Identifying Mitral Valve Prolapse at Risk for Arrhythmias and Fibrosis From Electrocardiograms Using Deep Learning.
Identifying Mitral Valve Prolapse at Risk for Arrhythmias and Fibrosis From Electrocardiograms Using Deep Learning.
复制标题
使用深度学习从心电图中识别二尖瓣脱垂是否有心律失常和纤维化的风险。
DOI：
10.1016/j.jacadv.2023.100446
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Delling,FrancescaN
中科院分区：
文献类型：
--
作者：
Tison,GeoffreyH;Abreau,Sean;Barrios,Joshua;Lim,LisaJ;Yang,Michelle;Crudo,Valentina;Shah,DipanJ;Nguyen,Thuy;Hu,Gene;Dixit,Shalini;Nah,Gregory;Arya,Farzin;Bibby,Dwight;Lee,Yoojin;Delling,FrancescaN
二尖瓣脱垂（mitral valve prolapse，MVP）是一种常见的瓣膜病，其亚组可发展为心源性猝死或心脏骤停。复杂心室异位（ComVE）是与心肌纤维化和MVP死亡率增加相关的心脏风险的标志物。ObjectivesThe authors试图评估基于心电图（ECG）的机器学习是否可以在心脏磁共振（CMR）成像上识别有ComVE、死亡和/或心肌纤维化风险的MVP。2012年至2020年期间，来自加利福尼亚大学旧金山分校弗朗西斯科的569名MVP患者的916例12导联ECG。一个单独的CNN被训练来检测晚期钆增强（LGE）使用1,369个ECG从87 MVP患者与对比CMR.ResultsThe ComVE的患病率为28%（160/569）。CNN检测ComVE的受试者工作特征曲线下面积（AUC）为0.80（95% CI：0.77-0.83），排除中重度二尖瓣返流[0.80（95% CI：0.77-0.83）]或双叶MVP [0.81（95% CI：0.76-0.85）]患者后仍较高。检测全因死亡率的AUC为0.82（95% CI：0.77-0.87）。与ComVE预测相关的ECG节段与心室去极化/复极化相关（早中期ST段和V1、V3和III的QRS）。LGE在乳头肌或基底下外侧壁是目前在24%的患者与可用CMR; AUC检测LGE为0.75（95%CI：0.68-0.82）conclusionsCNN分析的12导联心电图可以检测MVP的风险，室性心律失常，死亡和/或纤维化，并可以确定新的心电图相关的心脏病风险。基于ECG的CNN可以帮助选择那些需要更密切随访和/或CMR的MVP患者。
BackgroundMitral valve prolapse (MVP) is a common valvulopathy, with a subset developing sudden cardiac death or cardiac arrest. Complex ventricular ectopy (ComVE) is a marker of arrhythmic risk associated with myocardial fibrosis and increased mortality in MVP.ObjectivesThe authors sought to evaluate whether electrocardiogram (ECG)-based machine learning can identify MVP at risk for ComVE, death and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging.MethodsA deep convolutional neural network (CNN) was trained to detect ComVE using 6,916 12-lead ECGs from 569 MVP patients from the University of California-San Francisco between 2012 and 2020. A separate CNN was trained to detect late gadolinium enhancement (LGE) using 1,369 ECGs from 87 MVP patients with contrast CMR.ResultsThe prevalence of ComVE was 28% (160/569). The area under the receiver operating characteristic curve (AUC) of the CNN to detect ComVE was 0.80 (95% CI: 0.77-0.83) and remained high after excluding patients with moderate-severe mitral regurgitation [0.80 (95% CI: 0.77-0.83)] or bileaflet MVP [0.81 (95% CI: 0.76-0.85)]. AUC to detect all-cause mortality was 0.82 (95% CI: 0.77-0.87). ECG segments relevant to ComVE prediction were related to ventricular depolarization/repolarization (early-mid ST-segment and QRS from V1, V3, and III). LGE in the papillary muscles or basal inferolateral wall was present in 24% patients with available CMR; AUC for detection of LGE was 0.75 (95% CI: 0.68-0.82).ConclusionsCNN-analyzed 12-lead ECGs can detect MVP at risk for ventricular arrhythmias, death and/or fibrosis and can identify novel ECG correlates of arrhythmic risk. ECG-based CNNs may help select those MVP patients requiring closer follow-up and/or a CMR.