Detection of Parkinson’s Disease Using Non-invasive Biomarkers

Parkinson’s disease (PD) is the second most common neurodegenerative disorder, affecting a global population exceeding 10 million. This research focuses on early PD detection, using non-invasive biomarkers selected based on symptoms like tremors and voice analysis. These biomarkers include voice analysis, dynamic keystrokes, Inertial Measurement Unit (IMU) data, and handwritten patterns. Our study involves the development of machine learning and deep learning models for various biomarkers, to arrive at accurate disease prediction. These biomarkers offer increased diagnostic accuracy and also serve as the foundation for a cost-free self-assessment tool. This paper seeks to deliver a reliable solution with a strong focus on accessibility, offering individuals a digital platform to evaluate their Parkinson’s Disease risk independently. It offers a comprehensive evaluation that integrates multiple diagnostic techniques, rather than relying on a single feature for Parkinson’s disease detection. The platform also ensures timely medical guidance along with effective symptom monitoring, ultimately enhancing overall quality of life. The integration of innovative technologies in disease detection aligns seamlessly with the evolving healthcare landscape, that enables a more patient-centric and efficient approach to Parkinson’s disease management.