Valvular & structural heart disease
Machine Learning–Based Phenogrouping in Mitral Valve Prolapse (MVP) Identifies Profiles Associated With Myocardial Fibrosis and Cardiovascular Events
Authors' conclusion
Clustering enabled the identification of 4 clusters with distinct echocardiographic LV and LA remodeling profiles associated with myocardial fibrosis and clinical outcomes.
Study context
- Population
- Patients with mitral valve prolapse (age 54 ± 15 years)
- Participants
- 429 patients
- Exposure
- Echocardiographic clusters 1–4
- Outcome
- Myocardial fibrosis (CMR) and CV events by cluster
Methodological detailsbicentric, unsupervised machine learning clustering
- Bicentric
- Unsupervised machine learning clustering
Main finding
As reported in the abstract
- Clusters 3 and 4 associated with higher rates of CV events
- Cluster analysis significantly improved diagnostic accuracy over conventional analysis
- Clusters 3 and 4 vs Clusters 1 and 2: P < 0.0001
Observational data: associations, not effects.
Further findings
Severe mitral regurgitation (MR)
- Severe MR
- 195 (45%)
Decision tree: most relevant classifying variables
- Severity of MR, left ventricular (LV) systolic strain <21%, indexed left atrial (LA) volume >42 mL/m²
Original publication
Machine Learning–Based Phenogrouping in MVP Identifies Profiles Associated With Myocardial Fibrosis and Cardiovascular Events. JACC Cardiovasc Imaging. Published 17 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →