Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI Registry.
IF 3.8
Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Ralph Kwame Akyea, Stefano Figliozzi, Pedro M Lopes, Klemens B Bauer, Sara Moura-Ferreira, Lara Tondi, Saima Mushtaq, Stefano Censi, Anna Giulia Pavon, Ilaria Bassi, Laura Galian-Gay, Arco J Teske, Federico Biondi, Domenico Filomena, Vasileios Stylianidis, Camilla Torlasco, Denisa Muraru, Pierre Monney, Giuseppina Quattrocchi, Viviana Maestrini, Luciano Agati, Lorenzo Monti, Patrizia Pedrotti, Bert Vandenberk, Angelo Squeri, Massimo Lombardi, António M Ferreira, Juerg Schwitter, Giovanni Donato Aquaro, Gianluca Pontone, Amedeo Chiribiri, José F Rodríguez Palomares, Ali Yilmaz, Daniele Andreini, Anca-Rezeda Florian, Marco Francone, Tim Leiner, João Abecasis, Luigi Paolo Badano, Jan Bogaert, Georgios Georgiopoulos, Pier-Giorgio Masci
下载PDF
{"title":"Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI Registry.","authors":"Ralph Kwame Akyea, Stefano Figliozzi, Pedro M Lopes, Klemens B Bauer, Sara Moura-Ferreira, Lara Tondi, Saima Mushtaq, Stefano Censi, Anna Giulia Pavon, Ilaria Bassi, Laura Galian-Gay, Arco J Teske, Federico Biondi, Domenico Filomena, Vasileios Stylianidis, Camilla Torlasco, Denisa Muraru, Pierre Monney, Giuseppina Quattrocchi, Viviana Maestrini, Luciano Agati, Lorenzo Monti, Patrizia Pedrotti, Bert Vandenberk, Angelo Squeri, Massimo Lombardi, António M Ferreira, Juerg Schwitter, Giovanni Donato Aquaro, Gianluca Pontone, Amedeo Chiribiri, José F Rodríguez Palomares, Ali Yilmaz, Daniele Andreini, Anca-Rezeda Florian, Marco Francone, Tim Leiner, João Abecasis, Luigi Paolo Badano, Jan Bogaert, Georgios Georgiopoulos, Pier-Giorgio Masci","doi":"10.1148/ryct.230247","DOIUrl":null,"url":null,"abstract":"<p><p>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 <i>k</i>-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], <i>P</i> = .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. <b>Keywords:</b> MR Imaging, Cardiac, Cardiac MRI, Mitral Valve Prolapse, Cluster Analysis, Ventricular Arrhythmia, Sudden Cardiac Death, Unsupervised Machine Learning <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e230247"},"PeriodicalIF":3.8000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211946/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology. Cardiothoracic imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryct.230247","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
引用
批量引用
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.
心律失常二尖瓣脱垂表型:使用多中心心脏磁共振成像注册表的无监督机器学习分析。
目的 使用无监督机器学习来识别心律失常性二尖瓣脱垂(MVP)风险增加的表型群。材料与方法 该回顾性研究纳入了 2007 年 10 月至 2020 年 6 月期间在 15 家欧洲三级中心接受晚期钆增强(LGE)心脏 MRI 检查的 MVP 患者,他们均无血流动力学意义上的二尖瓣反流或左心室(LV)功能障碍。研究终点是持续性室性心动过速、(中止的)心脏性猝死或不明原因晕厥的综合结果。采用无监督数据驱动的分层 K-均值算法来识别表型集群。通过 Cox 比例危险度模型评估集群与研究终点之间的关联。结果 共发现 474 名患者(平均年龄 47 岁 ± 16 [SD];女性 244 人,男性 230 人)有两个表型集群。与第1组患者相比,第2组患者(474人中有199人,占42%)的二尖瓣变性(即双叶MVP和瓣叶移位)、左右心腔重构和心肌纤维化(通过LGE心脏磁共振成像评估)更为严重。人口统计学和临床特征(即 Holter 监测中的症状和心律失常)对区分两个群组的作用微乎其微。与第 1 组相比,第 2 组患者在中位随访 39 个月后出现研究终点的风险明显更高(危险比:3.79 [95% CI:1.19, 12.12],P = .02)。结论 在没有明显二尖瓣反流或左心室功能障碍的 MVP 患者中,无监督机器学习主要根据心脏 MRI 特征识别出两个具有不同心律失常结局的表型群。这些结果鼓励使用基于影像学的深度表型对 MVP 进行心律失常风险预测。关键词磁共振成像,心脏,心脏磁共振成像,二尖瓣脱垂,聚类分析,室性心律失常,心脏性猝死,无监督机器学习 本文有补充材料。© RSNA, 2024.
本文章由计算机程序翻译,如有差异,请以英文原文为准。