Tendências e perspectivas da inteligência artificial na toxicologia: uma revisão de literatura

Abstract

In recent years, Artificial Intelligence (AI) has stood out as an essential tool in drug discovery and the advancement of Pharmacology. The implementation of AI models requires caution due to potential risks, and the quality of data used is crucial to ensure the effectiveness of these models. AI-based strategies are gradually replacing traditional models in Clinical Pharmacology, especially through virtual clinical trials and decision support tools. The aim of this work is to investigate the application of AI in Toxicology, analyzing how advances in this field impact the analysis, prediction, and interpretation of toxicological data. We will explore fundamental AI concepts such as machine learning and artificial neural networks, and their use in medical sciences for diagnosis, personalized treatments, and disease prediction. To achieve this goal, we conducted a literature review in electronic databases including PubMed, SciELO, Embase, and Web of Science. The search included the following MeSH (Medical Subject Headings) terms related to AI and Toxicology “(‘Artificial Intelligence’ OR ‘Machine Learning’ OR ‘Deep Learning’) AND ‘Toxicology’ OR ‘Toxicity’ OR ‘Poisoning’ OR ‘Toxic Substances’)” from which relevant data were extracted from 14 studies published between the years 2014 and 2024. However, challenges persist in the application of AI and machine learning in Toxicology, including model interpretation and data quality.