Identifying relationships between sleep posture and non-specific spinal symptoms in adults: A scoping review

Preferences and Avoidance of Sleeping Positions Among Patients With Chronic Low Back Pain: A Cross-Sectional Study

Background Chronic low back pain (CLBP) is a common issue among the working-age population. Sleeping position may affect CLBP, with the prone position commonly suggested to be avoided. This study aims to examine the relationship between preferred and avoided sleeping positions and to explore the frequency of increased pain in various sleeping positions among patients with nonspecific CLBP and pain and disability levels. Methods This cross-sectional study included all adult patients referred for specialist consultation for CLBP at the outpatient clinic of the Central Hospital of Central Finland's spine department. Pain intensity was measured using a visual analog scale (VAS), and disability was assessed with the Oswestry Disability Index (ODI). Patients completed a questionnaire detailing the main sleeping positions and positions avoided due to low back pain (LBP). Results The study enrolled 375 consecutive patients, with a mean age of 51 ± 17 years; 64% (n=240) were female. The mean VAS score was 63 ± 24, and the mean Oswestry Index was 38 ± 18%. The majority of patients (87%, n=327) reported sleeping in a side-lying position, followed by supine (47%, n=176) and prone (22%, n=82) positions. A negative correlation was found between age and the preference for sleeping in the prone position. No significant gender differences in sleep positions were observed (p=0.69). Sleep was disturbed in 77% of patients (n=289) due to LBP, and 87% (n=327) reported difficulties due to LBP when getting up. Overall, 92% of participants (n=345) experienced difficulties sleeping or getting up in the morning due to LBP. Many patients avoided certain positions due to pain: 42% (n=157) avoided the prone position, 35% (n=131) the back, 15% (n=56) the left side, and 13% (n=49) the right side. Although the prone position was most commonly linked with pain, especially among women, our findings suggest that any sleeping position could potentially exacerbate pain in individuals with CLBP. Conclusions This study highlights the variability in how sleeping positions affect pain in patients with nonspecific CLBP. While the prone position is most frequently associated with increased pain, individual preferences and responses vary significantly, and often sidelying and supine positions provoke pain. The diversity in sleeping positions that exacerbate pain highlights the need for tailored advice in the management of patients with CLBP.

Depth-Camera-Based Under-Blanket Sleep Posture Classification Using Anatomical Landmark-Guided Deep Learning Model

Emerging sleep health technologies will have an impact on monitoring patients with sleep disorders. This study proposes a new deep learning model architecture that improves the under-blanket sleep posture classification accuracy by leveraging the anatomical landmark feature through an attention strategy. The system used an integrated visible light and depth camera. Deep learning models (ResNet-34, EfficientNet B4, and ECA-Net50) were trained using depth images. We compared the models with and without an anatomical landmark coordinate input generated with an open-source pose estimation model using visible image data. We recruited 120 participants to perform seven major sleep postures, namely, the supine posture, prone postures with the head turned left and right, left- and right-sided log postures, and left- and right-sided fetal postures under four blanket conditions, including no blanket, thin, medium, and thick. A data augmentation technique was applied to the blanket conditions. The data were sliced at an 8:2 training-to-testing ratio. The results showed that ECA-Net50 produced the best classification results. Incorporating the anatomical landmark features increased the F1 score of ECA-Net50 from 87.4% to 92.2%. Our findings also suggested that the classification performances of deep learning models guided with features of anatomical landmarks were less affected by the interference of blanket conditions.

A Vision-Based System for In-Sleep Upper-Body and Head Pose Classification

Sleep quality is known to have a considerable impact on human health. Recent research shows that head and body pose play a vital role in affecting sleep quality. This paper presents a deep multi-task learning network to perform head and upper-body detection and pose classification during sleep. The proposed system has two major advantages: first, it detects and predicts upper-body pose and head pose simultaneously during sleep, and second, it is a contact-free home security camera-based monitoring system that can work on remote subjects, as it uses images captured by a home security camera. In addition, a synopsis of sleep postures is provided for analysis and diagnosis of sleep patterns. Experimental results show that our multi-task model achieves an average of 92.5% accuracy on challenging datasets, yields the best performance compared to the other methods, and obtains 91.7% accuracy on the real-life overnight sleep data. The proposed system can be applied reliably to extensive public sleep data with various covering conditions and is robust to real-life overnight sleep data.

Examining relationships between sleep posture, waking spinal symptoms and quality of sleep: A cross sectional study

INTRODUCTION

Research with a focus on sleep posture has been conducted in association with sleep pathologies such as insomnia and positional obstructive sleep apnoea. Research examining the potential role sleep posture may have on waking spinal symptoms and quality of sleep is however limited. The aims of this research were to compare sleep posture and sleep quality in participants with and without waking spinal symptoms.

METHODS

Fifty-three participants (36 female) were, based on symptoms, allocated to one of three groups; Control (n = 20, 16 female), Cervical (n = 13, 10 female) and Lumbar (n = 20, 10 female). Participants completed an online survey to collect general information and patient reported outcomes and were videoed over two consecutive nights to determine sleep posture using a validated classification system including intermediate sleep postures.

RESULTS

Participants in the symptomatic groups also reported a lower sleep quality than the Control group. Compared to Control group participants, those in the Cervical group had more frequent posture changes (mean (SD); 18.3(6.5) versus 23.6(6.6)), spent more time in undesirable/provocative sleep postures (median IQR; 83.8(16.4,105.2) versus 185.1(118.0,251.8)) minutes and had more long periods of immobility in a provocative posture, (median IQR: 0.5(0.0,1.5) versus 2.0 (1.5,4.0)). There were no significant differences between the Control and Lumbar groups in the number of posture changes (18.3(6.5) versus 22.9(9.1)) or the time spent in provocative sleep postures (0.5(0.0,1.5) versus 1.5(1.5,3.4)) minutes.

DISCUSSION

This is the first study using a validated objective measure of sleep posture to compare symptomatic and Control group participants sleeping in their home environment. In general, participants with waking spinal symptoms spent more time in provocative sleep postures, and experienced poorer sleep quality.

A Blanket Accommodative Sleep Posture Classification System Using an Infrared Depth Camera: A Deep Learning Approach with Synthetic Augmentation of Blanket Conditions

Surveillance of sleeping posture is essential for bed-ridden patients or individuals at-risk of falling out of bed. Existing sleep posture monitoring and classification systems may not be able to accommodate the covering of a blanket, which represents a barrier to conducting pragmatic studies. The objective of this study was to develop an unobtrusive sleep posture classification that could accommodate the use of a blanket. The system uses an infrared depth camera for data acquisition and a convolutional neural network to classify sleeping postures. We recruited 66 participants (40 men and 26 women) to perform seven major sleeping postures (supine, prone (head left and right), log (left and right) and fetal (left and right)) under four blanket conditions (thick, medium, thin, and no blanket). Data augmentation was conducted by affine transformation and data fusion, generating additional blanket conditions with the original dataset. Coarse-grained (four-posture) and fine-grained (seven-posture) classifiers were trained using two fully connected network layers. For the coarse classification, the log and fetal postures were merged into a side-lying class and the prone class (head left and right) was pooled. The results show a drop of overall F1-score by 8.2% when switching to the fine-grained classifier. In addition, compared to no blanket, a thick blanket reduced the overall F1-scores by 3.5% and 8.9% for the coarse- and fine-grained classifiers, respectively; meanwhile, the lowest performance was seen in classifying the log (right) posture under a thick blanket, with an F1-score of 72.0%. In conclusion, we developed a system that can classify seven types of common sleeping postures under blankets and achieved an F1-score of 88.9%.