Detection of Sleeping Pattern using EEG Signals with Deep Learning

The stop signal task has been used to quantify the human inhibitory control. The inter-subject and intra-subject variability was investigated under the inhibition of human response with a realistic environmental scenario. In present study, we used a battleground scenario where a sniper-scope picture was the background, a target picture was a go signal, and a nontarget picture was a stop signal. The task instructions were to respond on the target image and inhibit the response if a nontarget image appeared. This scenario produced a threatening situation and endorsed the evaluation of how subject’s response inhibition manifests in a real situation. In this study, 32 channels of electroencephalography (EEG) signals were collected from 20 participants during successful stop (response inhibition) and failed stop (response) trials. These EEG signals were used to predict two possible outcomes: successful stop or failed stop. The inter-subject variability (between-subjects) and intra-subject variability (within-subjects) affect the performance of participants in the classification system. The EEG signals of successful stop versus failed stop trials were classified using quadratic discriminant analysis (QDA) and linear discriminant analysis (LDA) (i.e., parametric) and K-nearest neighbor classifier (KNNC) and Parzen density-based (PARZEN) (i.e., nonparametric) under inter- and intra-subject variability. The EEG activities were found to increase during response inhibition in the frontal cortex (F3 and F4), presupplementary motor area (C3 and C4), parietal lobe (P3 and P4), and occipital (O1 and O2) lobe. Therefore, power spectral density (PSD) of EEG signals (1-50Hz) in F3, F4, C3, C4, P3, P4, O1, and O2 electrodes were measured in successful stop and failed stop trials. The PSD of the EEG signals was used as the feature input for the classifiers. Our proposed method shows an intra-subject classification accuracy of 97.61% for subject 15 with QDA classifier in C3 (left motor cortex) and an overall inter-subject classification accuracy of 71.66% ± 9.81% with the KNNC classifier in F3 (left frontal lobe). These results display how inter-subject and intra-subject variability affects the performance of the classification system. These findings can be used effectively to improve the psychopathology of attention deficit hyperactivity disorder (ADHD), obsessive-compulsive disorder (OCD), schizophrenia, and suicidality.

The significance of sleep in sustaining mental and physiological equilibrium, as well as the relationship between sleep disturbance and disease and death, has long been accepted in medicine. Deep Learning methods have provided State Of The Art performance in tackling numerous challenges in the medical arena since the advent of the domain of HealthTech. Polysomnography is a type of sleep study that uses electroen-cephalogram (EEG) measurements, among other parameters, to get a better picture of a patient’s sleep patterns. Various brain activity correspond to different stages of sleep. Monitoring and interpreting EEG signals and the body’s reactions to the changes in these cycles can help identify disruptions in sleep patterns. Successfully classified sleep patterns can in turn help medical professionals with the prognosis of several pervasive sleep related diseases like sleep apnea and seizures. To address the pitfalls associated with the traditional manual review of EEG signals that help classify sleep stages, in this work, several Convolutional Neural Networks were trained and analysed to classify the five phases od sleep (Wake, N1, N2, N3, N4 and REM by AASM’s standard) using data from raw, single channel EEG signals. With PhysioNet’s Sleep-EDF dataset, this comparative analysis of the performance of popular convolutional neural network architectures can serve as a benchmark to the problem of utilizing EEG data to classify sleep stages. The analysis shows that CNN based methods are adept at extracting and generalizing temporal information, making it suitable for classifying EEG based data.

Electrical field of the heart (ECG) propagates throughout the body and introduce artifact in EEG recordings which may lead to incorrect interpretation of monitoring result. Hence in this paper, we present a method of automatic detection and reduction of ECG artifact from EEG. ECG has its own spike like property and periodicity. Moreover, it also has lack of correlation with the EEG signal. We have utilized the aforementioned properties to detect ECG artifact in EEG and have employed a method to remove it automatically. In the first step of the algorithm, an energy function based method is used to emphasize the R-waves of contaminated ECG artifact and thereafter, an adaptive thresholding method along with clustering is used to detect contaminated candidate R-spikes of ECG artifact in EEG signal. After that utilizing periodic information of R-wave, a searching mechanism is employed as post processing to detect the R-peaks more accurately. Thereafter, noise model of ECG artifact contaminated with EEG is generated and finally it is subtracted from the EEG recordings to decontaminate it from the artifact. Before subtraction, a time varying alignment procedure is applied to increase the effectiveness of the artifact reduction method. Results obtained from our extensive experiments show that the proposed method is effective and encouraging in terms of automatic ECG artifact detection and reduction from EEG signal.

Sleep stage classification is important to accurately predict and diagnose patients with sleep disorders. Though various deep learning approaches have been implemented to classify sleep classes, these consist limitations that impact the accuracy and processing time of the classification model. The aim of this research is to enhance the accuracy and minimize the training time of the deep learning classification model. The proposed system consists of One Dimensional Convolutional Neural Network (CNN) with enhanced loss function to improve the accuracy of scoring of five different sleep classes. Preprocessing, Feature Extraction and Classification are the main components of the proposed system. Initially, EEG signals are fed to an adaptive filter for preprocessing, in order to remove any noise in signal. Thereafter, feature is extracted through multiple convolutional and pooling layers, and finally the classification is done by fully connected layer using softmax activation with enhanced loss function. The proposed solution is tested on data samples from multiple datasets with five classes of Sleep classification. Based on the obtained results, the proposed solution has found to achieve an accuracy of 96.26% which is almost 4.2% higher than the state-of-the-art solution which is 92.76%. Furthermore, the processing time has been reduced by 11 milliseconds against the state-of-the-art solution. The proposed system focused on classifying sleep stages in five classes using EEG signals with deep learning approach. It enhances the loss function in order to minimize errors in the prediction of sleep classes and improves the accuracy of the model. Furthermore, the training speed of the model has also been reduced by applying batch normalization techniques inside the model. In the future, larger datasets of different sleep disorder patients with varying features can be used for training and implementing the proposed solution. The datasets can also be pre-processed using additional techniques to refine the data before feeding to the neural network model.

Background/Objectives: Sleep stage analysis is considered to be the key factor for understanding and diagnosing various sleep disorders, as it provides insights into sleep quality and overall health. Methods: Traditional methods of sleep stage classification, such as manual scoring and basic machine learning approaches, often suffer from limitations including subjective biases, limited scalability, and inadequate accuracy. Existing deep learning models have improved the accuracy of sleep stage classification but still face challenges such as overfitting, computational inefficiencies, and difficulties in handling imbalanced datasets. To address these challenges, we propose the Sleep Stage Analysis with Multilayer Perceptron (SLA-MLP) model. Results: SLA-MLP leverages advanced deep learning techniques to enhance the classification of sleep stages from EEG signals. The key steps of this approach include data collection, where diverse and high-quality EEG data are gathered; preprocessing, which involves signal cropping, spectrogram conversion, and normalization to prepare the data for analysis; data balancing, where class weights are adjusted to address any imbalances in the dataset; feature extraction, utilizing Temporal Convolutional Networks (TCNs) to extract meaningful features from the EEG signals; and final classification, applying a Multilayer Perceptron (MLP) to accurately predict sleep stages. Conclusions: SLA-MLP demonstrates superior performance compared to traditional methods by effectively addressing the limitations of existing models. Its robust preprocessing techniques, advanced feature extraction, and adaptive data balancing strategies collectively contribute to obtaining more accurate results, having an accuracy of 97.23% for the S-DSI, 96.23 for the S-DSII and 97.23% for the S-DSIII dataset. This model offers a significant advancement in the field, providing a more precise tool for sleep research and clinical applications.

Human emotion is the mind's reaction to external stimuli. Since human emotions are dynamic and hard to predict in the real world, studies focusing on this area have gained a lot of importance. Emotion recognition using EEG(electroencephalogram) signals has recently seen prevalent use of many deep learning and machine learning techniques.In this paper, we have used a real time dataset which includes 15 subjects (7 Males and 8 Females) and their EEG signals are recorded using video stimuli. The real time data is preprocessed and features are extracted from the preprocessed data using different feature extraction methods. The accuracy and loss of model are calculated and compared with raw and preprocessed data. The proposed model - EEGEM (Electroencephalogram Ensemble Model) is compared with other machine and deep learning techniques. EEGEM is a ensemble model with the combination of LSTM and CNN together to achieve the desired output. The accuracy achieved using this model is 95.56% and it has outperformed other existing models.

Sleep disorders has a vital effect on mental depression and many other diseases of human body. Diagnosing the sleep disorder in an early curable stage may help to provide better treatment and save the life. The EEG (Electroencephalogram) signal is one of the most uses bio signal for capturing brain activities to detect and diagnosis the sleep disorders. Empirical mode decomposition (EMD) is an efficient time-frequency data analysis technique for diagnosing disease by analyzing EEG signal. However, it is a challenging issue to select the optimal intrinsic mode functions (IMFs) of Empirical mode decomposition (EMD) for extracting discriminant properties of EEG signals to diagnosis the sleep disorder. From this point of view, this paper presents a model to select optimal IMF of EMD for diagnosing the sleep disorder using EEG brain signal. In this proposed model, EMD is applied to decompose and analyze EEG signal for extracting biomarker/feature of sleep disorders. During the EMD decomposition process, different levels of IMF are extracted and features, i.e., Shannon Entropy, Spectral Entropy, Standard deviation, Skewness and Kurtosis are calculated from those IMFs for detecting the sleep disorders. In identification process, the multiclass support vector machine (MC-SVM) classification algorithm is used and sleep disorders are classified based on trained knowledge. Finally, the performance of proposed model is evaluated for different IMFs of EMD and find the optimal IMF for sleep disorder diagnosis. For evaluating the proposed model, a benchmark dataset including 4 types of data such as Apnea, REM, PLM and healthy subjects are used in experiment. According to the experimental result, the proposed model achieves the optimal classification performance for IMF 8, i.e., 93.24% average classification accuracy.

The Electroencephalogram (EEG) is one of the useful biosignals to detect the sleep disorders. This paper discusses on the changes in the electrical activity of the human brain related to distinct sleep disorders. The EEG data has been collected from PhysioNet database. The purpose of the research is to detect the different human sleep disorders through Electroencephalogram (EEG) signal with time-frequency analysis by receiving information from the internal changes of brain state. The paper presents the detection of sleep disorders based on some salient features of EEG signal. For this purpose seven different disorders have been specified such as sleep breathing disorder, rapid eye movement behavior disorder, periodic leg movement disorder, insomnia disorder, narcolepsy disorder, nocturnal frontal lobe epilepsy disorder, bruxism disorder and with them one healthy subject. Several EEG records have been collected for these sleep disorders and analyzed using discrete wavelet transform. The discrete wavelet transform (DWT) is used to extract different significant features from the analyzed signal by computing the subband coefficients and evaluating statistical measures like energy, variance, waveform length and standard deviation which are used to detect different sleep disorders.

Objective To investigate the effect of sleep quality on glycemic control and relevant factors involved in subjects with type 2 diabetic mellitus(T2DM). Methods A total of 200 inpatients with T2DM were enrolled in this study. Each patient completed Pittsburg Sleep Quality Index (PSQI) questionnaire. The glycemic control target was <7%. All patients were evaluated by Zung Self-rating Depression Scale (SDS) for the mental status, the score of SDS ≥50 was defined as a depressive state. Patients were divided into two groups: non-sleep disorder group (n=88) and sleep disorder group (n=112) according to PSQI score ≥7 which was defined as the sleep disorder. The clinical characteristics of two groups were compared and analyzed. Results The incidence of sleep disorder was 56% in the overall population. In the sleep disorders group, Age, hemoglobin A, glycosylated (HbA1c), fasting plasma glucose, 0.5-hour as well as 2-hour postprandial plasma glucose, fasting serum total cholesterol, triglycerides, the score of SDS and the incidence of depression were significantly greater (t=-19.49--1.99, χ2=9.931, all P<0.05), whereas fasting C-peptide, 0.5-hour postprandial C-peptide and body mass index (BMI) were significantly lower (t=2.07, 2.14, 2.35, all P<0.05) than those of the non-sleep disorder group. Glycemic control target rate of PSQI<5 group, PSQI≥5 to 7 group, PSQI ≥7 to 9 group and PSQI≥9 group was 27.9%, 19.6%, 10.0% and 8.6%, respectively. Patients with a higher score of PSQI were less likely to reach glycemic targets (P< 0.05). Multiple logistic regression analysis indicated that sleep disorders was positively correlated with increased age, male, HbA1c and depression, however, sleep disorders was negatively related to BMI (OR=1.04, 2.38, 2.98, 2.14, 0.89, respectively, all P<0.05). There was a positive association between sleep disorders, 2-hour postprandial plasma glucose and HbA1c≥7%, however, HbA1c≥7% was inversely associated with insulin therapy (OR=2.81, 1.21, 0.33, all P<0.05). Conclusion Sleep disorders are prevalent in patients with T2DM. Hyperglycemia and sleep disorders interact with each other. Sleep disorders probably cause psychological health problems. Management of sleep quality and glucose control in patients with T2DM should be an effective approach for sleep and higher glycemic control target rate. Key words: Diabetic mellitus, type 2; Sleep quality; Hemoglobin A, glycosylated

Electroencephalography (EEG) is used in the diagnosis, monitoring, and prognostication of many neurological ailments including seizure, coma, sleep disorders, brain injury, and behavioral abnormalities. One of the primary challenges of EEG data is its sensitivity to a breadth of non-stationary noises caused by physiological-, movement-, and equipment-related artifacts. Existing solutions to artifact detection are deficient because they require experts to manually explore and annotate data for artifact segments. Existing solutions to artifact correction or removal are deficient because they assume that the incidence and specific characteristics of artifacts are similar across both subjects and tasks (i.e., “one-size-fits-all”). In this paper, we describe a novel EEG noise-reduction method that uses representation learning to perform patient- and task-specific artifact detection and correction. More specifically, our method extracts 58 clinically relevant features and applies an ensemble of unsupervised outlier detection algorithms to identify EEG artifacts that are unique to a given task and subject. The artifact segments are then passed to a deep encoder-decoder network for unsupervised artifact correction. We compared the performance of classification models trained with and without our method and observed a 10% relative improvement in performance when using our approach. Our method provides a flexible end-to-end unsupervised framework that can be applied to novel EEG data without the need for expert supervision and can be used for a variety of clinical decision tasks, including coma prognostication and degenerative illness detection. By making our method, code, and data publicly available, our work provides a tool that is of both immediate practical utility and may also serve as an important foundation for future efforts in this domain.

Diagnosis of sleep disorders in optimized time slot based machine learning techniques on EEG energy level patterns

Objective To investigate sleep quality of hospitalized type 2 diabetes mellitus(T2DM) patients, and evaluate relationship of sleep quality and metabolic indexes, resting energy expenditure and body composition. Method Three hundred hospitalized T2DM patients were included and Pittsburgh Sleep Quality Index(PSQI) questionnaire was used to evaluate their subjective sleep characteristics. Their general clinical data and biochemical indexes (including blood lipid, glucose, glycosylated hemoglobin (HbA1c) etc.) were collected and steamed bun test was carried out to get the secretion information of insulin and C-peptide in patients at 0 and 120 minutes, and then resting energy expenditure and body composition were measured. Patients with PSQI total scores ≥8 were classified as the sleep-disordered group, others were classified as normal sleep group. Independent samplet test and Independent- samples Mann- Whitney test were used to analyze normal and abnormal distribution measurement data respectively. Chi-squared test was used to analyze enumeration data. The influence factors of sleep disorder were analyzed by multivariate logistic regression analysis. Results 39.7% (119/300) hospitalized T2DM patients had sleeping disorder. Patients in T2DM sleep- disordered group had a female predominance (χ2=10.10,P<0.05) , higher level of HbA1c (8.85% (7.50,10.50)% vs 8.00% (7.10,10.00)% ,Z=- 2.301,P<0.05) and lower resting energy expenditure (Z=- 3.722,P<0.05). Body fat composition analysis showed that patients in sleep- disordered group had lower muscle mass((45±8) vs (49±9) kg,t=-4.066,P<0.05) and lower skeletal muscle mass(t=- 4.083, P<0.05). Besides, in sleep-disordered group, patients had higher proportions of stroke(χ2=4.538, P< 0.05), and usage of statin drugs(73.1% vs 60%, χ2=4.948, P<0.05). Logistic regression analysis showed that HbA1c(OR 1.13, 95%CI 0.999- 1.279,P=0.053), usage of statin drugs (OR 1.75, 95%CI 0.957- 3.203,P= 0.069) and muscle mass (OR 0.956, 95%CI 0.927- 0.986,P=0.005) were related with sleep disorder. Conclusion Female T2DM Patients with stroke or with using of statin drugs are more likely to have sleep disorder. For T2DM patients with above risk factors, more interventions of sleep may make better sleep quality and taking more exercises may bring better glycemic control. Key words: Diabetes mellitus ,type 2; Sleep quality, body composition

Objective To explore the mediating effect of anxiety in perimenopausal women between sleep disturbance and life quality. Methods A total of 516 perimenopmenopausal women in Shenyang, Liaoning province and Jinzhou city were investigated using the Pittsburgh sleep quality index(PSQI), the self-rating anxiety scale(SAS) and the WHO quality of life(WHOQOL-BREF). Results The scores of sleep disorder, anxiety and quality of life were (14.31±2.75), (49.94±9.58) and (54.02±4.50) in perimenopausal women.There was a positive correlation between anxiety and sleep disorder (r=8.32, P<0.01), and a negative correlation between anxiety, sleep disorder and quality of life (r=-5.37, -5.62, P<0.01). Anxiety had a mediating effect between sleep disorders and quality of life.The intermediate effect value was -0.201, accounting for 32.4%. Conclusion Anxiety has some mediating effects between sleep disorders and quality of life in perimenopausal women, and regulating anxiety can relieve sleep disorders and reduce their impact on quality of life. Key words: Perimenopause; Sleep disorders; Quality of life; Anxiety; Mediating effect

The topic 'Emerging Talents in Sleep Disorders' is dedicated to highlighting students and early career researchers within the field of sleep disorders. They are bringing exciting new ideas to the field. However, many of these ideas are not communicated to a broader audience. We recognize that this is because many students and early career researchers may lack a platform to share their ideas. This topic gives an opportunity to succeed with their manuscripts.Chen Tien-Yu et al., reported the prevalence and effects of sleep-disordered breathing on middle-aged patients with sedative-free generalized anxiety disorder ( https://doi.org/10.3389/fpsyt.2022.1067437 ). Generalized anxiety disorder (GAD) and sleepdisordered breathing (SDB) share similar symptoms, such as poor sleep quality, irritability, and poor concentration during daily activities. This study investigates the proportion of undiagnosed SDB and its impacts on anxiety severity and autonomic function in newly diagnosed, sedativefree GAD patients. They found that an average age 55 years and mean BMI 23 kg/m2 patients with GAD and matched controls had an undiagnosed SDB prevalence of approximately 50%. Also noticed that SDB correlated with worsening anxiety severity and reduced cardiac autonomic function. Importantly, age and BMI were major risk factors for predicting undiagnosed SDB. Nakajima S et al described the transdiagnostic association between subjective insomnia and depressive symptoms in major psychiatric disorders (https://doi.org/10.3389/fpsyt.2023.1114945). Comorbid depressive symptoms are associated with clinically important issues such as reduced quality of life, a poor prognosis, and increased suicide risk. This study investigated whether the association between insomnia and depressive symptoms is also found in other psychiatric disorders. In schizophrenia, a relation between depressive symptoms and insomnia was also found by objective sleep assessment methods using sleep EEG. Their results suggest that the association between subjective insomnia and depressive symptoms is a transdiagnostic feature in major psychiatric disorders.Ding Q et al examined validation of a portable monitor compared with polysomnography for screening of obstructive sleep apnea in polio survivors (https://doi.org/10.3389/fneur.2023.1137535). Sleep-disordered breathing (SDB) is highly prevalent in polio survivors. Obstructive sleep apnea (OSA) is the most frequent type. Full polysomnography (PSG) is recommended for OSA diagnosis in patients with comorbidities by current practice guidelines, but it is not always accessible. They studied whether type 3 portable monitor (PM) or type 4 PM might be a viable alternative to PSG for the diagnosis of OSA in post-polio subjects. The insightful study showed Type 3 PM and Type 4 PM could be alternative ways to screen OSA for polio survivors, especially for moderate to severe OSA. Sun J et al reviewed Global research on cancer and sleep: a bibliometric and visual analysis of the last two decades (https://doi.org/10.3389/fneur.2023.1139746). This systemic review analyzed the research status, hotspots, and frontiers of global research on cancer and sleep through bibliometrics and provided references and guidance for future research. Cancer and sleep disruption and the influencing factors of sleep quality is an emerging topic. This study systematically analyzed the hotspots and frontiers in the field of cancer and sleep research. The authors named multiple foal topics for further research studies such as, intervention measures for the cancer symptom cluster, the bioavailability of exogenous melatonin, the relationship between OSA and cancer, the mechanism of tumor-induced sleep disruption, the dose-response relationship between sleep duration and cancer risk.Sleep problems are a growing public health concern worldwide. The 2023 Sleep in America poll conducted by the National Sleep Foundation showed that almost 65% of adults who are dissatisfied with their sleep have mild or severe depressive symptoms (1). The International Classification of Sleep Disorders by American Academy of Sleep Medicine lists 60 specific sleep disorders, the most common of which are insomnia, sleep apnea, restless legs syndrome, and narcolepsy (2).The close association between altered sleep pattern and diseases makes sleep a valuable diagnostic biomarker for non-invasive early diagnosis of some diseases. As sleep disorders increase with age and age is considered one of the major predictors of morbidity and mortality. Despite the diverse nature of sleep disorders, they have far-reaching, detrimental effects on population health and increase both morbidity and mortality of various chronic diseases (3). The chronic effects of sleep disorders deserve more attention from doctors, researchers, and society. As well as a better understanding of the mechanisms of sleep, new approaches to diagnose and treat sleep disorders are urgently needed. The editorial team thanks reviewers for their constructive criticism.

The Impact of Sleep Fragmentation on Sleep Homeostasis, Brain and Peripheral Energy Metabolism and Spatial Learning