Artificial Intelligence Modeling for Predicting Zoonotic Disease Hotspots: A Comprehensive Review of Data-Driven Approaches within the One Health Framework

Background: Zoonotic diseases are responsible for over ۷۰% of emerging infectious diseases and represent a major threat to public health, food security, and socio-economic stability. In recent years, artificial intelligence (AI) has become a crucial tool for identifying and predicting transmission hotspots, utilizing machine learning (ML) and deep learning (DL) models, particularly in zoonotic disease spillovers from livestock to humans. Methods: This review systematically analyzes the applications of AI in modeling zoonotic risks. Algorithms such as Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and transformer-based models (e.g., BERT-infect) have shown strong predictive ability when trained on integrated multi-source datasets that combine epidemiological, environmental, climatic, genomic, socio-economic, and indigenous data, enabling the production of precise spatiotemporal risk maps. Results: Case studies from Shaanxi, China (brucellosis), the Iberian Peninsula (Crimean-Congo hemorrhagic fever), and multiple regions across Africa and Asia have validated the effectiveness of AI models in identifying zoonotic transmission hotspots and developing early warning systems. Despite these advances, key challenges persist—such as limited standardized data, geographic bias, insufficient spatiotemporal validation, and the low interpretability of complex models—which continue to hinder their practical implementation. Conclusion: The future of zoonotic hotspots modeling depends on developing hybrid frameworks that align with the One Health approach that can integrate scientific evidence with local knowledge and policy priorities. Such integrative systems can strengthen targeted surveillance, improve resource allocation, and enable proactive prevention of future zoonotic outbreaks.

کلیدواژه ها:

Artificial Intelligence ، Zoonotic Diseases ، Hotspots ، One Health