Parkinson Disease Detection via Handwriting Analysis

Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by motor and non-motor symptoms. 1 Early and accurate diagnosis is crucial for effective management. Traditional diagnostic methods face limitations in sensitivity, specificity, and accessibility. This study explores the potential of offline handwriting analysis using static images for PD detection. We developed a Convolutional Neural Network (CNN) model to analyze handwritten Archimedean spiral drawings from publicly available datasets (HandPD and NewHandPD). The model's performance was evaluated, demonstrating the feasibility of static image-based handwriting analysis as a tool for PD detection. The results highlight the potential of our CNN model to achieve high accuracy in classifying PD, suggesting that offline handwriting analysis can contribute effectively to PD diagnosis