Aug 15, 2025
Episode 2 of “ReTuneIn”: Modeling Deep Brain Stimulation – From Neural Networks to Digital Twins
n the second episode of the ReTune podcast “ReTuneIn”, project leaders Dr. Jil Meier and Prof. Julian Neumann explore the diverse ways in which researchers within the ReTune consortium are investigating the mechanisms and optimization of deep brain stimulation (DBS).
With backgrounds in computational neuroscience and neurophysiology, Meier and Neumann approach the topic from complementary perspectives. The episode offers insights into how real-world brain recordings, in-silico models, and machine learning techniques are being combined to better understand Parkinson’s disease and develop more precise, individualized stimulation strategies.
Dr. Jil Meier discusses her work in Project B01, which focuses on simulating brain activity using biologically informed network models. Her team uses large-scale computational simulations to predict how different DBS parameters affect whole-brain dynamics—and ultimately to support clinical programming. The long-term goal: a simulation-assisted DBS system that can suggest optimized stimulation settings tailored to the individual patient.
Prof. Julian Neumann shares progress from his experimental work on neurophysiological decoding of movement intention and the role of deep brain networks in action selection and stopping in Project B03. He also highlights efforts to integrate data from invasive recordings and behavioral paradigms using interpretable machine learning models. Together, the two researchers discuss how their approaches may converge in a shared digital twin framework.
Episode 2 provides a glimpse into ReTune’s interdisciplinary collaboration – from modeling and machine learning to neurophysiological data collection – and how these tools are being used to develop new paradigms for neuromodulation in movement disorders.
Listen to Episode 2 now:
© Picture: TRR 295 ReTune
