Non-communicable diseases (NCDs) are a major cause of mortality in Sub-Saharan Africa (SSA), where limited healthcare infrastructure hinders detection and effective management. This study aims to evaluates the role of Artificial Intelligence (AI) in enhancing early detection and risk prediction of NCDs in resource-constrained settings. A systematic review was conducted following PRISMA guidelines, covering 38 peer-reviewed studies published between January 2015 and April 2025. Data sources included PubMed, IEEE Xplore, Scopus, and Google Scholar. The review examined machine learning models such as logistic regression, decision trees, and deep neural networks, which showed promising predictive performance, with area under the curve (AUC) values ranging from 0.76 to 0.88 for conditions like hypertension, diabetes, and cardiovascular diseases. AI enabled mobile health platforms and wearable devices were effectively piloted in Kenya, Uganda, Rwanda, and Nigeria, supporting real-time community-based screening. However, critical barriers such as limited local datasets, reliance on externally trained models, and ethical concerns related to data privacy and bias were identified. The review underscores the need for locally adapted AI systems, stronger digital health infrastructure, and comprehensive regulatory frameworks to ensure equitable implementation. Recommendations include advancing explainable AI (XAI), foster interdisciplinary collaboration, and investing in indigenous data ecosystems. These findings provide actionable insights for policymakers and healthcare innovators aiming to integrate, ethical, scalable AI solutions into NCD prevention strategies across SSA.
View article PDF