Analyzing the Progression of Alzheimer's Disease in Human Brain Networks

In this study, we present a new hybrid model that integrates the anatomical and topological characteristics of a brain network. The aim is to effectively capture the structural and/or topological alterations that take place in networks as individuals transition from a healthy control state to the stage of Alzheimer's disease. The utilisation of a brain atlas allows for the assessment of the Euclidean distance between two specific regions of interest (ROIs) inside the brain. This distance is considered a metric of anatomical distance, providing a quantitative representation of an anatomical characteristic. Conversely, the measurement of topological similarity, which assesses a characteristic of topology, is determined by calculating the cosine distance between nodes following the embedding of the whole real brain network into a vector space of dimensionality d. The empirical findings obtained using real-brain network data indicate that the hybridization approach well captures the observed topological variations during the transition from a healthy cognitive state (HC) to Alzheimer's disease (AD).