Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network

Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features to investigate the brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthesia studies. In this paper, we propose a novel method based on Long Short-Term Memory (LSTM) and sparse denoising auto-encoder (SDAE) to combine the hybrid features of EEG to monitor the DoA. The EEG signals were preprocessed using wavelet transform, filtering etc.. For the later more than ten features including sample entropy, permutation entropy, spectral and alpha-ratio are extracted from EEG signal and we integrated the optional features such as permutation entropy and alpha-ratio to extract the essential structure and learn the efficient temporal model for monitoring the DoA. Compared with single feature and hybrid features with LSTM, our proposed model could accurately estimate the depth of anesthesia with higher prediction probability (Pₖ). The experimental results evaluated on the open access datasets demonstrated that our proposed method provided better performance than the methods using permutation entropy, alpha-ratio,LSTM and other traditional indices.