A COMPARATIVE STUDY ON CHRONIC KIDNEY CANCER PREDICTION USING SUPERVISED MACHINE LEARNING ALGORITHMS

Abstract

Early detection and appropriate treatment can halt or postpone the progression of this chronic condition until the point at which kidney transplantation or dialysis are the only options left for saving the patient's life. Consequently, it is crucial to have reliable tools for the purpose of early chronic renal disease detection.In this paper we will be using supervised machine learning models to predict chronic kidney disease.We integrated the influencing factors of Chronic kidney cancer ,collected a sample dataset , conducted data analysis and optimized the dataset .A kidney cancer prediction model was created using five supervised machine learning algorithms: Xgboost, gradient boosting, support vector machine, logistic regression, and random forest classifier.The predictive performance of these five algorithms were compared and discussed..The models are compared using a variety of metrics, including accuracy, precision, recall, F1 score, etc. The results of the experiment demonstrate that the random forest algorithm is the most accurate method for predicting kidney cancer. Key Words: Chronic kidney disease, Classification metrics, Logistic regression, Xgboost , Random forest classifier, Support vector machine, Gradient boosting