DBS effectively mitigates motor symptoms but its optimization is impeded by inter-individual differences and delayed effects. Current models, both animal-based and computational, provide crucial insights into DBS mechanisms and potential new targets, yet there is a significant challenge in applying these findings to individual patient care.

This project, building on the achievements of Lead-DBS, proposes the development of ReTuneTools. It is designed to refine DBS strategies across species, incorporating advanced multi-modal and outcome-focused deep learning models for DBS fine-tuning. It includes a robust, data-driven pipeline for mapping symptom networks between species, thereby establishing an essential feedback loop between human and animal studies, and strengthening project connections.