Abstract

Info

Title:: Monitoring depth of anesthesia during induction using EEG nonlinear characteristics combined with AdaBoost algorithm

Author(s):: TANG Weixiong1; 2; CHENG Yunzhang1; ZHANG Tianyi1; SONG Jinchao2; 1. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China 2. Department of Anesthesiology, Shidong Hospital Affiliated to University of Shanghai for Science and Technology, Shanghai 200082, China

Keywords:: Keywords: depth of anesthesia induction period electroencephalogram signal nonlinear characteristic AdaBoost algorithm

Abstract:: Abstract: A method that combines adaptive boosting (AdaBoost) algorithm with nonlinear characteristics of electroencephalogram (EEG) is proposed to estimate the depth of anesthesia. With 4 nonlinear features (KC complexity, wavelet entropy, permutation entropy and fuzzy entropy) extracted from EEG signals as input and bispectral index as reference output, the depth of anesthesia during the induction is divided into awake, mild anesthesia and moderate anesthesia. The proposed method is evaluated using the EEG signals of 9 patients during the induction of general anesthesia, and the results show that the method achieves an accuracy of 86.69% in classifying 3 different anesthetic states, with a Kappa coefficient of 0.837. The proposed method can better distinguish the depth of anesthesia during the induction, which provides a new idea for monitoring the depth of anesthesia.