Parkinson’s disease (PD) is a neurodegenerative disorder characterized by dyskinesia and is closely related to oxidative stress. Uric acid (UA) is a natural antioxidant found in the body. Previous studies have shown that UA has played an important role in the development and development of PD and is an important biomarker. Subthalamic nucleus deep brain stimulation (STN-DBS) is a common treatment for PD.
Based on resting state function MRI (rs-fMRI), the relationship between UA-related brain function connectivity (FC) and STN-DBS outcomes in PD patients was studied. We use UA and DC values from different brain regions to build the FC characteristics and then use the SVR model to predict the outcome of the operation.
The results show that PD patients with UA-related FCs are closely related to STN-DBS efficacy and can be used to predict prognosis. A machine learning model based on UA-related FC was successfully developed for PD patients.
The two biomarkers, UA and rs-fMRI, were combined to predict the prognosis of STN-DBS in treating PD. Neurosurgeons are provided with effective tools to screen the best candidate and predict the prognosis of the patient.