1006 Comprehensive Clinical Scales and Machine Learning for Predicting Motor Symptom Improvement in Parkinson's Disease Patients Undergoing Deep Brain Stimulation

INTRODUCTION: Parkinson's Disease (PD) is a growing burden with varied clinical manifestations and responses to Subthalamic Nucleus Deep Brain Stimulation (STN-DBS). At present, there is no effective and simple machine learning model based on comprehensive clinical scales to predict the improvement in motor symptoms of PD treated with DBS. METHODS: A total of 647 PD patients from the First Affiliated Hospital of University of Science and Technology of China were enrolled retrospectively. Modeling with 5 kinds of machine learning algorithms (SVM, LR, RF, LigtGBM and XGBoost ), and using the Qingdao municipal hospital, 123 cases of PD patients as the external data verify the validity of the model. RESULTS: The LightGBM model outperformed others, demonstrating an internal test set AUC of 0.874 (95%CI [0.822-0.927]) and an average AUC of 0.921±0.03 during crossvalidation. The external validation yielded an AUC of 0.769 (95% CI[0.685-0.853]). Key predictive variables identified include MMSE scores, HAMA scores, years of education, medication improvement rate, and preoperative UPDRS scores. On the basis of the selected variables and the machine-learning model, we developed a web calculator for clinical use. CONCLUSIONS: The results indicate that the LightGBM model based on the top seven influencing factors is a promising tool for predicting the improvement in motor symptoms of PD after 1 year of DBS.