Machine Learning Techniques for Disease Prediction
Abstract
Machine Learning techniques have turned up with variety of applications recently in support of human level Artificial Intelligence. Different models for various applications are built and trained using Machine Learning. In this paper, we have implemented some of the Machine Learning techniques for disease prediction more accurately. The Cleveland heart disease dataset and Pima-Indians-Diabetes dataset are used in our experimentation. The Machine Learning algorithms like Decision Tree, Random Forest, K-Nearest Neighbor and Naive Bayes are applied on those datasets using Jupiter notebook. Accuracy of these algorithms for both the datasets is observed with different train and test split ratio. We used Weka tool to calculate Confusion matrix for the Machine Learning techniques. We have studied applications of Machine Learning techniques to predict various diseases like heart diseases, diabetes, liver diseases, breast cancer, Parkinson’s disease, atherosclerosis diseases, thyroid disease. Our work can be further extended by comparing Machine Learning algorithms with different parameters like Precision, Recall, Sensitivity and Specificity.