The model performance (r, MSE) characterizes the strength of relationship between true and predicted labels. Condition and region weights show the predictive contribution of the two different conditions (harmful, harmless) and fear-related brain regions (parcellated according
689 to the AAL atlas, L = left, R = right) to the final decision function of each MKL model (questionnaires A-E 690 with model performance p < 0.05, FDR- and uncorrected). Brain regions (feature set): Thalamus (1), Hippocampus (2), Amygdala (3), Insula (4), mOFC: Rectus (5),
692 Frontal_Sup_Orb (6), Frontal_Med_Orb (7), lateral OFC: Frontal_Mid_Orb (8), Frontal_Inf_Orb (9), mPFC: Frontal_Sup_Medial (10), anterior cingulate cortex (Cingulum_Ant (11). indicates not visible contralateral homologue.