AUTHOR=Hartung Thomas 

TITLE=Artificial intelligence as the new frontier in chemical risk assessment

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 6 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2023.1269932

DOI=10.3389/frai.2023.1269932

ISSN=2624-8212

ABSTRACT=The rapid progress of AI impacts various areas of life, including toxicology, and promises a major role for AI in future risk assessments. Toxicology has shiQed from a purely empirical science focused on observing chemical exposure outcomes to a data-rich field ripe for AI integra$on. AI methods are well-suited to handling and integra$ng large, diverse data volumes -a key challenge in modern toxicology. Addi$onally, AI enables Predic$ve Toxicology, as demonstrated by the automated read-across tool RASAR that achieved 87% balanced accuracy across nine OECD tests and 190,000 chemicals, outperforming animal test reproducibility. AI's ability to handle big data and provide probabilis$c outputs facilitates probabilis$c risk assessment. Rather than just replica$ng human skills at larger scales, AI should be viewed as a transforma$ve technology. Despite poten$al challenges like model black-boxing and dataset biases, explainable AI (xAI) is emerging to address these issues.