Editorial: Contemporary applications of machine learning and artificial intelligence for the management of heart failure

Aug 5, 2026

Upload by Sage

Editorial on contemporary machine learning and artificial intelligence strategies for heart failure management, highlighting four original studies in Frontiers in Cardiovascular Medicine. The contributions span early diagnosis with novel biomarkers, disease stratification via transcriptomics, mechanistic interpretation of apoptotic pathways, and remote predictive telemonitoring using real-time AI models. The editorial frames heart failure as a major global cardiovascular challenge and emphasizes how data-driven tools can enable personalized, proactive care while reducing decompensation risk, hospitalizations, and burdens on healthcare systems. It also addresses integration promises and practical challenges for routine clinical use.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages2

Reading Time5 min

AccessFree to download

Editorial on the Research Topic

Contemporary applications of machine learning and artificial intelligence for the management of heart failure

Machine learning and AI approaches in four featured studies

Editorial discussion: promise and challenges for routine integration

TYPE Editorial PUBLISHED 03 June 2025 DOI 10.3389/fcvm.2025.1611859 EDITED AND REVIEWED BY Kiyotake Ishikawa, Icahn School of Medicine at Mount Sinai, United States *CORRESPONDENCE Andre Rodrigues Duraes [andreduraes@gmail.com](andreduraes@gmail.com) RECEIVED 14 April 2025 ACCEPTED 26 May 2025 PUBLISHED 03 June 2025 CITATION Duraes AR, Gomes-Neto M and Bocchi EA (2025) Editorial: Contemporary applications of machine learning and artiﬁcial intelligence for the management of heart failure. Front. Cardiovasc. Med. 12:1611859 . doi: 10.3389/fcvm.2025.1611859 COPYRIGHT © 2025 Duraes, Gomes-Neto and Bocchi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Editorial: Contemporary applications of machine learning and artiﬁcial intelligence for the management of heart failure Andre Rodrigues Duraes1*, Mansueto Gomes-Neto1 and Edimar Alcides Bocchi2 1Federal University of Bahia (UFBA), Salvador, Brazil, 2Heart Institute (InCor), São Paulo, Sao Paulo, Brazil Heart failure (HF) is a complex syndrome with substantial clinical and economic impact. This editorial highlights four original articles published in Frontiers in Cardiovascular Medicine that showcase contemporary applications of machine learning and artiﬁcial intelligence (AI) in HF management. These studies address early diagnosis through novel biomarkers, disease stratiﬁcation based on transcriptomics, mechanistic insight into apoptotic pathways, and predictive telemonitoring using real-time AI models. Collectively, these contributions exemplify the transformative potential of data-driven technologies in personalizing care and preventing decompensation in HF. We discuss both the promise and challenges of integrating these tools into routine. KEYWORDS heart failure, machine learning, artiﬁcial intelligence, biomarkers, precision medicine, telemonitoring, cardiomyopathy, healthcare technology Editorial on the Research Topic Contemporary applications of machine learning and artiﬁcial intelligence for the management of heart failure Heart failure (HF) remains one of the top challenges in cardiovascular medicine worldwide. It’s associated with high morbidity, frequent hospitalizations, and a growing economic burden on healthcare systems. Recent advancements in precision medicine and artiﬁcial intelligence (AI) offer exciting new avenues for understanding, diagnosing, and managing HF—especially in early or pre-symptomatic stages. This issue of Frontiers in Cardiovascular Medicine brings together four original studies that shine light on these frontiers, from genetic biomarkers to predictive AI tools. Together, they exemplify the contemporary applications of machine learning and artiﬁcial intelligence for the management of heart failure—now emerging as key allies in advancing personalized and proactive cardiovascular care. Yu et al. used a strong bioinformatics and machine learning approach to identify four key genes—SMOC2, OGN, FCN3, and SERPINA3—that may serve as early markers for acute decompensated heart failure (ADHF) triggered by venous congestion. Often, venous congestion sets in well before symptoms are visible. These genes showed excellent diagnostic performance (AUCs > 0.9), and the study offers a well-validated diagnostic model that could help catch worsening HF earlier. In the near future, and Frontiers in Cardiovascular Medicine 01 [frontiersin.org](frontiersin.org) with the emergence of more research evaluating this complex mechanism, patients with heart failure—a condition affecting over 64 million people worldwide and as

FAQs

What four areas do the featured studies address in heart failure management?

They cover early diagnosis using novel biomarkers, transcriptomics-based disease stratification, mechanistic insight into apoptotic pathways, and predictive telemonitoring with real-time AI models.

How can AI help with earlier detection of acute decompensated heart failure?

A study uses machine learning and bioinformatics to identify specific genes as early markers and provides a diagnostic model with strong performance, supporting earlier recognition before visible symptoms.

What is the role of remote AI telemonitoring in preventing hospitalizations?

An AI model trained on TIM-HF2 trial data predicts HF-related hospitalizations within seven days and can outperform rule-based systems, enabling targeted monitoring of patients at highest predicted risk.

Aug 5, 2026

Upload by Sage