Kidney Disease Prediction Using Machine Learning

Abstract

In present, Machine learning is one of the most used technique to predict various disease in health sector. Not only in health sector, but also in every sector, predicting something using machine learning has been a popular one. In Bangladesh, most people are unaware of Kidney related problems. When they suffer from serious kidney problems, they start to take treatment. But if they know about the features which are important to find kidney related problems, then the total number of affected people will be decreased. We have applied various feature selection method in our collected dataset to find the most suitable attributes which are responsible for various kidney disease such as: CKD (Chronic Kidney Disease), ESRD (end stage Renal Disease), UTI (Urinary Tract Infection). We have applied 11 machine learning model to predict the various kidney diseases. We have split our dataset into train dataset and test dataset to predict the kidney disease. Highest performance was achieved by Random Forest Classifier and Decision Tree Classifier. In future, we will extend our dataset to find even more better performance and we will implement it using an android application and web application.