Alzheimer's Disease Prediction using Hybrid Machine Learning Techniques

Abstract

Artificial intelligence (AI) and machine learning (ML) have shown benefits in many domains during their growth, particularly considering the enormous amount of data generated recently. For quicker and more precise decision-making regarding illness projections, it might be more dependable. Models can be used to analyze and visualize diseases. The article compares several machine learning algorithms and hybrid machine learning models. A range of machine learning techniques is also available. The following techniques were tested: Random Forest, AdaBoost Classifier, Gaussian NB, Decision Tree, and Logistic Regression (LR). Following the process, the RF classifier performs better than previous algorithms with an accuracy of 92.5%. We created two sets of hybrid models: two-classifier and three-classifier combinations. The best-performing models yielded impressive results; RF and AdaBoost achieved 92.55% accuracy in the two-classifier combinations. Of the three classifier combinations, the accuracy of DT, AdaBoost, and LR was the greatest at 95.46%