发表机构
Amsterdam University Medical Center; University of Amsterdam; ETH Zurich; Amsterdam Cardiovascular Sciences（阿姆斯特丹大学医学中心; 阿姆斯特丹大学; 苏黎世联邦理工学院; 阿姆斯特丹心血管科学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出通过对比预训练将心脏磁共振结构知识迁移至心电图，利用英国生物银行数据提升恰加斯病检测，在多个基准上超越基线，验证了跨域泛化能力。
AI 中文摘要
恰加斯病是拉丁美洲心肌病的主要原因。心脏磁共振（CMR）成像能够表征其结构异常，但在流行地区，扫描仪和专家阅片者仍然稀缺。心电图（ECG）价格低廉且广泛可用，但结构性疾病必须从电信号中间接推断。我们提出通过对比预训练将CMR衍生的结构知识迁移到ECG。利用来自英国生物银行的63,193对配对ECG-CMR检查，我们使用非对称InfoNCE目标将ECG编码器与临床基础的CMR嵌入空间对齐。尽管在预训练期间未见到恰加斯病例，所得表示仍提升了基于ECG的恰加斯检测性能。在CODE-15%和SaMi-Trop上，冻结的线性探针在五折交叉验证中实现了0.851的AUROC和0.427的Top5%预测风险敏感度（Top5%-TPR），而未经对齐的ECG-FM基线分别为0.827和0.377。在PhysioNet/CinC 2025挑战赛测试集上，我们的模型在SaMi-Trop-3上获得最高AUROC，并在三个表现最佳的方法中取得最佳ELSA-Brasil挑战分数，表明影像监督的ECG表示能够泛化到预训练分布之外的人群和设置。
英文摘要
Chagas disease is a major cause of cardiomyopathy in Latin America. Cardiac magnetic resonance (CMR) imaging can characterize its structural abnormalities, but scanners and expert readers remain scarce in endemic regions. Electrocardiography (ECG) is inexpensive and widely available, yet structural disease must be inferred indirectly from electrical signals. We propose to transfer CMR-derived structural knowledge to ECG through contrastive pre-training. Using 63,193 paired ECG-CMR examinations from the UK Biobank, we align an ECG encoder with a clinically grounded CMR embedding space using an asymmetric InfoNCE objective. Despite seeing no Chagas cases during pre-training, the resulting representation improves ECG-based Chagas detection. Across CODE-15% and SaMi-Trop, a frozen linear probe achieves an AUROC of 0.851 and sensitivity at the top 5% of predicted risk (Top5%-TPR) of 0.427 in five-fold cross-validation, compared with 0.827 and 0.377 for an unaligned ECG-FM baseline. On the PhysioNet/CinC 2025 Challenge test set, our model obtains the highest AUROC on SaMi-Trop-3 and the best ELSA-Brasil challenge score among the three top-performing methods, indicating that imaging-supervised ECG representations can generalize to populations and settings beyond the pre-training distribution.
