Abstract：
OBJECTIVE: To compare the accuracy and generalizability of an automated deep neural network and the Philip Sleepware G3™ Somnolyzer system (Somnolyzer) for sleep stage scoring using American Academy of Sleep Medicine (AASM) guidelines.
METHODS: Sleep recordings from 104 participants were analyzed by a convolutional neural network (CNN), the Somnolyzer and skillful technicians. Evaluation metrics were derived for different combinations of sleep stages. A further comparison between the Somnolyzer and the CNN model using a single-channel signal as input was also performed. Sleep recordings from 263 participants with a lower prevalence of OSA served as a cross-validation dataset to validate the generalizability of the CNN model.
RESULTS: The overall agreement between automated and manual scoring for sleep staging in 104 participants outperformed that of the Somnolyzer according to various metrics (accuracy: 81.81 % vs. 77.07 %; F1: 76.36 % vs. 73.80 %; Cohen\'s kappa: 0.7403 vs. 0.6848). The results showed that the left electrooculography (EOG) single-channel model had minor advantages over the Somnolyzer. In terms of consistency with manual sleep staging, the CNN model demonstrated superior performance in identifying more pronounced sleep transitions, particularly in the N2 stage and sleep latency metrics. Conversely, the Somnolyzer showed enhanced proficiency in the analysis of REM stages, notably in measuring REM latency. The accuracy in the cross-validation set of 263 participants was also above 80 %.
CONCLUSIONS: The CNN-based automated deep neural network outperformed the Somnolyzer and is sufficiently accurate for sleep study analyses using the AASM classification criteria.
METHODS: Sleep recordings from 104 participants were analyzed by a convolutional neural network (CNN), the Somnolyzer and skillful technicians. Evaluation metrics were derived for different combinations of sleep stages. A further comparison between the Somnolyzer and the CNN model using a single-channel signal as input was also performed. Sleep recordings from 263 participants with a lower prevalence of OSA served as a cross-validation dataset to validate the generalizability of the CNN model.
RESULTS: The overall agreement between automated and manual scoring for sleep staging in 104 participants outperformed that of the Somnolyzer according to various metrics (accuracy: 81.81 % vs. 77.07 %; F1: 76.36 % vs. 73.80 %; Cohen\'s kappa: 0.7403 vs. 0.6848). The results showed that the left electrooculography (EOG) single-channel model had minor advantages over the Somnolyzer. In terms of consistency with manual sleep staging, the CNN model demonstrated superior performance in identifying more pronounced sleep transitions, particularly in the N2 stage and sleep latency metrics. Conversely, the Somnolyzer showed enhanced proficiency in the analysis of REM stages, notably in measuring REM latency. The accuracy in the cross-validation set of 263 participants was also above 80 %.
CONCLUSIONS: The CNN-based automated deep neural network outperformed the Somnolyzer and is sufficiently accurate for sleep study analyses using the AASM classification criteria.
摘要：
目的：比较自动深度神经网络和PhilipSleepwareG3™Somnolizer系统（Somnolizer）使用美国睡眠医学学会（AASM）指南进行睡眠阶段评分的准确性和通用性。
方法：通过卷积神经网络（CNN）分析了104名参与者的睡眠记录，Somnolizer和熟练的技术人员。针对睡眠阶段的不同组合得出评估度量。还进行了使用单通道信号作为输入的Somnolyzer和CNN模型之间的进一步比较。来自263名OSA患病率较低的参与者的睡眠记录作为交叉验证数据集，以验证CNN模型的普遍性。
结果：根据各种指标，104名参与者的自动和手动睡眠分期评分之间的总体一致性优于Somnolyzer（准确性：81.81％vs.77.07%；F1：76.36%vs.73.80%；科恩的卡帕：0.7403vs.0.6848）。结果表明，左眼电图（EOG）单通道模型比Somnolizer具有较小的优势。在与手动睡眠分期的一致性方面，CNN模型在识别更明显的睡眠过渡方面表现优异，特别是在N2阶段和睡眠延迟度量中。相反，Somnolyzer在快速眼动阶段的分析中表现出了更高的熟练程度，特别是在测量REM延迟方面。263名参与者的交叉验证组中的准确性也高于80%。
结论：基于CNN的自动深度神经网络优于Somnolizer，并且对于使用AASM分类标准的睡眠研究分析足够准确。
方法：通过卷积神经网络（CNN）分析了104名参与者的睡眠记录，Somnolizer和熟练的技术人员。针对睡眠阶段的不同组合得出评估度量。还进行了使用单通道信号作为输入的Somnolyzer和CNN模型之间的进一步比较。来自263名OSA患病率较低的参与者的睡眠记录作为交叉验证数据集，以验证CNN模型的普遍性。
结果：根据各种指标，104名参与者的自动和手动睡眠分期评分之间的总体一致性优于Somnolyzer（准确性：81.81％vs.77.07%；F1：76.36%vs.73.80%；科恩的卡帕：0.7403vs.0.6848）。结果表明，左眼电图（EOG）单通道模型比Somnolizer具有较小的优势。在与手动睡眠分期的一致性方面，CNN模型在识别更明显的睡眠过渡方面表现优异，特别是在N2阶段和睡眠延迟度量中。相反，Somnolyzer在快速眼动阶段的分析中表现出了更高的熟练程度，特别是在测量REM延迟方面。263名参与者的交叉验证组中的准确性也高于80%。
结论：基于CNN的自动深度神经网络优于Somnolizer，并且对于使用AASM分类标准的睡眠研究分析足够准确。
