No abstract

Premature forecasting of hepatitis is extremely imperative to save an individual years and take appropriate steps to control the ailment. Decision Tree algorithms have been effectively useful in a variety of fields particularly in medicinal discipline. This manuscript investigates the premature forecasting of hepatitis by means of a variety of decision tree algorithms. In this manuscript, we build up a Hepatitis prediction model that can aid medical experts in envisaging Hepatitis condition supported on the medicinal data of patients. At the outset, we have chosen 19 imperative medicinal attributes viz., age, sex, antivirals, steroid, fatigue, anorexia, malaise, spleen palpable, etc., in addition to one target class. Secondly, we build up a prediction model using Pruned C4.5-J48 Decision Tree, Unpruned C4.5-J48, Reduced Error Pruned C4.5-J48 and Hoeffding Tree algorithms classifier for classifying Hepatitis based on these clinical attributes. Lastly, the precision of Pruned J48 decision tree approach proves to be more superior then the other approaches. Outcome acquired illustrates that Albumin and Ascites are the foremost predictive attributes which provides enhanced classification in opposition to the supplementary attributes.