Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks.

The accurate estimation of energy expenditure from simple objective accelerometry measurements provides a valuable method for investigating the effect of physical activity (PA) interventions or population surveillance. Methods have been evaluated previously, but none utilize the temporal aspects of the accelerometry data. In this study, we investigated the energy expenditure prediction from acceleration measured at the subjects' hip, wrist, thigh, and back using recurrent neural networks utilizing temporal elements of the data. The acceleration was measured in children (N = 33) performing a standardized activity protocol in their natural environment. The energy expenditure was modelled using Multiple Linear Regression (MLR), stacked long short-term memory (LSTM) networks, and combined convolutional neural networks (CNN) and LSTM. The correlation and mean absolute percentage error (MAPE) were 0.76 and 19.9% for the MLR, 0.882 and 0.879 and 14.22% for the LSTM, and, with the combined LSTM-CNN, the best performance of 0.883 and 13.9% was achieved. The prediction error for vigorous intensities was significantly different (p < 0.01) from those of the other intensity domains: sedentary, light, and moderate. Utilizing the temporal elements of movement significantly improves energy expenditure prediction accuracy compared to other conventional approaches, but the prediction error for vigorous intensities requires further investigation.

Walking performance in individuals with lumbar spinal stenosis-possible outcome measures and assessment of known-group validity.

BACKGROUND CONTEXT: One of the primary goals of treatments received by individuals with lumbar spinal stenosis with neurogenic claudication is to improve walking ability. Thus, a thorough and valid assessment of walking ability in patients with lumbar spinal stenosis is needed. Duration of continuous walking and steps per day could be relevant when evaluating walking ability in daily living. PURPOSE: To describe and evaluate a method for estimating continuous walking periods in daily living and to evaluate the known-group validity of steps per day in individuals with lumbar spinal stenosis. STUDY DESIGN: This is a cross-sectional observational study. PATIENT SAMPLE: The study contains three study groups: individuals with lumbar spinal stenosis, individuals with low back pain, and a background population from the Lolland-Falster Health Study (LOFUS). OUTCOME MEASURES: Participants in all three study groups wore an accelerometer on the thigh for seven days. METHODS: Accelerometer data were processed to summarize the continuous walking periods according to their length: the number of short (4-9 seconds), moderate (10-89 seconds), and extended (≥90 seconds) continuous walking periods per day, and the number of steps per day. Results from the three groups were compared using negative binomial regression with lumbar spinal stenosis as the reference level. RESULTS: Continuous walking periods of moderate length were observed 1.48 (95% CI 1.27, 1.72) times more often in individuals from the background population than in individuals with LSS. Continuous walking periods of extended length were observed 1.53 (95% CI 1.13, 2.06) times more often by individuals with low back pain and 1.60 (95% CI 1.29, 1.99) times more often by individuals from the background population. The number of steps per day was 1.22 (95% CI 1.03, 1.46) times larger in individuals with LBP and 1.35 (95% CI 1.20, 1.53) times larger in individuals from background population. CONCLUSIONS: The impact of neurogenic claudication on walking ability in daily living seems possible to describe by continuous walking periods along with steps per day. The results support known-group validity of steps per day. This is the next step toward a clinically relevant and comprehensive assessment of walking in daily living in individuals with lumbar spinal stenosis.

Associations between children's physical literacy and well-being: is physical activity a mediator?

BACKGROUND: Physical literacy (PL) is a multi-dimensional concept that provides a holistic understanding of movement and physical activity. PL contains an affective, a physical, and a cognitive domain, which together lay the foundation for the individual's capacity and the tendency for participating in physical activities currently and throughout life. PL is increasingly regarded as a 'cause of the causes' to health promotion. Cross-sectional studies have shown associations between children's PL, physical activity behaviours, and well-being. This study aims to examine the associations between Danish children's PL and their physical and psychosocial well-being and whether the associations are mediated by moderate- to vigorous intensity physical activity (MVPA). METHODS: Cross-sectional data from Danish schoolchildren aged 7-13 years were collected in Jan-Dec 2020 in the Danish Assessment of Physical Literacy (DAPL) project. PL was assessed with the DAPL which measures the affective, cognitive, and physical domains of PL. MVPA (min/day) was measured with accelerometers (Axivity), psychosocial well-being was measured with The Strengths and Difficulties Questionnaire, and physical well-being was measured with the KIDSCREEN questionnaire. Structural equation models were constructed with PL and MVPA as predictors of physical well-being and four aspects of psychosocial well-being. RESULTS: A positive moderate association between PL and physical well-being, partly mediated by MVPA was observed. PL was positively associated with the positive aspects of psychosocial well-being and negatively associated with the negative aspects (behaviour problems). None of the associations between PL and aspects of psychosocial well-being were mediated by MVPA. CONCLUSIONS: The study contributes to evidence on the link between PL, physical activity, and health outcomes. The study found beneficial relations between PL and physical and psychosocial well-being. MVPA mediated part of the relationship between PL and physical well-being but not psychosocial well-being.

Recommendations for Determining the Validity of Consumer Wearables and Smartphones for the Estimation of Energy Expenditure: Expert Statement and Checklist of the INTERLIVE Network.

BACKGROUND: Consumer wearables and smartphone devices commonly offer an estimate of energy expenditure (EE) to assist in the objective monitoring of physical activity to the general population. Alongside consumers, healthcare professionals and researchers are seeking to utilise these devices for the monitoring of training and improving human health. However, the methods of validation and reporting of EE estimation in these devices lacks rigour, negatively impacting on the ability to make comparisons between devices and provide transparent accuracy. OBJECTIVES: The Towards Intelligent Health and Well-Being Network of Physical Activity Assessment (INTERLIVE) is a joint European initiative of six universities and one industrial partner. The network was founded in 2019 and strives towards developing best-practice recommendations for evaluating the validity of consumer wearables and smartphones. This expert statement presents a best-practice validation protocol for consumer wearables and smartphones in the estimation of EE. METHODS: The recommendations were developed through (1) a systematic literature review; (2) an unstructured review of the wider literature discussing the potential factors that may introduce bias during validation studies; and (3) evidence-informed expert opinions from members of the INTERLIVE network. RESULTS: The systematic literature review process identified 1645 potential articles, of which 62 were deemed eligible for the final dataset. Based on these studies and the wider literature search, a validation framework is proposed encompassing six key domains for validation: the target population, criterion measure, index measure, testing conditions, data processing and the statistical analysis. CONCLUSIONS: The INTERLIVE network recommends that the proposed protocol, and checklists provided, are used to standardise the testing and reporting of the validation of any consumer wearable or smartphone device to estimate EE. This in turn will maximise the potential utility of these technologies for clinicians, researchers, consumers, and manufacturers/developers, while ensuring transparency, comparability, and replicability in validation. TRIAL REGISTRATION: PROSPERO ID: CRD42021223508.

Recommendations for determining the validity of consumer wearable and smartphone step count: expert statement and checklist of the INTERLIVE network.

Consumer wearable and smartphone devices provide an accessible means to objectively measure physical activity (PA) through step counts. With the increasing proliferation of this technology, consumers, practitioners and researchers are interested in leveraging these devices as a means to track and facilitate PA behavioural change. However, while the acceptance of these devices is increasing, the validity of many consumer devices have not been rigorously and transparently evaluated. The Towards Intelligent Health and Well-Being Network of Physical Activity Assessment (INTERLIVE) is a joint European initiative of six universities and one industrial partner. The consortium was founded in 2019 and strives to develop best-practice recommendations for evaluating the validity of consumer wearables and smartphones. This expert statement presents a best-practice consumer wearable and smartphone step counter validation protocol. A two-step process was used to aggregate data and form a scientific foundation for the development of an optimal and feasible validation protocol: (1) a systematic literature review and (2) additional searches of the wider literature pertaining to factors that may introduce bias during the validation of these devices. The systematic literature review process identified 2897 potential articles, with 85 articles deemed eligible for the final dataset. From the synthesised data, we identified a set of six key domains to be considered during design and reporting of validation studies: target population, criterion measure, index measure, validation conditions, data processing and statistical analysis. Based on these six domains, a set of key variables of interest were identified and a 'basic' and 'advanced' multistage protocol for the validation of consumer wearable and smartphone step counters was developed. The INTERLIVE consortium recommends that the proposed protocol is used when considering the validation of any consumer wearable or smartphone step counter. Checklists have been provided to guide validation protocol development and reporting. The network also provide guidance for future research activities, highlighting the imminent need for the development of feasible alternative 'gold-standard' criterion measures for free-living validation. Adherence to these validation and reporting standards will help ensure methodological and reporting consistency, facilitating comparison between consumer devices. Ultimately, this will ensure that as these devices are integrated into standard medical care, consumers, practitioners, industry and researchers can use this technology safely and to its full potential.

Simple Method for the Objective Activity Type Assessment with Preschoolers, Children and Adolescents.

Background: The objective and accurate assessment of children's sedentary and physical behavior is important for investigating their relation to health. The purpose of this study is to validate a simple and robust method for the identification of sitting, standing, walking, running and biking performed by preschool children, children and adolescents in the age from 3 to 16 years from a single thigh-worn accelerometer. Method: A total of 96 children were included in the study and all subjects followed a structured activity protocol performed in the subject's normal kindergarten or school environment. Thigh acceleration was measured using the Axivity AX3 (Axivity, Newcastle, UK) device. Method development and accuracy was evaluated by equally dividing the subjects into a development and test group. Results: The sensitivity and specificity for identifying sitting and standing was above 99.3% and for walking and running above 82.6% for all age groups. The sensitivity and specificity for identifying biking was above 85.8% for children and adolescents and above 64.8% for the preschool group using running bikes. Conclusion: The accurate assessment of sitting, standing, walking, running and biking from thigh acceleration and with children in the age range of 3 to 16 is valid, although not with preschool children using running bikes.

Re-examination of accelerometer data processing and calibration for the assessment of physical activity intensity.

This review re-examines the use of accelerometer and oxygen uptake data for the assessment of activity intensity. Accelerometers capture mechanical work, while oxygen uptake captures the energy cost of this work. Frequency filtering needs to be considered when processing acceleration data. A too restrictive filter attenuates the acceleration signal for walking and, to a higher degree, for running. This measurement error affects shorter (children) more than taller (adults) individuals due to their higher movement frequency. Less restrictive filtering includes more movement-related signals and provides measures that better capture mechanical work, but may include more noise. An optimal filter cut-point is determined where most relevant acceleration signals are included. Further, accelerometer placement affects what part of mechanical work being captured. While the waist placement captures total mechanical work and therefore contributes to measures of activity intensity equivalent by age and stature, the thigh and wrist placements capture more internal work and do not provide equivalent measures. Value calibration of accelerometer measures is usually performed using measured oxygen uptake with the metabolic equivalent of task (MET) as reference measure of activity intensity. However, the use of MET is not stringent and is not a measure of activity intensity equivalent by age and stature. A candidate measure is the mass-specific net oxygen uptake, VO2 net (VO2 tot - VO2 stand). To improve measurement of physical activity intensity using accelerometers, research developments are suggested concerning the processing of accelerometer data, use of energy expenditure as reference for activity intensity, and calibration procedure with absolute versus relative intensity.

The ActiGraph counts processing and the assessment of vigorous activity.

The purpose of this study was to investigate the effect of different band-pass filters on the measurement bias with ActiGraph counts during high speed running and for estimating free-living vigorous physical activity (VPA). Two alternative band-pass filters were designed, extending the original frequency range from 0·29 to 1·66 Hz (AG) to 0·29-4 Hz (AC4) and 0·29-10 Hz (AC10). Sixty-two subjects in three age groups participated in a structured locomotion protocol consisting of multiple walking and running speeds. The time spent in free-living VPA using the three different band-pass filters were evaluated in 1121 children. Band-pass filter specific intensity cut-points from both linear regression and ROC analysis was identified from a calibration experiment using indirect calorimetry. The ActiGraph GT3X+ device recording raw acceleration at 30 Hz was used in all experiments. The linear association between counts and running speed was negative for AG but positive for AC4 and AC10 across all age groups. The time spent in free-living VPA was similar for all band-pass filters. Considering higher frequency information in the generation of ActiGraph counts with a hip/waist worn device reduces the measurement bias with running above 10 km·h-1 . However, additional developments are required to accurately capture all VPA, including intermittent activities.

Do extra compulsory physical education lessons mean more physically active children--findings from the childhood health, activity, and motor performance school study Denmark (The CHAMPS-study DK).

BACKGROUND: Primarily, this study aims to examine whether children attending sports schools are more active than their counterpart attending normal schools. Secondary, the study aims to examine if physical activity (PA) levels in specific domains differ across school types. Finally, potential modifications by status of overweight/obesity and poor cardio-respiratory fitness are examined. METHODS: Participants were from the first part of the CHAMPS-study DK, which included approximately 1200 children attending the 0th - 6th grade. At the sports schools, the mandatory physical education (PE) program was increased from 2 to 6 weekly lessons over a 3-year period. Children attending normal schools were offered the standard 2 PE lessons. PA was assessed at two different occasions with the GT3X ActiGraph accelerometer, once during winter in 2009/10 and once during summer/fall in 2010. Leisure time organized sports participation was quantified by SMS track. Based on baseline values in 2008, we generated a high-BMI and a low-cardio-respiratory fitness for age and sex group variable. RESULTS: There were no significant differences in PA levels during total time, PE, or recess between children attending sports schools and normal schools, respectively. However, children, especially boys, attending sports schools were more active during school time than children attending normal schools (girls: ß=51, p=0.065; boys: ß=113, p<0.001). However, in the leisure time during weekdays children who attended sports schools were less active (girls: ß=-41, p=0.004; boys: ß=-72, p<0.001) and less involved in leisure time organized sports participation (girls: ß=-0.4, p=0.016; boys: ß=-0.2, p=0.236) than children who attended normal schools. Examination of modification by baseline status of overweight/obesity and low cardio-respiratory fitness indicated that during PE low fit girls in particular were more active at sports schools. CONCLUSION: No differences were revealed in overall PA levels between children attending sports schools and normal schools. Sports schools children were more active than normal schools children during school time, but less active during leisure time. In girls, less organized sports participation at least partly explained the observed differences in PA levels during leisure time across school types. Baseline status of cardio-respiratory fitness modified school type differences in PA levels during PE in girls.