Identifying congestion phenotypes using unsupervised machine learning in acute heart failure
In worsening HF, clustering techniques identified clinical congestion profiles associated with both long-term clinical risk and differences in biomarkers, suggesting potential different underlying pathophysiologies. These clusters can be applied using the available online model to identify phenotypes as well as associated risks (https://cic-p-nancy.fr/ai-cong-hf/).
Authors
- Nicolas Girerd (ORCID: https://orcid.org/0000-0002-3278-2057)
- Tripti Rastogi (ORCID: https://orcid.org/0000-0002-9187-1762)
- Kévin Duarte (ORCID: https://orcid.org/0000-0002-0292-0498)
- Emmanuel Bresso (ORCID: https://orcid.org/0000-0002-5650-3155)
- Luca Monzo (ORCID: https://orcid.org/0000-0003-2958-943X)
- Jasper Tromp (ORCID: https://orcid.org/0000-0001-6043-0713)
- Adriaan A. Voors (ORCID: https://orcid.org/0000-0002-5417-4415)
- Jozine M. ter Maaten (ORCID: https://orcid.org/0000-0002-4910-9336)
- Guillaume Baudry (ORCID: https://orcid.org/0000-0002-9200-2729)
- Olivier Hutin
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
- Duke-NUS Medical School (SG)
- National University Health System (SG)
- French Clinical Research Infrastructure Network (FR)
- Défaillance Cardiovasculaire Aiguë et Chronique
Publication Details
- Journal
- European Heart Journal - Digital Health
- Published
- 2025-07-14
- DOI
- https://doi.org/10.1093/ehjdh/ztaf065
- Citations
- 6
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 8.33
Funders
- European Commission