← Back to Portfolio
NHS A&E Wait Time Prediction System
ML & AIAI-powered Emergency Department wait time prediction using Gradient Boosting (85.67% accuracy) with interactive patient check-in dashboard.
Overview
💡 Challenge
Emergency department patients lack visibility into expected wait times, leading to anxiety and poor resource allocation decisions.
⚡ Solution
Developed a machine learning system using Gradient Boosting to predict A&E wait times based on current occupancy, arrival patterns, triage priority, and staffing levels.
🎯 Impact
Enables hospitals to provide accurate wait time estimates to patients and optimize ED resource allocation based on predicted demand.
Technical Details
🛠️ Tech Stack
PythonScikit-learnGradient BoostingStreamlitPandasMatplotlib
✨ Key Features
- ✓Gradient Boosting model with 85.67% prediction accuracy (R² score)
- ✓Real-time wait time estimation based on 13 predictive features
- ✓Interactive patient check-in simulation with digital ticket generation
- ✓Department status dashboard showing occupancy, queue position, and staffing
Key Learnings
- →Synthetic healthcare data generation must reflect realistic ED patterns
- →Feature engineering from time-based and occupancy data improved model accuracy
- →Patient-facing interfaces require clear communication of uncertainty in predictions
📊 Data Notes
This project uses synthetic/open data to demonstrate capabilities while maintaining privacy and confidentiality. All methods and approaches are applicable to real-world scenarios.