Clustering of electronic health records in atrial fibrillation patients and impact on prognosis and patient trajectories: a UK linked-dataset study
Using unsupervised clustering we identified five distinct clinically actionable AF subphenotypes. The differences in outcomes and event rates at 5 years, suggests the possibility of specific tailored therapy and interventions requiring further investigation. Management of mental health should be part of holistic or integrated care management in this population.
Authors
- Carina Teixeira (ORCID: https://orcid.org/0000-0002-4102-9497)
- Amand F. Schmidt (ORCID: https://orcid.org/0000-0003-1327-0424)
- Gregory Y.H. Lip (ORCID: https://orcid.org/0000-0002-7566-1626)
- Dionisio Acosta (ORCID: https://orcid.org/0000-0003-2817-0178)
- Chris Finan (ORCID: https://orcid.org/0000-0002-3319-1937)
- Rui Providência (ORCID: https://orcid.org/0000-0001-9141-9883)
- Hiroyuki Yoshimura (ORCID: https://orcid.org/0009-0009-1991-5001)
- Z. Zhang
Institutions
- St Bartholomew's Hospital (GB)
- Medical University of Białystok (PL)
- University of Liverpool (GB)
- King's College - North Carolina (US)
- King's College London (GB)
- Barts Health NHS Trust (GB)
- Jefferson Davis Community College (US)
- Liverpool Heart and Chest Hospital (GB)
- University College London (GB)
- Liverpool John Moores University (GB)
- Aalborg University (DK)
Publication Details
- Journal
- European Heart Journal - Digital Health
- Published
- 2025-04-05
- DOI
- https://doi.org/10.1093/ehjdh/ztaf032
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- National Institute on Handicapped Research
- UK Research and Innovation
- National Institute for Health and Care Research
- British Heart Foundation
- HORIZON EUROPE Framework Programme