Artificial Bee Colony based Feature Selection for Effective Cardiovascular Disease Diagnosis

Machine learning has been an effective support system in medical diagnosis which involve large amount of data. Analyzing such data consumes more time in terms of execution and resources. All data features do not support for the end results. Hence it is very important to identify the features that contribute more in identifying the diseases. Those with less contribution can be eliminated. The need of feature selection arises when we need to reduce the massive medical data to reduced number of features. The objective of this paper is to design an effective algorithm that can remove irrelevant dimensions from large data and to predict more accurately the presence of disease. Artificial Bee Colony based feature selection is incorporated and a wrapper classifier is used for classification. A Binary Artificial Bee Colony (BABC) algorithm is used to find the best features in the disease identification. The fitness of BABC is evaluated using Naive Bayesian method. Results are validated using Cleveland Heart disease dataset taken from the UCI machine learning repository. The results indicate that, BABC–Naive Bayesian outperform the other methods.