Department of Neurology, Mayo Systems Electrophysiology Laboratory, Mayo Clinic, 200 First St SW, Rochester, MN 55905, United States of America. Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Jugoslavskych Partyzanu 1580/3, 160 00 Prague 6, Czechia. Department of Physiology and Biomedical Engineering, Mayo Clinic, 200 First St SW, Rochester, MN 55905, United States of America.
J Neural Eng. 2019 Apr;16(2):026004. doi: 10.1088/1741-2552/aae5ab. Epub 2018 Oct 2.
Automated behavioral state classification in intracranial EEG (iEEG) recordings may be beneficial for iEEG interpretation and quantifying sleep patterns to enable behavioral state dependent neuromodulation therapy in next generation implantable brain stimulation devices. Here, we introduce a fully automated unsupervised framework to differentiate between awake (AW), sleep (N2), and slow wave sleep (N3) using intracranial EEG (iEEG) only and validated with expert scored polysomnography.
Data from eight patients undergoing evaluation for epilepsy surgery (age [Formula: see text], three female) with intracranial depth electrodes for iEEG monitoring were included. Spectral power features (0.1-235 Hz) spanning several frequency bands from a single electrode were used to classify behavioral states of patients into AW, N2, and N3.
Overall, classification accuracy of 94%, with 94% sensitivity and 93% specificity across eight subjects using multiple spectral power features from a single electrode was achieved. Classification performance of N3 sleep was significantly better (95%, sensitivity 95%, specificity 93%) than that of the N2 sleep phase (87%, sensitivity 78%, specificity 96%).
Automated, unsupervised, and robust classification of behavioral states based on iEEG data is possible, and it is feasible to incorporate these algorithms into future implantable devices with limited computational power, memory, and number of electrodes for brain monitoring and stimulation.
在颅内脑电图（iEEG）记录中进行自动行为状态分类可能有助于 iEEG 解读和量化睡眠模式，从而为下一代植入式脑刺激设备中的行为状态相关神经调节治疗提供支持。在此，我们引入了一种完全自动化的无监督框架，仅使用颅内脑电图（iEEG）即可区分清醒（AW）、睡眠（N2）和慢波睡眠（N3）状态，并通过专家评分的多导睡眠图进行验证。
纳入了 8 名正在接受癫痫手术评估的患者（年龄 [Formula: see text]，3 名女性）的数据，这些患者接受颅内深度电极进行 iEEG 监测。使用单个电极的多个频带的频谱功率特征（0.1-235 Hz）来对患者的行为状态进行分类，分为 AW、N2 和 N3。
总体而言，使用单个电极的多个频谱功率特征，对 8 名患者的分类准确率达到 94%，敏感性为 94%，特异性为 93%。N3 睡眠的分类性能明显优于 N2 睡眠阶段（95%，敏感性 95%，特异性 93%）（87%，敏感性 78%，特异性 96%）。
基于 iEEG 数据的自动、无监督和稳健的行为状态分类是可行的，并且可以将这些算法纳入未来具有有限计算能力、内存和电极数量的植入式设备中，用于脑监测和刺激。
