Advancements in Cardiotoxicity Detection and Assessment through Artificial Intelligence: A Comprehensive Review
Bouatmane Ahmed, Daaif Abdelaziz, Abdelmajid Bousselham · 2024
This comprehensive review critically examines the forefront of artificial intelligence (AI) applications in cardiology, focusing on detecting and assessing cardiotoxicity and heart failure. It discusses various studies that demonstrate AI's revolutionary impact on cardiac healthcare, including deep learning for predicting pharmaceutical cardiotoxic effects, advanced AI models for identifying cardiotoxicity in stem cell-derived cardiomyocytes, and AI-enhanced imaging for monitoring cardiac complications in cancer patients. The review also explores AI systems for detecting early signs of heart failure in electrocardiograms and computational models for predicting drug interactions with hERG channels, which are vital for cardiac safety assessments. Additionally, it highlights the use of AI in preclinical research and drug safety evaluations. The reviewed studies underscore the potential of AI, especially deep learning techniques, in predicting and detecting drug-induced cardiotoxicity, offering new perspectives in assessing cardiotoxicity risks prior to drug administration and detecting early cardiac damage. However, the paper notes the necessity for further studies to validate and refine these AI models and suggests the integration of more diverse data and considerations for improved predictive performance.