Early Stage Alzheimer Disease Prediction Using Machine Learning Models

Alzheimer's disease is one of the most disabling diseases in the elderly.It affects reasoning and memory, and reduces the size of the brain overall, resulting in death.Developing more effective therapies for Alzheimer's disease depends on early detection of the condition.In this paper, authors suggest using machine learning techniques to detect early onset of Alzheimer's.They create a dataset based on the features that represent the early signs of AD.They obtain experimental results using Random Forest, Statistical Machine Learning (SVM), XGBoost, Naive Bayes, and other classifiers.They evaluate the experimental results using metrics such as Confusion Matrix, Precision and Sensitivity.On average, the XGBoost model provides 86% validation accuracy on AD test data, comparable to the established techniques in the literature.So, with the help of XGBoost Model we have built Early Onset Alzheimer prediction model using Python GUI.