#Healthcare Pattern Analysis for SDG 3 Machine Learning Model for Healthcare Access and Cost Analysis
#Overview This project implements an unsupervised machine learning model to analyze healthcare patterns in support of UN Sustainable Development Goal 3 (Good Health and Well-being). The model uses K-means clustering to identify patient groups and healthcare access patterns.
#Features
Patient clustering based on age, medical conditions, and costs Automated optimal cluster selection using silhouette analysis Privacy-preserving data processing Interactive visualizations of healthcare patterns Policy-relevant insights generation
#Prerequisites python -v 3.8+
#Dependencies #Install required packages: pip install pandas numpy scikit-learn matplotlib seaborn
#Project Structure Machine Learning/ │ ├── unsupervised.py # Main analysis script ├── archive/ │ └── healthcare_dataset.csv # Source dataset └── README.md
#Usage Clone the repository
1.Navigate to the project directory: cd "d:\PLP Academy\Codes\python\Machine Learning"
2.Run the analysis: python unsupervised.py #Key Components #Data Preprocessing: Ethical anonymization Feature scaling Categorical encoding
#Machine Learning: K-means clustering Silhouette analysis for optimal clustering Standardized feature scaling
#Visualizations:
Healthcare cost vs. age patterns Medical condition distribution Cluster analysis
#Output The model generates: Interactive visualizations Cluster analysis reports Healthcare policy insights Patient group statistics Ethical Considerations Patient privacy protection Data anonymization Unbiased analysis Healthcare equity focus #SDG 3 Alignment This model supports SDG 3 by:
Identifying healthcare access patterns Analyzing cost barriers Supporting evidence-based policy Promoting healthcare equity
#Contributing
Fork the repository Create your feature branch Commit your changes Push to the branch Open a Pull Request
Acknowledgments UN SDG 3 Framework Healthcare Dataset Contributors Python Data Science Community
#Work Done by: Group 13
- Amahle Mathebula- +27731535916
- Geofrey Killeta- +254111600888
- Victor Muthomi- +254757148346
- Brian Sangura- +254720638389
- Achieng Verra- +254797348617