Stavros I Dimitriadis1, Christos Salis2, David Linden3. 1. Division of Psychological Medicine and Clinical Neurosciences, School of Medicine, Cardiff University, Cardiff, United Kingdom; Cardiff University Brain Research Imaging Centre, School of Psychology, Cardiff University, Cardiff, United Kingdom; School of Psychology, Cardiff University, Cardiff, United Kingdom; Neuroinformatics Group, Cardiff University Brain Research Imaging Centre, School of Psychology, Cardiff University, Cardiff, United Kingdom; Neuroscience and Mental Health Research Institute, Cardiff University, Cardiff, United Kingdom. Electronic address: stidimitriadis@gmail.com. 2. University of Western Macedonia, Department of Informatics and Telecommunications Engineering, Kozani, Greece. 3. Division of Psychological Medicine and Clinical Neurosciences, School of Medicine, Cardiff University, Cardiff, United Kingdom; Cardiff University Brain Research Imaging Centre, School of Psychology, Cardiff University, Cardiff, United Kingdom; School of Psychology, Cardiff University, Cardiff, United Kingdom; Neuroscience and Mental Health Research Institute, Cardiff University, Cardiff, United Kingdom.
Abstract
OBJECTIVE: Limitations of the manual scoring of polysomnograms, which include data from electroencephalogram (EEG), electro-oculogram (EOG), electrocardiogram (ECG) and electromyogram (EMG) channels have long been recognized. Manual staging is resource intensive and time consuming, and thus considerable effort must be spent to ensure inter-rater reliability. As a result, there is a great interest in techniques based on signal processing and machine learning for a completely Automatic Sleep Stage Classification (ASSC). METHODS: In this paper, we present a single-EEG-sensor ASSC technique based on the dynamic reconfiguration of different aspects of cross-frequency coupling (CFC) estimated between predefined frequency pairs over 5 s epoch lengths. The proposed analytic scheme is demonstrated using the PhysioNet Sleep European Data Format (EDF) Database with repeat recordings from 20 healthy young adults. We validate our methodology in a second sleep dataset. RESULTS: We achieved very high classification sensitivity, specificity and accuracy of 96.2 ± 2.2%, 94.2 ± 2.3%, and 94.4 ± 2.2% across 20 folds, respectively, and also a high mean F1 score (92%, range 90-94%) when a multi-class Naive Bayes classifier was applied. High classification performance has been achieved also in the second sleep dataset. CONCLUSIONS: Our method outperformed the accuracy of previous studies not only on different datasets but also on the same database. SIGNIFICANCE: Single-sensor ASSC makes the entire methodology appropriate for longitudinal monitoring using wearable EEG in real-world and laboratory-oriented environments. Crown
OBJECTIVE: Limitations of the manual scoring of polysomnograms, which include data from electroencephalogram (EEG), electro-oculogram (EOG), electrocardiogram (ECG) and electromyogram (EMG) channels have long been recognized. Manual staging is resource intensive and time consuming, and thus considerable effort must be spent to ensure inter-rater reliability. As a result, there is a great interest in techniques based on signal processing and machine learning for a completely Automatic Sleep Stage Classification (ASSC). METHODS: In this paper, we present a single-EEG-sensor ASSC technique based on the dynamic reconfiguration of different aspects of cross-frequency coupling (CFC) estimated between predefined frequency pairs over 5 s epoch lengths. The proposed analytic scheme is demonstrated using the PhysioNet Sleep European Data Format (EDF) Database with repeat recordings from 20 healthy young adults. We validate our methodology in a second sleep dataset. RESULTS: We achieved very high classification sensitivity, specificity and accuracy of 96.2 ± 2.2%, 94.2 ± 2.3%, and 94.4 ± 2.2% across 20 folds, respectively, and also a high mean F1 score (92%, range 90-94%) when a multi-class Naive Bayes classifier was applied. High classification performance has been achieved also in the second sleep dataset. CONCLUSIONS: Our method outperformed the accuracy of previous studies not only on different datasets but also on the same database. SIGNIFICANCE: Single-sensor ASSC makes the entire methodology appropriate for longitudinal monitoring using wearable EEG in real-world and laboratory-oriented environments. Crown
Authors: Huy Phan; Fernando Andreotti; Navin Cooray; Oliver Y Chen; Maarten De Vos Journal: IEEE Trans Biomed Eng Date: 2018-10-22 Impact factor: 4.538
Authors: Tingting Li; Bofeng Zhang; Hehe Lv; Shengxiang Hu; Zhikang Xu; Yierxiati Tuergong Journal: Int J Environ Res Public Health Date: 2022-04-25 Impact factor: 3.390