Abstract
Cardiovascular diseases (CVDs) are the leading causes of morbidity and mortality worldwide. Yet, drug discovery for these conditions faces significant challenges due to the complexity and heterogeneity of their underlying pathology. Recently, artificial intelligence (AI) techniques-particularly explainable AI (XAI)-have emerged as powerful multi-omics data analyzing tools to unravel pathological mechanisms and novel therapeutic targets. However, the application of XAI in cardiovascular drug discovery remains in its infancy. This review discusses the potential for the integration of AI with multi-omics data to identify novel therapeutic targets and repurpose existing drugs for myocardial infarction (MI) and heart failure (HF). This review highlights the current gap in leveraging XAI for CVDs and discusses key challenges such as data heterogeneity, model interpretability, and translational validation. This review also describes emerging approaches, including combining AI with mechanistic models, that aim to enhance the biological relevance of AI predictions. By utilizing genomic, transcriptomic, epigenomic, proteomic, and metabolomic datasets, AI-driven methods can uncover new biomarkers and predict drug responses with greater precision. The application of AI in analyzing large-scale clinical and molecular data offers significant promise in accelerating drug discovery, refining therapeutic strategies, and improving outcomes for patients with CVDs. This review highlights recent advancements, challenges, and future directions for AI-guided drug discovery in the context of MI and HF.