Mapping the research landscape of artificial intelligence in heart failure: a bibliometric analysis

Heart failure (HF) is a complex syndrome with high morbidity and mortality. Despite advancements in treatment, its management remains a challenge. The objective of this study was to map the scientific landscape of artificial intelligence (AI) applications in HF management through a bibliometric analysis. Data were retrieved from the Web of Science Core Collection. Keywords related to AI and HF were used to identify relevant research articles. Various bibliometric tools, such as Biblioshiny, VOS viewer, and CiteSpace, were used for quantitative trends, collaboration networks, and thematic areas, which were assessed. A total of 1332 studies were included in the final analysis. Publication trends show a sharp increase in AI research related to HF from 2016 onward, with 317 studies published in 2025. The most frequent keywords in the field were heart failure (n = 599), machine learning (n = 516), and AI (n = 225). Other significant keywords included mortality (n = 201), diagnosis (n = 168), and risk (n = 162). Cluster analysis identified major research themes, including Cardiac & Cardiovascular Systems, Computer Science - Interdisciplinary Applications, Computer Science - Artificial Intelligence, Health Care Sciences & Services, Radiology, Nuclear Medicine & Medical Imaging, Cell Biology, Medical Informatics, Endocrinology & Metabolism, and Neurosciences. AI has rapidly become a central tool in HF management, with significant contributions from leading countries and institutions. However, further global collaboration and standardized reporting frameworks are needed to ensure the equitable translation of these technologies into clinical practice.