Heart failure & cardiomyopathies
Machine Learning Approach to Stratify Complex Heterogeneity of Chronic Heart Failure: A Report from the CHART-2 Study
Authors' conclusion
These results suggest the potential applicability of the machine leaning approach, providing useful clinical prognostic information to stratify complex heterogeneity in patients with HF.
Study context
- Population
- Chronic heart failure (HF) patients with a broad spectrum of left ventricular ejection fraction (LVEF) in the CHART-2 registry
- Participants
- 4,649 patients
- Exposure
- Cluster 1 vs Cluster 10
- Outcome
- CV death, non-CV death, all-cause death and freedom from HF hospitalization by cluster
- Follow-up
- 5 years
Methodological detailsCHART-2 study, random forest clustering, latent class analysis, 56 clinical parameters
- CHART-2 study
- Random forest clustering
- Latent class analysis
- 56 clinical parameters
Main finding
As reported in the abstract
5-year survival rate by cluster
CV death
Non-CV death
All-cause death
Free from HF hospitalization
- All 11 significant clinical parameters and two aetiologies (ischaemic and valvular heart disease) differed significantly among the 10 clusters
- P < 0.01
Observational data: associations, not effects.
Original publication
Machine Learning Approach to Stratify Complex Heterogeneity of Chronic Heart Failure: A Report from the CHART-2 Study. ESC Heart Fail. Published 14 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →