发表机构
University of Trieste; Azienda Sanitaria Universitaria Giuliano Isontina; Centre of Diagnosis and Management of Cardiomyopathies（的里雅斯特大学; 的里雅斯特大学综合卫生机构; 心肌病诊断与管理中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究评估β-VAE衍生的ECG特征及DTW重建误差对心肌瘢痕的鉴别能力，在300例患者队列中验证了相关特征的分类潜力，为基于ECG的心肌瘢痕筛查提供了新方向。
AI 中文摘要
心脏磁共振成像中的钆延迟强化（LGE）是心肌瘢痕的关键标志物，但其可及性有限，因此需要常规的心电图（ECG）筛查。我们在包含300名受试者的本地队列中，评估由β-变分自编码器（β-VAE）衍生的ECG特征能否区分LGE阳性（LGE+）与LGE阴性（LGE-）心肌病患者。我们将来自foundation模型（this http URL）的32维特征，与在正常PTB-XL ECG上训练的更浅层β-VAE的特征进行比较，评估下游分类性能以及基于动态时间规整（DTW）的重建误差。foundation模型结合随机森林的受试者工作特征曲线下面积（AUC）达到0.686，而所提出的β-VAE结合梯度提升的AUC为0.577、灵敏度为0.775。值得注意的是，根据曼-惠特尼U检验，12个导联中有10个导联的DTW重建误差在两类患者间存在显著差异，且有助于分类，结合逻辑回归的AUC达到0.643，支持DTW重建误差作为瘢痕相关ECG改变标志物的潜力。
英文摘要
Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether $β$-variational autoencoder (VAE)-derived ECG representations can discriminate LGE+ from LGE- cardiomyopathic patients in a local cohort of 300 subjects. We compared 32-dimensional features from the foundation ECGx.AI model with those from a shallower $β$-VAE trained on normal PTB-XL ECGs, evaluating downstream classification and Dynamic Time Warping (DTW)-based reconstruction errors. ECGx.AI reached an area under ROC of 0.686 with Random Forest, while the proposed $β$-VAE reached 0.577 with sensitivity of 0.775 with Gradient Boosting. Notably, DTW-reconstruction errors significantly differed between classes in 10 out of 12 leads according to Mann-Whitney U test and help in classification, leading to an area under ROC of 0.643 with Logistic Regression, supporting their potential as markers of scar-related ECG alterations.
CommentsAccepted at the PharML Workshop, ECML PKDD 2026
