STUDY OBJECTIVES Develop a high-performing, automated sleep scoring algorithm that can be applied to long-term scalp electroencephalography (EEG) recordings. METHODS Using a clinical dataset of polysomnograms from 6,431 patients (MGH-PSG dataset), we trained a deep neural network to classify sleep stages based on scalp EEG data. The algorithm consists of a convolutional neural network (CNN) for feature extraction, followed by a recurrent neural network (RNN) that extracts temporal dependencies of sleep stages. The algorithm's inputs are 4 scalp EEG bipolar channels (F3-C3, C3-O1, F4-C4, C4-O2), which can be derived from any standard PSG or scalp EEG recording. We initially trained the algorithm on the MGH-PSG dataset and used transfer learning to fine-tune it on a dataset of long-term (24-72 hour) scalp EEG recordings from 112 patients (scalpEEG dataset). RESULTS The algorithm achieved a Cohen's kappa of 0.74 on the MGH-PSG holdout testing set and cross-validated Cohen's kappa of 0.78 after optimization on the scalpEEG dataset. The algorithm also performed well on two publicly available PSG datasets, demonstrating high generalizability. Performance on all datasets was comparable to the inter-rater agreement of human sleep staging experts (Cohen's kappa ~ 0.75±0.11). The algorithm's performance on long-term scalp EEGs was robust over a wide age range and across common EEG background abnormalities. CONCLUSION We developed a deep learning algorithm that achieves human expert level sleep staging performance on long-term scalp EEG recordings. This algorithm, which we have made publicly available, greatly facilitates the use of large long-term EEG clinical datasets for sleep-related research.

中文翻译：

---

使用深度学习对长期头皮 EEG 记录进行专家级自动睡眠分期

研究目标 开发可应用于长期头皮脑电图 (EEG) 记录的高性能、自动睡眠评分算法。方法使用来自 6,431 名患者的多导睡眠图临床数据集（MGH-PSG 数据集），我们训练了一个深度神经网络，以根据头皮 EEG 数据对睡眠阶段进行分类。该算法由用于特征提取的卷积神经网络 (CNN) 和用于提取睡眠阶段时间依赖性的循环神经网络 (RNN) 组成。该算法的输入是 4 个头皮 EEG 双极通道（F3-C3、C3-O1、F4-C4、C4-O2），可以从任何标准 PSG 或头皮 EEG 记录中导出。我们最初在 MGH-PSG 数据集上训练算法，并使用迁移学习在 112 名患者的长期（24-72 小时）头皮 EEG 记录数据集（scalpEEG 数据集）上对其进行微调。结果 该算法在 MGH-PSG 保持测试集上实现了 0.74 的 Cohen's kappa，并在头皮脑电数据集上优化后交叉验证了 0.78 的 Cohen's kappa。该算法在两个公开可用的 PSG 数据集上也表现良好，表现出很高的通用性。在所有数据集上的表现与人类睡眠分期专家的评分者间一致性相当（Cohen's kappa ~ 0.75±0.11）。该算法在长期头皮脑电图上的性能在广泛的年龄范围内和常见的脑电图背景异常中表现稳健。结论 我们开发了一种深度学习算法，可在长期头皮 EEG 记录上实现人类专家级的睡眠分期性能。我们公开发布的该算法极大地促进了大型长期 EEG 临床数据集用于睡眠相关研究。