Background: Sleep disorders, such as obstructive sleep apnea (OSA), comorbid insomnia and sleep apnea (COMISA), and insomnia are common and can have serious health consequences. However, accurately diagnosing these conditions can be challenging as a result of the underrecognition of these diseases, the time-intensive nature of sleep monitoring necessary for a proper diagnosis, and patients’ hesitancy to undergo demanding and costly overnight polysomnography tests. Objective: We aim to develop a machine learning algorithm that can accurately predict the risk of OSA, COMISA, and insomnia with a simple set of questions, without the need for a polysomnography test. Methods: We applied extreme gradient boosting to the data from 2 medical centers (n=4257 from Samsung Medical Center and n=365 from Ewha Womans University Medical Center Seoul Hospital). Features were selected based on feature importance calculated by the Shapley additive explanations (SHAP) method. We applied extreme gradient boosting using selected features to develop a simple questionnaire predicting sleep disorders (SLEEPS). The accuracy of the algorithm was evaluated using the area under the receiver operating characteristics curve. Results: In total, 9 features were selected to construct SLEEPS. SLEEPS showed high accuracy, with an area under the receiver operating characteristics curve of greater than 0.897 for all 3 sleep disorders, and consistent performance across both sets of data. We found that the distinction between COMISA and OSA was critical for accurate prediction. A publicly accessible website was created based on the algorithm that provides predictions for the risk of the 3 sleep disorders and shows how the risk changes with changes in weight or age. Conclusions: SLEEPS has the potential to improve the diagnosis and treatment of sleep disorders by providing more accessibility and convenience. The creation of a publicly accessible website based on the algorithm provides a user-friendly tool for assessing the risk of OSA, COMISA, and insomnia.

The prevalence of artificial light exposure has enabled us to be active any time of the day or night, leading to the need for high alertness outside of traditional daytime hours. To address this need, we developed a personalized sleep intervention framework that analyzes real-world sleep–wake patterns obtained from wearable devices to maximize alertness during specific target periods. Our framework utilizes a mathematical model that tracks the dynamic sleep pressure and circadian rhythm based on the user’s sleep history. In this way, the model accurately predicts real-time alertness, even for shift workers with complex sleep and work schedules (N = 71, t = 13~21 days). This allowed us to discover a new sleep–wake pattern called the adaptive circadian split sleep, which incorporates a main sleep period and a late nap to enable high alertness during both work and non-work periods of shift workers. We further developed a mobile application that integrates this framework to recommend practical, personalized sleep schedules for individual users to maximize their alertness during a targeted activity time based on their desired sleep onset and available sleep duration. This can reduce the risk of errors for those who require high alertness during nontraditional activity times and improve the health and quality of life for those leading shift work-like lifestyles.

Shift work disrupts the body's circadian rhythms and increases the risk of health problems. Despite evidence of neuropsychological disturbances in shift workers (SW), the brain functional status as measured by brain perfusion in chronic shift work has not been evaluated previously. We investigated the regional cerebral blood flow (rCBF) in SW using perfusion MRI (pMRI) and evaluated the relationships between altered rCBF and sleep, mood, psychometric measures, and quality of life. Fifteen rotational SW and 15 day workers (DW) were enrolled. The participants were all female nurses working at a university-affiliated hospital. During 2 weeks of actigraphy they underwent pMRI scanning and psychometric testing on the last day immediately after working. Demographic characteristics, insomnia, daytime sleepiness, and mood were compared between the groups. The participants were aged 35.3±2.9 years (mean±SD) and had been performing their current work for more than 2 years. The demographic characteristics did not differ between SW and DW, but the levels of insomnia, anxiety, depression, and hyperactivity-restlessness in psychometric measures were higher in SW than in DW. Cerebral perfusion in SW was significantly decreased in the cuneus, fusiform/parahippocampal gyri, and cerebellum of the right hemisphere, while it was increased in the inferior occipital gyrus of the left hemisphere. Perfusion changes in SW were significantly correlated with depression and insomnia severity. The onset and duration irregularity of sleep among SW were related to insomnia, mood, hyperactivity/ restlessness, and quality of life. SW experience considerably more insomnia and mood disturbances than do DW, and this is significantly related to perfusion changes in multiple brain areas.

Shift workers frequently suffer from insomnia and mood disturbances, but little is known about the relationships of these conditions with the chronotypes and different working schedules of shift workers. We hypothesized that different shift-work schedules are associated with different severities of sleep and mood disturbances, and that the individual chronotype plays a role in sleep disturbances in shift workers. This study enrolled 276 participants, comprising 77 nurses working in a three-shift schedule (3S, 27.9%), 60 firefighters working in a 24-h-every-other-day shift schedule (EOD, 21.7%), and 139 day workers (DW, 50.4%). All of the participants completed the following questionnaires to assess their sleep disturbances, mood, and chronotype: Insomnia Severity Index (ISI), Epworth Sleepiness Scale, Hospital Anxiety and Depression Scale, and Morningness-Eveningness Questionnaire. ISI questionnaires were worse in both shift workers compare to DW, 35.1% of 3S, 23% of EOD had clinically significant insomnia (ISI score >14). Depressive mood and anxiety symptom were significantly worse in 3S compare to EOD. The sleep disturbance by ISI score had significant correlations with depressive mood and anxiety symptoms for both EOD and 3S (EOD: rho=0.57, rho=0.57, 3S: rho=0.37, rho=0.33 respectively). Chronotype type in shift workers had no significant correlation with sleep disturbance, depressive mood, nor anxiety symptom. However, after adjustment, the eveningness chronotype have relationship to the depressive mood in shift workers. Sleep disturbances are more frequent in shift workers than DW. Depressive mood and anxiety symptoms were frequently reported in 3S, then EOD. Different shift schedules cab be a determinant of depressive mood and anxiety symptom.

Park E, et al. J Korean Acad Psychiatr Ment Health Nurs. 2013 Jun;22(2):88-96. http://dx.doi.org/10.12934/jkpmhn.2013.22.2.88