Ensemble Classifiers for a 4-Way Classification of Alzheimer’s Disease

Abstract

Machine Learning (ML) techniques remain a massively influential tool in the Computer-Aided Diagnosis (CAD) of several health applications. Mainly due to its ability to rapid learning of end-to-end models accurately using compound data. Recent years have seen an extensive application of Deep Learning (DL) models in solving the 4-way classification of Alzheimer’s Disease (AD) and achieved good results too. However, traditional machine learning classifiers such as KNN, XGBoost, SVM, etc perform either the same or better than the DL models and usually require less data for training. This property is very useful when it comes to medical applications which is characterized by unavailability of large labelled datasets. In this paper, we demonstrate the application of state-of-the-art ML classifiers in the 4-way classification of AD using the OASIS dataset. Furthermore, an ensemble classifier model is proposed based on ML models. The proposed ensemble classifier achieved an accuracy of 94.92% which is approximately 5% accuracy increase compared to individual classifier approach. The source code used in this work are publicly available at: https://github.com/snoushath/AII2022.git