Automated sleep classification with chronic neural implants in freely behaving canines.
Automated sleep classification with chronic neural implants in freely behaving canines.
复制标题
在自由行为的犬科动物中使用慢性神经植入物进行自动睡眠分类。
DOI：
10.1088/1741-2552/aced21
复制
发表时间：
2023
影响因子：
4
通讯作者：
Van
中科院分区：
文献类型：
--
作者：
Mivalt,Filip;Sladky,Vladimir;Worrell,Samuel;Gregg,NicholasM;Balzekas,Irena;Kim,Inyong;Chang,Su-Youne;Montonye,DanielR;Duque-Lopez,Andrea;Krakorova,Martina;Pridalova,Tereza;Lepkova,Kamila;Brinkmann,BenjaminH;Miller,KaiJ;Van
目的自由活动动物的长期颅内脑电图（iEEG）提供了有价值的电生理信息，并与动物行为相关联，有助于研究脑功能。在这里，我们开发并验证了一个基于脑电图的自动睡眠-觉醒分类器，该分类器使用来自同步视频、加速度计、头皮脑电图（EEG）和脑电图监测的专家睡眠标签。视频、头皮脑电图和加速度计记录由一位委员会认证的睡眠专家手动评分，分为睡眠-觉醒状态：清醒、快速眼动（REM）睡眠和三个非快速眼动睡眠类别（NREM1、2、3）。专家标签被用来训练、验证和测试一个完全自动化的脑电图睡眠-觉醒分类器。主要结果基于eeg的分类器总体分类准确率为0.878±0.055,Cohen’s Kappa评分为0.786±0.090。随后，我们使用基于脑电图的自动分类器对自由行为的狗进行了数周的睡眠调查。结果表明，犬在白天有大量的睡眠时间，但白天小睡睡眠的特点与夜间睡眠的特点有三个关键特征：白天NREM睡眠周期较少（10.81±2.34个周期/天vs 22.39±3.88个周期/夜，p< 0.001）， NREM睡眠周期持续时间较短（13.83±8.50分钟/天vs 15.09±8.55分钟/夜）；p< 0.001)，与夜间睡眠相比，狗在NREM睡眠中所占的睡眠时间比例更高，REM睡眠时间更少（NREM每天0.88±0.09,REM 0.12±0.09,NREM 0.80±0.08,REM 0.20±0.08,p< 0.001）。意义这些结果支持了脑电睡眠-觉醒自动分类器用于犬类行为研究的可行性和准确性。
ObjectiveLong-term intracranial electroencephalography (iEEG) in freely behaving animals provides valuable electrophysiological information and when correlated with animal behavior is useful for investigating brain function.ApproachHere we develop and validate an automated iEEG-based sleep–wake classifier for canines using expert sleep labels derived from simultaneous video, accelerometry, scalp electroencephalography (EEG) and iEEG monitoring. The video, scalp EEG, and accelerometry recordings were manually scored by a board-certified sleep expert into sleep–wake state categories: awake, rapid-eye-movement (REM) sleep, and three non-REM sleep categories (NREM1, 2, 3). The expert labels were used to train, validate, and test a fully automated iEEG sleep–wake classifier in freely behaving canines.Main resultsThe iEEG-based classifier achieved an overall classification accuracy of 0.878±0.055 and a Cohen's Kappa score of 0.786±0.090. Subsequently, we used the automated iEEG-based classifier to investigate sleep over multiple weeks in freely behaving canines. The results show that the dogs spend a significant amount of the day sleeping, but the characteristics of daytime nap sleep differ from night-time sleep in three key characteristics: during the day, there are fewer NREM sleep cycles (10.81±2.34 cycles per day vs. 22.39±3.88 cycles per night; p< 0.001), shorter NREM cycle durations (13.83±8.50 min per day vs. 15.09±8.55 min per night; p< 0.001), and dogs spend a greater proportion of sleep time in NREM sleep and less time in REM sleep compared to night-time sleep (NREM 0.88±0.09, REM 0.12±0.09 per day vs. NREM 0.80±0.08, REM 0.20±0.08 per night; p< 0.001).SignificanceThese results support the feasibility and accuracy of automated iEEG sleep–wake classifiers for canine behavior investigations.