Classification And Prediction Of Chronic Kidney Disease Using Novel Decision Tree Algorithm By Comparing Random Forest For Obtaining Better Accuracy

Abstract

Aim: Chronic Kidney Disease (CKD), also referred to as long-term nephrotic syndrome, has risen exponentially in importance. A person may only remain missing their kidneys for an estimate of 18 days, which creates a huge need for hemodialysis and kidney replacements. The main objective of this study aims to find the best-suited algorithm that will give us the most ideal prediction. We will be comparing Novel Decision Tree with Random forest to find out which of these can give us the best accuracy. Material and Methods: The study used 143 samples with Novel Decision Tree and Random Forest is executed with varying training and testing splits for predicting the accuracy for kidney disease prediction with the G-power value of 80% and the kidney datasets were gathered from different websites, together with data from more recent studies, a criterion of 0.05%, a reliability range of 95%, a means, and a confidence interval. The performance of the classifiers are evaluated based on their accuracy rate using the chronic kidney disease dataset. Results: The accuracy of predicting kidney disease in Novel Decision Tree (96.66%) and Random Forest (62.25%) is obtained. By using independent samples t-tests, it can be shown that there is a statistically 2-tailed notable change in efficiency seen between two algorithms of 0.000 (p<0.05). Conclusion: The report’s findings suggest that the Innovative can be used to predict kidney illness Decision Tree (DT) algorithm appears to be significantly better than the Random Forest (RF) with improved accuracy.