In the present study, a data-driven analysis of structural MRI data was conducted with pediatric epilepsy patients. We first resolve neurobiological heterogeneity based on neuroanatomical features, and then investigate the clinical relevance of using MRI data to predict seizure relapse status after treatment in each identified patient subgroup. Our study limits the influence of treatment and course of illness effects, potentially enhancing the ability to identify illness-specific biomarkers that delineate patient subgroups, and can also be used to evaluate the utility of such biomarkers in predicting illness progression and treatment response.
This abstract and the presentation materials are available to members only; a login is required.