AI-driven real-time surveillance for infectious disease detection and response in resource-limited settings: Lessons from Kenya

Background: Infectious disease outbreaks continue to pose significant public health challenges globally, particularly in low- and middle-income countries where surveillance systems are often constrained by limited resources, delayed reporting mechanisms, and fragmented health information systems. The increasing frequency of emerging and re-emerging infectious diseases highlights the urgent need for innovative surveillance approaches that facilitate timely detection, response, and decision-making. Advances in Artificial Intelligence (AI), digital health technologies, and health informatics offer unprecedented opportunities to strengthen disease surveillance and improve public health outcomes.

Objective: This presentation explores the potential of AI-driven real-time surveillance systems to enhance infectious disease detection, monitoring, and response in resource-limited settings, drawing lessons from public health initiatives and disease surveillance programs in Kenya.

Methods: A review of surveillance approaches implemented within Kenyan health systems was conducted, focusing on tuberculosis control programs, malaria surveillance initiatives, community-based disease monitoring, and digital health innovations. Emerging applications of machine learning, predictive analytics, Geographic Information Systems (GIS), mobile health platforms, and electronic community health information systems were examined to assess their contribution to early outbreak detection and response.

Results: Evidence indicates that AI-supported surveillance systems can significantly improve the timeliness, completeness, and accuracy of disease reporting. Integration of digital platforms with routine surveillance systems facilitates real-time case identification, automated alert generation, spatial mapping of disease hotspots, and predictive modeling of outbreak risks. Community-level reporting mechanisms combined with mobile technologies have demonstrated potential to strengthen case detection in underserved populations. Furthermore, AI-assisted analytics can support resource allocation, risk stratification, and public health decision-making during disease outbreaks.

Conclusion: AI-driven surveillance systems represent a transformative approach to strengthening public health preparedness and response in resource-constrained environments. The Kenyan experience demonstrates the potential for integrating digital health technologies, GIS, and artificial intelligence into routine surveillance systems to improve outbreak detection and control. Investments in digital infrastructure, workforce capacity building, data governance, and cross-sector collaboration will be critical to realizing the full benefits of AI-enabled public health surveillance globally.

Keywords: Artificial Intelligence, Disease Surveillance, Digital Health, Public Health Informatics Infectious Diseases, Outbreak Detection, Kenya, Health Systems Strengthening, GIS, Epidemiology.