In this article, we discuss operational aspects of deep learning solutions for Alzheimer’s disease. First, we introduce clinical and neural aspects of Alzheimer’s disease. After that, we discuss traditional computer-aided diagnosis methods, such as support vector machines, random forests, and logistic regressions, which use statistical and machine learning techniques to identify and predict Alzheimer’s disease. We then describe basic operational aspects of the use of deep learning, and how they provide some benefits over traditional computer-aided diagnosis methods. Finally, we describe the advantages and limitations of using deep learning, and future directions on the applications of deep learning to Alzheimer’s disease.
Alzheimer’s Disease: Understanding Biomarkers, Big Data, and Therapy, Volume , 1 January 2021,