Understanding and predicting infectious disease transmission remains a central challenge in global health due to the complex interplay of pathogen evolution, host biology, environmental conditions, and human behavior. Traditional epidemiological models, while foundational, are often limited in their ability to integrate heterogeneous, high-dimensional data or capture nonlinear, cross-scale dynamics that govern real-world outbreaks. Recent advances in artificial intelligence and big data analytics are fundamentally reshaping this landscape. This review provides a comprehensive overview of recent progress in Artificial Intelligence (AI)-enabled infectious disease research, highlighting how Machine learning (ML), deep learning and network-based approaches integrate diverse data streams including epidemiological surveillance, pathogen genomics, multi-omics profiles, environmental variables, and human mobility to decode transmission dynamics across molecular, ecological, and population scales. Case studies spanning viral, vector-borne, bacterial and zoonotic pathogens illustrate how AI models enhance outbreak forecasting, identify high-risk populations, and link molecular variation with transmissibility and disease severity. Beyond predictive performance, review discuss about AI in driving a conceptual shift from parameter driven epidemiology toward mechanism-aware, multi-scale modeling of infection and spread. • AI integrates epidemiological, genomic, environmental, and mobility data to decode transmission. • Deep learning outperforms classical models in forecasting viral and vector-borne outbreaks. • Explainable AI links environmental, biological, and behavioral drivers to transmission risk. • AI-enabled models improve prediction of zoonotic spillover and persistent bacterial infections. • Integration of AI with multi-omics advances mechanism-aware, precision epidemiology.
Michael et al. (Thu,) studied this question.