Abstract

Info

Title:: Identification of adolescent schizophrenia based on EEG entropy features

Author(s):: LIAN Xiaoqin1; 2; WANG Zitong1; 2; GAO Chao1; 2; CAI Mohao1; 2; LI Jin1; 2; WU Yelan1; 2; 1. School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China 2. Key Laboratory of Industrial Internet and Big Data, China National Light Industry, Beijing Technology and Business University, Beijing 100048, China

Keywords:: Keywords: electroencephalogram signal adolescent schizophrenia entropy convolutional neural network

Abstract:: Abstract: An automated identification method for adolescent schizophrenia based on brain electroencephalogram (EEG) entropy features is proposed for further improving the diagnostic accuracy of adolescent schizophrenia. The raw EEG signals are decomposed into 5 commonly used rhythm bands: Delta, Theta, Alpha, Beta, and Gamma. The permutation entropy, fuzzy entropy, and sample entropy are extracted from each rhythm band and then organized into a feature matrix structured by electrode location×frequency band. Finally, an ECA-CNN model integrating efficient channel attention (ECA) and convolutional neural network (CNN) is constructed for feature classification and realizing the automated identification of adolescent schizophrenia. The results demonstrate that the proposed ECA-CNN model has higher recognition accuracy than the traditional machine learning models, achieving an accuracy of 99.08%, a sensitivity of 99.27%, a specificity of 98.85%, a precision of 99.01%, a F1 score of 99.14%, and a Kappa coefficient of 0.981 4. This study provides a new idea and method for the diagnosis of adolescent schizophrenia.