Heart failure & cardiomyopathies
Pathophysiological insights into machine learning-based subphenotypes of acute heart failure with preserved ejection fraction
Authors' conclusion
Distinctive characteristics of biomarkers in HFpEF phenotypes would indicate differential underlying mechanisms to be elucidated. The contribution of inflammation to the pathogenesis varied considerably among different HFpEF phenotypes. Systemic inflammation substantially contributes to the pathophysiology of the classic HFpEF phenotype with cardiac hypertrophy.
Study context
- Population
- Patients with acute decompensated heart failure with preserved ejection fraction (HFpEF) (PURSUIT-HFpEF registry subcohort with multibiomarker tests)subcohort of N=1231
- Participants
- 212 patients
- Comparison
- Biomarkers across 4 machine learning-based HFpEF phenotypes
- Phenotype 1n = 69
- Phenotype 2n = 49
- Phenotype 3n = 41
- Phenotype 4n = 53
- Primary endpoint
- Biomarker characteristics in each phenotype
Methodological detailsretrospective analysis, multicentre, predefined biomarker subcohort, machine learning-based clustering
- Retrospective analysis
- Multicentre
- Predefined biomarker subcohort
- Machine learning-based clustering
Primary result
As reported in the abstract
Biomarkers (NT-proBNP, hs-CRP, TNF-α, GDF-15, troponin T, cystatin C)
- Phenotype 1: lowest N-terminal pro-brain natriuretic peptide (NT-proBNP), high-sensitive CRP, TNF-α, GDF-15, troponin T and cystatin C
- Phenotype 2: highest values of these markers
- Phenotype 3: second highest GDF-15 and cystatin C
- Phenotype 4: low NT-proBNP and relatively high GDF-15
Original publication
Pathophysiological insights into machine learning-based subphenotypes of acute heart failure with preserved ejection fraction. Heart. Published 12 October 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →