Heart failure (HF) is a condition with high prevalence and a significant impact on global health, associated with elevated rates of mortality, morbidity, and costs. It is a complex syndrome whose pathophysiology involves marked hemodynamic alterations—such as reduced cardiac output and systemic congestion—demanding increasingly precise diagnostic and therapeutic approaches (CHEUNGPASITPORN et al., 2024). In this context, artificial intelligence (AI) has emerged as a promising tool for enhancing care in patients with HF. Through techniques such as machine learning, deep learning, supervised and unsupervised algorithms, reinforcement learning, and neural networks, AI enables the processing of large volumes of clinical, laboratory, and imaging data, facilitating early disease detection, outcome prediction, and treatment personalization (CHEUNGPASITPORN et al., 2024; SINGH et al., 2025). The integration of AI with blood biomarkers has allowed for greater precision in risk stratification and therapy individualization in HF patients, contributing to more effective clinical decisions and slowing disease progression. Moreover, the concept of interoception—the body’s ability to perceive and interpret internal signals such as heart rate and respiration—has proven relevant in the cardiovascular context. Interoceptive alterations can negatively impact prognosis, and AI can assist in understanding and monitoring these physiological mechanisms (SUN et al., 2023; SINGH et al., 2025)