Cognitive prediction using regional connectivities and network biomarkers in Alzheimer's disease.

Achieving a deep understanding of brain mechanisms requires multi-scale perspectives to capture the architecture of complex networks. In this study, we focused on patients with cognitive impairment and constructed individual brain networks from neuroimaging data. We introduced a Significant Edges Selection (SES) method, which effectively extracts the most informative connections while suppressing noise. Using these refined features, we computed network characteristics and applied machine learning models to predict cognitive performance, achieving a prediction accuracy of correlation r = 0.683 under rigorous leave-one-out cross-validation. Importantly, we identified core brain regions and large-scale networks that drive predictive performance. Specifically, the secondary visual (VIS2), frontoparietal control (FPN), and default mode (DMN) networks emerged as the most strongly associated with cognitive decline. Our findings highlight a multi-scale framework, spanning connections, brain regions, and networks, that not only yields robust cognitive prediction but also provides novel insights into AD-related mechanisms. This work advances predictive modeling in Alzheimer's Disease (AD) and offers valuable guidance for early diagnosis and mechanistic research.