USE OF ARTIFICIAL INTELLIGENCE IN RISK STRATIFICATION IN PATIENTS WITH HEART FAILURE PROGNOSTIC APPLICATIONS AND CHALLENGES IN CLINICAL PRACTICE

Abstract

Heart failure (HF) is one of the leading causes of hospitalization and cardiovascular mortality worldwide. Risk stratification of these patients is crucial to guide therapeutic decisions, optimize resources, and reduce adverse outcomes. In recent years, artificial intelligence (AI) has been incorporated as a clinical decision support tool, using machine learning algorithms and deep neural networks to predict outcomes such as mortality, readmission, and the need for transplantation. This article reviews the literature on the application of AI in risk stratification of HF patients, highlighting advances, limitations, and future perspectives. Evidence shows that AI-based models outperform traditional risk scores, such as the Seattle Heart Failure Model, especially when applied to large clinical datasets and cardiac imaging.