Machine Learning in Drug-induced Adverse Reaction Modeling: Case Studies of Drug-induced Cardiotoxicity Modeling

Le résumé fourni par la source

Drug-induced cardiotoxicity is a major safety concern across all stages of drug discovery and development. Experimental methods, including in vitro assays and animal testing, are time-consuming, expensive, and may not fully predict cardiotoxicity in humans. Machine learning and deep learning provide new alternative methods to predict drug-induced cardiotoxicity, enhancing drug discovery and development. This chapter reviews currently available machine learning and deep learning models for predicting drug-induced cardiotoxicity. These models use different algorithms and leverage various data sources, including chemical structures, pharmacological properties, clinical trial data, and post-market surveillance data, making machine learning and deep learning a crucial component in drug discovery and development. This chapter also discusses the ongoing challenges and suggests potential future directions for applying machine learning and deep learning in cardiotoxicity prediction to reduce animal testing and accelerate drug discovery and development.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.