individuals would suffer from heart diseases. Southeast Asia and eastern Mediterranean region is the most prominent areas of concern because of changes of life styles, food habits, and occupational culture. Heart diseases mainly affect individuals with 65 years old and older but still expanding in developing countries due to lack of health care in these countries. The recent reports of WHO also indicates, the need for accurate methods for prediction at early stage by efficient periodical examination of heart to diagnose heart diseases are very crucial for health care planning of such countries. The number and size of medical databases are rapidly increasing, and the advanced models of data mining techniques could help physicians to make efficient and applicable decisions. The challenges of heart disease data include the feature selection, the number of the samples; imbalance of the samples, lack of magnitude for some features, etc. This study mainly focuses on the feature selection improvement and decreasing the numbers of the features. In this study, meta-heuristic approach is suggested in order to select prominent features of the heart disease. Evaluation result shows that by using the proposed algorithm, the accuracy of feature selection technique has been improved newline