Individual Structural Covariance Network Predicts Long-Term Motor Improvement in Parkinson's Disease with STN-DBS.

Abstract

The efficacy of long-term chronic subthalamic nucleus deep brain stimulation (STN-DBS) in treating Parkinson's Disease (PD) exhibits substantial variability among individuals. The preoperative identification of suitable DBS candidates through predictive means becomes crucial. Our study aims to investigate the predictive value of characterizing individualized structural covariance networks for long-term efficacy of DBS, offering patients a precise and cost-effective preoperative screening tool. We included 138 PD patients and 40 healthy controls. We developed individualized structural covariance networks from T1-weighted images utilizing Network Template Perturbation, and computed the networks' topological characteristics. Patients were categorized according to their long-term motor improvement following STN-DBS. Intergroup analyses were conducted on individual network edges and topological indices, alongside correlation analyses with long-term outcomes for the entire patient cohort. Finally, machine learning (ML) algorithms were employed for regression and classification to predict post-DBS motor improvement. Among the PD patients, six edges (left Middle Frontal and left Caudate Nucleus, right Olfactory and right Insula, left Superior Medial Frontal Gyrus and right Insula, right Middle Frontal and left Paracentral Lobule, right Middle Frontal and Cerebellum, left Lobule VIIb of the Cerebellum and the vermis of the Cerebellum) exhibited significant results in intergroup comparisons and correlation analyses. Increased degree centrality and local efficiency of the cerebellum, parahippocampal gyrus, and postcentral gyrus were associated with DBS improvement. A regression model constructed from these six edges revealed a significant correlation between predicted and observed changes in the unified Parkinson's disease rating scale (R=0.671, P<0.001), and receiver operating characteristic analysis demonstrated an area under the curve of 0.802, effectively distinguishing between patients with good and moderate improvement post-DBS. Our findings reveal the link between individual structural covariance network fingerprints in PD patients and long-term motor outcome following STN-DBS. Additionally, binary and continuous cerebellum-basal ganglia-frontal structural covariance network edges have emerged as potential predictive biomarkers for DBS motor outcome. subthalamic nucleus deep brain stimulation = STN-DBS; Parkinson's Disease = PD; machine learning = ML); Network Template Perturbation = NTP.