Alzheimer’s disease prediction using three machine learning methods

Alzheimer's disease (AD) is the most common incurable neurodegenerative illness, a term that encompasses memory loss as well other cognitive abilities. The purpose of study using precise early-stage gene expression data from blood generated clinical dataset, goal was to construct classification model might predict early stages disease. Using information gain (IG), selection characteristics chosen provide substantial for distinguishing between normal control (NC) and AD participants. divided into various sizes; three distinct machine learning (ML) algorithms were used generate models: support vector (SVM), Naïve Bayes (NB), k-nearest neighbors (K-NN). WEKA software tool variety performance measures, capacity effectively impairment status compared tested. current findings reveal an SVM-based can accurately differentiate cognitively impaired patients healthy people with 96.6% accuracy. As discovered validated pattern in distinguishes controls, demonstrating changes specific be detected far disease's core site.