A Comparative Study of Data Mining Techniques for Predicting Disease Using Statlog Heart Disease Database

Data Mining (DM), frequently treated as synonymous to Knowledge Discovery in Databases (KDD) is actually a part of knowledge discovery process and is the process of extracting information including hidden patterns, trends and relationships between variables from large databases in order to make the information understandable and meaningful. The ultimate goal of data mining is prediction of unknown patterns and predictive data mining is the most common type of that which has the most direct real life applications. The process basically consists of three stages: (1) the initial data exploration, (2) model building or pattern identification with validation/verification process and (3) deployment of the data mining model. Therefore, in this research paper data mining techniques will be compared using the benchmark datasets. The different types of data classification methods and techniques are available such as Statistics, Visualization, Clustering, Decision Tree, Association Rule, Neural Networks, K-Nearest Neighbor Method and Genetic algorithms. The objective of this research paper is to do the comparative study and evaluation of decision tree, artificial neural network with the help of Statlog Heart Diseases Database collected from UCI machine learning repository. The advantages and disadvantages, of the data mining techniques depend on the capability and efficiency of the data mining techniques or algorithms to classify the large volume of database and predicting the relevant patterns for decision making process. The consequences of choosing any technique and the methods of implementation is very important factor. Data mining techniques such as Decision Tree and Artificial Neural Networks are used for the classification of Statlog heart disease datasets. These supervise machine learning algorithms are compared on the basis of classification accuracy and performance matrices.