Hypertension is a critical public health issue, especially in African countries where early detection and management are hampered by resource constraints. This study introduces a robust, machine learning-powered web platform designed for the prediction and management of hypertension risk in African populations. The system leverages a Decision Tree model, achieving a 97% accuracy rate, and is embedded in a user-friendly web interface for real-time risk assessment and patient management. The platform supports personalized dashboards, secure data handling, and seamless integration with electronic health records (EHRs). Data were gathered from outreach programs across Nigeria, encompassing key parameters such as age, sex, systolic and diastolic blood pressure, and body mass index. Comparative analysis with Logistic Regression and Support Vector Machine models highlights the superior performance and interpretability of the Decision Tree approach. The platform is engineered for scalability and adaptability to diverse healthcare environments. Future enhancements will focus on expanding the dataset, incorporating additional health indicators, and exploring advanced machine learning techniques for improved predictive power. This research demonstrates a significant step forward in digital health innovation for Africa, offering a scalable, interpretable, and practical solution for hypertension risk management.
Keywords: Africa, Electronic Health Records (EHR), Hypertension, Machine Learning, Medical Informatics
Citation: Damilare., Daramola et.al., (2025). Advancing Hypertension Risk Prediction in African Healthcare: A Machine Learning Approach with Web-Based Visualization and Interpretability. J AI & Mach Lear., 1(2):1-8.