2026/03/31 by Siyuan Du, Siyi Li, Shuwei Bai +10 · 2 voices
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · Neuroscience · #Counterfactual thinking #Deep brain stimulation #Disease #Dropout (neural networks) #EEG and Brain-Computer Interfaces #Functional Brain Connectivity Studies #Generative grammar #Generative model #Neurological disorders and treatments #Neuromodulation #Outcome (game theory) #Overfitting #Virtual patient #cs.AI #cs.CE #cs.CV #q-bio.NC
paper · pdf · doi:10.48550/arxiv.2603.29176
openalex publication_date 2026/03/31 · arxiv published 2026/03/31 · arxiv updated 2026/03/31 · openalex created_date 2026/04/02 · openalex updated_date 2026/07/28
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.