Performance of Classification Algorithms in Heart Disease Data

Abstract

The healthcare industry is one of the world largest and fastest growing industries. In healthcare industries having the large amounts of
data, it maintains general health in populations and communities through the promotion of healthy behavior and prevention of disease. In
healthcare industry the heart disease is most challenging problem. In this paper proposes the classification algorithms to evaluate the
performance of the classifiers by using heart disease prediction data. We evaluate the performance of the classifiers of Bayes (BayesNet, Naïve
Bayes, Naïve Bayes updateable), functions (Logistics, Multilayer Perception, RBF Network, SMO, simple Logistics), Lazy (IB1, IBK, Kstar,
LWL), Meta(AdaBoost, Attribute Selected Classifier, Bagging, CVParameter Selection, Classification via Regression, Decorate, Filtered
Classifier, Grading, LogitBoost, Multi BoostAB, Multiclass Classifier, Multischeme, Ordinal class classifier, Raced Incremental Logit Boost,
Random Committ, Stacking, StackingC), Misc(Hyper Pipes, VFI), Rule(conjunctive rule, Decision Table, JRip, OneR, NNge, PART, Ridor,
ZeroR), trees(Decision stump, J48, NB Tree, REP Tree, Random Forest, Random Tree).The prediction accuracy of the classifiers are evaluated
using 10 folds cross validation. The final result shows the performance of the classifiers based on the prediction Accuracy.

Keywords: Classification, Bayes, Lazy, Rule, Meta, Tree.