Early Prediction of Heart Diseases Using Data Mining Techniques

Abstract

Largest-ever study of deaths shows heart diseases have emerged as the number one killer in world. About 25 per cent of deaths in the age group of 25- 69 years occur because of heart diseases. If all age groups are included, heart diseases account for about 19 per cent of all deaths. It is the leading cause of death among males as well as females. It is also the leading cause of death in all regions though the numbers vary. The proportion of deaths caused by heart disease is the highest in south India (25 per cent) and lowest - 12 per cent - in the central region of India. The prediction of heart disease survivability has been a challenging research problem for many researchers. Since the early dates of the related research, much advancement has been recorded in several related fields. Therefore, the main objective of this manuscript is to report on a research project where we took advantage of those available technological advancements to develop prediction models for heart disease survivability.

We used three popular data mining algorithms CART (Classification and Regression Tree), ID3 (Iterative Dichotomized 3) and decision table (DT) extracted from a decision tree or rule-based classifier to develop the prediction models using a large dataset. We also used 10-fold crossvalidation methods to measure the unbiased estimate.

Keywords: Heart disease, Survivability, Data Mining, CART, ID3, Decision table