Ensemble method based predictive model for analyzing disease datasets: a predictive analysis approach

Abstract

Medical datasets have attracted the research community for possible analysis and suitable prediction, which helps the human to take proper precautions in preventing future diseases. To perform related operations, data mining techniques have been widely used in developing decision support systems for disease prediction through a set of medical datasets. This work proposes a new predictive model for disease prediction using pre-processing techniques for various disease datasets. The proposed model not only analyses the datasets also improves the performance by using ensemble methods. To process the datasets, pre-processing techniques such as discretization, resampling, principal component, and decision tree have been used. To classify the datasets, classification techniques such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Tree (DT), and Random Forest (RF) have been used. The algorithms are applied with 10 fold validation technique. A predictive analysis has also been performed on various disease datasets, where every dataset results in significant improvement for various performance measures. We perform a predictive analysis on the datasets such as CKD (Chronic Kidney Disease), Cardiovascular Disease (CVD) or heart, Diabetes, Hepatitis disease, Cancer disease and ILPD (Indian Liver Patient disease). Experimental results show that the proposed predictive model outperforms in terms of better accuracy.