Background:Classical methods for detecting left ventricular (LV) hypertrophy (LVH) using 12-lead ECGs are insensitive. Deep learning models using ECG to infer cardiac magnetic resonance (CMR)-derived LV mass may improve LVH detection.Methods:Within 32 239 individuals of the UK Biobank prospective cohort who underwent CMR and 12-lead ECG, we trained a convolutional neural network to predict CMR-derived LV mass using 12-lead ECGs (left ventricular mass-artificial intelligence [LVM-AI]). In independent test sets (UK Biobank [n=4903] and Mass General Brigham [MGB, n=1371]), we assessed correlation between LVM-AI predicted and CMR-derived LV mass and compared LVH discrimination using LVM-AI versus traditional ECG-based rules (ie, Sokolow-Lyon, Cornell, lead aVL rule, or any ECG rule). In the UK Biobank and an ambulatory MGB cohort (MGB outcomes, n=28 612), we assessed associations between LVM-AI predicted LVH and incident cardiovascular outcomes using age- and sex-adjusted Cox regression.Results:LVM-AI predicted LV mass correlated with CMR-derived LV mass in both test sets, although correlation was greater in the UK Biobank (r=0.79) versus MGB (r=0.60, P<0.001 for both). When compared with any ECG rule, LVM-AI demonstrated similar LVH discrimination in the UK Biobank (LVM-AI c-statistic 0.653 [95% CI, 0.608 -0.698] versus any ECG rule c-statistic 0.618 [95% CI, 0.574 -0.663], P=0.11) and superior discrimination in MGB (0.621; 95% CI, 0.592 -0.649 versus 0.588; 95% CI, 0.564 -0.611, P=0.02). LVM-AI-predicted LVH was associated with incident atrial fibrillation, myocardial infarction, heart failure, and ventricular arrhythmias.Conclusions:Deep learning-inferred LV mass estimates from 12-lead ECGs correlate with CMR-derived LV mass, associate with incident cardiovascular disease, and may improve LVH discrimination compared to traditional ECG rules.

中文翻译：

---

深度学习从 12 导联心电图预测心脏磁共振衍生的左心室质量和肥大

背景：使用 12 导联心电图检测左心室 (LV) 肥大 (LVH) 的经典方法不敏感。使用 ECG 推断心脏磁共振 (CMR) 衍生的 LV 质量的深度学习模型可能会改善 LVH 检测。方法：在接受 CMR 和 12 导联 ECG 的 UK Biobank 前瞻性队列的 32 239 名个体中，我们训练了一个卷积神经网络以使用 12 导联 ECG（左心室质量-人工智能 [LVM-AI]）预测 CMR 衍生的 LV 质量。在独立测试集（英国生物银行 [n=4903] 和 Mass General Brigham [MGB，n=1371]）中，我们评估了 LVM-AI 预测和 CMR 衍生的 LV 质量之间的相关性，并比较了使用 LVM-AI 与传统 ECG 的 LVH 鉴别基于规则（即 Sokolow-Lyon、Cornell、lead aVL 规则或任何 ECG 规则）。在英国生物银行和门诊 MGB 队列中（MGB 结果，n = 28 612），我们使用年龄和性别调整的 Cox 回归评估了 LVM-AI 预测的 LVH 与事件心血管结果之间的关联。结果：在两个测试集中，LVM-AI 预测的 LV 质量与 CMR 衍生的 LV 质量相关，尽管UK Biobank (r=0.79) 与 MGB（r=0.60，两者 P<0.001）的相关性更大。与任何 ECG 规则相比，LVM-AI 在英国生物库中表现出类似的 LVH 歧视（LVM-AI c 统计量 0.653 [95% CI，0.608 -0.698] 与任何 ECG 规则 c-统计量 0.618 [95% CI，0.574 - 0.663], P=0.11) 和 MGB 中的高辨别力（0.621；95% CI，0.592 -0.649 对比 0.588；95% CI，0.564 -0.611，P=0.02）。LVM-AI 预测的 LVH 与心房颤动、心肌梗死、心力衰竭和室性心律失常有关。结论：