Parkinsons Disease Progression Prediction using Advanced Machine Learning Techniques

Parkinson's disease (PD) is a neurodegenerative condition that affects people over time and significantly lowers their quality of life. Patients with PD experience both motor and non-motor symptoms. Through clinical evaluation, the Unified Parkinson's Disease Rating Scale (UPDRS) is used to quantify the severity of Parkinson's disease. No definitive diagnostic tests for PD currently exist. Emerging machine learning techniques show potential to forecast future UPDRS scores for making informed medical decisions and enable better disease management. This paper studies research leveraging proteomic data to forecast PD prognosis, focusing on advanced machine learning techniques like CatBoost Regressor, ElasticNet, XGBoost Regressor, RandomForest Regressor, ExtraTrees Regressor and DecisionTree Regressor.