A Machine Learning Framework for Alzheimer’s Disease Detection: A Random Forest Approach with OASIS Data.

Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that causes memory loss, cognitive decline, and behavioral changes, making it a major global health challenge. With over 55 million people affected worldwide, timely and accurate diagnosis is crucial to improve patient outcomes. Traditional diagnostic methods such as MRI scans and clinical evaluations, while reliable, are often costly, time-consuming, and require expert involvement. Recent advances in Artificial Intelligence (AI) and Machine Learning (ML) offer alternative approaches by detecting hidden patterns in patient data for early prediction. In this study, the OASIS Longitudinal Dataset, containing MRI, demographic, and cognitive features, was utilized to develop a predictive model for Alzheimer’s detection. A Random Forest Classifier was employed due to its robustness in handling heterogeneous data and its ability to provide feature importance insights. After preprocessing and training, the model achieved high accuracy in classifying subjects into non-demented, mildly demented, and moderately demented groups, with Clinical Dementia Rating (CDR), age, and MMSE scores identified as key predictors. The results demonstrate that Random Forest offers a reliable and interpretable solution for Alzheimer’s prediction, supporting its role as a clinical decision-support tool.