Artificial intelligence (AI) is increasingly being embedded into infectious disease surveillance systems across sub-Saharan Africa, offering opportunities to close long-standing gaps in early outbreak detection, data analytics, and resource allocation. This review synthesises emerging evidence on AI-enabled public health surveillance in Nigeria and the wider African continent, drawing on peer-reviewed literature published between 2020 and 2025. The review examines three domains of application: (i) digital surveillance and early-warning platforms such as the Surveillance Outbreak Response Management and Analysis System (SORMAS), the District Health Information Software 2 (DHIS2), and natural language processing (NLP)-based epidemic intelligence tools; (ii) machine learning-based predictive analytics for malaria, tuberculosis, cholera, monkeypox, and coronavirus disease 2019 (COVID-19); and (iii) AI-assisted case-finding and treatment-adherence monitoring. Persistent barriers to scale-up include fragmented digital infrastructure, unreliable electricity and internet connectivity, scarcity of local data-science expertise, poor data quality and interoperability, and unresolved ethical, governance, and algorithmic-bias concerns. Opportunities identified include cross-sectoral data-sharing frameworks, investment in local AI talent, context-specific model validation, and regional coordination led by the Africa Centres for Disease Control and Prevention (Africa CDC) and the Nigeria Centre for Disease Control and Prevention (NCDC). The review concludes that AI holds transformative potential for African public health surveillance, provided infrastructural, ethical, and capacity-building gaps are deliberately addressed through coordinated policy action.