Sudan Local Chapter - Analyzing Healthcare Accessibility in Sudan
Sudan faces severe healthcare accessibility challenges due to conflict, displacement, and resource constraints. Chronic diseases such as diabetes and hypertension, along with frequent outbreaks of infectious diseases like malaria, exacerbate the situation. Traditional disease surveillance methods often rely on retrospective data, limiting timely intervention. This project aims to develop a machine learning-based disease forecasting system to enhance healthcare accessibility and response efforts.
The goal is to create a robust and scalable solution for predicting disease outbreaks and improving healthcare resource allocation.
- Data Collection & Preprocessing: Gathering historical and geospatial data while ensuring data quality.
- Exploratory Data Analysis (EDA): Identifying patterns, trends, and high-risk regions. Visualization with PowerBI and Tableau.
- Supervised Learning Models: Developing predictive models to forecast disease outbreaks and determination of accessibility to healthcare facilities.
-Forecast disease outbreaks (Logistic Regression): Test Accuracy 87%, Train Accuracy 85%
-Accessibility to healthcare facilities (Logistic Regression) : Test Accuracy 98%, Train Accuracy 90% - Deployment: Creating an interactive web application for prediction of malaria and accessibility to healthcare professionals.
- Front-end & Testing: Creating an intuitive interface for predictions.