ABSTRACT
Machine learning techniques are increasingly embraced in neuroimaging studies of healthy and diseased human brains. They have been used successfully in predicting phenotypes, or even clinical outcomes, and in turning functional connectome metrics into phenotype biomarkers of both healthy individuals and patients. In this study, we used functional connectivity characteristics based on resting state functional magnetic resonance imaging data to accurately classify healthy elderly in terms of their phenotype status. Additionally, as the functional connections that contribute to the classification can be identified, we can draw inferences about the network that is predictive of the investigated phenotypes. Our proposed pipeline for phenotype classification can be expanded to other phenotypes (cognitive, psychological, clinical) and possibly be used to shed light on the modifiable risk and protective factors in normative and pathological brain aging.
ABSTRACT
INTRODUCTION: Past research on Alzheimer's disease (AD) has focused on biomarkers, cognition, and neuroimaging as primary predictors of its progression, albeit additional ones have recently gained attention. When turning to the prediction of the progression from one stage to another, one could benefit from the joint assessment of imaging-based biomarkers and risk/protective factors. METHODS: We included 86 studies that fulfilled our inclusion criteria. RESULTS: Our review summarizes and discusses the results of 30 years of longitudinal research on brain changes assessed with neuroimaging and the risk/protective factors and their effect on AD progression. We group results into four sections: genetic, demographic, cognitive and cardiovascular, and lifestyle factors. DISCUSSION: Given the complex nature of AD, including risk factors could prove invaluable for a better understanding of AD progression. Some of these risk factors are modifiable and could be targeted by potential future treatments.
