AI 中文总结
该研究提出LAEF，一种7M参数的导联无关心电图基础模型，预训练于9.2M份12导联心电图，在18个下游数据集的1-2导联即时诊断场景下，性能优于零填充替代方案，与更大规模的12导联基线相当。
AI 中文摘要
智能手表、手持心电图记录仪等即时 cardiac设备通常采集1-2个导联信号，但现有的心电图基础模型在架构上受限于固定的12导联输入，在导联减少的配置下性能下降或无法工作。我们提出LAEF（Lead-Agnostic ECG Foundation，导联无关心电图基础模型），这是一个拥有700万参数的心电图基础模型，可原生处理任意导联子集，无需零填充或架构修改。LAEF将心电图表示为可变大小的时空图，具有基于生理动机的导联内和导联间连接，由图注意力网络处理，该网络可随活动导联数量自然扩展。LAEF在920万份12导联心电图上通过带随机导联采样的掩码节点建模进行预训练，学习到对导联配置具有鲁棒性的表示。在18个下游数据集上，LAEF在全导联可用时，与规模大12倍的专用12导联基线模型性能相当；在面向即时诊断的直接场景（1-2个导联）下，它在18个数据集中的17个上，使用单个随机采样导联时，优于所有零填充替代方案，在18个数据集中的14个上，使用2个导联时也优于这些方案，平均AUROC提升3.2个百分点。表示分析将这一优势与架构的导联无关性关联起来，对164种心血管疾病的导联重要性研究显示，在单个标准输入导联下，人群水平性能稳定，同时仍能恢复已确立的临床导联-疾病关联。
英文摘要
Point-of-care cardiac devices such as smartwatches and handheld ECG recorders typically capture 1--2 leads, yet existing ECG foundation models are architecturally constrained to fixed 12-lead inputs, degrading or failing under these reduced configurations. We introduce LAEF (Lead-Agnostic ECG Foundation), a 7M-parameter ECG foundation model that can natively process any lead subset without zero-padding or architectural modification. LAEF represents ECGs as variable-size spatiotemporal graphs with physiologically motivated intra- and inter-lead connectivity, processed by a Graph Attention Network that scales naturally with active lead count.Pre-trained on 9.2M 12-lead ECGs via masked node modelling with stochastic lead sampling, LAEF learns representations robust to lead configuration. Across 18 downstream datasets, LAEF is on par with specialized 12-lead baselines over 12$\times$ larger at full lead availability. Under direct point-of-care-oriented diagnostics (1--2 leads), it outperforms all zero-padded alternatives on 17 out of 18 datasets with with a single randomly sampled lead and on 14 out of 18 with 2 leads, with an average AUROC gain of +3.2 points. Representation analysis links this advantage to architectural lead-agnosticism, and a lead-importance study across 164 cardiovascular conditions shows population-level performance is stable across single standard input leads while still recovering established clinically lead-condition associations.
