Artificial Intelligence in Adverse Outcome Pathways: A Review of Strategies for Automated Information Extraction, Quantitative Analysis, and Iterative Optimization

The rapid emergence of novel chemical substances escalates the occupational and environmental health risks, posing significant challenges to the traditional toxicological risk assessment framework. While adverse outcome pathways (AOPs) have become a pivotal theoretical framework for alternative toxicity testing and future risk assessments, their development and optimization remain hindered by time-consuming and labor-intensive manual processing. This narrative review systematically elucidates how artificial intelligence (AI) facilitates the development and optimization of AOPs. Specifically, AI automates the extraction of knowledge modules for AOPs via natural language processing, quantifies key relationships through integrating methods like Bayesian networks, and supports continuous AOP refinement using machine learning platforms. Together, these technologies establish a modern, data-driven, and iterative framework. Furthermore, the review discusses the current limitations in applying AI to the AOP domain alongside its substantial potential to enhance chemical risk assessment and regulatory decision-making. Ultimately, this work aims to provide new insights and methodologies for advancing AOP development, thereby strengthening the risk assessment and regulation of chemical exposures in environmental and occupational settings.