Scalable Modeling of Nonlinear Network Dynamics in Neurodegenerative Disease

Mechanistic models of progressive neurodegeneration offer great potential utility for clinical use and novel treatment development. Toward this end, several connectome-informed models of neuroimaging biomarkers have been proposed. However, these models typically do not scale well beyond a small number of biomarkers due to heterogeneity in individual disease trajectories and a large number of parameters. To address this, we introduce the Connectome-based Monotonic Inference of Neurodegenerative Dynamics (COMIND). The model combines concepts from diffusion and logistic models with structural brain connectivity. This guarantees monotonic disease trajectories while maintaining a limited number of parameters to improve scalability. We evaluate our model on simulated data as well as on the Parkinson's Progressive Markers Initiative (PPMI) data. Our model generalizes to anatomical imaging representations from a standard brain atlas without the need to reduce biomarker number.