Artificial Intelligence-Powered One Health: A Predictive Framework for Managing Persistent Chemical Threats across...

The increasing burden of persistent organic pollutants, per- and polyfluoroalkyl substances, heavy metals, and emerging contaminants represents a global threat to human, animal, and ecosystem health. Current management strategies remain fragmented and reactive, limiting the effectiveness of the One Health paradigm. This review introduces an artificial intelligence (AI)-powered One Health framework designed to transition from surveillance to predictive prevention. Using a literature review across PubMed, Scopus, Google Scholar, and Web of Science (up to October 2025), recent advances in machine learning, deep learning, geospatial AI, and physics-informed models for chemical risk assessment are synthesized. The proposed framework integrates four core capabilities: (1) geospatial AI for real-time source tracking and fate modeling, (2) multispecies exposome reconstruction for unified exposure assessment, (3) predictive toxicology engines enabling cross-species risk extrapolation, and (4) AI-driven optimization of remediation and policy scenarios. Ethical and governance challenges, including algorithmic bias, transparency, and environmental justice, are critically examined. By integrating the holistic vision of One Health with the predictive capabilities of AI, this framework advances the concept of "Precision Environmental Health", supporting anticipatory governance and promoting equitable interventions at a global scale.