From patterns to prognosis: machine learning–derived clusters in advanced heart failure
Machine learning-based clustering revealed two distinct phenotypes in advanced HF with differing clinical features and prognoses. This approach may enhance risk stratification and inform individualized therapeutic strategies in this high-risk population.
Authors
- Kaan Kırali (ORCID: https://orcid.org/0000-0003-0044-4691)
- Barkın Kültürsay (ORCID: https://orcid.org/0000-0002-1424-2209)
- Seda Tanyeri (ORCID: https://orcid.org/0000-0002-0933-9233)
- Cem Doğan (ORCID: https://orcid.org/0000-0002-2004-142X)
- Rezzan Deniz Acar (ORCID: https://orcid.org/0000-0003-1870-4527)
- Deniz Mutlu (ORCID: https://orcid.org/0000-0003-4432-4595)
- Azmican Kaya (ORCID: https://orcid.org/0009-0005-8935-3308)
- Özgür Yaşar Akbal (ORCID: https://orcid.org/0000-0002-3882-0288)
- Süleyman Çağan Efe (ORCID: https://orcid.org/0000-0002-6067-6841)
- Murat Karaçam (ORCID: https://orcid.org/0000-0001-7323-8843)
- Gülümser Sevgin Halil (ORCID: https://orcid.org/0000-0003-0412-5292)
Institutions
- State Hospital (GB)
- Bitlis Eren University (TR)
- Minneapolis Heart Institute Foundation (US)
- Kartal Koşuyolu High Specialization Training and Research Hospital (TR)
- Munzur University (TR)
Publication Details
- Journal
- Frontiers in Cardiovascular Medicine
- Published
- 2025-10-23
- DOI
- https://doi.org/10.3389/fcvm.2025.1669538
- Citations
- 1
- Primary Topic
- Heart Failure Treatment and Management
- Type
- article
- Field-Weighted Citation Impact
- 1.39