Advanced Parkinson's Disease Classification Using Hybrid Model: SVM and Random Forest

Parkinson's disease (PD) is a progressive and chronic neurodegenerative condition that significantly impairs motor and cognitive functions, posing a considerable burden on global healthcare systems. Early and precise diagnosis is vital to improving patient outcomes, yet traditional diagnostic techniques often encounter limitations due to overlapping symptoms with other neurological disorders and the subtle nature of early PD indicators. This research introduces a machine learning-driven approach that employs a hybrid ensemble model integrating Support Vector Machine (SVM) and Random Forest classifiers to enhance diagnostic accuracy by analyzing vocal and acoustic features. To address dataset imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) is applied, enabling the model to identify meaningful patterns within underrepresented data. Principal Component Analysis (PCA) is utilized to reduce dimensionality, preserving critical data variance while minimizing computational complexity and mitigating overfitting. Hyper-parameter tuning further optimizes each classifier, bolstering the model's accuracy and robustness. Comparative analyses demonstrate that this hybrid ensemble model effectively distinguishes PD patients from healthy individuals, showcasing its potential as a reliable predictive tool in clinical applications. This study high-lights the promise of advanced machine learning methodologies in supporting early PD detection, offering clinicians a valuable resource for timely intervention and improved patient care.