Although deep learning algorithms have proven their efficiency in automatic
sleep staging, the widespread skepticism about their "black-box" nature has
limited its clinical acceptance. In this study, we propose WaveSleepNet, an
interpretable neural network for sleep staging that reasons in a similar way to
sleep experts. In this network, we utilize the latent space representations
generated during training to identify characteristic wave prototypes
corresponding to different sleep stages. The feature representation of an input
signal is segmented into patches within the latent space, each of which is
compared against the learned wave prototypes. The proximity between these
patches and the wave prototypes is quantified through scores, indicating the
prototypes' presence and relative proportion within the signal. The scores are
served as the decision-making criteria for final sleep staging. During
training, an ensemble of loss functions is employed for the prototypes'
diversity and robustness. Furthermore, the learned wave prototypes are
visualized by analysing occlusion sensitivity. The efficacy of WaveSleepNet is
validated across three public datasets, achieving sleep staging performance
that are on par with the state-of-the-art models when several WaveSleepNets are
combine into a larger network. A detailed case study examined the
decision-making process of the WaveSleepNet which aligns closely with American
Academy of Sleep Medicine (AASM) manual guidelines. Another case study
systematically explained the misidentified reason behind each sleep stage.
WaveSleepNet's transparent process provides specialists with direct access to
the physiological significance of its criteria, allowing for future adaptation
or enrichment by sleep experts.

本研究提出 WaveSleepNet，一种可解释的神经网络用于睡眠分期，在训练过程中利用隐藏空间表示来识别不同睡眠阶段的特征波样本，通过评分确定波样本在输入信号中的存在和相对比例，并通过多个损失函数进行训练以确保波样本的多样性和稳健性。通过对三个公共数据集的验证，证实 WaveSleepNet 达到与最先进模型相媲美的睡眠分期性能，通过详细案例研究解释了 WaveSleepNet 的决策过程，并与美国睡眠医学会（AASM）手册指南紧密对齐，其透明的过程为专家们提供了直接访问其标准的生理意义，以供睡眠专家未来的调整或丰富。