Artificial intelligence in HFpEF: Diagnosis, prognosis, and management strategies

Abstract

Heart failure with preserved ejection fraction (HFpEF) accounts for more than half of all HF cases and its incidence and prevalence continue to increase, with a substantial burden of morbidity and mortality. Despite advances in our understanding of heterogeneous pathophysiology underlying HFpEF, the diagnosis, risk assessment, and management of this disease entity remain challenging in everyday practice. Artificial intelligence (AI) algorithm can handle large amounts of complex data and machine learning (ML), a subfield of AI, allows for the identification of relevant patterns by learning from big data. Considering the vast datasets generated from patients with HFpEF over the course of their illness, the application of AI and ML algorithms in HFpEF has the potential to improve patient care through enhancing early and precise diagnosis, personalized treatment based on phenotypes, and efficient monitoring. In this review, we provide an overview of the use of AI and ML in patients with HFpEF, focusing on diagnosis, phenotyping, risk stratification and prognosis, and management. Additionally, we discuss the limitations in the clinical adaptability of AI and suggest the future research directions for developing novel and feasible AI-based HFpEF model.

Keywords: Artificial intelligence; Heart failure with preserved ejection fraction; Machine learning.