Individual prediction of trauma-focused therapy outcome in veterans with posttraumatic stress disorder using neuroimaging data

Background: Trauma-focused psychotherapy is a first-line treatment for PTSD but 30–50% of patients do not benefit sufficiently (Bradley et al., 2005). Neuroimaging has been proposed as a potential biomarker predicting treatment-response in PTSD patients (Colvonen et al., 2017; Yuan et al., 2018). Objective: We investigated whether neuroimaging data could distinguish between treatment responders and non-responders on the group and single-subject level. Method: A total of 44 male veterans with PTSD underwent baseline structural and resting-state MRI followed by trauma-focused therapy (EMDR or TFCBT). Grey-matter volumes (GMV) were extracted from the MRI data and resting-state networks (RSN) were estimated using group-ICA of data from 28 matched trauma-exposed healthy controls. GMV and RSNs were used to find differences between responders and non-responders on the group and single-subject level. Treatment response was defined as 30% decrease in total Clinician-Administered PTSD Scale for the DSM-IV (CAPS-IV) score from pre- to post-treatment assessment. Gaussian process classifiers with 10 times repeated 10-fold cross-validation were used for classification. Results: An RSN centred on the pre-SMA could distinguish between responders and non-responders on an individual level with 81.4% accuracy (p < .001), 84.5% sensitivity, 78% specificity and AUC of 0.93, while an RSN centred on the bilateral superior frontal gyrus differed between groups (pFWE < .05). No significant singlesubject classification or group differences were 54 ESTSS 2019 Rotterdam Symposium Abstract Book observed for GMV. Conclusions: Rs-fMRI is capable of providing personalized predictions of treatment response in a sample of veterans with PTSD. It therefore has the potential to be useful as a biomarker of treatment response