This study assessed the relationship between body posture displacements and cardiopulmonary function test (CPET) and skill related physical fitness tests. One hundred male (60%) and female collegiate athletes (22.2 ± 4yrs) with a normal body mass index (BMI up to 24.9) were assessed via the PostureScreen Mobile app to quantify postural displacements as head, thorax and pelvis rotations and translations. CPET and physical performance tests including the agility T-test, the vertical jump test, the stork static balance test (SSBT) and the dynamic Y-balance test (YBT) were performed. Spearman correlation (r) and p-values are reported. Postural parameters were found to have moderate-to-high associations with CPET and the agility test, moderate correlations with the vertical jump test and the SSBT (head and pelvic postures only), and weak correlations with the YBT. As postural parameters were more asymmetric, both CPET and performance skills scores were worse. For examples: 1) a medium positive correlation was found between cranio-vertebral angle (CVA) and vertical jump test (r = 0.54; p-value < 0.001) and SSBT (r = 0.57; p-value < 0.001), while a strong negative correlation was found between CVA and agility test (r = -0.86; p-value < 0.001). 2) A strong positive correlation was found between CVA and oxygen uptake efficiency slope, load watts VO2 at VT, VO2 / kg, load watts at respiratory compensation point (RCP), (r = 0.65 and r = 0.71; p < 0.001). Conversely, a significant negative correlation was found between CVA and VE / VO2 at VT (r = -0.61; p < 0.001). Postural rotations and translations of the head, thorax and pelvis were statistically correlated with physical performance skills and CPET in young collegiate athletes. There were moderate-to-high associations with cardiopulmonary functions and agility tests, moderate correlations with the vertical jump test, and weak correlations with the YBT. Postural alignment may be important for optimal physical performance and optimal cardiopulmonary function. Further research is necessary to elucidate reasons for these correlations as found in our sample of young and healthy athletes.

There is great interest in thoracic kyphosis as it is thought to be a contributor to neck pain, neck disability, and sensorimotor control measures; though this has not been completely inves-tigated in treatment or case control studies. This case control design investigated participants with non-specific chronic neck pain. Eighty participants with a defined hyper-kyphosis (> 55°) were compared to 80 matched participants with normal thoracic kyphosis (< 55°). Participants were matched for age and neck pain duration. Hyper-kyphosis was further categorized into two distinct types: postural kyphosis (PK) and Scheuermann’s kyphosis (SK). Posture measures included formetric thoracic kyphosis and the craniovertebral angle (CVA) to assess forward head posture. Sensorimotor control was assessed by the following measures: smooth pursuit neck torsion test (SPNT), overall stability index (OSI) and left and right rotation repositioning accuracy. A measure of autonomic nervous system function included the amplitude and latency of skin sympathetic response (SSR). Differences in variable measures were examined using the Student’s t-test to compare the means of continuous variables between the two groups. Pearson correlation was used to evaluate the relationship between participant’s thoracic kyphosis magnitude (in each group separately and as an entire population) and their CVA, SPNT, OSI, head repositioning ac-curacy, and SSR latency and amplitude. Hyper-kyphosis participants had a significantly greater neck disability index compared to the normal kyphosis group (p < 0.001) with the SK group having greatest disability (p < 0.001). Statistically significant differences between the two kyphosis groups and the normal kyphosis group for all the sensorimotor measured variables were identified with the SK group having the most decreased efficiency of the measures in the hyper-kyphosis group, including: SPNT, OSI and left and right rotation repositioning accuracy. Also, there was a signif-icant difference in neurophysiological findings for SSR amplitude (entire sample of kyphosis vs. normal kyphosis, p < 0.001), but there was no significant difference for SSR latency (p = .07). The CVA was significantly greater in the hyper-kyphosis group (p < 0.001). The magnitude of the thoracic kyphosis correlated with worsening CVA (with the SK group having the smallest CVA; p < 0.001) and the magnitude of the decreased efficiency of the sensorimotor control measures and the amplitude and latency of the SSR. The PK group, overall, showed the greatest correlations between thoracic kyphosis and measured variables. Participants with hyper-thoracic kyphosis exhibited abnormal sensorimotor control and autonomic nervous system dysfunction compared to those with normal thoracic kyphosis.

An ongoing EU Horizon 2020 Project called BionicVEST is investigating the effect of constant electrical stimulation (ES) of the inferior vestibular nerve in patients with bilateral vestibular dysfunction (BVD)[1]. The evidence is that constant ES results in improved postural stability and gait performance and so the question of central importance is how could constant ES of mainly saccular afferents in these BVD patients cause this improved performance? We suggest that the constant ES is substituting for the absent saccular neural input to the vestibular nuclei and the cerebellum in these BVD patients and indirectly via these structures to other structures which have been of great recent interest in motor control. One target area, the anterior midline cerebellum (the uvula) has recently been targeted as a location for deep brain stimulation in human patients to improve postural stability and gait. There are projections from midline cerebellum to basal ganglia including the striatum, structures involved in the initiation of gait. It may be that the effect of this activation of peripheral saccular afferent neurons is analogous to the effect of deep brain stimulation (DBS) by electrodes in basal ganglia acting to help alleviate the symptoms of patients with Parkinson's disease.

Sleep postures monitoring systems in the hospital aim at transforming sensing signals into quantitative data to characterize the sleep behaviors of the patient. However, a home-care sleep posture monitoring system needs to be user friendly. In this paper, we present iSleePost - a user-friendly home-care intelligent sleep posture monitoring system. We address the labor-intensive labeling issue of traditional machine learning approaches in the training phase. Our proposed mobile health (mHealth) system leverages the communications and computation capabilities of mobile phones for provisioning a continuous sleep posture monitoring service. Our experiments show that iSleePost can achieve 90 percent accuracy in recognizing sleep postures. More importantly, iSleePost demonstrates that an easily-wear wrist sensor can accurately quantify sleep postures.

Central nervous system (CNS) uses vision, vestibular, and somatosensory information to maintain body stability. Research has shown that there is more lumbar proprioception error among low back pain (LBP) individuals as compared to healthy people. In this study, two groups of 20 healthy people and 20 non-specific low back pain participants (LBP) took part in this investigation. This investigation focused on somatosensory sensors and in order to alter proprioception, a vibrator (frequency of 70Hz, amplitude of 0.5 mm) was placed on the soleus muscle area of each leg and two vibrators were placed bilaterally across the lower back muscles. Individuals, whose vision was occluded, were placed on two surfaces (foam and rigid) on force plate, and trunk angles were recorded simultaneously. Tests were performed in 8 separate trials; the independent variables were vibration (4 levels) and surface (2 levels) for within subjects and 2 groups (healthy and LBP) for between subjects (4×2×2). MANOVA and multi-factor ANOVA tests were done. Linear parameters for center of pressure (COP) (deviation of amplitude, deviation of velocity, phase plane portrait (PPP), and overall mean velocity) and nonlinear parameters for COP and trunk angle ((recurrence quantification analysis) RQA and Lyapunov exponents) were chosen as dependent variables. Results indicated that NSLBP individuals relied more on ankle proprioception for postural stability. Similarly, RQA parameters for the COP on both sides and for the trunk sagittal angle indicated more repeated patterns of movement among the LBP cohort. Analysis of short and long Lyapunov exponents showed that people with LBP caused no use of all joints in their bodies (non-flexible), are less stable than healthy subjects.

Pig behavior is an integral part of health and welfare management, as pigs usually reflect their inner emotions through behavior change. The livestock environment plays a key role in pigs' health and wellbeing. A poor farm environment increases the toxic GHGs, which might deteriorate pigs' health and welfare. In this study a computer-vision-based automatic monitoring and tracking model was proposed to detect short-term pigs' physical activities in a compromised environment. The ventilators of the livestock barn were closed for an hour, three times in a day (07:00-08:00, 13:00-14:00, and 20:00-21:00) to create a compromised environment, which increases the GHGs level significantly. The corresponding pig activities were observed before, during, and after an hour of the treatment. Two widely used object detection models (YOLOv4 and Fast-er R-CNN) were trained and compared their performances in terms of pig localization and posture detection. The YOLOv4, which outperformed the Faster R-CNN model, coupled with a Deep-SORT tracking algorithm to detect and track the pig activities. The results showed that the pigs became more inactive with the increase in GHG concentration, reducing their standing and walking activities. Moreover, the pigs also shortened their sternal-lying posture increasing the lateral lying posture duration at higher GHG concentration. The high detection accuracy (mAP: 98.67%) and tracking accuracy (MOTA: 93.86% and MOTP: 82.41%) signify the models’ efficacy in monitoring and tracking pigs' physical activities non-invasively.

The aim of the study was to assess the relationship between the shape of the anterior-posterior curvature of the spine and body composition in school-children. The study included 257 children, aged 11-12. Correct spinal curvature was established in 106 (41.08%) subjects. Other types included: decreased kyphosis and correct lordosis - 40 participants (15.50%), correct kyphosis and decreased lordosis - 24 individuals (9.30%), increased kyphosis and correct lordosis - 17 subjects (6.59%), correct kyphosis and increased lordosis - 22 children (8.53%), decreased kyphosis and decreased lordosis - 32 people (12.40%), decreased kyphosis and increased lordosis - 4 of the examined subjects (1.55%), increased kyphosis and lordosis - 13 people (5.04%). In addition, 134 (51.94%) demonstrated scoliotic posture and 8 (3.10%) scoliosis. There were significant relationships between the shape of the anterior-posterior curvatures and body composition in school-children. Those with a strong body build (predominance of mesomorphs) were generally characterised by the correct formation of these curvatures. In contrast, lean people (with the predominance of ectomorphic factors) were more likely to experience abnormalities. No correlations with body composition were observed in the group with scoliotic posture or scoliosis.

Postural deficits such as hyperlordosis (hollow back) or hyperkyphosis (hunchback) are relevant health issues. Diagnoses depend on the experience of the examiner and are therefore often subjective and prone to errors. Machine learning (ML) methods in combination with explainable ar-tificial intelligence (XAI) tools have proven useful for providing an objective, data-based orien-tation. However, only a few works have considered posture parameters, leaving the potential of more human-friendly XAI interpretations still untouched. Therefore, the present work proposes an objective, data-driven ML system for medical decision support that enables especially human-friendly interpretations using counterfactual explanations (CFs). Posture data for 1151 subjects were recorded by means of stereophotogrammetry. An expert-based classification of the subjects regarding the presence of hyperlordosis or hyperkyphosis was initially performed. Using a Gaussian progress classifier, the models were trained and interpreted using CFs. Label errors were flagged and re-evaluated using confident learning. Very good classification performances for both hyperlordosis and hyperkyphosis were found, whereby the re-evaluation and correction of the test labels led to a significant improvement (MPRAUC = 0.97). A statistical evaluation showed that the CFs seemed to be plausible in general. In the context of personalized medicine, the present study’s approach could be of importance for reducing diagnostic errors and thereby improving the individual adaptation of therapeutic measures. Likewise, it could be a basis for the development of apps for preventive posture assessment.

Automated lying-posture tracking is important in preventing bed-related disorders such as pressure injuries, sleep apnea, and lower-back pain. Prior research studied in-bed lying posture tracking using sensors of different modalities (e.g., accelerometer and pressure sensors). However, there remain significant gaps in research about how to design efficient in-bed lying posture tracking systems. These gaps can be articulated through several research questions as follows. First, can we design a single-sensor, pervasive, and inexpensive system that can accurately detect lying postures? Second, what computational models are most effective in the accurate detection of lying postures? Finally, what physical configuration of the sensor system is most effective for lying posture tracking? To answer these important research questions, in this article, we propose a comprehensive approach to design a sensor system that uses a single accelerometer along with machine learning algorithms for in-bed lying posture classification. We design two categories of machine learning algorithms based on deep learning and traditional classification with handcrafted features to detect lying postures. We also investigate what wearing sites are most effective in accurate detection of lying postures. We extensively evaluate the performance of the proposed algorithms on nine different body locations and four human lying postures using two datasets. Our results show that a system with a single accelerometer can be used with either deep learning or traditional classifiers to accurately detect lying postures. The best models in our approach achieve an F-Score that ranges from 95.2% to 97.8% with a coefficient of variation from 0.03 to 0.05. The results also identify the thighs and chest as the most salient body sites for lying posture tracking. Our findings in this article suggest that because accelerometers are ubiquitous and inexpensive sensors, they can be a viable source of information for pervasive monitoring of in-bed postures.