review · Life Sciences
Adverse drug reactions present a major obstacle in pharmaceutical development, driving up failure rates and overall costs. Conventional testing through laboratory assays and animal models often struggles to forecast human-specific side effects accurately due to physiological differences and capacity limits. Artificial intelligence and machine learning offer alternative methods by analysing large datasets, including chemical features, biological profiles, and electronic health records. These computational models can detect potential toxicity risks early in the development pipeline, supporting the principles of replacing, reducing, and refining animal experimentation. Ensuring the reliability of these tools requires rigorous validation against established methods and independent data. Although issues surrounding data quality, model interpretability, and regulatory acceptance remain to be fully resolved, adopting predictive computational models can speed up the discovery of safer therapies and lower the risk of expensive failures in later clinical stages.
Discovering that a medicine is toxic late in its development is costly and delays vital treatments. Using machine learning to forecast harmful side effects early makes drug development safer, faster, and less expensive. It also reduces the need for animal testing by using existing data to predict how human bodies will respond to new chemical compounds.
This work points to software applications for pharmaceutical developers and biotechnology firms seeking to screen drug candidates early. Potential users include preclinical safety teams and regulatory bodies aiming to lower attrition rates. Because this is a broad review highlighting persistent challenges in data quality, model interpretability, and regulatory acceptance, the overall field remains an evolving technology rather than a universally adopted, off-the-shelf standard.
AI-generated from the published abstract. Always read the original work before citing.
Adverse drug reactions (ADRs) are a major challenge in drug development, contributing to high attrition rates and significant financial losses. Due to species differences and limited scalability, traditional toxicity testing methods, such as in vitro assays and animal studies, often fail to predict human-specific toxicities accurately. The emergence of artificial intelligence (AI) and machine learning (ML) has introduced transformative approaches to predictive toxicology, leveraging large-scale datasets such as omics profiles, chemical properties, and electronic health records (EHRs). These AI-powered models provide early and accurate identification of toxicity risks, reducing reliance on animal testing and improving the efficiency of drug discovery. This review explores the role of AI models in predicting ADRs, emphasizing their ability to integrate diverse datasets and uncover complex toxicity mechanisms. Validation techniques, including cross-validation, external validation, and benchmarking against traditional methods, are discussed to ensure model robustness and generalizability. Furthermore, the ethical implications of AI, its alignment with the 3Rs principle (Replacement, Reduction, and Refinement), and its potential to address regulatory challenges are highlighted. By expediting the identification of safe drug candidates and minimizing late-stage failures, AI models significantly reduce costs and development timelines. However, challenges related to data quality, interpretability, and regulatory integration persist. Addressing these issues will enable AI to fully revolutionize predictive toxicology, ensuring safer and more effective drug development processes.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.lfs.2025.123821
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
