EEG UNDER ANESTHESIA A general method for calculation of depth of anesthesia
We investigated the problem of automatic depth of anesthesia (DOA) estimation from electroencephalogram (EEG) recordings. The electroencephalographic (EEG) derived bis-pectral index (BIS) is a sensitive index that reflects the hypnotic component of anesthesia. But as the depth of anesthesia monitoring technology, BIS has its obvious limitations. Compared with the Bispectral Index (BIS), we propose time-frequency domain signal processing technique and Nonlinear dynamical analysis novel to DOA assessment, multiple parameters are employed, and obtain DOA model using statistic method, to evaluate the relationship between EEG features and index of DOA. In emulation and clinical practice, our method has achieved good results, that could enhance existing monitoring devices and propose a general method to find more effective parameters model for Monitored Anesthesia Care.
EEG depth of anesthesia (DOA) Feature extraction Lasso regression Logistic regression
Lei Wang Zhengqiang Ni Jun Meng Fuming Qiu Jian Huang
College of Electrical Engineering, Zhejiang University Hangzhou, China 310027 Department of Oncology, Second Affiliated Hospital Zhejiang University School of Medicine, Hangzhou,
国际会议
成都
英文
23-27
2011-01-14（万方平台首次上网日期，不代表论文的发表时间）