• Yun Zhang, Yubo Wang, Suping Cai, Jun Li, Junchan Ren, Qiang Wang, and Liyu Huang.
• Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul 1; 2019: 4525-4528.

AbstractVarious EEG features have been proposed for differentiating the consciousness and unconsciousness states during general anesthesia. However, their performance for detecting the fluctuation of consciousness level remains unclear. In this work, we recorded 60-channels EEG data during propofol anesthesia, and extracted 110 EEG features that were shown to be sensitive to the change of consciousness level. Then, we used classification model to evaluate the performance of these features in distinguishing the response state fluctuating around the point of loss of behavioral responsiveness (LOBR) to external stimuli. We found that EEG features, including delta power, SynchFastSlow, and the topographical ratio of alpha power, were efficient in distinguishing the stable change in consciousness level with an accuracy of 95.8%, however, these features performed poorly in distinguishing the response state around the point of LOBR with an accuracy of 66.9%. Using EEG features selected specifically for detecting consciousness fluctuation, approximately 10% improvement in accuracy was obtained. Our results suggested that the EEG features that were sensitive to the stable change of consciousness level and fluctuation of consciousness level were largely different. EEG features including theta band power and functional connectivity are more relevant to the fluctuation of consciousness level.

10 keywords...

hide…