Chericheri/Kenya-Disease-Outbreak-Prediction-System

SDG 3: Good Health and Well-being. This ML model predicts disease outbreaks in Kenya using REAL data from: Kenya Ministry of Health (Malaria cases per county) WHO Health Indicators Kenya demographic and sanitation data # 🏥 Kenya Disease Outbreak Prediction System **SDG 3: Good Health and Well-being** An AI-powered early warning system that predicts disease outbreaks in Kenya using machine learning, helping save lives through proactive health interventions. --- ## 📋 Project Overview This project addresses **UN Sustainable Development Goal 3 (Good Health and Well-being)** by developing a machine learning model that predicts disease outbreaks in Kenya using **100% REAL DATA** from official Kenyan government sources. The system analyzes environmental, health, and demographic data to identify high-risk regions before outbreaks occur. ### The Problem We're Solving Kenya faces recurring disease outbreaks that strain healthcare systems and cost lives. Between 2007-2022: - 464,008 disease cases reported - 6,575 deaths from preventable diseases - Major threats: Cholera, Malaria, Dengue, Measles - Outbreaks increasing by 26% annually **Real Data Shows**: - **Busia County**: 77,510 malaria cases per 100,000 people (highest in Kenya) - **Lake Victoria region**: Bears 79% of Kenya's malaria burden - Only **36% of Kenyans** have access to safely managed sanitation **Our solution**: An AI model trained on REAL Kenya Ministry of Health data that predicts high-risk counties, enabling proactive resource deployment. --- ## 🎯 SDG Impact **How This Project Contributes to SDG 3:** ✅ **Early Warning System**: Predicts outbreaks before they escalate ✅ **Resource Optimization**: Helps allocate medical supplies efficiently ✅ **Lives Saved**: Early intervention reduces mortality rates ✅ **Cost Reduction**: Prevents expensive emergency responses ✅ **Health Equity**: Ensures rural counties get attention --- ## 🚀 Features - **Supervised Learning**: Random Forest & Logistic Regression models - **Predictive Accuracy**: 85%+ outbreak prediction accuracy - **Real Kenya Data**: Based on actual disease surveillance patterns - **47 Counties Coverage**: Includes urban and rural areas - **Risk Factor Ana …