Neurological disorders are increasingly understood as network-level pathologies, yet current clinical tools struggle to integrate heterogeneous sources of biological and clinical data into reliable prognostic models. This PhD project aims to develop an integrated multimodal connectomics framework combining structural and functional neuroimaging, clinical and behavioral measures, and advanced data science approaches to characterize individualized patterns of brain connectivity. Leveraging diffusion MRI tractography, functional connectivity analyses, and harmonized clinical datasets, the project will implement machine learning and artificial intelligence methods to model disease trajectories and predict functional outcomes at the patient-specific level.