A Voting Ensemble Approach for Hepatitis Disease Detection

Abstract

The inflammation of the liver is termed as Hepatitis. Several different types of hepatitis are from A to G. For example, Hepatitis A is caused by the hepatitis A virus. Similarly, other type of Hepatitis virus is formed by the name, say Hepatitis G. Some types of virus will not create any serious problems. Long-lasting (chronic) and cause scarring of the liver (cirrhosis), loss of liver function and in some cases, liver cancer are also caused by this disease. An automated tool is suggested in this paper that recognizes patients with hepatitis syndromes. This paper proceeds by implementing an automated tool by implementing multi-phase classification approach. During the first phase, numerous classifiers such as Support Vector Machine, Multi-layer Perceptron, naïve Bayes, k-Nearest neighbor, Decision tree are implemented. AdaBoost, Gradient Boost, and Random Forest are implemented as phase-2 classifiers. These implemented classifiers are evaluated as well as compared in terms of prediction performance. Voting ensemble based approach is proposed in this paper as final phase classification that accepts top two classifier models obtained from first and second phase classification respectively. The reason of using the proposed classifier is to enhance the prediction performance so that patients with hepatitis disease are identified correctly.