Analysis of Pre-processing and Post-processing Methods and Using Data Mining to Diagnose Heart Diseases

Today, a great deal of data is generated in the medical field. Acquiring useful knowledge from this raw data requires data processing and detection of meaningful patterns and this objective can be achieved through data mining. Using data mining to diagnose and prognose heart diseases has become one of the areas of interest for researchers in recent years. In this study, the literature on the application of classification algorithms for heart disease will be reviewed. The present study is an attempt to evaluate the studies carried out in this field so that the results of this review may lead to development of a clear view on the future studies. Here, first, the major medical tasks are specified and then, each article is investigated based on these tasks. Finally, some results, in terms of frequency algorithms in the use of classification algorithms, pre-processing and post-processing methods, will be provided. In this study, 49 articles obtained from similar studies with related subject matters, (from 2003 to 2015) are collected and reviewed. Obviously, the number of articles on applications of classification algorithms in heart disease is quite significant, therefore, it is impossible to review all of them in the present study. It is hoped that this study can provide results that pave the path for future research and further developments in this area.