Significant Feature Selection Method for Health Domain using Computational Intelligence- A Case Study for Heart Disease

Abstract

In the medical field, the diagnosing of cardiovascular disease is that the most troublesome task. The diagnosis of heart disease is difficult as a decision relied on grouping of large clinical and pathological data. Due to this complication, the interest increased in a very vital quantity between the researchers and clinical professionals regarding the economical and correct heart disease prediction. In case of heart disease, the correct diagnosis in early stage is important as time is the very important factor. Heart disease is the principal supply of deaths widespread, and the prediction of Heart Disease is significant at an untimely phase. Machine learning in recent years has been the evolving, reliable and supporting tools in medical domain and has provided the best support for predicting disease with correct case of training and testing. The main idea behind this work is to find relevant heart disease feature among the large number of feature using rough computational Intelligence approach. The proposed feature selection approach performance is better than traditional feature selection approaches. The performances of the rough computation approach is tested with different heart disease data sets and validated with real-time data sets.