This project involved the end-to-end development and deployment of a machine learning system designed to analyze vocal patterns for early indicators of Parkinson’s disease. I engineered a robust model pipeline, training and comparing multiple algorithms like Random Forest and Gradient Boosting on a set of acoustic features, and then built an interactive Streamlit application to make the technology accessible. The entire project, from the initial code to the final deployed application, was version-controlled and shared on GitHub, culminating in a live tool that was successfully integrated into a WordPress website for public demonstration and use.
This system is designed not as a diagnostic tool but as a potential assistive technology, and its future evolution must be guided by close collaboration with healthcare professionals to ensure it meets clinical needs and integrates safely into existing workflows.
Key Tasks Completed:
Trained and optimized multiple machine learning models (Random Forest, Gradient Boosting, SVM)
Engineered comprehensive feature set from voice measurement parameters
Developed an interactive Streamlit web application for risk assessment
Deployed the live application on Streamlit Community Cloud
Uploaded and managed project code and resources on GitHub
Successfully integrated the application into a WordPress website for public access
⚠️ Attention
If you see the message “This app has gone to sleep due to inactivity”, it simply means the service we use is hosted on a free platform that automatically goes to sleep when there hasn’t been any activity.
Just click “Wake it up.”
After it loads, you will see the application shown in the image below.