Comparison of Novel Machine Learning Algorithms for Predicting Chronic Renal Disease

Chronic Renal Disease (CRD) is a serious sickness that affects the entire world and is the primary cause of mortality for many other illnesses. Due to the lack of visible symptoms at the beginning of CRD, people usually neglect the illness. Early CRD diagnosis enables individuals to receive prompt therapy to slow the course of their illness. Because it quickly and accurately identifies potentials, model-based machine learning can help doctors accomplish this aim. In this paper, an ML strategy for CRD forecasting. The UCI machine learning repository provided the CRD dataset, which has a high number of uncertain data values. To address unknown values or unknown data, KNN estimation was employed, which picks multiple instances that contain the most comparable measures to manage the undetermined data value for every insufficient sample. Missing data is prevalent in real therapy situations, therefore individuals may skip particular measurements for a variety of reasons. The technique is generated using five machine learning algorithms (SVM, Logistic Regression, k-nearest neighbor, Random Forest, and Neural Network). Random forest outscored the other models of machine learning regarding accuracy.