Early Detection of Alzheimer’s Disease Using Cognitive Features A Voting-Based Ensemble Machine Learning Approach

Abstract

Early detection is key to effective care of Alzheimer's disease. Quicker treatment and better outcomes are possible with early disease detection. This work uses cognitive characteristics and ensemble machine learning to diagnose Alzheimer's. Ensembles improve forecast accuracy by combining machine learning algorithms. Cognitive tests from Alzheimer's patients and healthy controls are cleaned up into a dataset. This data underpins machine learning. Features are selected to highlight the most relevant cognitive traits for Alzheimer's disease identification. This stage helps identify the most symptomatic cognitive features of the illness. Neighborhood Component Analysis and Correlation-based Filtration are unique feature selection methods in this work. Selecting essential cognitive traits from the dataset enhances AD diagnosis. Alzheimer's disease detection is greatly improved by the proposed method. This improvement is essential for early AD detection and treatment. This study detects early Alzheimer's disease 100% of the time using CNN, CNN with Long Short-Term Memory (LSTM), and an effective Stacking Classifier.