Related Experiment Video
Updated: Jun 8, 2026
Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice
Published on: February 14, 2017
Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI
Ralph Kwame Akyea1, Stefano Figliozzi1, Pedro M Lopes1
1From the Primary Care Stratified Medicine Research Group, Centre for Academic Primary Care, Lifespan and Population Health Unit, School of Medicine, University of Nottingham, Nottingham, England (R.K.A.); IRCCS Humanitas Research Hospital, Rozzano, Italy (S.F., L.M., M.F.); School of Biomedical Engineering and Imaging Sciences-Faculty of Life Sciences and Medicine, King's College London, Westminster Bridge Rd, London SE1 7EH, England (S.F., V.S., A.C., G.G., P.G.M.); Department of Cardiology, Hospital de Santa Cruz, Centro Hospitalar de Lisboa Ocidental, Carnaxide, Lisbon, Portugal (P.M.L., A.M.F., J.A.); Department of Cardiology, University Hospital Muenster, Muenster, Germany (K.B.B., A.Y., A.R.F.); Department of Cardiology, Hartcentrum, Jessa Hospital, Hasselt, Belgium (S.M.F.); Faculty of Medicine and Life Sciences, Hasselt University, Hasselt, Belgium (S.M.F.); Multimodality Cardiac Imaging Section, IRCSS Policlinico San Donato, San Donato Milanese, Italy (L.T., M.L.); Department of Radiology, Ca' Granda Ospedale Maggiore Policlinico, University of Milan, Milan, Italy (L.T.); Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy (S.M., G.P.); GVM Care & Research, Maria Cecilia Hospital, Cotignola, Italy (S.C., A.S.); Center for Cardiac MR, Lausanne University Hospital, CHUV, Lausanne, Switzerland (A.G.P., P.M., J.S.); Cardiologia-4, Dipartimento Cardio-toraco-vascolare A. De Gasperis, ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy (I.B., G.Q., P.P.); Department of Cardiology, Hospital Universitario Vall d'Hebron, Institut de Recerca (VHIR), Universitat Autònoma de Barcelona, Barcelona, Spain (L.G.G., J.F.R.P.); Centro de Investigación Biomédica en Red, CIBERCV, Madrid, Spain (L.G.G., J.F.R.P.); Department of Cardiology, Division of Heart and Lungs, University Medical Center Utrecht, Utrecht, the Netherlands (A.J.T., T.L.); Fondazione CNR/Regione Toscana G. Monasterio, Pisa, Italy (F.B., C.D.A.); Department of Clinical, Internal, Anesthesiology and Cardiovascular Sciences, Sapienza University of Rome, Rome, Italy (D.F., V.M., L.A.); Department of Cardiology, Istituto Auxologico Italiano, IRCCS, Milan, Italy (C.T., D.M., L.P.B.); Department of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy (D.M., L.P.B.); Faculty of Biology and Medicine, University of Lausanne, Lausanne, Switzerland (P.M., J.S.); Gasthuisberg University Hospital, Leuven, Belgium (B.V., J.B.); Department of Biomedical, Surgical and Dental Sciences (G.P.) and Department of Clinical Sciences and Community Health, Cardiovascular Section (D.A.), University of Milan, Milan, Italy; and Department of Clinical Therapeutics, National and Kapodistrian University of Athens, Athens, Greece (G.G.).
Unsupervised machine learning identified two patient groups with mitral valve prolapse (MVP). One group, characterized by cardiac MRI findings, faces a significantly higher risk of dangerous arrhythmias and sudden cardiac death.
Area of Science:
- Cardiology
- Medical Imaging
- Machine Learning
Background:
- Mitral valve prolapse (MVP) can be associated with serious arrhythmic events.
- Predicting arrhythmic risk in MVP patients without significant mitral regurgitation or left ventricular dysfunction remains challenging.
Purpose of the Study:
- To apply unsupervised machine learning to identify distinct phenotypic clusters within MVP patients.
- To assess the association between these clusters and the risk of adverse arrhythmic outcomes.
Main Methods:
- Retrospective analysis of 474 patients with MVP undergoing cardiac MRI with late gadolinium enhancement (LGE).
- Utilized a hierarchical k-mean algorithm for unsupervised clustering.
- Assessed the composite endpoint of sustained ventricular tachycardia, sudden cardiac death, or syncope using Cox proportional hazards models.
Main Results:
- Two phenotypic clusters were identified. Cluster 2 (42%) exhibited more severe mitral valve degeneration, cardiac chamber remodeling, and myocardial fibrosis on LGE-cardiac MRI compared to Cluster 1.
- Demographic and clinical data had minimal impact on cluster differentiation.
- Cluster 2 patients had a 3.79-fold increased risk of the study endpoint compared to Cluster 1, adjusted for LGE extent.
Conclusions:
- Unsupervised machine learning effectively identified two phenotypic clusters in MVP patients based on cardiac MRI features.
- These clusters demonstrate significantly different risks for arrhythmic events.
- In-depth, imaging-based phenotyping using cardiac MRI is valuable for arrhythmic risk stratification in MVP.
More Related Videos
08:31A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair
Published on: October 16, 2021
08:10Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Related Concept Videos
01:27Mitral Valve Prolapse I: Introduction
01:22Mitral Valve Prolapse II: Assessment and Management
01:19Mitral Valve Prolapse III: Nursing Management
01:20Mitral Regurgitation I: Introduction
01:23Mitral Regurgitation II: Clinical Features and Diagnostic Tests
01:23Mitral Stenosis II: Clinical features and Diagnostic Tests