A Review of A Novel Decision Tree Based Classifier for Accurate Multi Disease Prediction

Many researchers have worked on the disease prediction systems using the data mining techniques. Some of the systems are for predicting a single disease and some for the predicting the multiple diseases. Still there is scope to improve the efficiency of the disease prediction. In this synopsis, we are presenting a novel classification based disease prediction system. It uses the concept of classification using the decision tree. Our proposed technique uses greedy approach to select the best attribute for construction of the decision tree. The modified information gain is used. The attribute with highest information gain is selected as the root of the tree. The experimental results have shown that the proposed algorithms classify the data sets more accurately and efficiently. In this synopsis, we have also presented an overview of existing data classification algorithms. These algorithms are described more or less on their own. Data Classification is a very popular and computationally expensive task. We have also elaborated the fundamentals of data classification. From a large number of available algorithms that have been developed we will compare the most important ones.