Comparative Analysis of Machine Learning Algorithms for Predicting Alzheimer's Disease

Alzheimer's disease (AD) is a progressive neurodegenerative disease marked by the loss of neurons in the brain leading to dementia. Early detection provides better patient outcomes and more time before the progression of the disease. In this study, a variety of machine learning models developed specifically- namely; a custom Random Forest model, Support Vector Machine SVM, Logistic Regression LR model, Decision Tree DT, and a custom boosting model- will be developed and compared here that can be able to predict AD using both MRI and clinical data within the OASIS database. The result shows that a custom model of Random Forest achieved an accuracy of 86.21%. It highlights the significance of the adaptation of algorithms in machine learning to individual datasets. This study exemplifies how customized machine learning methods enhance the accuracy of neurodegenerative diseases, particularly Alzheimer's disease.