ParkiSense is an advanced AI-powered application designed to assist in the early detection of Parkinson’s disease through keystroke dynamics, voice analysis, and an AI chatbot. Built using Gradio, machine learning models, and Gemini AI, ParkiSense provides an accessible tool for Parkinson’s awareness and analysis.
✅ Keystroke-Based Detection - Analyzes typing patterns to predict Parkinson’s probability. ✅ Voice Analysis - Examines speech features to detect potential symptoms. ✅ Gemini Chatbot - AI-powered chatbot to answer Parkinson’s-related queries. ✅ User-Friendly Interface - Built with Gradio for an intuitive experience. ✅ Progressive Web App (PWA) - Can be installed on mobile/desktop for quick access.
- Python (ML & Backend)
- Gradio (UI & API)
- Pandas, NumPy, SciPy (Data Processing)
- Librosa, Parselmouth (Voice Feature Extraction)
- Pynput (Keystroke Monitoring)
- Gemini AI (Chatbot Integration)
- Flask/FastAPI (Optional API backend)
- Keystroke Analysis: Type in the provided text box, and the model detects abnormalities in typing patterns.
- Voice Analysis: Record a short voice clip, and the model extracts speech features for prediction.
- Chatbot Support: Ask questions about Parkinson’s, symptoms, and more!
git clone https://github.com/AP4549/ParkiSense.gitpython app.pyThis project is licensed under the MIT License. See LICENSE for details.
Want to improve ParkiSense? Fork the repo, make your changes, and submit a PR!
git checkout -b feature-branch
git commit -m "New Feature"
git push origin feature-branch🌟 If you find this project helpful, please give it a star ⭐ on GitHub!