Optimizing Random Forest Classifier for Detection of Alzheimer's Using OASIS

Abstract

Alzheimer's disease (AD) is a progressive brain disorder impacting behavior, memory, and cognition, with over a million cases reported annually in India. The risk significantly increases beyond age 65. Early diagnosis and treatment can result in better recovery. We propose a predictive model using the Random Forest algorithm and the OASIS dataset for early AD diagnosis, leveraging MRI data, clinical notes, genetic markers, and cognitive test results. Our model was evaluated against several others, including Decision Tree, AdaBoost, SVM, and Logistic Regression. With a 97.3% accuracy and a 2.7% error rate, our Random Forest Classifier o utperformed t he others, demonstrating superior predictive power for early AD diagnosis and potentially improving patient care.