Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model

TL;DR

This study introduces a generative virtual brain model to predict individual outcomes of neuromodulation therapies in Parkinson's disease using resting-state fMRI, demonstrating high accuracy and potential for clinical application.

Contribution

It develops a pretraining-finetuning framework with a large-scale generative model to accurately predict neuromodulation outcomes and generate mechanistic insights.

Findings

High fidelity individualized virtual brains with r=0.935 to empirical data

Predicted clinical responses with AUPR over 0.85 for TI and DBS

Validated predictions with external and prospective datasets

Abstract

Parkinson's disease (PD) affects over ten million people worldwide. Although temporal interference (TI) and deep brain stimulation (DBS) are promising therapies, inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost. Previous explorations either resort to limited statistical biomarkers that are insufficient to characterize variability, or employ AI-driven methods which is prone to overfitting and opacity. We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI. Critically, a generative virtual brain foundation model, pretrained on a collective dataset (2707 subjects, 5621 sessions) to capture universal disorder patterns, was finetuned on PD cohorts receiving TI (n=51) or DBS (n=55) to yield individualized virtual brains with high fidelity to empirical functional connectivity (r=0.935). By constructing counterfactual estimations between pathological and healthy neural states within these personalized models, we predicted clinical responses (TI: AUPR=0.853; DBS: AUPR=0.915), substantially outperforming baselines. External and prospective validations (n=14, n=11) highlight the feasibility of clinical translation. Moreover, our framework provides state-dependent regional patterns linked to response, offering hypothesis-generating mechanistic insights.