BACKGROUND:
The rapid global spread of infectious diseases, fueled by international air travel, necessitates the implementation of advanced surveillance at key transit points, such as airports. In Sub-Saharan Africa (SSA), airport disease surveillance often relies on manual methods such as temperature screening, which are ineffective for detecting asymptomatic cases. Artificial Intelligence (AI) offers a transformative potential to enhance real-time detection and early warning systems.

OBJECTIVE:
To evaluate the feasibility and potential impact of implementing AI-driven disease surveillance systems at airports in SSA, and provides strategies to overcome the challenges hindering the implementation of AI-driven systems at airports in resource-limited settings

METHODS:
This narrative review involved a comprehensive literature search conducted through major academic databases, including PubMed, ScienceDirect, and Web of Science, along with key organizational websites such as the World Health Organization (WHO) and the Tanzania Ministry of Health. Data were extracted and synthesized to examine AI effectiveness, ethical concerns, and infrastructure in disease surveillance at airports.

RESULTS:
The implemention of AI-driven disease surveillance systems at international airports in Sub-Saharan Africa is feasible, with successful applications observed in countries like Senegal and Seychelles. AI systems have demonstrated improvements in outbreak prediction and response times. However, the feasibility of broader implementation is constrained by challenges such as inadequate infrastructure, data quality issues, and a lack of trained personnel. Addressing these barriers through targeted investments and capacity-building initiatives is essential for scaling AI systems across the region.

CONCLUSIONS:
While AI-based disease surveillance systems are feasible in SSA airports, their success hinges on overcoming infrastructure gaps, ethical concerns, and resource limitations. This review highlights the importance of context-specific AI models, robust regulatory frameworks, and capacity-building initiatives in facilitating the integration of AI in disease surveillance.Future studies should focus on pilot projects to evaluate AI systems addressing the specific barriers identified in this review.