Estimation of the neuromodulation parameters from the planned volume of tissue activated in deep brain stimulation

Deep brain stimulation (DBS) is a therapy with promissory results for the treatment of movement disorders. It delivers electric stimulation via an electrode to a specific target brain region. The spatial extent of neural response to this stimulation is known as volume of tissue activated (VTA). Changes in stimulation parameters that control VTA, such as amplitude, pulse width and electrode configuration can affect the effectiveness of the DBS therapy. In this study, we develop a novel methodology for estimating suitable DBS neuromodulation parameters, from planned VTA, that attempts to maximize the therapeutic effects, and to minimize the adverse effects of DBS. For estimating the continuous outputs (amplitude and pulse width), we use multi-output support vector regression, taking the geometry of the VTA as input space. For estimating the electrode polarity configuration, we perform several classification problems, also using support vector machines from the same input space. Our methodology attains promising results for both the regression setting, and for predicting electrode active contacts and their polarity. Combining biological neural modeling techniques together with machine learning, we introduce a novel area of research where parameters of neuromodulation in DBS can be tuned by manually specifying a desired geometric volume.