Electroencephalography (EEG) Based Neonatal Sleep Staging and Detection Using Various Classification Algorithms

作     者：Hafza Ayesha Siddiqa Muhammad Irfan Saadullah Farooq Abbasi Wei Chen 

作者机构：Center for Intelligent Medical ElectronicsDepartment of Electronic EngineeringFudan UniversityShanghai200433China Department of Biomedical EngineeringRiphah International UniversityIslamabad45320Pakistan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第77卷第11期

页      面：1759-1778页

核心收录：

学科分类：1002[医学-临床医学] 100204[医学-神经病学] 10[医学] 

基　　金：Funding Statement: This research work is funded by Chinese Government Scholarship. The findings and conclusions of this article are solely the responsibility of the authors and do not represent the official views of the Chinese Government Scholarship 

主　　题：AutoML Random Forest adaboost EEG neonates PSG hyperparameter tuning sleep-wake classification 

摘      要：Automatic sleep staging of neonates is essential for monitoring their brain development and maturity of the nervous *** based neonatal sleep staging provides valuable information about an infant’s growth and health,but is challenging due to the unique characteristics of EEG and lack of standardized *** study aims to develop and compare 18 machine learning models using Automated Machine Learning(autoML)technique for accurate and reliable multi-channel EEG-based neonatal sleep-wake *** study investigates autoML feasibility without extensive manual selection of features or hyperparameter *** data is obtained from neonates at post-menstrual age 37±05 weeks.352530-s EEG segments from 19 infants are used to train and test the proposed *** are twelve time and frequency domain features extracted from each *** model receives the common features of nine channels as an input vector of size *** model’s performance was evaluated based on a variety of evaluation *** maximum mean accuracy of 84.78%and kappa of 69.63%has been obtained by the AutoML-based Random Forest *** is the highest accuracy for EEG-based sleep-wake classification,until ***,for the AutoML-based Adaboost Random Forest model,accuracy and kappa were 84.59%and 69.24%,*** performance achieved in the proposed autoML-based approach can facilitate early identification and treatment of sleep-related issues in neonates.