TRACE：面向临床心电图的易处理路由自编码器
TRACE: Tractable Routing Autoencoder for Clinical ECG
- Shenzhen University of Advanced Technology（深圳理工大学）
- Monash University（莫纳什大学）
- University of Queensland（昆士兰大学）
- University of Cambridge（剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
TRACE通过预定义的32维临床潜空间划分和路由机制，在保持决策路径可审计性的同时，以八分之一参数超越ECG基础模型，实现可干预的诊断与重建。
AI中文摘要：
深度学习推进了自动化心电图（ECG）诊断，但该领域最准确的模型——在数百万条记录上预训练的基础模型——不具备决策路径可审计性：临床医生无法将诊断追溯到生理路径，也无法对某条路径进行干预。我们提出TRACE，一种面向临床心电图的易处理路由自编码器，其32维临床潜空间根据领域知识预先指定，而非通过优化发现。TRACE将该空间划分为灌注、结构和传导子空间，按设计将每个子空间路由到各自的诊断头，用正交性惩罚正则化该划分，并通过允许潜变量扰动的解码器重建心电图。在PTB-XL和Georgia数据集上，TRACE超越了无约束分类器，并领先于在千万条记录上预训练的心电图基础模型（以冻结特征的线性探针评估），而参数量约为后者的八分之一。在无结构类别的九标签CPSC2018队列上，该框架仅需将路由表重新指定为灌注/节律/传导划分即可迁移。联合探针、擦除和扰动分析验证了路由契约，且扰动去极化和复极化路径可调节重建波形。移除指定的划分及其正交性惩罚，在PTB-XL上损失1.70 AUC和11.30个宏F1点，在Georgia上损失2.76 AUC和16.92个宏F1点。容量匹配的置换对照将任意分配置于本体路由的0.34 AUC点以内，且宏F1在统计上持平（p=0.619）：本体在无宏F1代价的情况下提供决策路径可审计性。
英文摘要：
Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions of recordings, are not decision-pathway auditable: a clinician cannot trace a diagnosis to a physiological pathway or intervene on one. We propose TRACE, a Tractable Routing Autoencoder for Clinical ECG, whose 32-dimensional clinical latent space is specified in advance from domain knowledge rather than discovered by optimization. TRACE partitions this space into perfusion, structure, and conduction subspaces, routes each to its own diagnostic head by design, regularizes the partition with an orthogonality penalty, and reconstructs the ECG through a decoder that permits latent perturbation. On PTB-XL and Georgia, TRACE exceeds unconstrained classifiers and stays ahead of an ECG foundation model pretrained on ten million recordings, evaluated by linear probe on frozen features, at roughly an eighth of the parameter count. On the nine-label CPSC2018 cohort, which carries no structural class, the framework transfers with only the routing table re-specified to a perfusion/rhythm/conduction partition. Joint probe, erasure, and perturbation analyses verify the routing contract, and perturbing the depolarization and repolarization pathways modulates the reconstructed waveform. Removing the specified partition and its orthogonality penalty costs 1.70 AUC and 11.30 macro-F1 points on PTB-XL, and 2.76 AUC and 16.92 macro-F1 points on Georgia. A capacity-matched permutation control places arbitrary assignments within 0.34 AUC points of the ontology routing and leaves macro-F1 statistically level (p=0.619): the ontology supplies decision-pathway auditability at no macro-F1 cost.
