Parkinsons Disease Detection Using Speech Signals with Machine Learning and Deep Learning Techniques

Parkinson’s Disease (PD) is a progressive neurological disorder that affects movement, coordination, and speech. Early detection plays a crucial role in improving patient care and treatment outcomes. This paper presents a speech-based system for detecting Parkinson’s Disease using both machine learning and deep learning approaches. The study utilizes the UCI Parkinson’s Telemonitoring dataset, which contains biomedical voice measurements from Parkinson’s patients. Important speech features such as jitter, shimmer, and harmonic components are used for analysis. Models including Support Vector Machine (SVM), XGBoost, Multilayer Perceptron (MLP), and Convolutional Neural Network (CNN) are implemented and compared. Experimental results show that the CNN model achieves the highest accuracy, outperforming traditional methods. The system also supports prediction on new speech samples, making it suitable for real-time applications. Overall, the proposed approach provides a non-invasive and efficient solution for early detection of Parkinson’s Disease.