Analysis of EEG Patterns in Vigil and Fatigue States during the Execution of Laparoscopic Tasks

Fatigue decreases efficiency in performance of several professional activities; therefore, being in that state could trigger technical mistakes which consequences could be lethal, such as in health area, where a surgical error due to the absence of rest can lead to the patient death. For this reason, in this study the vigil and fatigue (due to sleep) states, that affect cognitive processes in medical students, were identified through Electroencephalographic (EEG) patterns. The EEG signals of 18 physician students were analyzed within the theta band (4 - 8 Hz) over fronto-central recording sites, and the alpha band (8 - 13 Hz) rhythms over temporal and parieto-occipital recording sites during the execution of laparoscopic tasks before and after their guard. The signal-processing pipeline consisted in preprocessing based on individual component analysis, absolute band power estimates, and SVM classification. The f-score to differ between vigil and fatigue was 90.89%, where the first state showed more slightly identifiable EEG patterns reaching a sensitivity of 90.18%. The pre-processed EEG signals are shared in this site.疲劳会降低多项专业活动的执行效率，处于该状态下可能引发致命性技术失误——例如在医疗领域，因休息不足导致的手术差错可致使患者死亡。为此，本研究通过脑电（Electroencephalographic, EEG）特征，识别了影响医学生认知过程的清醒状态与睡眠源性疲劳状态。研究采集了18名医学生在值班前后执行腹腔镜操作任务时的脑电信号，分别分析其额中央导联的θ频段（4~8 Hz）脑电信号，以及颞叶、顶枕叶导联的α频段（8~13 Hz）脑电节律。本研究的信号处理流程包括基于独立成分分析的预处理、绝对频带功率估算，以及支持向量机（Support Vector Machine, SVM）分类。区分清醒与疲劳状态的F1分数达90.89%；其中清醒状态的脑电特征更具辨识度，灵敏度为90.18%。本研究已将预处理后的脑电信号共享于本平台。