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.).
Abstract:
Purpose To use unsupervised machine learning to identify phenotypic clusters with increased risk of arrhythmic mitral valve prolapse (MVP). Materials and Methods This retrospective study included patients with MVP without hemodynamically significant mitral regurgitation or left ventricular (LV) dysfunction undergoing late gadolinium enhancement (LGE) cardiac MRI between October 2007 and June 2020 in 15 European tertiary centers. The study end point was a composite of sustained ventricular tachycardia, (aborted) sudden cardiac death, or unexplained syncope. Unsupervised data-driven hierarchical k-mean algorithm was utilized to identify phenotypic clusters. The association between clusters and the study end point was assessed by Cox proportional hazards model. Results A total of 474 patients (mean age, 47 years ± 16 [SD]; 244 female, 230 male) with two phenotypic clusters were identified. Patients in cluster 2 (199 of 474, 42%) had more severe mitral valve degeneration (ie, bileaflet MVP and leaflet displacement), left and right heart chamber remodeling, and myocardial fibrosis as assessed with LGE cardiac MRI than those in cluster 1. Demographic and clinical features (ie, symptoms, arrhythmias at Holter monitoring) had negligible contribution in differentiating the two clusters. Compared with cluster 1, the risk of developing the study end point over a median follow-up of 39 months was significantly higher in cluster 2 patients (hazard ratio: 3.79 [95% CI: 1.19, 12.12], P = .02) after adjustment for LGE extent. Conclusion Among patients with MVP without significant mitral regurgitation or LV dysfunction, unsupervised machine learning enabled the identification of two phenotypic clusters with distinct arrhythmic outcomes based primarily on cardiac MRI features. These results encourage the use of in-depth imaging-based phenotyping for implementing arrhythmic risk prediction in MVP. Keywords: MR Imaging, Cardiac, Cardiac MRI, Mitral Valve Prolapse, Cluster Analysis, Ventricular Arrhythmia, Sudden Cardiac Death, Unsupervised Machine Learning Supplemental material is available for this article. © RSNA, 2024.
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
Mitral Valve Prolapse I: Introduction
Mitral Valve Prolapse II: Assessment and Management
Mitral Valve Prolapse III: Nursing Management
Mitral Regurgitation I: Introduction
Mitral Regurgitation II: Clinical Features and Diagnostic Tests
Mitral Stenosis II: Clinical features and Diagnostic Tests