Simulation-based inference on virtual brain models of disorders

• DOI: 10.1088/2632-2153/ad6230
• Publication Date: 2024-07-11T22:42:28Z
• Authors: Meysam Hashemi; Abolfazl Ziaeemehr; Marmaduke M Woodman; Jan Fousek; Spase Petkoski; Viktor K Jirsa
• Keywords: Computer engineering. Computer hardware; [SCCO.NEUR]Cognitive science/Neuroscience; virtual brain models; QA75.5-76.95; stimulation; TK7885-7895; 03 medical and health sciences; simulation-based inference; 0302 clinical medicine; virtual brain models simulation-based inference degradation structural and functional connectivity non-identifiability stimulation hierarchical structure; hierarchical structure; Electronic computers. Computer science; non-identifiability; structural and functional connectivity; degradation

Abstract Connectome-based models, also known as virtual brain models (VBMs), have been well established in network neuroscience to investigate pathophysiological causes underlying a large range of diseases. The integration an individual’s imaging data VBMs has improved patient-specific predictivity, although Bayesian estimation spatially distributed parameters remains challenging even with state-of-the-art Monte Carlo sampling. imply latent nonlinear state space driven by noise and input, necessitating advanced probabilistic machine learning techniques for widely applicable estimation. Here we present simulation-based inference on (SBI-VBMs), demonstrate that training deep neural networks both spatio-temporal functional features allows accurate generative disorders. systematic use stimulation provides effective remedy the non-identifiability issue estimating degradation limited smaller subset connections. By prioritizing model structure over data, show hierarchical SBI-VBMs renders more effective, precise biologically plausible. This approach could broadly advance precision medicine enabling fast reliable prediction