Obsessive-compulsive disorder (OCD) is a complex and severe mental illness characterized by multiple symptoms and is considered a leading cause of non-fatal health loss. However, nearly 20% of patients do not respond to standard pharmacological or psychological treatments. Currently, we lack objective brain-based biomarkers. To address this issue, we used a novel device for electrophysiology recording and applied deep brain stimulation (DBS) to 16 OCD patients. In this study, we aim to use long-term invasive neural signal collection and machine learning techniques to reveal the complex relationship between these signals and OCD symptoms. By applying advanced machine learning algorithms, our goal is to establish highly accurate prediction models to identify biomarkers associated with the occurrence and progression of OCD. The research will focus on the spatiotemporal features of neural signals and build personalized OCD decoding models based on individual differences through the integration and analysis of large-scale data. By delving into the information contained in neural signals, we hope to provide academic and practical innovations for the development of personalized treatment approaches for OCD.