README.md

🏥 Health Parameter Transition Dashboard

A comprehensive interactive dashboard for analyzing health parameter transitions between old and new measurements, with location-based filtering capabilities.

📊 Features

Health Parameters Analyzed

• HbA1c - Blood glucose control indicator
• LDL - Low-density lipoprotein cholesterol
• BMI - Body Mass Index
• BP - Blood Pressure
• Biometrics - Overall biometric assessment
• MHI - Mental Health Index

Dashboard Capabilities

• Transition Analysis: Compare old vs new health parameter tags (Red/Orange/Green)
• Location Filtering: Filter analysis by shared location
• Interactive Visualizations:
  • Transition heatmaps
  • Sankey flow diagrams
  • Summary bar charts
• Key Metrics:
  • Improvement rates
  • Decline rates
  • Stability rates
  • User counts per parameter
• Export Functionality: Download summary reports as CSV files

Tag Classification System

• 🟢 Green: Optimal/Good health status
• 🟡 Orange: Sub-optimal/Warning status
• 🔴 Red: Alert/Poor health status

🚀 Quick Start

Prerequisites

• Python 3.7 or higher
• pip package manager

Installation

1. Clone or download the project files

   # Ensure you have these files in your directory:
   # - health_dashboard.py
   # - run_dashboard.py
   # - requirements.txt
   # - Combines 2,3,7,9,11(Sheet1).csv
   

2. Install required packages

   pip install -r requirements.txt
   

3. Run the dashboard

   python run_dashboard.py
   

   Or directly with Streamlit:

   streamlit run health_dashboard.py
   

4. Access the dashboard

   • Open your web browser and go to: http://localhost:8501
   • The dashboard will automatically load with your data

📈 Using the Dashboard

1. Location Filter

• Use the sidebar to select a specific location or view "All Locations"
• The dashboard will update all visualizations based on your selection

2. Overall Summary

• View key metrics at the top: total users, average improvement/decline rates
• See the summary chart showing transition rates across all parameters

3. Parameter-wise Analysis

• Navigate through tabs for each health parameter
• Each tab shows:
  • Metrics: User counts and transition statistics
  • Heatmap: Visual transition matrix
  • Sankey Diagram: Flow visualization of transitions
  • Detailed Table: Raw transition data

4. Key Insights

• Automatically generated insights based on the data
• Highlights parameters with excellent improvement or concerning decline rates

5. Export Data

• Click "Generate Summary Report" to create downloadable CSV files
• Reports include all transition statistics by parameter

📊 Understanding the Visualizations

Transition Heatmap

• Rows: Old health status
• Columns: New health status
• Values: Number of users who transitioned
• Colors: Intensity indicates frequency of transitions

Sankey Diagram

• Left side: Old status distribution
• Right side: New status distribution
• Flows: Show movement between statuses
• Width: Proportional to number of users

Summary Charts

• Stacked bars: Show percentage breakdown of improvements/declines/stable
• Colors: Green (improved), Red (declined), Orange (stable)

🔍 Data Requirements

The dashboard expects a CSV file with the following columns:

• Location Shared: Location information for filtering
• Health parameter columns (old and new tags):
  • Hba1c tag old, Hba1c tag
  • LDLtag old, LDLtag
  • BMItag old, BMItag
  • Bptag old, Bptag
  • biometric tag old, biometric tag
  • MHI old, MHI NEW

🛠️ Technical Details

Dependencies

• Streamlit: Web application framework
• Pandas: Data manipulation and analysis
• Plotly: Interactive visualizations
• NumPy: Numerical computations

Performance Features

• Data caching for faster load times
• Responsive design for various screen sizes
• Efficient transition calculations

📝 Interpreting Results

Improvement Indicators

• Green → Green: Maintained optimal status
• Orange → Green: Improved from sub-optimal to optimal
• Red → Orange/Green: Improved from alert status

Decline Indicators

• Green → Orange/Red: Declined from optimal status
• Orange → Red: Declined from sub-optimal to alert

Key Metrics

• Improvement Rate: Percentage of users who moved to better health status
• Decline Rate: Percentage of users who moved to worse health status
• Stable Rate: Percentage of users who maintained the same status

🎯 Use Cases

1. Health Program Evaluation: Assess effectiveness of health interventions
2. Location-based Analysis: Compare health outcomes across different locations
3. Parameter-specific Insights: Identify which health areas need attention
4. Trend Monitoring: Track health improvements or declines over time
5. Resource Allocation: Focus resources on parameters with high decline rates

🔧 Troubleshooting

Common Issues

1. Data file not found

   • Ensure Combines 2,3,7,9,11(Sheet1).csv is in the same directory
   • Check file name spelling and extension

2. Missing packages

   • Run: pip install -r requirements.txt
   • Ensure you have Python 3.7+ installed

3. Dashboard won't load

   • Check if port 8501 is available
   • Try: streamlit run health_dashboard.py --server.port 8502

4. No data showing

   • Verify your CSV has the required columns
   • Check that location filter includes your data

📞 Support

For issues or questions:

1. Check the troubleshooting section above
2. Verify your data format matches the requirements
3. Ensure all dependencies are properly installed

📄 License

This dashboard is provided as-is for health data analysis purposes.

---

Made with ❤️ for better health outcomes