发现生理信号深度学习依赖非周期成分，影响解读可靠性
A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning
- 提出频谱审计框架，分离非周期与周期成分并验证其影响
- 睡眠判别任务中性能下降超0.42准确率点，临床异常检测也显著受影响
- 适用于脑电、心电等生理信号，提升模型可解释性
生理时间序列的深度学习通常依赖于特定领域的特征——如脑电图（EEG）中的振荡节律和心电图（ECG）中的形态复合波——但这些信号均叠加在一种与觉醒水平、年龄和病理状态相关的宽带非周期1/f类包络之上。本文提出一种频谱审计框架，结合非周期/周期成分分解、保持相位的傅里叶干预、假对照实验及仿真验证。结果显示，非周期成分的依赖具有任务相关性且在六种神经架构中普遍：在睡眠-清醒分类中，平坦化处理导致平衡准确率下降超过0.42点；临床异常检测下降0.07–0.13；而运动想象任务则影响极小。七种EEG基础模型中有六种显示在临床EEG上存在经错误发现率（FDR）检验显著的非周期依赖；年龄、性别及记录年代控制虽降低但未消除该效应。在PTB-XL ECG数据上应用该审计，发现经人口统计学匹配后仍存在0.32–0.36的性能下降，表明此混杂因素不仅存在于EEG。研究建议将非周期控制纳入标准流程，以实现可解释的生理时间序列深度学习。
原文摘要 · Abstract (English)
Deep learning on physiological time series is interpreted through domain-specific features -- oscillatory rhythms in EEG, morphological complexes in ECG -- yet these signals sit atop a broadband aperiodic 1/f-like envelope that covaries with arousal, age, and pathology. We introduce a spectral audit framework combining aperiodic/periodic decomposition, phase-preserving Fourier interventions, sham controls, and simulation validation. Aperiodic reliance was task-dependent and architecture-general: across six neural architectures, flattening drops exceeded 0.42 balanced-accuracy points for sleep-wake classification, reached 0.07-0.13 for clinical abnormality detection, and remained minimal for motor imagery. Six of seven EEG foundation models showed FDR-significant aperiodic reliance on clinical EEG; age/sex and recording-era controls reduced but did not eliminate the effect. Applying the audit to PTB-XL ECG revealed neural drops of 0.32--0.36 persisting after demographic matching, confirming this confound class extends beyond EEG. Aperiodic controls should become standard for interpretable physiological time-series deep learning.
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。