maternal health risk prediction model
Summary
Maternal mortality remains a major public health challenge, especially in low-resource communities where pregnant women often lack early access to quality healthcare. Many complications such as hypertension, anemia, gestational diabetes, and high-risk pregnancies are detected too late, leading to preventable maternal and infant deaths. To address this challenge, I developed a Maternal Health Risk Prediction Model using machine learning techniques to identify pregnant women who are at low, medium, or high risk during pregnancy based on key health indicators such as age, blood pressure, blood sugar, body temperature, and heart rate. This project can support organizations like World Health Organization and UNICEF by: Enabling early detection of high-risk pregnancies Supporting data-driven maternal healthcare interventions Assisting healthcare workers in rural and underserved communities Improving maternal and child health outcomes Reducing preventable maternal mortality through predictive analytics The model demonstrates how artificial intelligence and data science can strengthen healthcare systems, improve decision-making, and contribute to achieving global maternal health and Sustainable Development Goals (SDGs). Technologies used include Python, Pandas, Scikit-learn, data visualization, and machine learning classification algorithms.