A gamified Parkinson's disease assessment platform that transforms clinical eye coordination testing into an engaging, interactive experience.
NeuroBalance leverages real-time eye-tracking technology to monitor patient reflexes and coordination through a Pong-style game, providing healthcare professionals with quantified insights into neurodegeneration progression.
WATCH VIDEO DEMO HERE: https://www.youtube.com/watch?v=ZqUpHCXDKHU
Parkinson's disease causes inevitable loss of eye coordination due to impaired cerebrospinal fluid (CSF) circulation and neurodegeneration. Traditional assessment methods are often:
- Clinical and non-engaging for patients
- Difficult to track progression over time
- Lacking in quantifiable, real-time metrics
NeuroBalance transforms this assessment into an interactive balance training game that both evaluates and helps improve motor control.
- 👁️ Real-Time Eye Tracking: WebGazer library integration for precise gaze detection
- 🎮 Interactive Gameplay: Classic Pong game controlled entirely by eye movements
- 📊 Clinical Severity Scoring: Automated assessment based on three key metrics:
- Latency: Response time between eye movement and paddle movement
- Drift: Stability of gaze fixation
- Accuracy: Precision of eye-controlled paddle movements
- 🚦 Three-Tier Assessment System:
- 🟢 Green: Low severity - Vision functioning normally
- 🟡 Yellow: Medium severity - Notable coordination decline
- 🔴 Red: High severity - Significant impairment detected
- 📈 Progression Tracking: Historical data for monitoring changes over time
- React - UI framework
- TypeScript - Type-safe development
- WebGazer.js - Eye-tracking library
- Flask - Python web framework
- Python - Data processing and API logic
- Node.js (v18+)
- Python (v3.9+)
- Webcam (for eye tracking)
- Clone the repository
git clone https://github.com/yourusername/neurobalance.git
cd neurobalance- Install frontend dependencies
cd frontend
npm install- Install backend dependencies
cd ../backend
pip install -r requirements.txt- Start the Flask backend
cd backend
python app.pyThe API will run on http://localhost:5000
- Start the React frontend
cd frontend
npm startThe app will open at http://localhost:3000
- Allow webcam access when prompted and follow the calibration instructions
- Calibration: Follow the on-screen prompts to calibrate eye tracking
- Play: Control the paddle using only your eye movements
- Assessment: Complete the game session (typically 2-3 minutes)
- Results: View your severity score and detailed metrics breakdown
| Metric | Description | Impact |
|---|---|---|
| Latency | Time delay between gaze shift and paddle response | Higher latency indicates slower neural processing |
| Drift | Involuntary eye movement and fixation instability | Increased drift suggests declining motor control |
| Accuracy | Precision of eye-controlled movements | Lower accuracy correlates with coordination loss |
3rd Place - HackAMind 2025
Recognized for innovative approach to neurological health assessment and patient engagement.
- Multi-patient dashboard for healthcare providers
- Historical trend analysis and visualization
- Integration with electronic health records (EHR)
- Mobile app version for at-home assessments
- Additional games for varied assessment scenarios
- Machine learning model for predictive progression analysis
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the project
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Suhaan Temkar - Lead Developer
GitHub | LinkedIn
- WebGazer.js team for the eye-tracking library
- HackAMind 2025 organizers
- Medical professionals who provided consultation on Parkinson's assessment
Made with ❤️ at HackAMind 2025