Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.03643 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911191794712576 |
|---|---|
| author | Carter, Nicholas Gupta, Arkaprava Ganguli, Prateek Dietrich, Benedikt Krishna, Vibhor Chakraborty, Samarjit |
| author_facet | Carter, Nicholas Gupta, Arkaprava Ganguli, Prateek Dietrich, Benedikt Krishna, Vibhor Chakraborty, Samarjit |
| contents | Deep Brain Stimulation (DBS) is a highly effective treatment for Parkinson's Disease (PD). Recent research uses reinforcement learning (RL) for DBS, with RL agents modulating the stimulation frequency and amplitude. But, these models rely on biomarkers that are not measurable in patients and are only present in brain-on-chip (BoC) simulations. In this work, we present an RL-based DBS approach that adapts these stimulation parameters according to brain activity measurable in vivo. Using a TD3 based RL agent trained on a model of the basal ganglia region of the brain, we see a greater suppression of biomarkers correlated with PD severity compared to modern clinical DBS implementations. Our agent outperforms the standard clinical approaches in suppressing PD biomarkers while relying on information that can be measured in a real world environment, thereby opening up the possibility of training personalized RL agents specific to individual patient needs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | In-Vivo Training for Deep Brain Stimulation Carter, Nicholas Gupta, Arkaprava Ganguli, Prateek Dietrich, Benedikt Krishna, Vibhor Chakraborty, Samarjit Machine Learning Deep Brain Stimulation (DBS) is a highly effective treatment for Parkinson's Disease (PD). Recent research uses reinforcement learning (RL) for DBS, with RL agents modulating the stimulation frequency and amplitude. But, these models rely on biomarkers that are not measurable in patients and are only present in brain-on-chip (BoC) simulations. In this work, we present an RL-based DBS approach that adapts these stimulation parameters according to brain activity measurable in vivo. Using a TD3 based RL agent trained on a model of the basal ganglia region of the brain, we see a greater suppression of biomarkers correlated with PD severity compared to modern clinical DBS implementations. Our agent outperforms the standard clinical approaches in suppressing PD biomarkers while relying on information that can be measured in a real world environment, thereby opening up the possibility of training personalized RL agents specific to individual patient needs. |
| title | In-Vivo Training for Deep Brain Stimulation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.03643 |