Parkinson’s Detection Using Voice Features and Spiral Drawings

Abstract

Parkinson's is a dynamic neurodegenerative disease that presents multiple symptoms that advance over time. Our project proposes an innovative Parkinson's discovery machine learning model that combines both voice examination and spiral drawings assessments to capture numerous angles of the disease's symptomatology. Our approach looks for developing a comprehensive Parkinson’s detection model over different stages and symptoms of the disease. By integrating voice analysis techniques to discern subtle changes in speech patterns and spiral drawing assessments to evaluate motor function, our method aims to provide a more holistic assessment of PD symptoms. By leveraging the complementary strengths of voice analysis and spiral drawing assessments, our proposed PD detection project aims to overcome the limitations of existing approaches and provide clinicians with a more comprehensive model for early detection, diagnosis and monitoring of Parkinson's Disease. Ultimately, this initiative strives to enhance patient outcomes, improve treatment efficacy, and advance our understanding of PD progression.