Abstract
Sleep staging is an important part of clinical neurology. However, it is still performed manually by technical experts and is labor-intensive and time-consuming. To overcome these obstacles in the manual sleep staging process, a large number of machine learning-based classifiers with hand-engineered features have been proposed. Additionally, combinations of a deep neural network (DNN) have been recently highlighted as the state-of-the-art classifiers in view of their effectiveness for automatic sleep staging. In spite of the existence of a large number of these types of classifiers, to-this-date, no prior DNN-based approach has attempted sleep-stage classification using pediatric electroencephalographic (EEG) signals. In this paper, we propose a novel end-to-end classifier based on a multi-domain hybrid neural network (HNN-multi) approach consisting of a convolutional neural network and bidirectional long short-term memory for automatic sleep staging with pediatric scalp EEG recordings. To find effective temporal, spatial, and domain-specific conditions, we investigated noticeable changes in the classification performance corresponding to: 1) the length of input signals; 2) the number of channels; and 3) the types of input signals in the time and frequency domains. Our HNN-based classifier yielded the best performance metrics using 30-s time series in combination with an instantaneous frequency using a 19-channel, three-stage classification, with overall accuracy, F1 score, and Cohen’s Kappa, equal to 92.21%, 0.90, and 0.88, respectively. We suggest that an effective combination of temporal and spatial time-domain clues with time-varying frequency domain information plays a pivotal role in pediatric, automatic sleep staging. Sufficiently reasonable performance of our HNN-based approach coping with the highly complicated pediatric EEG signatures hopefully sheds light on the clinical feasibility of the DNN-based automatic sleep staging for pediatric neurology.
Highlights
Sleep staging in electroencephalography (EEG) is an important initial step for the identification of vigilance andThe associate editor coordinating the review of this manuscript and approving it for publication was Yongqiang Cheng.subsequent analyses in the field of clinical neurology
Jiang et al [10] obtained statistical and nonlinear features from signal decomposition in the time and frequency domains with the empirical mode decomposition and bandpass filtering for five-stage classification based on the random forest (RF) approach followed by the hidden Markov model (HMM) with an accuracy > 89%
To handle the issue of the biased performance on machine learning-based models that resulted from the imbalanced dataset, we split our dataset based on a stratified sampling method [34]
Summary
Sleep staging in electroencephalography (EEG) is an important initial step for the identification of vigilance andThe associate editor coordinating the review of this manuscript and approving it for publication was Yongqiang Cheng.subsequent analyses in the field of clinical neurology. Electroencephalographers and neurologists perform the manual sleep staging with other EEG interpretation steps simultaneously, such as artifact rejection and feature recognition, for in-depth EEG analysis, which may hamper their efficiency by burdensome manual tasks. Chriskos et al [8] estimated functional connectivity including the synchronization likelihood and relative wavelet entropy in the time and frequency domains, respectively, for four-stage classification based on SVMs and k-nearest neighbors (kNNs), and achieved an accuracy > 90%. Memar and Faradji [11] extracted time domain statistical measures, nonlinear features, including the fractal dimension and entropy, and instantaneous phases from eight frequency subbands of EEG recordings and achieve an accuracies > 87% in six-stage classification based on the RF. Dimitriadis et al [15] proposed a phase-amplitude coupling, one of the cross-frequency coupling methods, for six-stage classification based
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.