guest ::
| Home > Publications database > Prediction of Inter-Individual Differences from Diffusion MRI Acquisitions |
| Home > Publications database > Prediction of Inter-Individual Differences from Diffusion MRI Acquisitions |
| Dissertation / PhD Thesis | FZJ-2026-05214 |
2026
This record in other databases:
Please use a persistent id in citations: doi:10.34734/FZJ-2026-05214
Abstract: Personality neuroscience aims to discover links between personality traits and features of the brain. Previous neuroimagingstudies have investigated the connection between the brain structure, microstructural properties of brain tissue, or thefunctional connectivity (FC) and these personality traits. Analyses relating personality to diffusion- weighted MRI measureswere limited to investigating the voxel- wise or tract- wise association of microstructural properties with trait scores. Themain goal of our study was to determine whether there is an individual predictive relationship between the structural connectome(SC) and the big !ve personality traits. To that end, we expanded past work in two ways: First, by focusing onthe entire structural connectome (SC) instead of separate voxels and tracts; and second, by predicting personality traitscores instead of performing a statistical correlation analysis to assess an out- of- sample performance. Prediction of personalityfrom the SC is, however, not yet as established as prediction of behavior from the FC, and sparse studies in this!eld so far delivered rather heterogeneous results. We, therefore, further dedicated our study to investigate whether andhow different pipeline settings in"uence prediction performance. In a sample of 426 unrelated subjects with high- qualityMRI acquisitions from the Human Connectome Project, we analyzed 19 different brain parcellations, 3 SC weightings, 3groups of subjects, and 4 feature classes for the prediction of the 5 personality traits using a ridge regression. From thelarge number of evaluated pipelines, only very few lead to promising results of prediction accuracy r#>#0.2, while the vastmajority lead to a small prediction accuracy centered around zero. A markedly better prediction was observed for a cognitiontarget con!rming the chosen methods for SC calculation and prediction and indicating limitations of the personalitytrait scores and their relation to the SC. We therefore report that, for methods evaluated here, the SC cannot predict personalitytrait scores. Overall, we found that all considered pipeline conditions in"uence the predictive performance of bothcognition and personality trait scores. The strongest differences were found for the trait openness and the SC weightingby number of streamlines which outperformed the other traits and weightings, respectively. As there is a substantial variationin prediction accuracy across pipelines even for the same subjects and the same target, these !ndings highlight thecrucial importance of pipeline settings for predicting individual traits from the SC.
|
The record appears in these collections: |
PDF