Prediction and Classification of Alzheimer’s Disease using Deep Learning

The goal of this study is to predict the different stages of Alzheimer’s using deep learning which is a cutting edge machine learning technique. Alzheimer is a neurodegenerative disease that affects many people especially elders. Hence the early detection of Alzheimer helps in controlling the disease. In the recent years, the diagnosis of Alzheimer has become one of the challenging problems in medical field. Deep learning is an efficient technique to predict it in its early stages. The MRI scan images is taken as the input dataset. The Convolutional neural network was used for preprocessing and training the given dataset. The system's main purpose is to detect Dementia in different patients based on various categories. The technique was developed using Magnetic Resonance Imaging (MRI) data from Kaggle and Open Access Series of Imaging Studies (OASIS). The OASIS dataset has a dimension of 300 rows x 15 columns of patients’ data on different stages of Alzheimer’s. Various performance criteria, such as accuracy, precision, Recall and F1 score, are evaluated for the OASIS Dataset. Different classifiers are used to discover the appropriate parameters for each model, including Logistic Regression, KNN, Decision Tree, Neural Network, Random Forests, and Gradient Boosting to predict the different stages of Alzheimer disease.