Deep brain stimulation（DBS）is a neurosurgical procedure for treating neurodegenerative diseases and neurological disorders such as Parkinson’s disease（PD）and epilepsy.The electrode placement accuracy is crucial to exploit the potential of the surgical treatment and avoid stimulation-induced side-effects.However,current surgical planning systems based on pre-operative MR and CT images of the brain cannot take into account intra-operative brainshift,resulting in suboptimal electrode placement undermining clinical outcomes.In this dissertation,a support vector regression（SVR）model was constructed based on 92 patient-specific data of PD patients,aiming to introduce a brain-shift aware pre-operative trajectory planning method to be incorporated on top of the current static pre-operative images.The model was tested on 22 unseen patients.Two target nuclei were manually delineated based on pre-operative MR and CT images.Spatial coordinates of the two nuclei were collected and compared to the post-surgical electrode position from CT images to quantify brain-shift caused displacement.Analysis of a total of 45 features showed that the pre-operative target coordinates are the parameters mainly related to the displacement of the electrode and thus driving the model prediction for both nuclei.The mean absolute error（MAE）of the prediction of the post-operative coordinates was 0.69 mm during validation and 0.76 mm on unseen data.This study demonstrates the potential of using SVR modelling to improve current DBS surgical planning procedure and pre-operative risk-assessment.