Characterization of post-traumatic stress disorder using resting-state fMRI with a multi-level parametric classification approach.

Functional neuroimaging studies have found intra-regional activity and inter-regional connectivity alterations in patients with post-traumatic stress disorder (PTSD). However, the results of these studies are based on group-level statistics and therefore it is unclear whether PTSD can be discriminated at single-subject level, for instance using the machine learning approach. Here, we proposed a novel framework to identify PTSD using multi-level measures derived from resting-state functional MRI (fMRI). Specifically, three levels of measures were extracted as classification features: (1) regional amplitude of low-frequency fluctuations (univariate feature), which represents local spontaneous synchronous neural activity; (2) temporal functional connectivity (bivariate feature), which represents the extent of similarity of local activity between two regions, and (3) spatial functional connectivity (multivariate feature), which represents the extent of similarity of temporal correlation maps between two regions. Our method was evaluated on 20 PTSD patients and 20 demographically matched healthy controls. The experimental results showed that the features of each level could successfully discriminate PTSD patients from healthy controls. Furthermore, the combination of multi-level features using multi-kernel learning can further improve the classification performance. Specifically, the classification accuracy obtained by the proposed framework was 92.5 %, which was an increase of at least 5 and 17.5 % from the two-level and single-level feature based methods, respectively. Particularly, the limbic structure and prefrontal cortex provided the most discriminant features for classification, consistent with results reported in previous studies. Together, this study demonstrated for the first time that patients with PTSD can be identified at the individual level using resting-state fMRI data. The promising classification results indicated that this method may provide a complementary approach for improving the clinical diagnosis of PTSD.