Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen’s kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.

使用腕戴式可穿戴光电体积描记法（PPG）进行不引人注目的家庭睡眠监测可以为更好的睡眠障碍筛查和健康监测开辟道路。然而，PPG 很少被纳入采用多导睡眠图黄金标准睡眠注释的大型睡眠研究中。因此，训练数据密集型的最先进的深度神经网络具有挑战性。在这项工作中，首先使用包含心电图 (ECG) 数据（292 名参与者，584 条记录）的大型睡眠数据集训练深度循环神经网络，以执行 4 级睡眠阶段分类（清醒、快速眼动、N1/N2） ，和N3）。通过三种不同的迁移学习，其权重的一小部分适应了更小、更新的 PPG 数据集（60 名健康参与者，101 条记录）。使用领域和决策组合迁移学习策略获得了最佳结果（Cohen 的 kappa 为 0.65 ± 0.11，准确度为 76.36 ± 7.57%），显着优于 PPG 训练和 ECG 训练的基线。基于 PPG 的 4 级睡眠阶段分类的这种性能在文献中是前所未有的，使家庭睡眠阶段监测更接近临床应用。这项工作展示了迁移学习在通过重用类似的、较旧的非可穿戴数据集来开发新传感器技术的可靠方法方面的优点。进一步的研究应该评估我们对失眠和睡眠呼吸暂停等睡眠障碍患者的治疗方法。