Comparison of automated deep neural network against manual sleep stage scoring in clinical data.

OBJECTIVE: To compare the accuracy and generalizability of an automated deep neural network and the Philip Sleepware G3™ Somnolyzer system (Somnolyzer) for sleep stage scoring using American Academy of Sleep Medicine (AASM) guidelines. METHODS: Sleep recordings from 104 participants were analyzed by a convolutional neural network (CNN), the Somnolyzer and skillful technicians. Evaluation metrics were derived for different combinations of sleep stages. A further comparison between the Somnolyzer and the CNN model using a single-channel signal as input was also performed. Sleep recordings from 263 participants with a lower prevalence of OSA served as a cross-validation dataset to validate the generalizability of the CNN model. RESULTS: The overall agreement between automated and manual scoring for sleep staging in 104 participants outperformed that of the Somnolyzer according to various metrics (accuracy: 81.81 % vs. 77.07 %; F1: 76.36 % vs. 73.80 %; Cohen's kappa: 0.7403 vs. 0.6848). The results showed that the left electrooculography (EOG) single-channel model had minor advantages over the Somnolyzer. In terms of consistency with manual sleep staging, the CNN model demonstrated superior performance in identifying more pronounced sleep transitions, particularly in the N2 stage and sleep latency metrics. Conversely, the Somnolyzer showed enhanced proficiency in the analysis of REM stages, notably in measuring REM latency. The accuracy in the cross-validation set of 263 participants was also above 80 %. CONCLUSIONS: The CNN-based automated deep neural network outperformed the Somnolyzer and is sufficiently accurate for sleep study analyses using the AASM classification criteria.

Effects of gender and age on sleep EEG functional connectivity differences in subjects with mild difficulty falling asleep.

Introduction: Difficulty falling asleep place an increasing burden on society. EEG-based sleep staging is fundamental to the diagnosis of sleep disorder, and the selection of features for each sleep stage is a key step in the sleep analysis. However, the differences of sleep EEG features in gender and age are not clear enough. Methods: This study aimed to investigate the effects of age and gender on sleep EEG functional connectivity through statistical analysis of brain functional connectivity and machine learning validation. The two-overnight sleep EEG data of 78 subjects with mild difficulty falling asleep were categorized into five sleep stages using markers and segments from the "sleep-EDF" public database. First, the 78 subjects were finely grouped, and the mutual information of the six sleep EEG rhythms of δ, θ, α, ß, spindle, and sawtooth wave was extracted as a functional connectivity measure. Then, one-way analysis of variance (ANOVA) was used to extract significant differences in functional connectivity of sleep rhythm waves across sleep stages with respect to age and gender. Finally, machine learning algorithms were used to investigate the effects of fine grouping of age and gender on sleep staging. Results and discussion: The results showed that: (1) The functional connectivity of each sleep rhythm wave differed significantly across sleep stages, with delta and beta functional connectivity differing significantly across sleep stages. (2) Significant differences in functional connections among young and middle-aged groups, and among young and elderly groups, but no significant difference between middle-aged and elderly groups. (3) Female functional connectivity strength is generally higher than male at the high-frequency band of EEG, but no significant difference in the low-frequency. (4) Finer group divisions based on gender and age can indeed improve the accuracy of sleep staging, with an increase of about 3.58% by using the random forest algorithm. Our results further reveal the electrophysiological neural mechanisms of each sleep stage, and find that sleep functional connectivity differs significantly in both gender and age, providing valuable theoretical guidance for the establishment of automated sleep stage models.

Surge of Sympathetic Activity during Hyperventilation at the End of Apnea for Patients with Obstructive Sleep Apnea.

Background and Objectives: The mechanisms connecting obstructive sleep apnea (OSA) and cardiovascular disease are multifactorial, involving intermittent hypoxia, hypercapnia, and sympathetic activation. The aim of this study was to explore the oscillations of sympathetic activity during the sleep apnea episodes throughout the entire night in patients with OSA. Materials and Methods: The participants received whole-night polysomnography (PSG), and electrocardiogram (EKG) data from the PSG were collected for heart rate variability (HRV) analysis. HRV measurements were conducted in the time and frequency domains. The root mean square of successive differences between normal heartbeats (RMSSD), which reflects parasympathetic activity, and the ratio of the absolute power of the low-frequency band (0.04-0.15 Hz) to the absolute power of the high-frequency band (0.015-0.4 Hz) (LF/HF ratio), which indicates sympathetic activity, were computed. Results: A total of 43 participants (35 men and 8 women) were included in the analysis. The mean age of the participants was 44.1 ± 11.3 years old, and the mean BMI was 28.6 ± 5.4 kg/m2. The sleep apnea episodes throughout the entire night in patients with OSA were selected randomly and occurred most frequently during the non-REM stages (39, 90.7%). The selected sleep apnea episodes typically exhibited multiple apneas, often interrupted by snoring respiration and followed by hyperventilation at the end of the episode (HE). Our findings indicate that the centers of the 5 min HRV window for the lowest and highest LF/HF ratios, at 111.8 ± 88.2 and 117.4 ± 88.6 min after sleep onset, respectively, showed a statistically significant difference (p < 0.001). Similarly, the ratios of the lowest and highest LF/HF, at 0.82 ± 0.56 and 3.53 ± 2.94, respectively, exhibited a statistically significant difference (p < 0.001). Conclusions: In the current study, the selected sleep apnea episodes throughout the entire night in patients with OSA occurred primarily during the non-REM stages. Additionally, we observed that sympathetic activity reached its peak in the window that includes hyperventilation at the end stage of apnea, potentially posing a cardiovascular risk. However, additional studies are needed to validate these results.

Combining a wireless radar sleep monitoring device with deep machine learning techniques to assess obstructive sleep apnea severity.

STUDY OBJECTIVES: The gold standard for diagnosing obstructive sleep apnea (OSA) is polysomnography (PSG). However, PSG is a time-consuming method with clinical limitations. This study aimed to create a wireless radar framework to screen the likelihood of 2 levels of OSA severity (ie, moderate-to-severe and severe OSA) in accordance with clinical practice standards. METHODS: We conducted a prospective, simultaneous study using a wireless radar system and PSG in a Northern Taiwan sleep center, involving 196 patients. The wireless radar sleep monitor, incorporating hybrid models such as deep neural decision trees, estimated the respiratory disturbance index relative to the total sleep time established by PSG (RDIPSG_TST), by analyzing continuous-wave signals indicative of breathing patterns. Analyses were performed to examine the correlation and agreement between the RDIPSG_TST and apnea-hypopnea index, results obtained through PSG. Cut-off thresholds for RDIPSG_TST were determined using Youden's index, and multiclass classification was performed, after which the results were compared. RESULTS: A strong correlation (ρ = 0.91) and agreement (average difference of 0.59 events/h) between apnea-hypopnea index and RDIPSG_TST were identified. In terms of the agreement between the 2 devices, the average difference between PSG-based apnea-hypopnea index and radar-based RDIPSG_TST was 0.59 events/h, and 187 out of 196 cases (95.41%) fell within the 95% confidence interval of differences. A moderate-to-severe OSA model achieved an accuracy of 90.3% (cut-off threshold for RDIPSG_TST: 19.2 events/h). A severe OSA model achieved an accuracy of 92.4% (cut-off threshold for RDIPSG_TST: 28.86 events/h). The mean accuracy of multiclass classification performance using these cut-off thresholds was 83.7%. CONCLUSIONS: The wireless-radar-based sleep monitoring device, with cut-off thresholds, can provide rapid OSA screening with acceptable accuracy and also alleviate the burden on PSG capacity. However, to independently apply this framework, the function of determining the radar-based total sleep time requires further optimizations and verification in future work. CITATION: Lin S-Y, Tsai C-Y, Majumdar A, et al. Combining a wireless radar sleep monitoring device with deep machine learning techniques to assess obstructive sleep apnea severity. J Clin Sleep Med. 2024;20(8):1267-1277.

Childhood maltreatment and sleep apnea: Findings from a cross-sectional general population study.

OBJECTIVE: Cumulative evidence indicates that childhood maltreatment (CM) is associated with sleep disturbances possibly suggesting sleep apnea. However, the relation between CM and objective measures of sleep apnea as determined by polysomnography (PSG) has not yet been assessed. METHODS: Using a cross-sectional design and based on PSG measurements from N = 962 subjects from the SHIP-Trend general population study, we used linear regression models to investigate the relationship between apnea-hypopnea (AHI) and oxygen desaturation index (ODI) and Epworth sleepiness scale (ESS) metrics and the Childhood Trauma Questionnaire (CTQ). All significant models were additionally adjusted for obesity, depression, metabolic syndrome, risky health behaviors, and socioeconomic factors. RESULTS: While both AHI and ESS were positively associated with the CTQ sum score, ODI was not. Investigating the CTQ subscales, ESS was associated with emotional abuse and emotional neglect; AHI was associated with physical and sexual abuse as well as physical neglect. For both the sum score and the subscales of the CTQ, ESS effects were partially mediated by depressive symptoms, while AHI effects were mediated by obesity, risky health behaviors, and metabolic syndrome. CONCLUSION: The findings of this general population study suggest an association between CM, particularly physical neglect, and objective as well as subjective indicators of sleep apnea, which were partially mediated by depressive symptoms and obesity.

Comparative analysis of sleep parameters and structures derived from wearable flexible electrode sleep patches and polysomnography in young adults.

Polysomnography (PSG) is the gold standard for clinical sleep monitoring, but its cost, discomfort, and limited suitability for continuous use present challenges. The flexible electrode sleep patch (FESP) emerges as an economically viable and patient-friendly solution, offering lightweight, simple operation, and self-applicable. Nevertheless, its utilization in young individuals remains uncertain. The objective of this study was to compare sleep data obtained by FESP and PSG in healthy young individuals and analyze agreement for sleep parameters and structure classification. Overnight monitoring with FESP and PSG recordings in 48 participants (mean age: 23 yr) was done. Correlation analysis, Bland-Altman plots, and Cohen's kappa coefficient assessed consistency. Sensitivity, specificity, and predictive values compared classification against PSG. FESP showed strong correlation and consistency with PSG for sleep monitoring. Bland-Altman plots indicated small errors and high consistency. Kappa values (0.70-0.84) suggested substantial agreement for sleep stage classification. Pearson correlation coefficient values for sleep stages (0.75-0.88) and sleep parameters (0.80-0.96) confirm that FESP has a strong application. Intraclass correlation coefficient yielded values between 0.65 and 0.97. In addition, FESP demonstrated an impressive accuracy range of 84.12-93.47% for sleep stage classification. The FESP also features a wearable self-test program with an error rate of no more than 8% for both deep sleep and wake. In young adults, FESP demonstrated reliable monitoring capabilities comparable to PSG. With its low cost and user-friendly design, FESP is a potential alternative for portable sleep assessment in clinical and research applications. Further studies involving larger populations are needed to validate its diagnostic potential.NEW & NOTEWORTHY By comparison with PSG, this study confirmed the reliability of an efficient, objective, low-cost, and noninvasive portable automatic sleep-monitoring device FESP, which provides effective information for long-term family sleep disorder diagnosis and sleep quality monitoring.

Performance of the Dreem 2 EEG headband, relative to polysomnography, for assessing sleep in Parkinson's disease.

GOAL AND AIMS: To pilot the feasibility and evaluate the performance of an EEG wearable for measuring sleep in individuals with Parkinson's disease. FOCUS TECHNOLOGY: Dreem Headband, Version 2. REFERENCE TECHNOLOGY: Polysomnography. SAMPLE: Ten individuals with Parkinson's disease. DESIGN: Individuals wore Dreem Headband during a single night of polysomnography. CORE ANALYTICS: Comparison of summary metrics, bias, and epoch-by-epoch analysis. ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES: Correlation of summary metrics with demographic and Parkinson's disease characteristics. CORE OUTCOMES: Summary statistics showed Dreem Headband overestimated several sleep metrics, including total sleep, efficiency, deep sleep, and rapid eye movement sleep, with an exception in light sleep. Epoch-by-epoch analysis showed greater specificity than sensitivity, with adequate accuracy across sleep stages (0.55-0.82). IMPORTANT SUPPLEMENTAL OUTCOMES: Greater Parkinson's disease duration and rapid eye movement behavior were associated with more wakefulness, and worse Parkinson's disease motor symptoms were associated with less deep sleep. CORE CONCLUSION: The Dreem Headband performs similarly in Parkinson's disease as it did in non-Parkinson's disease samples and shows promise for improving access to sleep assessment in people with Parkinson's disease.

A Case of Sleep Terrors with Sleepwalking Whose Therapeutic Effect by the Kampo Medicine Shokenchuto was Confirmed by Overnight Polysomnography / 日本東洋医学雑誌

We report a case of sleep terrors complicated with sleepwalking. The patient was 9-year-old boy who suddenly woke up, walked, or screamed in his sleep. These symptoms were sometimes induced by such as fever elevation or school events. In order to prevent injury while sleeping, he was suggested taking medicine to suppress the nocturnal behavior. After taking shokenchuto based on his findings of qi deficiency, the episodes gradually disappeared and the frequency of fever elevation decreased. In this report, we present the improvements of sleep parameters provided by overnight polysomnography, performed before and after treatment. Shokenchuto is known as one of the curative medicines for sleep terrors, but this is the first report showing objective therapeutic effects using overnight polysomnography.

Characteristics of Sleep Disorders Related to Huntington’s Disease：A Case Report and Literature Review / 中风与神经疾病杂志

@#Objective　To explore the characteristics of polysomnography in patients with Huntington’s disease（HD） accompanied by sleep disorders，so as to improve clinicians attention to sleep disorders in HD patients. Methods　Analyze the polysomnography of one patient with HD，and retrieve related literature. Results　The patient’s two polysomnography showed sleep fragmentation and a significant increase in the number of nightly awakenings. From the perspective of sleep structure，the patient’s stage 1 sleep（N1 stage） increased，while the percentage of the deep sleep stage（N3 stage） and rapid eye movement during sleep（R stage） was significantly reduced，and during the two sleep monitoring，abnormal behaviors and muscle dysfunction during REM sleep were not recorded. Conclusion　Sleep disorders have an effect on the symptoms of HD patients and are an ideal direction for further research on potential interventions.

Obstructive sleep apnoea detection using convolutional neural network based deep learning framework

This letter presents an automated obstructive sleep apnoea (OSA) detection method with high accuracy, based on a deep learning framework employing convolutional neural network. The proposed work develops a system that takes single lead electrocardiography signals from patients for analysis and detects the OSA condition of the patient. The results show that the proposed method has some advantages in solving such problems and it outperforms the existing methods significantly. The present scheme eliminates the requirement of separate feature extraction and classification algorithms for the detection of OSA. The proposed network performs both feature learning and classifies the features in a supervised manner. The scheme is computation-intensive, but can achieve very high degree of accuracy—on an average a margin of more than 9% compared to other published literature till date. The method also has a good immunity to the contamination of the signals by noise. Even with pessimistic signal to noise ratio values considered here, the methods already reported are not able to outshine the present method. The software for the algorithm reported here can be a good contender to constitute a module that can be integrated with a portable medical diagnostic system.

Evaluation of upper airway obstruction site in OSAHS by apneagraph and spiral CT / 中国现代医生

Objective To evaluate the clinical value of Apneagraph(AG200)and CT scan in diagnosing obstructive sleep apnea hypopnea syndrome(OSAHS). Methods Twenty-two moderate and 18 severe obstructive sleep apnea hypopnea syndrome(OSAHS) patients diagnosed by polysomnography(PSG) performed one-night pressure monitoring by Apnea-graph, the apnea hypopnea index (AHI),the site of upper airway callapse and the obstructive proportion of different level. The cross-sectional areas of the pharyngeal wall of retropalate, lingua regions planes were scanned by MSCT scan in the waking state were analyzed. The obstruction levels determined by pressure monitored and found in CT screening were compared. Results Apneagraph and CT scan had good performance in the diagnosis of OSAHS. There was no difference between two methods(P>0.05).Conclusion Apneagraph and CT scan can serve as a useful device to diagnose OSAHS.The diagnostic rate of OSAHS (especially severe OSAHS)can be elevated by combining Apneagraph and CT scan.

Application of breathing pattern parameters to extraction of REM sleep information / 医疗卫生装备

Objective To extract breathing pattern parameters during sleep and get the varying law of NREM and REM sleep stages. Method A newly designed respiratory inductive plethysmography (RIP) and a polysomnography (PSG) are utilized to record whole-night-sleep data simultaneously. The breathing pattern parameters obtained by RIP are dealt with according to the results of sleep stages and sleep apnea by PSG. Then the rule found out and summarized from the experiment is applied to distinguish REM sleep. Conclusion RC/VT can be used as an effective parameter to differentiate NREM and REM sleep. Using this parameter, the results of RIP totally accord with the results of PSG.

Role of serotonergic projection from dorsal raphe nuclei to basolateral amygadaloid in regulation of sleep / 中国药理学通报

AIM To investigate the role of serotonergic projection from dorsal raphe nuclei (DRN) to basolateral amygadaloid (BLA) in the regulation of sleep and waking state. METHODS stereotaxic microinjection and polysomnography were employed. RESULTS Microinjection of L Glu into the DRN caused an enhancement of wake (W) and a decrease of slow wave sleep (SWS) and paradoxical sleep (PS). However, microinjection of L Glu into the DRN plus bilateral microinjection of methysergide (MS) into the BLA reversed the effects of L Glu. Microinjection of PCPA into the DRN caused an enhancement of SWS and a decrease of W. Microinjection of PCPA into the DRN plus bilateral microinjection of 5 HTP into the BLA reversed the effects of PCPA. CONCLUSION These results suggest that the role of the DRN in the regulation of sleep and waking state is partly mediated by serotonergic projection from the DRN to the BLA.