Center for Sleep Sciences and Medicine, Stanford University, CA, USA; Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark; Danish Center for Sleep Medicine, Glostrup University Hospital, Glostrup, Denmark.
Center for Sleep Sciences and Medicine, Stanford University, CA, USA; Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark; Danish Center for Sleep Medicine, Glostrup University Hospital, Glostrup, Denmark.
Clin Neurophysiol. 2020 Jun;131(6):1187-1203. doi: 10.1016/j.clinph.2020.02.027. Epub 2020 Apr 2.
Significant interscorer variability is found in manual scoring of arousals in polysomnographic recordings (PSGs). We propose a fully automatic method, the Multimodal Arousal Detector (MAD), for detecting arousals.
A deep neural network was trained on 2,889 PSGs to detect cortical arousals and wakefulness in 1-second intervals. Furthermore, the relationship between MAD-predicted labels on PSGs and next day mean sleep latency (MSL) on a multiple sleep latency test (MSLT), a reflection of daytime sleepiness, was analyzed in 1447 MSLT instances in 873 subjects.
In a dataset of 1,026 PSGs, the MAD achieved an F1 score of 0.76 for arousal detection, while wakefulness was predicted with an accuracy of 0.95. In 60 PSGs scored by nine expert technicians, the MAD performed comparable to four and significantly outperformed five expert technicians for arousal detection. After controlling for known covariates, a doubling of the arousal index was associated with an average decrease in MSL of 40 seconds (p = 0.0075).
The MAD performed better or comparable to human expert scorers. The MAD-predicted arousals were shown to be significant predictors of MSL.
This study validates a fully automatic method for scoring arousals in PSGs.
在多导睡眠图（PSG）记录的唤醒手动评分中发现显著的评分者间变异性。我们提出了一种完全自动的方法，即多模态唤醒检测器（MAD），用于检测唤醒。
一个深度神经网络在 2889 份 PSG 上进行训练，以检测皮质唤醒和 1 秒间隔的觉醒。此外，在 873 名受试者的 1447 个多睡眠潜伏期测试（MSLT）实例中，分析了 MAD 预测的 PSG 标签与次日平均睡眠潜伏期（MSL）之间的关系，MSLT 反映了日间嗜睡。
在 1026 份 PSG 的数据集，MAD 对唤醒检测的 F1 评分为 0.76，而对觉醒的预测准确率为 0.95。在 60 份由九位专家技术员评分的 PSG 中，MAD 在唤醒检测方面的表现与四位专家技术员相当，明显优于五位专家技术员。在控制了已知的协变量后，唤醒指数增加一倍与 MSL 平均减少 40 秒相关（p=0.0075）。
MAD 的表现优于或与人类专家评分者相当。MAD 预测的唤醒被证明是 MSL 的显著预测因子。
本研究验证了一种用于 PSG 中唤醒评分的全自动方法。
