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.

Validation of Oura ring energy expenditure and steps in laboratory and free-living.

BACKGROUND: Commercial activity trackers are increasingly used in research and compared with research-based accelerometers are often less intrusive, cheaper, with improved storage and battery capacity, although typically less validated. The present study aimed to determine the validity of Oura Ring step-count and energy expenditure (EE) in both laboratory and free-living. METHODS: Oura Ring EE was compared against indirect calorimetry in the laboratory, followed by a 14-day free-living study with 32 participants wearing an Oura Ring and reference monitors (three accelerometers positioned at hip, thigh, and wrist, and pedometer) to evaluate Oura EE variables and step count. RESULTS: Strong correlations were shown for Oura versus indirect calorimetry in the laboratory (r = 0.93), and versus reference monitors for all variables in free-living (r ≥ 0.76). Significant (p < 0.05) mean differences for Oura versus reference methods were found for laboratory measured sitting (- 0.12 ± 0.28 MET), standing (- 0.27 ± 0.33 MET), fast walk (- 0.82 ± 1.92 MET) and very fast run (- 3.49 ± 3.94 MET), and for free-living step-count (2124 ± 4256 steps) and EE variables (MET: - 0.34-0.26; TEE: 362-494 kcal; AEE: - 487-259 kcal). In the laboratory, Oura tended to underestimate EE with increasing discrepancy as intensity increased. The combined activities and slow running in the laboratory, and all MET placements, TEE hip and wrist, and step count in free-living had acceptable measurement errors (< 10% MAPE), whereas the remaining free-living variables showed close to (≤13.2%) acceptable limits. CONCLUSION: This is the first study investigating the validity of Oura Ring EE against gold standard methods. Oura successfully identified major changes between activities and/or intensities but was less responsive to detailed deviations within activities. In free-living, Oura step-count and EE variables tightly correlated with reference monitors, though with systemic over- or underestimations indicating somewhat low intra-individual validity of the ring versus the reference monitors. However, the correlations between the devices were high, suggesting that the Oura can detect differences at group-level for active and total energy expenditure, as well as step count.

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.

Stronger Association between High Intensity Physical Activity and Cardiometabolic Health with Improved Assessment of the Full Intensity Range Using Accelerometry.

An improved method of physical activity accelerometer data processing, involving a wider frequency filter than the most commonly used ActiGraph filter, has been shown to better capture variations in physical activity intensity in a lab setting. The aim of the study was to investigate how this improved measure of physical activity affected the relationship with markers of cardiometabolic health. Accelerometer data and markers of cardiometabolic health from 725 adults from two samples, LIV 2013 and SCAPIS pilot, were analyzed. The accelerometer data was processed using both the original ActiGraph method with a low-pass cut-off at 1.6 Hz and the improved method with a low-pass cut-off at 10 Hz. The relationship between the physical activity intensity spectrum and a cardiometabolic health composite score was investigated using partial least squares regression. The strongest association between physical activity and cardiometabolic health was shifted towards higher intensities with the 10 Hz output compared to the ActiGraph method. In addition, the total explained variance was higher with the improved method. The 10 Hz output enables correctly measuring and interpreting high intensity physical activity and shows that physical activity at this intensity is stronger related to cardiometabolic health compared to the most commonly used ActiGraph method.

Reexamination of Accelerometer Calibration with Energy Expenditure as Criterion: VO2net Instead of MET for Age-Equivalent Physical Activity Intensity.

Accelerometer calibration for physical activity (PA) intensity is commonly performed using Metabolic Equivalent of Task (MET) as criterion. However, MET is not an age-equivalent measure of PA intensity, which limits the use of MET-calibrated accelerometers for age-related PA investigations. We investigated calibration using VO2net (VO2gross - VO2stand; mL⋅min-1⋅kg-1) as criterion compared to MET (VO2gross/VO2rest) and the effect on assessment of free-living PA in children, adolescents and adults. Oxygen consumption and hip/thigh accelerometer data were collected during rest, stand and treadmill walk and run. Equivalent speed (Speedeq) was used as indicator of the absolute speed (Speedabs) performed with the same effort in individuals of different body size/age. The results showed that VO2net was higher in younger age-groups for Speedabs, but was similar in the three age-groups for Speedeq. MET was lower in younger age-groups for both Speedabs and Speedeq. The same VO2net-values respective MET-values were applied to all age-groups to develop accelerometer PA intensity cut-points. Free-living moderate-and-vigorous PA was 216, 115, 74 and 71 min/d in children, adolescents, younger and older adults with VO2net-calibration, but 140, 83, 74 and 41 min/d with MET-calibration, respectively. In conclusion, VO2net calibration of accelerometers may provide age-equivalent measures of PA intensity/effort for more accurate age-related investigations of PA in epidemiological research.

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.

A culturally adapted lifestyle intervention addressing a Middle Eastern immigrant population at risk of diabetes, the MEDIM (impact of Migration and Ethnicity on Diabetes In Malmö): study protocol for a randomized controlled trial.

BACKGROUND: Studies have shown that lifestyle interventions are effective in preventing or delaying the onset of type 2 diabetes in high-risk patients. However, research on the effectiveness of lifestyle interventions in high-risk immigrant populations with different cultural and socioeconomic backgrounds is scarce. The aim was to design a culturally adapted lifestyle intervention for an immigrant population and to evaluate its effectiveness and cost-effectiveness. METHODS/DESIGN: In this randomized controlled trial, 308 participants (born in Iraq, living in Malmö, Sweden and at high risk of type 2 diabetes) will be allocated to either a culturally adapted intervention or a control group. The intervention will consist of 10 group counseling sessions focusing on diet, physical activity and behavioral change over 6 months, and the offer of exercise sessions. Cultural adaptation includes gender-specific exercise sessions, and counseling by a health coach community member. The control group will receive the information about healthy lifestyle habits provided by the primary health care center. The primary outcome is change in fasting glucose level. Secondary outcomes are changes in body mass index, insulin sensitivity, physical activity, food habits and health-related quality of life. Measurements will be taken at baseline, after 3 and 6 months. Data will be analyzed by the intention-to-treat approach. The cost-effectiveness during the trial period and over the longer term will be assessed by simulation modeling from patient, health care and societal perspectives. DISCUSSION: This study will provide a basis to measure the effectiveness of a lifestyle intervention designed for immigrants from the Middle East in terms of improvement in glucose metabolism, and will also assess its cost-effectiveness. Results from this trial may help health care providers and policy makers to adapt and implement lifestyle interventions suitable for this population group that can be conducted in the community. TRIAL REGISTRATION: ClinicalTrials.gov, NCT01420198.

Walkability parameters, active transportation and objective physical activity: moderating and mediating effects of motor vehicle ownership in a cross-sectional study.

BACKGROUND: Neighborhood walkability has been associated with physical activity in several studies. However, as environmental correlates of physical activity may be context specific, walkability parameters need to be investigated separately in various countries and contexts. Furthermore, the mechanisms by which walkability affects physical activity have been less investigated. Based on previous research, we hypothesized that vehicle ownership is a potential mediator. We investigated the associations between walkability parameters and physical activity, and the mediating and moderating effects of vehicle ownership on these associations in a large sample of Swedish adults. METHODS: Residential density, street connectivity and land use mix were assessed within polygon-based network buffers (using Geographic Information Systems) for 2,178 men and women. Time spent in moderate to vigorous physical activity was assessed by accelerometers, and walking and cycling for transportation were assessed by the International Physical Activity Questionnaire. Associations were examined by linear regression and adjusted for socio-demographic characteristics. The product of coefficients approach was used to investigate the mediating effect of vehicle ownership. RESULTS: Residential density and land use mix, but not street connectivity, were significantly associated with time spent in moderate to vigorous physical activity and walking for transportation. Cycling for transportation was not associated with any of the walkability parameters. Vehicle ownership mediated a significant proportion of the association between the walkability parameters and physical activity outcomes. For residential density, vehicle ownership mediated 25% of the association with moderate to vigorous physical activity and 20% of the association with the amount of walking for transportation. For land use mix, the corresponding proportions were 34% and 14%. Vehicle ownership did not moderate any of the associations between the walkability parameters and physical activity outcomes. CONCLUSIONS: Residential density and land use mix were associated with time spent in moderate to vigorous physical activity and walking for transportation. Vehicle ownership was a mediator but not a moderator of these associations. The present findings may be useful for policy makers and city planners when designing neighborhoods that promote physical activity.

Study protocol: a multi-professional team intervention of physical activity referrals in primary care patients with cardiovascular risk factors--the Dalby lifestyle intervention cohort (DALICO) study.

BACKGROUND: The present study protocol describes the trial design of a primary care intervention cohort study, which examines whether an extended, multi-professional physical activity referral (PAR) intervention is more effective in enhancing and maintaining self-reported physical activity than physical activity prescription in usual care. The study targets patients with newly diagnosed hypertension and/or type 2 diabetes. Secondary outcomes include: need of pharmacological therapy; blood pressure/plasma glucose; physical fitness and anthropometric variables; mental health; health related quality of life; and cost-effectiveness. METHODS/DESIGN: The study is designed as a long-term intervention. Three primary care centres are involved in the study, each constituting one of three treatment groups: 1) Intervention group (IG): multi-professional team intervention with PAR, 2) Control group A (CA): physical activity prescription in usual care and 3) Control group B: treatment as usual (retrospective data collection). The intervention is based on self-determination theory and follows the principles of motivational interviewing. The primary outcome, physical activity, is measured with the International Physical Activity Questionnaire (IPAQ) and expressed as metabolic equivalent of task (MET)-minutes per week. Physical fitness is estimated with the 6-minute walk test in IG only. Variables such as health behaviours; health-related quality of life; motivation to change; mental health; demographics and socioeconomic characteristics are assessed with an electronic study questionnaire that submits all data to a patient database, which automatically provides feed-back to the health-care providers on the patients' health status. Cost-effectiveness of the intervention is evaluated continuously and the intermediate outcomes of the intervention are extrapolated by economic modelling. DISCUSSIONS: By helping patients to overcome practical, social and cultural obstacles and increase their internal motivation for physical activity we aim to improve their physical health in a long-term perspective. The targeted patients belong to a patient category that is supposed to benefit from increased physical activity in terms of improved physiological values, mental status and quality of life, decreased risk of complications and maybe a decreased need of medication.

Free-living energy expenditure in children using multi-sensor activity monitors.

AIMS: To improve the energy expenditure algorithm of the activity monitor ActiReg, and to validate ActiReg and the activity monitor SenseWear in free-living children. METHODS: The development of the ActiReg algorithm was performed in 20 healthy 11-13 years old children on treadmill walking and running with indirect calorimetry as reference. The original and new ActiReg algorithms and SenseWear using software versions InnerView 5.1 and 6.1 were validated in 20 healthy 14-15 years old children against doubly labelled water. RESULTS: The new ActiReg algorithm improved the assessment of energy expenditure during walking and running, but the response from the monitor levelled off after 7 km h(-1). The new algorithm and InnerView 6.1 decreased the mean (sd) difference to doubly labelled water from 11 (25) (P<0.05) to 0 (22) kJ kg(-1) d(-1) for ActiReg, and from 17 (20) (P<0.01) to -10 (21) (P<0.05) kJ kg(-1) d(-1) for SenseWear. However, the correlations between energy expenditure and the individual error for the new ActiReg algorithm and InnerView 6.1 were r= -0.50 (P<0.05) and r= -0.73 (P<0.01). CONCLUSIONS: The new ActiReg algorithm and InnerView 6.1 improved the activity monitors at group level, but the error was dependent on physical activity level. Both activity monitors need further developments for use in children.

Energy cost in children assessed by multisensor activity monitors.

PURPOSE: The SenseWear Pro2 Armband (SWA; BodyMedia, Inc., Pittsburg, PA), the Intelligent Device for Energy Expenditure and Activity (IDEEA; Minisun LLC, Fresno, CA), and the ActiReg (AR; PreMed AS, Oslo, Norway) were compared with indirect calorimetry to determine the ability of these devices to assess energy cost in children during resting and different physical activities. METHODS: Fourteen children, 11-13 yr old, wore the SWA, the IDEEA, and the AR during resting, sitting, stationary bicycling, jumping on a trampoline, playing basketball, stair walking, and walking/running along a 50-m track. The Oxycon Mobile portable metabolic system (VIASYS Healthcare, Conshohocken, PA) was used as the criterion method for energy cost. RESULTS: For resting and sitting, the three activity monitors showed comparable results, but none of them accurately assessed energy cost for stationary bicycling, jumping on a trampoline, or playing basketball. The IDEEA was the only activity monitor that accurately assessed energy cost for stair walking. Also, the IDEEA showed a close estimate of energy cost across the walking and the running intensities, whereas the SWA accurately assessed energy cost for slow to normal walking but showed increased underestimation of energy cost with increasing speed. The AR overestimated energy cost during walking and during slow running but did not respond to increasing running speed. CONCLUSIONS: To be able to capture children's physical activity, all three activity monitors need to be further developed. Overall, the IDEEA showed the highest ability to assess energy cost in this study, but SWA may be more feasible for use in children under free-living conditions.

Energy cost of physical activities in children: validation of SenseWear Armband.

PURPOSE: To examine the validity of SenseWear Pro2 Armband in assessing energy cost of physical activities in children, and to contribute with values of energy costs in an overview of physical activities in children. METHODS: Energy cost was assessed by SenseWear Pro2 Armband in 20 healthy children, 11-13 yr, while lying down resting, sitting playing games on mobile phone, stepping up and down on a step board, bicycling on a stationary bike, jumping on a trampoline, playing basketball, and walking/running on a treadmill at the speeds 2, 3, 4, 5, 6, 7, 8, and 10 km x h(-1). During these activities, energy cost was also assessed from VO2 and VCO2 measured by Oxycon Mobile portable metabolic system, which was used as criterion method. RESULTS: The difference in energy cost between SenseWear Pro2 Armband and Oxycon Mobile was -0.7 (0.5) (P < 0.001) for resting, -2.0 (0.9) (P < 0.001) for playing games on mobile phone, -6.6 (2.3) (P < 0.001) for stepping on the step board, -12.0 (3.7) (P < 0.001) for bicycling, -2.7 (11.9) (P = 0.34) for jumping on the trampoline, and -14.8 (6.4) kJ x min(-1) (P < 0.001) for playing basketball. The difference in energy cost between SenseWear Pro2 Armband and Oxycon Mobile for increasing treadmill speed was 1.3 (3.1) (P = 0.048), 0.1 (2.9) (P = 0.82), -1.2 (2.6) (P = 0.049), -1.6 (3.2) (P = 0.044), -3.1 (3.7) (P = 0.0013), -4.9 (3.7) (P < 0.001), -5.3 (3.7) (P < 0.001), and -11.1 (3.5) kJ x min(-1) (P < 0.001). CONCLUSIONS: SenseWear Pro2 Armband underestimated energy cost of most activities in this study, an underestimation that increased with increased physical activity intensity. A table of energy costs (MET values) of physical activities in children measured by indirect calorimetry is presented as an initiation of the creation of a compendium of physical activities in children.