Quantitative assessment of sitting time in ambulant adults with Muscular Dystrophy

Background Current investigations into physical behaviour in Muscular Dystrophy (MD) have focussed largely on physical activity (PA). Negative health behaviours such as sedentary behaviour (Physical Behaviour) and sitting time (Posture Classification) are widely recognised to negatively influence health, but by contrast are poorly reported, yet could be easier behaviours to modify. Methods 14 ambulant men with MD and 12 healthy controls (CTRL) subjects completed 7-days of free-living with wrist-worn accelerometry, assessing physical behaviour (SB or PA) and Posture Classification (Sitting or Standing), presented at absolute (minutes) or relative (% Waking Hours). Participant body composition (Fat Mass and Fat Free Mass) were assessed by Bioelectrical Impedance, while functional status was assessed by 10 m walk test and a functional scale (Swinyard Scale). Results Absolute Sedentary Behaviour (2.2 Hours, p = 0.025) and Sitting Time (1.9 Hours, p = 0.030 was greater in adults with MD compared to CTRL and Absolute Physical Activity (3.4 Hours, p < 0.001) and Standing Time (3.2 Hours, p < 0.001) was lower in adults with MD compared to CTRL. Absolute hours of SB was associated with Fat Mass (Kg) (R = 0.643, p < 0.05) in ambulatory adults with MD, Discussion This study has demonstrated increased Sedentary Behaviour (2.2 hours) and Sitting time (1.9 Hours) in adults with MD compared to healthy controls. Extended waking hours in sitting and SB raises concerns with regards to progression of potential cardio-metabolic diseases and co-morbidities in MD.

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%.

Classification of Free-Living Body Posture with ECG Patch Accelerometers: Application to the Multicenter AIDS Cohort Study

As health studies increasingly monitor free-living heart performance via ECG patches with ac- celerometers, researchers will seek to investigate cardio-electrical responses to physical activity and sedentary behavior, increasing demand for fast, scalable methods to process accelerometer data. We provide the first published analysis of tri-axial accelerometry data from Zio XT patch and introduce an extension of posture classification algorithms for use with ECG patches worn in the free-living environment. Our novel extensions to posture classification include (1) estimation of an upright posture for each individual without the reference measurements used by existing posture classification algorithms; (2) correction for device removal and re-positioning using novel spherical change-point detection; and (3) classification of upright and recumbent periods using a clustering and voting process rather than a simple inclination threshold used in other algorithms. Methods were built using data from 14 participants from the Multicenter AIDS Cohort Study (MACS), and applied to 1, 250 MACS participants. As no posture labels exist in the free-living environment, we evaluate the algorithm against labelled data from the Towson Accelerometer Study and against data labelled by hand from the MACS study.