用深度学习补全不完整的心电图，让AI能更好诊断心脏问题。
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incomplete Recordings for Cardiac Assessment
- 基于一维Transformer的自编码器，根据已有波形推断缺失导联数据。
- 在多个数据集上使缺失区域误差降低超50%，关键波形重建更准确。
- 适合临床电子病历中残缺心电图的补全，提升AI分析可用性。
完整12导联数字心电图（ECG）对人工智能驱动的心血管评估至关重要，但许多临床记录（尤其是从图像数字化而来）因显示格式短、波形未完全数字化、导联丢失或信号污染而缺损。本文提出ImputeECG，一种掩码条件的一维Transformer自编码器，可在保留已观测样本的前提下完成12导联、10秒的ECG。模型在PTB-XL上训练，并在PTB-XL和CPSC2018上模拟不完整场景下评估，另在43,633条来自凯伦临床队列的真实数据中进行图像化后验证。评估聚焦于原始缺失区域，分析形态特征与下游诊断效能。在PTB-XL上，相比最强基线，ImputeECG将缺失区域平均绝对误差（MAE）降低41.7%-51.0%，均方误差（MSE）降低54.0%-63.7%，在R峰时间、RR间期、QRS持续时间、QT间期以及P波、QRS波群、T波重建上误差更低。在CPSC2018上，MAE降低49.7%-51.9%，体现良好泛化能力。下游多标签分类任务中，ImputeECG使最不完整设置下的性能恢复至92.28% AUROC和33.88% AUPRC，接近完整心电图表现；在CPSC2018上，完成后的心电图实现94.75%-95.89% AUROC和78.83%-81.86% AUPRC。在凯伦队列中，完成心电图将零样本性别预测的AUROC从82.6%提升至85.8%，年龄预测的平均绝对误差从10.72年降至9.87年。这些结果支持心电图补全作为实用策略，将不完整记录转化为可用于AI分析的12导联、10秒数字信号，拓展心电图数据库在数字心脏评估中的应用范围。
原文摘要 · Abstract (English)
Complete digital 12-lead electrocardiograms (ECGs) are essential for AI-enabled cardiovascular assessment, yet many clinical ECG records, particularly those digitized from ECG images, remain incomplete because of short display formats, incomplete waveform digitization, lead loss, or signal corruption. We developed ImputeECG, a mask-conditioned one-dimensional Transformer autoencoder that completes 12-lead, 10-s ECGs while retaining all observed samples. The model was trained on PTB-XL and evaluated on PTB-XL and CPSC2018 under simulated incomplete settings, with additional real-world validation in a 43,633-record Kailuan clinical cohort after ECG image digitization. Metrics were computed over originally missing regions, with analyses of morphology and downstream diagnostic utility. On PTB-XL, ImputeECG reduced missing-region MAE by 41.7-51.0% and MSE by 54.0-63.7% versus the strongest baseline, with lower errors in R-peak timing, RR interval, QRS duration, QT interval, and P-wave, QRS-complex, and T-wave reconstruction. On CPSC2018, ImputeECG reduced MAE by 49.7-51.9%, supporting external generalization. In downstream multi-label classification, ImputeECG restored performance to 92.28% AUROC and 33.88% AUPRC in the most incomplete PTB-XL setting, approaching complete-ECG performance. On CPSC2018, completed ECGs achieved 94.75-95.89% AUROC and 78.83-81.86% AUPRC across settings. In Kailuan, ECG completion improved zero-shot sex prediction AUROC from 82.6% to 85.8% and reduced age prediction MAE from 10.72 to 9.87 years after image-based ECG digitization. These findings support ECG completion as a practical strategy for converting incomplete ECG records into AI-ready 12-lead, 10-s digital signals and extending the usable scope of ECG archives for digital cardiac assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。