Neonatal EEG sleep stage classification based on deep learning and HMM

Abstract

Objective. Automatic sleep stage scoring is of great importance for investigating sleep architecture during infancy. In this work, we introduce a novel multichannel approach based on deep learning networks and hidden Markov models (HMM) to improve the accuracy of sleep stage classification in term neonates. Approach. The classification performance was evaluated on quiet sleep (QS) and active sleep (AS) stages, each with two sub-states, using multichannel EEG data recorded from sixteen neonates with postmenstrual age of 38–40 weeks. A comprehensive set of linear and nonlinear features were extracted from thirty-second EEG segments. The feature space dimensionality was then reduced by using an evolutionary feature selection method called MGCACO (Modified Graph Clustering Ant Colony Optimization) based on the relevance and redundancy analysis. A bi-directional long-short time memory (BiLSTM) network was trained for sleep stage classification. The number of channels was optimized using the sequential forward selection method to reduce the spatial space. Finally, an HMM-based postprocessing stage was used to reduce false positives by incorporating the knowledge of transition probabilities between stages into the classification process. The method performance was evaluated using the K-fold (KFCV) and leave-one-out cross-validation (LOOCV) strategies. Main results. Using six-bipolar channels, our method achieved a mean kappa and an overall accuracy of 0.71–0.76 and 78.9%–82.4% using the KFCV and LOOCV strategies, respectively. Significance. The presented automatic sleep stage scoring method can be used to study the neurodevelopmental process and to diagnose brain abnormalities in term neonates.

Modeling Neonatal EEG Using Multi-Output Gaussian Processes

“…Time-series features are feed onto an SVM classifier. [32] Sleep stages are classified using linear/non-linear EEG features fed into a BiLSTM network. The output of the net is post-processed using a hidden Markov model.…”

Supervised Classification with Short-Term Memory of Sleep Stages using Cardio-respiratory and Body Movement Variables

“…The accuracy of such methods is calculated compared to the full PSG method. For instance, accuracy from 74.10% to 92.04% are reached using only EEG features [31], [32], [33], [20], [26]. A 92.04% accuracy is obtained by Nakamura et al [34] in a study comprising 22 subjects using Support Vector Machine method.…”

Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions

“…It resembles how manual scoring is done by sleep experts who normally need to attend to a much larger context around a target epoch in order to determine its label [57]. From modelling perspective, this has commonly been accomplished by Hidden Markov Models (HMM) (see [58] for example) before the evolution of deep learning. However, the early works [6,18,38,56] came with some limitations.…”