发表机构
Collège Jean-de-Brébeuf（让-德-布雷伯夫学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对WPW检测的471:1类别不平衡问题，在控制数据泄漏的前提下，比较多种信号表示，发现特征融合模型表现与两成员投票相当，部署模型为筛查预筛选工具。
AI 中文摘要
Wolff-Parkinson-White（WPW）综合征是一种先天性心脏预激，具有重要临床意义，且常被常规12导联心电图漏检。检测难度较大：其特征表现细微，且该疾病发病率低。我们整合了两个公开的12导联心电图数据集PTB-XL与Chapman-Shaoxing-Ningbo，共66951条记录，其中WPW病例142例，患病率为0.21%（约471:1）。在一项预先指定的、控制泄漏的协议下，仅使用一次留出的折叠数据，我们比较了七种信号表示形式，同时保持数据划分与评估方式固定。在这些数据集及适度计算预算下，增加多样性与容量并未提升性能上限：最正交的检测器显著降低性能，特征融合模型与两成员投票模型表现相当，卷积网络达到小波检测器的性能但未超过，自监督预训练未通过预先指定的门限测试。无泄漏学习曲线在每次规模下重新选择特征，最强部署检测器在全部115个正例时仍在提升（配对90%-100%差值为+0.027，95%置信区间[0.019, 0.033]），因此未显示出饱和迹象。针对独立证据的误差分析发现，漏检病例的QRS波更窄，在我们展示该效应的符号取决于使用的描记器后，我们在流程外的机器测量中确认了这一点；不确定标签在漏检病例中未出现富集；部分明显的假阳性是数据集本身标记为预激的记录，这表明部分标签问题存在于负类中。我们测得非嵌套选择的乐观度为平均精度0.11至0.13。部署的输出是冻结参考分布中的百分位排名，而非概率。在留出折叠的14个正例上，其平均精度达0.595，ROC曲线面积为0.950。它是筛查预筛选工具，而非诊断工具。
英文摘要
Wolff-Parkinson-White (WPW) syndrome is a congenital cardiac pre-excitation, clinically important and often missed on the resting 12-lead ECG. Detection is hard: the signature is subtle and the condition rare. We pool two public 12-lead corpora, PTB-XL and Chapman-Shaoxing-Ningbo: 66,951 recordings, 142 of them WPW, a prevalence of 0.21% (about 471:1). Under one pre-specified, leakage-controlled protocol, with a held-out fold contacted exactly once, we compare seven representations of the signal, holding the split and the evaluation fixed. Within these corpora and under a modest compute budget, added diversity and capacity do not raise the ceiling: the most orthogonal detector significantly hurts, a feature-union model matches a two-member vote, a convolutional network reaches the wavelet detector without exceeding it, and self-supervised pretraining fails a pre-specified gate. A leak-free learning curve, re-selecting features at every size, still rises at the full 115 positives for the strongest deployed detector (paired 90-to-100% difference +0.027, 95% CI [0.019, 0.033]), so it is not shown to have saturated. An error analysis tested against independent evidence finds that the missed cases have a narrower QRS, confirmed by an on-machine measurement outside our pipeline after we show the sign of this effect depends on which delineator measures it; that uncertain labels show no enrichment among the misses; and that some apparent false positives are recordings the corpus itself codes as pre-excited, placing part of the label problem in the negative class. We measure the optimism of non-nested selection at 0.11 to 0.13 average precision. The deployed output is a percentile rank in a frozen reference distribution, not a probability. On the held-out fold, on 14 positives, it reaches an average precision of 0.595 and an ROC area of 0.950. It is a screening pre-filter, not a diagnostic tool.
Comments36 pages, 7 figures. Code, frozen models, out-of-fold scores and the full decision log: https://github.com/nathaelaltman/wpw-ecg-detection
