Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals

• Published in: Computers in biology and medicine Vol. 106; pp. 71 - 81
• Main Authors: Michielli, Nicola, Acharya, U. Rajendra, Molinari, Filippo
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2019; Elsevier Limited
• Subjects: Adult; Algorithms; Classification; Cognition; Cognitive ability; Drowsiness; EEG; EEG signals; Electroencephalography; Event-related potentials; Eye movements; Feature extraction; Female; Human performance; Humans; Internal Medicine; Long short-term memory; Male; Neural networks; Neural Networks, Computer; Neurocognitive performance; NREM sleep; Other; Principal components analysis; Protocol (computers); Recurrent neural networks; REM sleep; Signal Processing, Computer-Assisted; Sleep; Sleep analysis; Sleep and wakefulness; Sleep deprivation; Sleep Stages - physiology; Wakefulness; Long short-term memory; Recurrent neural networks; Sleep analysis; EEG signals; Neurocognitive performance
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.01.013

Automated evaluation of a subject's neurocognitive performance (NCP) is a relevant topic in neurological and clinical studies. NCP represents the mental/cognitive human capacity in performing a specific task. It is difficult to develop the study protocols as the subject's NCP changes in a known predictable way. Sleep is time-varying NCP and can be used to develop novel NCP techniques. Accurate analysis and interpretation of human sleep electroencephalographic (EEG) signals is needed for proper NCP assessment. In addition, sleep deprivation may cause prominent cognitive risks in performing many common activities such as driving or controlling a generic device; therefore, sleep scoring is a crucial part of the process. In the sleep cycle, the first stage of non-rapid eye movement (NREM) sleep or stage N1 is the transition between wakefulness and drowsiness and becomes relevant for the study of NCP. In this study, a novel cascaded recurrent neural network (RNN) architecture based on long short-term memory (LSTM) blocks, is proposed for the automated scoring of sleep stages using EEG signals derived from a single-channel. Fifty-five time and frequency-domain features were extracted from the EEG signals and fed to feature reduction algorithms to select the most relevant ones. The selected features constituted as the inputs to the LSTM networks. The cascaded architecture is composed of two LSTM RNNs: the first network performed 4-class classification (i.e. the five sleep stages with the merging of stages N1 and REM into a single stage) with a classification rate of 90.8%, and the second one obtained a recognition performance of 83.6% for 2-class classification (i.e. N1 vs REM). The overall percentage of correct classification for five sleep stages is found to be 86.7%. The objective of this work is to improve classification performance in sleep stage N1, as a first step of NCP assessment, and at the same time obtain satisfactory classification results in the other sleep stages. •A novel cascaded RNN architecture with LSTM blocks is proposed for the automated scoring of sleep stages.•A single-channel EEG based automated system.•Use of a publicly available sleep-EDF database.•The method outperforms the state-of-the-art methods in the N1 stage detection.•A first step forward to automated assessment of neurocognitive performance.