Machine Learning in Alzheimer’s Disease: Prognostic Prediction via Neuroimaging and Numerical Data

Abstract

Alzheimer's disease (AD) is often detected too late or inaccurately in clinical practice. Therefore, improvement in the current methods of AD detection will provide opportunities for early intervention, symptomatic treatment, and, overall, better quality of patients’ and their caregivers’ lives. The paper is an in-depth study of how functional brain imaging and support vector machine (SVM) could be utilized to detect the risk for AD which works by assessing and plotting data into multi-dimensional graphs for various results. It aims to identify patients in presymptomatic stages for early treatment to delay or prevent progressive cognitive decline and disease. With knowledge of machine learning, our medical tool is a breakthrough in the methodology of AD detection. The future of our tool requires a substantive amount of brain scan data for the machine learning algorithm to produce reliable results, so further research in this field of study is crucial and strongly encouraged.