Anesthesia Assessment Based on ICA Permutation Entropy Analysis of Two-Channel EEG Signals

Abstract

Inaccurate assessment may lead to inaccurate levels of dosage given to the patients that may lead to intraoperative awareness that is caused by under dosage during surgery or prolonged recovery in patients that is caused by over dosage after the surgery is done. Previous research and evidence show that assessing anesthetic levels with the help of electroencephalography (EEG) signals gives an overall better aspect of the patient's anesthetic state. This paper presents a new method to assess the depth of anesthesia (DoA) using Independent Component Analysis (ICA) and permutation entropy analysis. ICA is performed on two-channel EEG to reduce the noise then Wavelet and permutation entropy are applied on these channels to extract the features. A linear regression model was used to build the new DoA index using the selected features. The new index designed by proposed methods performs well under low signal quality and it was overall consistent in most of the cases where Bispectral index (BIS) may fail to provide any valid value.