Automatic sleep staging: A computer assisted approach for optimal combination of features and polysomnographic channels

• Published in: Expert systems with applications Vol. 40; no. 17; pp. 7046 - 7059
• Main Authors: Khalighi, Sirvan, Sousa, Teresa, Pires, Gabriel, Nunes, Urbano
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.12.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Automatic sleep staging; Biological and medical sciences; Channels; Computer science; control theory; systems; Data processing. List processing. Character string processing; EEC; Electrodiagnosis. Electric activity recording; Exact sciences and technology; Eye movements; Feature extraction; Features selection; Fundamental and applied biological sciences. Psychology; Invariants; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Memory organisation. Data processing; Nervous system; Patients; Pattern recognition. Digital image processing. Computational geometry; Polysomnographic signals; Sleep; Sleep dataset; Sleep. Vigilance; Software; Support vector machines; The maximum overlap discrete wavelet transform; Vertebrates: nervous system and sense organs; Wavelet transforms; Features selection; Sleep dataset; Automatic sleep staging; Polysomnographic signals; The maximum overlap discrete wavelet transform; Performance evaluation; Invariant; Histogram; Time frequency domain method; Expert; Electroencephalography; Overlap; Modeling; Eye movement; Vector support machine; Selection criterion; Electromyography; Hospital; Overlay; Pattern extraction; Frequency domain method; Pattern recognition; Discrete wavelet transforms; Polysomnography; Wake; Time domain method; Sleep; Wavelet transformation; Extreme value; Feature extraction; Automatic analysis
• DOI: 10.1016/j.eswa.2013.06.023
• ISSN: 0957-4174

•A subject-independent automatic sleep staging method with application in sleep–wake detection and in multiclass sleep staging.•An extensive dataset with 40 polysomnographic (PSG) recording.•A time–frequency based feature extraction method using maximum overlap discrete wavelet transform (MODWT).•A two-step feature selector to find the most discriminative features.•The best combinations of the PSG channels in sleep–wake detection and in multiclass sleep staging. To improve applicability of automatic sleep staging an efficient subject-independent method is proposed with application in sleep–wake detection and in multiclass sleep staging (awake, non-rapid eye movement (NREM) sleep and rapid eye movement (REM) sleep). In turn, NREM is further divided into three stages denoted here by N1, N2, and N3. To assess the method, polysomnographic (PSG) records of 40 patients from our ISRUC-Sleep dataset, which was scored by an expert clinician in the central hospital of Coimbra, are used. To find the best combination of PSG signals for automatic sleep staging, six electroencephalographic (EEG), two electrooculographic (EOG), and one electromyographic (EMG) channels are analyzed. An extensive set of feature extraction techniques are applied, covering temporal, frequency and time–frequency domains. The maximum overlap wavelet transform (MODWT), a shift invariant transform, was used to extract the features in time–frequency domain. The extracted feature set is transformed and normalized to reduce the effect of extreme values of features. The most discriminative features are selected through a two-step method composed by a manual selection step based on features’ histogram analysis followed by an automatic feature selector. The selected feature set is classified using support vector machines (SVMs). The system achieved the best performance by combining 6 channels (C3, C4, O1, left EOG (LOC), right EOG (ROC) and chin EMG (X1)) for sleep–wake detection, and 9 channels (C3, C4, O1, O2, F3, F4, LOC, ROC, X1) for multiclass sleep staging.