Early Detection of Parkinson’s Disease using Handwriting and Voice Analysis: A Machine Learning Approach

Artificial Intelligence and Machine Learning Engineering

Parkinson's disease (PD) is a neurodegenerative disorder characterized by a range of motor and non-motor symptoms, making early diagnosis challenging yet critical for effective treatment. This project presents a novel approach to PD detection, utilizing a combination of voice recordings, spiral drawings, and wave patterns to create a comprehensive dataset. By integrating advanced machine learning techniques, such as Support Vector Machines (SVM) and Random Forest, with rigorous data preprocessing, we aim to offer a reliable, non-invasive, and user-friendly diagnostic tool. Our methodology begins with data acquisition from diverse sources, followed by preprocessing steps like grayscale conversion, image resizing, and thresholding to standardize the data. Feature extraction methods, including Histogram of Oriented Gradients (HOG), extract relevant patterns from images, while key statistical features are derived from voice recordings. The resulting models, optimized with GridSearchCV, are evaluated through metrics like accuracy, F1-score, and precision to ensure robustness. Deployment in a Flask-based web application allows patients to upload their data and doctors to interpret the results, paving the way for earlier detection of PD and improved patient outcomes.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.