A DEEP LEARNING BASED METHOD FOR PARKINSON'S DISEASE DETECTION USING SVM

Parkinson’s disease (PD) is a critical neurological disorder that requires accurate and early diagnosis to improve patient quality of life. A machine learning-based prediction system was proposed, using a support vector machine (SVM) and L1-Norm feature selection for accurate target classification. The system was validated using K-fold cross-validation and metrics such as accuracy, sensitivity, specificity, precision, F1 score, and execution time. The experimental findings suggest that the proposed method can accurately predict PD and be easily integrated into healthcare for diagnosis purposes. This approach fills a gap in feature selection and classification using voice recordings data.