Comparative Analysis of Hepatitis C Using Decision Tree Classifier and Artificial Neural Network Classifier

Abstract

Aim: The goal of this study is to compare the accuracy, sensitivity, and specificity of a Decision tree classifier and ANN classifier in detecting Innovative Hepatitis C Detection using modern methodologies. Materials and Methods: The data for this study was collected via the kaggle website. Samples were considered as (N=22) for Decision tree and (N=22) for ANN according to clinicalc.com, by keeping alpha error-threshold value 0.05, enrollment ratio as 0.1, 95% confidence interval,G power as 80%, total sample size calculated. The accuracy, sensitivity, and specificity were calculated using MATLAB and a standard data set. Results: Comparison of accuracy, sensitivity, and specificity is done by independent sample t-test SPSS software. There is a statistically insignificant difference between Decision Tree Classifier and Artificial Neural Network Classifiers. The Decision Tree with p=0.003, p<0.05-accuracy (0.41%), p=0.003, p<0.05-sensitivity (0.41%), p=0.570, p>0.05-specificity (0.42%) showed better results in comparison to ANN. Conclusion: Decision Tree showed better accuracy, sensitivity, and specificity than ANN to predict Innovative Hepatitis C Detection in a faster way.