An Emprical Analysis of Conventional Mechanisms for Early Detection of Alzheimer's Disorder

Alzheimer's disease (AD) is a progressive neurodegenerative condition which often presents as cognitive impairment and memory loss. Early diagnosis is necessary to get effective intervention. Therefore, this study compared the performance of various machine learning (ML) and deep learning (DL) algorithms for the early detection of AD focusing clinical data. Ensemble models such as Random Forest and Gradient Boosting gave the highest accuracies of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 6. 5 1 \%}$</tex> and 96.28 %, respectively, indicating their capacity to grapple with the complexities involved in high-dimensional data in the AD diagnosis. As for deep learning models, Deep Neural Networks (DNNs) have been able to achieve an accuracy of 87.44 % while Convolutional Neural Networks (CNNs) have achieved <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 0. 0 0 \%}$</tex>. In addition, Multi-Objective Genetic Algorithms (MOGAs) were also used for feature selection in order to further maximally improve model through selection of best performing biomarkers for AD.