Performance Evaluation and Comparative Analysis of Machine Learning Techniques to Predict the Chronic Kidney Disease

Chronic kidney disease is one of the most fatal diseases affecting people worldwide. As a result, it is critical to forecast and identify this illness as early as possible, enabling medical professionals and patients to take the necessary and appropriate steps. In this paper, we propose a framework using machine learning techniques including logistic regression (LR), naive Bayes (NB), support vector machine (SVM), and decision tree (DT) for better prediction of chronic kidney disease. A publicly available dataset containing 25 parameters and 400 records of patients was employed. We conducted a thorough exploratory data analysis to improve the quality assessment of dataset. The DT method outperformed the other three algorithms by achieving the highest training and testing accuracy rate as 100% and 99.16%, respectively. To validate the model, other performance evaluation metrics were calculated. The model has provided a better predicted outcome when compared to similar research studies. Our proposed model can be used in the healthcare industry for better decision making regarding chronic kidney disease.