Artificial intelligence to support clinical practice across the inpatient heart failure care pathway: a systematic review
TL;DR
Artificial intelligence applications supporting adult patients with heart failure from admission through inpatient management to discharge were heterogeneous and supported clinical decision-making, patient identification, and medication adherence prediction, using electronic health record-derived data.
Abstract
Abstract Heart failure is a complex clinical syndrome requiring repeated reassessment, close monitoring, and timely treatment decisions throughout hospitalization. With the increasing emergence of artificial intelligence applications, there is growing interest in how artificial intelligence-based tools may support physicians along the inpatient heart failure care pathway. This systematic review assessed artificial intelligence applications supporting adult patients with heart failure from admission through inpatient management to discharge. The review followed PRISMA guidelines and was prospectively registered in PROSPERO (CRD420261336670). PubMed, Web of Science, and Embase were searched through February 2026. Eligible studies evaluated artificial intelligence-based interventions or tools relevant to inpatient heart failure care. Studies limited to intensive care, isolated imaging settings, classic telemedicine, or theoretical prediction models without demonstrated clinical use were excluded. Study selection was performed using Covidence, and methodological quality was assessed with STROBE criteria for observational studies and RoB 2 for randomized controlled trials. 19 studies were included, comprising 16 observational studies and three randomized controlled trials. Seven studies addressed admission, four inpatient management, and eight discharge-related applications. During admission, artificial intelligence mainly supported early recognition of heart failure and reduced ejection fraction, with the strongest evidence for ECG-based models. In inpatient care, applications were heterogeneous and supported clinical decision-making, patient identification, and medication adherence prediction, using electronic health record-derived data. At discharge, large language models and digital tools mainly supported patient education and self-management, although limited actionability and implementation barriers remained. Artificial intelligence may support inpatient heart failure care, but evidence of measurable clinical benefit remains limited. Trial Registration PROSPERO: CRD420261336670.