Improving deep brain stimulation through artificial intelligence
Deep brain stimulation (DBS) is an effective therapy for Parkinson’s disease, essential tremor, dystonia and other disorders. DBS has substantially advanced our knowledge about the electrophysiology and functional anatomy of movement disorders by facilitating invasive brain recordings in patients. Although these findings are of great interest to basic research, they hardly impact clinical practice so far. This project seeks to change this by generating clinically relevant predictions from electrophysiological and imaging data. We will record many electrophysiological and imaging predictors of DBS effects and side-effects in the same patients, integrate them into a structured database, analyze the data using scalable computational approaches for pattern recognition and derive clinically useful recommendations, e.g. on the configuration of the DBS system. In doing so, we hope to support clinical decision making while generating new insights into the relationship between electrophysiological/imaging markers and symptoms at the same time. The project is funded by the Brunhilde Moll Foundation.