A narrative review of artificial intelligence applications in wastewater epidemiology

Abstract The rise of data-driven public health has witnessed the integration of wastewater-based epidemiology (WBE) and artificial intelligence (AI) for real-time disease detection. This convergence demonstrates the potential for predictive modelling to support population-based interventions. The COVID-19 pandemic accelerated the adoption of these technologies, highlighting the utility of WBE for early detection of community transmission. This narrative review, complemented by case examples, examines AI-driven models that support pattern recognition, predict temporal trends, and detect anomalies from wastewater data. Complemented by spatial analytics, early studies suggest that these approaches may support public health practitioners and researchers in mapping pathogen distributions, identifying potential risk hotspots, and exploring community-level transmission dynamics. However, challenges remain in data harmonization, model interpretability, infrastructure readiness, and policy integration. Addressing these methodological and ethical challenges can transform wastewater data into insights that could guide disease monitoring and response, strengthening preparedness for outbreaks and environmental health threats across public health systems.