The contributions of brain structural and functional variance in predicting age, sex and treatment

Abstract

Structural and functional neuroimaging have been widely used to track and predict demographic and clinical variables, including treatment outcomes. However, it is challenging to establish and compare the respective weights and contributions of brain structure and function in prediction studies. The present study aimed to directly investigate the respective roles of brain structural and functional indices, along with their contributions to the prediction of demographic variables (age/sex) and clinical changes in schizophrenia patients. The present study enrolled 492 healthy people from the Southwest University Adult Lifespan Dataset (SALD) for demographic variable analysis and 39 patients with schizophrenia from the West China Hospital for treatment analysis. We conducted a model fit test with two variables (one voxel-based structural metric and another voxel-based functional metric) and then performed variance partitioning on the voxels that could be predicted sufficiently. Permutation tests were applied to compare the difference in contribution between each pair of structural and functional measurements. We found that voxel-based structural indices had stronger predictive value for age and sex, while voxel-based functional metrics showed stronger predictive value for treatment. Therefore, through variance partitioning, we could clearly and directly explore and compare the voxel-based structural and functional indices with respect to particular variables. In sum, for the variables reflecting long-term changes (age) and constant biological features (sex), the voxel-based structural metrics would contribute more than voxel-based functional metrics, but for the variable reflecting short-term changes (schizophrenia treatment), the functional metrics could contribute more.

Keywords

• Model fit
• Variance partitioning
• Structural metrics
• Functional metrics
• Voxel-based analysis