Chronic Kidney Disease (CKD) Diagnosis using Multi-Layer Perceptron Classifier

Abstract

Chronic Kidney Disease or CKD is one of the most widespread Kidney diseases that affect people on a larger scale. It gives rise to other biological problems like weak bones, anemia, nerve damage, high blood pressure and can even lead to complete kidney failure. Millions of deaths are caused each year because of CKD. The diagnosis of CKD is a problematic job as there is no major symptom that serves a classification feature in detecting this disease. This paper proposes a Multi-Layer Perceptron Classifier that uses a fully connected Deep Neural Network to predict whether a patient suffers from the problem of CKD or not. The model is trained on a dataset of around 400 patients and considers various symptoms like blood pressure, age, sugar level, red blood cell count, etc. that assist the model in performing accurate classification. Our experimental results show that the proposed model can perform classification with the testing accuracy of 92.5&, surpassing the scores achieved by SVM and Naïve Bayes Classifier.