An extreme convolutional network model for brain disease prediction using smote and learning approaches

Abstract

Brain disease is considered a major cause of increased mortality worldwide. Clinical decision support system (CDSS) is utilized for predicting individuals with brain disease in its earlier state. This work proposes a novel disease prediction approach for earlier prediction by handling the dataset issues, where an improved SMOTE sampling approach is used for balancing the target data distribution. Then, Extreme Convolutional Network Model ([Formula: see text] is used for predicting the disease with better accuracy. For the validation purpose, two publicly available ADNI-1 and ADNI-2 online datasets are used for the model construction, and the outcomes are compared with other techniques like Support Vector Machine (SVM), Artificial Neural Network (ANN), Voxel-based SVM (VW-SVM), standard Convolutional Neural Network (CNN), Deep Neural Network (DNN) and Weighted-Score Multimodal DNN (WS-MTDNN). The outcomes show that the proposed [Formula: see text] model outperforms various existing approaches with 94% and 95% accuracies on the input ADNI-1 and ADNI-2 datasets. Also, the CDSS-based framework is designed to assist the doctors in critical cases and help reduce the mortality rate.