Effective sleep analysis is hampered by the lack of automated tools catering to disordered sleep patterns and cumbersome monitoring hardware. In this paper, we apply deep learning on a set of 57 EEG features extracted from a maximum of two EEG channels to accurately differentiate between patients with insomnia or controls with no sleep complaints. We investigated two different approaches to achieve this. The first approach used EEG data from the whole sleep recording irrespective of the sleep stage (stage-independent classification), while the second used only EEG data from insomnia-impacted specific sleep stages (stage-dependent classification). We trained and tested our system using both healthy and disordered sleep collected from 41 controls and 42 primary insomnia patients. When compared with manual assessments, an NREM + REM based classifier had an overall discrimination accuracy of 92% and 86% between two groups using both two and one EEG channels, respectively. These results demonstrate that deep learning can be used to assist in the diagnosis of sleep disorders such as insomnia.
Tools used by clinicians to diagnose and treat insomnia typically include sleep diaries and questionnaires. Overnight polysomnography (PSG) recordings are used when the initial diagnosis is uncertain due to the presence of other sleep disorders or when the treatment, either behavioral or pharmacologic, is unsuccessful. However, the analysis and the scoring of PSG data are time-consuming. To simplify the diagnosis process, in this paper we have proposed an efficient insomnia detection algorithm based on a central single electroencephalographic (EEG) channel (C3) using only deep sleep. We also analyzed several spectral and statistical EEG features of good sleeper controls and subjects suffering from insomnia in different sleep stages to identify the features that offered the best discrimination between the two groups. Our proposed algorithm was evaluated using EEG recordings from 19 patients diagnosed with primary insomnia (11 females, 8 males) and 16 matched control subjects (11 females, 5 males). The sensitivity of our algorithm is 92%, the specificity is 89.9%, the Cohen's kappa is 0.81 and the agreement is 91%, indicating the effectiveness of our proposed method.
In this work, we present a k-means classifier using Hjorth parameters extracted from the central electroencephalogram (EEG) signals to accurately detect insomnia. To develop and test our classifier we used data from thirty six subjects: 18 patients diagnosed with primary insomnia (10 females, 8 males) and 18 controls (10 females, 8 males). The main findings of our work can be summarized as follows: 1) the Hjorth parameters, particularly the mobility and the complexity, accurately quantify the differences between the EEG sleep from insomnia patients and controls; 2) these differences can be observed across both C3 and C4 central channels; and 3) a kmeans classifier based on Hjorth parameters extracted from the C3 channel is able to accurately detect epochs from insomnia patients with a Cohen's Kappa of 0.83, sensitivity of 91.9% and specificity of 91%.
Studies have shown that patients suffering from sleep deprivation have a risk for hypertension, diabetes and depression that is higher than normal sleepers. Treatment for all these problems requires accurate analysis of the sleep stages and patterns in the polysomnographic signals collected in overnight recording over several months. However, manual sleep staging is a repetitive and time-consuming process as marking one typical eight hours overnight polysomnographic recording can take up to two hours to complete. Due to increased processing capabilities, it is now possible to automate this process and assist the sleep expert. A large number of algorithms have been proposed during the last few decades. This review article presents an overview of the existing automatic sleep staging methods, discusses the different challenges and proposes future prospects for new research opportunities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.