Performance Enhancement of design tree classification model using various entropies

Abstract

Decision trees are a simple and powerful form of multiple variable analyses which allows predicting, explaining, describing, or classifying an outcome. It is used for exploring large and complex bodies of data in order to discover useful patterns. The objective of this work is to improve the classification accuracy of Decision tree model. newlineAn Adverse Event is any unfavorable and unintended sign (including an abnormal laboratory finding), symptom, or disease temporally associated with the use of a medical treatment or procedure that may or may not be considered related to the medical treatment or procedure. The major identifiable risk factor for adverse event includes demographic features of patients and concurrent illnesses, hypersensitivity to related drugs, drugs currently taken etc. The outcome of the serious adverse event is classified into seven different categories by Food and Drug Administration. An important goal of the health system is to identify which factors have influenced the adverse events. Data mining methods that can transform data into meaningful knowledge to inform patient safety have proven essential for this purpose. In order to classify the Adverse event Thyroid cancer outcomes based on the risk factors, two Decision tree-based classifier models have been proposed. They are the Decision tree classifier modeled with Naïve entropy and Renyi entropy along with the Association function. newlineDecision tree-based classifier model with Naïve entropy for calculating the information gain is proposed for classifying the adverse event. Initially, the missing values are handled using mean of nearby points. Then, the Association function is used to determine the relative degree between the given attribute and class C newline