A Hybrid Model for Accurate Prediction of Progression in Parkinson’s Disease

Evaluating the extent of motor impairment is an important aspect in Parkinson's disease, where the Unified Parkinson's Disease Rating Scale (UPDRS) plays a crucial role. The UPDRS assessment is traditional, time-consuming and labor intensive. This paper presents a stacked regression model using Light gradient-boosting machine (LightGBM) and CatBoost to automate and enhance UPDRS score predictions. It is an important advancement in managing Parkinson's disease that provides more efficient and individualized care for patients through ensemble learning.