Neural network versus activity-specific prediction equations for energy expenditure estimation in children

Objectives: This study aimed to provide an improved energy expenditure estimation for heavy-load physical labor using accelerometer data and heart rate (HR) measured by wearables and to support food preparation and supply management for disaster relief and rescue operations as an expedition team. Methods: To achieve an individually optimized estimation for energy expenditure, a model equation parameter was determined based on the measurements of physical activity and HR during simulated rescue operations. The metabolic equivalent of task (MET), which was measured by using a tri-axial accelerometer and individual HR, was used, where two (minimum and maximum) or three (minimum, intermediate, and maximum) representative reference points were selected for each individual model fitting. In demonstrating the applicability of our approach in a realistic situation, accelerometer-based METs and HR of 30 males were measured using the tri-axial accelerometer and wearable HR during simulated rescue operations over 2days. Results: Data sets of 27 rescue operations (age:34.2 ± 7.5years; body mass index (BMI):22.9 ± 1.5kg/m2) were used for the energy expenditure estimation after excluding three rescue workers due to their activity type and insufficient HR measurement. Using the combined approach with a tri-axial accelerometer and HR, the total energy expenditure increased by 143% for two points and 133% for three points, compared with the estimated total energy expenditure using only the accelerometer-based method. Conclusion: The use of wearables provided a reasonable estimation of energy expenditure for physical workers with heavy equipment. The application of our approach to disaster relief and rescue operations can provide important insights into nutrition and healthcare management.

Determining the total energy expenditure is extremely important in the field of health sciences, with the voluntary physical activity the most variable component. This work contextualizes metabolic equivalent (MET), a simple and practical method for estimating the energy expenditure of exercise and physical activity in adults. The MET is based on the resting oxygen consumption value of 3.5 mL/kg/min, but the exact origin of this value is unknown. In contrast, studies in heterogeneous and specific populations (i. e. obese, elderly) show lower values than the default value. Consequently, the energy expenditure in voluntary physical activity may be underestimated, since they are based in the elevation (multiples) of oxygen consumption when compared to the resting state. In this context, recent studies suggest a correction of the value of 1 MET through the Harris-Benedict equation (3.5 ÷ estimated resting metabolic rate (mL/kg/min)), provides a more individualized and accurate estimation of the energy expenditure directly measured (indirect calorimetry). This factor can favor the better planning of nutritional interventions and physical training. Calculations and estimates are always subject to errors due to physical/biological variations among individuals and environmental factors. This factor can favor the better planning of nutritional interventions and physical training. However, does not justify the use of a universal value (1 MET = 3.5 mL/kg/min) for entire population, which results in inadequate estimates of energy expenditure in physical activities. On the other hand, new studies must be carried out so that correction factors may be proposed for specific populations, given that are also controversies between the predictive equations of resting metabolic rate.

Objective: Objectively and efficiently measuring physical activity is a common issue facing the fields of medicine, public health, education, and sports worldwide. In response to the problem of low accuracy in predicting energy consumption during human motion using accelerometers, a prediction model for asynchronous energy consumption in the human body is established through various algorithms, and the accuracy of the model is evaluated. The optimal energy consumption prediction model is selected to provide theoretical reference for selecting reasonable algorithms to predict energy consumption during human motion. Methods: A total of 100 subjects aged 18-30years participated in the study. Experimental data for all subjects are randomly divided into the modeling group (n = 70) and validation group (n = 30). Each participant wore a triaxial accelerometer, COSMED Quark pulmonary function tester (Quark PFT), and heart rate band at the same time, and completed the tasks of walking (speed range: 2km/h, 3km/h, 4km/h, 5km/h, and 6km/h) and running (speed range: 7km/h, 8km/h, and 9km/h) sequentially. The prediction models were built using accelerometer data as the independent variable and the metabolic equivalents (METs) as the dependent variable. To calculate the prediction accuracy of the models, root mean square error (RMSE) and bias were used, and the consistency of each prediction model was evaluated based on Bland-Altman analysis. Results: The linear equation, logarithmic equation, cubic equation, artificial neural network (ANN) model, and walking-and-running two-stage model were established. According to the validation results, our proposed walking-and-running two-stage model showed the smallest overall EE prediction error (RMSE = 0.76METs, Bias = 0.02METs) and the best performance in Bland-Altman analysis. Additionally, it had the lowest error in predicting EE during walking (RMSE = 0.66METs, Bias = 0.03METs) and running (RMSE = 0.90METs, Bias < 0.01METs) separately, as well as high accuracy in predicting EE at each single speed. Conclusion: The ANN-based walking-and-running two-stage model established by separating walking and running can better estimate the walking and running EE, the improvement of energy consumption prediction accuracy will be conducive to more accurate to monitor the energy consumption of PA.

Purpose: There is a lack of data on the energy cost of childrens everyday activities, adult values are often used as surrogates. In addition, the influence of body weight on the energy cost of activity when expressed as metabolic equivalents (METs) has not been vigorously explored. Methods: In this study 20 elementary school students 9~12 years of age completed 18 various physical activities while energy expenditure was measured continuously using a portable telemetry gas exchange system (K₄b², Cosmed, Rome, Italy). Results: The average age was 10.4 years and the average height and weight was 145.1 ㎝ and 43.6 ㎏, respectively. Oxygen consumption (VO₂), energy expenditure and METs at the time of resting of the subjects were 5.41 mL/㎏/min, 1.44 ㎉/㎏/h, and 1.5 METs, respectively. METs values by 18 physical activities were as follows: Homework and reading books (1.6 METs), playing game with a mobile phone or video while sitting (1.6 METs), watching TV while sitting on a comfortable chair (1.7 METs), playing video game or mobile phone game while standing (1.9 METs), sweeping a room with a broom (2.7 METs) and playing a board game (2.8 METs) belong to light intensity physical activities. By contrary, speedy walking and running were 6.6 and 6.7 METs, respectively, which belong to high intensity physical activities over 6.0 METs. When the effect of body weight on physical activity energy expenditure was determined, R² values increased with 0.116 (playing a game at sitting), 0.176 (climbing up and down stairs), 0.246 (slow walking), and 0.455 (running), which showed that higher activity intensity increased explanation power of body weight on METs value. Conclusion: This study is important for direct evaluation of energy expenditure by physical activities of children, and it could be used directly for revising and complementing the existing activity classification table to fit for children.

Accurate estimation of Energy Expenditure (EE) in ambulatory settings is a key element in determining the causal relation between aspects of human behavior related to physical activity and health. We present a new methodology for activity-specific EE algorithms. The proposed methodology models activity clusters using specific parameters that capture differences in EE within a cluster, and combines these models with Metabolic Equivalents (METs) derived from the compendium of physical activities. We designed a protocol consisting of a wide set of sedentary, household, lifestyle and gym activities, and developed a new activity-specific EE algorithm applying the proposed methodology. The algorithm uses accelerometer (ACC) and heart rate (HR) data acquired by a single monitoring device, together with anthropometric variables, to predict EE. Our model recognizes six clusters of activities independent of the subject in 52.6 hours of recordings from 19 participants. Increases in EE estimation accuracy ranged from 18 to 31% compared to state of the art single and multi-sensor activity-specific methods.

Dear Editor in Chief, We read with interest the recent article by Potter et al. (1) that represents a new opportunity for methodological advances in using global positioning systems (GPS) to estimate outdoor walking energy expenditure (EE). The authors proposed a method that consisted of smoothing GPS-based EE estimates to better match EE estimated by a mobile metabolic sensor in non–steady-state conditions. The theoretical basis for this method was supported by the authors as follows: “The delayed respiratory response to physical activity […] complicates the use of walking equations on a second-by-second basis. Energy expenditure will be overestimated initially before a respiratory steady state is reached.” This assumption is physiologically wrong, and that is probably why it is not supported by any specific reference cited in their article. In fact, the transient change and non–steady-state V˙O2 at the beginning of a given physical activity, or when physical activity intensity varies, means that gas exchange measurements are, by their very nature, limited to estimate actual EE as long as a steady state is not reached (2). Unless considering that the actual EE needed for a given work is different between the beginning of walking and a couple of minutes (3–4 min) after, EE estimated by walking equations should better reflect actual EE than EE estimated from gas exchange during the transitional non–steady-state period. Thus, to our opinion, the right question should be “How to accurately estimate actual EE during conditions of non–steady-state exercise during which EE estimated by gas exchange measurements is flawed?,” and not “How to modify EE estimated by walking equations to better match EE estimated by gas exchange measurements during non-steady state exercise?.” The flawed theoretical basis supported by Potter et al. (1) makes difficult the analysis of their results regarding the comparison of the accuracy of three speed- and grade-based equations (3–6) using GPS for estimating outdoor walking EE on complex terrain. Further, additional limitations prevent unbiased comparisons between the EE estimations achieved by each equation, including (i) the absence of information regarding the precision of the GPS device used and the method for GPS speed computation; (ii) the use of an original equation (5) to estimate outdoor walking EE during downhill walking, whereas such estimations were not allowed by that original equation; and (iii) the conversion of V˙O2 data to watts, which inevitably added error when cross validating the two equations that were initially developed to estimate METs or V˙O2. In fact, there is little doubt that the Pandolf–Santee equation (3,4) would have better fitted actual EE as compared with the two other equations tested, all the more so as this equation includes a specific component for extra load carriage, which was not the case for the two other equations. Pierre-Yves de Müllenheim Bénédicte Noury-Desvaux Institute of Physical Education and Sports Sciences (IFEPSA)West Catholic University (UCO)Les Ponts-de-Cé, FRANCE Laboratory of Exercise Physiology and Vascular MedicineUniversity HospitalAngers, FRANCE Alexis Le Faucheur Univ Rennes, M2S-EA 7470Rennes, FRANCE Clinical Investigation CenterINSERM CIC 1414Rennes, FRANCE

Activity self-reports are a commonly used tool in assessing daily physical activity (PA) and associated energy expenditure (EE). This study examined the effect of relative body fatness (%BF) on differences between self-reported and measured duration and associated EE in healthy adults. Men and women (n = 115, age 38+/-9 years), ranging in %BF from 7.9% to 58.9%, spent two separate days (normal and exercise) in a whole-room indirect calorimeter where EE was measured. While in the room calorimeter, subjects reported the type, intensity, and duration of each performed PA. The Compendium of Physical Activity was used to calculate the energy cost of each reported activity. The EE of all self-reported activities (EEr) was categorized into four intensity levels, synchronized, and compared with EE from the room calorimeter (EEm). With increasing %BF, subjects significantly overestimated duration of more strenuous activities (> or =4.5), while underestimating moderate activities (2.5 to 4.4 metabolic equivalents (METs)). Misreporting of duration and/or intensity caused an overestimation or underestimation of PA-associated EE at these levels. Reported EE sleep was lower than measured EE sleep, although both had similar durations. As a result, total EEr was similar to EEm. Individual variability of daily total PA and associated EE generated from self-reports in adults is high. Persons with a higher %BF report duration and/or intensity of moderate to high levels of PA with lower accuracy than leaner individuals. We conclude using the Compendium of Physical Activity is not suitable for the accurate estimation of self-reported EE of AA in adults with a higher %BF.

BackgroundPhysical activity is associated with health in women. Published MET-values (MET: metabolic equivalent of task) may assess physical activity and energy expenditure but tend to be too low for subjects with a high total body fat (TBF) content and therefore inappropriate for many contemporary women. The MET-value for an activity is the energy expenditure of a subject performing this activity divided by his/her resting energy expenditure, often assumed to be 4.2 kJ/kg/h. Relationships between TBF and MET have been little studied although overweight and obesity is common in women. Available data indicate that MET-values decrease during pregnancy but more studies in pregnant contemporary women are needed.Subjects and methodsUsing indirect calorimetry we measured energy expenditure and assessed MET-values in women, 22 non-pregnant (BMI: 18–34) and 22 in gestational week 32 (non-pregnant BMI: 18–32) when resting, sitting, cycling (30 and 60 watts), walking (3.2 and 5.6 km/h) and running (8 km/h). Relationships between TBF and MET-values were investigated and used to predict modified MET-values. The potential of such values to improve calculations of total energy expenditure of women was investigated.ResultsThe resting energy expenditure was below 4.2 kJ/kg/h in both groups of women. Women in gestational week 32 had a higher resting energy metabolism (p < 0.001) and 7–15% lower MET-values (p < 0.05) than non-pregnant women. MET-values of all activities were correlated with TBF (p < 0.05) in non-pregnant women and modified MET-values improved estimates of total energy expenditure in such women. In pregnant women, correlations (p ≤ 0.03) between TBF and MET were found for running (8 km/h) and for walking at 5.6 km/h.ConclusionsOur results are relevant when attempts are made to modify the MET-system in contemporary pregnant and non-pregnant women. MET-values were decreased in gestational week 32, mainly due to an increased resting energy metabolism and studies describing how body composition affects the one MET-value (i.e. the resting energy metabolism in kJ/kg/h) during pregnancy are warranted. Studies of how pregnancy and TBF affect MET-values of high intensity activities are also needed. Corrections based on TBF may have a potential to improve the MET-system in non-pregnant women.

1720 PURPOSE: The ability to accurately predict energy expenditure is essential for exercise prescription; however, little research is available when comparing the measured energy expenditure with prediction equations. Furthermore, little research is available comparing walking and running energy expenditure on a track to treadmill. The primary purpose of this study was to establish how well the published prediction equations for the energy expenditure of walking and running compare to the actual measured values. To accomplish this we reexamined whether differences exist in energy expenditure of walking vs. running 1600 meters, and if energy expenditure differences occur due to being on the track or treadmill which could confound the estimation of energy expenditure. METHODS: Indirect calorimetry was measured on 12 male and 12 female subjects while walking (4.8 km/hr) and running (9.6 km/hr) 1600 meters on the treadmill. A subgroup of 7 males and 10 females also performed the 1600 meter run/walk on the track. The measured energy expenditures were compared to prediction equations available in the literature. RESULTS: Running utilized significantly more energy for 1600 meters than walking in both genders (treadmill: running 481 ± 20, walking 340 ± 19 kJ; track: running 480 ± 23, walking 430 ± 14 kJ, P<0.01), and greater energy expenditures were found in the males than females (P<0.05). When adjusted for lean body mass, the greater energy expenditures for 1600 meters in males disappeared. There were no differences between the track and treadmill energy expenditures regardless of speed. The predictions using the ACSM or Léger equations for running did not differ significantly from the actual energy expenditures (total error-ACSM: 20 and −14.4 kJ for running and walking respectively; Légers walking: 10.1 kJ). Both the McArdle's table value for walking and running and van der Walt's prediction for walking significantly overestimated (P<0.01) energy expenditure for 1600 meters. CONCLUSIONS: ACSM's prediction model for walking and running as well as the Léger equation for walking appear to be the most suitable for the prediction of energy expenditure for both running and walking, while McArdle's table and van der Walt equation were not as strong predictors of energy expenditure.

PURPOSE To determine the accuracy of estimates of energy expenditure using branched equations for synchronised accelerometry and heart rate (AHR) during a 2 h period of structured activity reflecting low to moderate intensity physical activities. METHODS 10 male and 10 female subjects (mean age 26 ± 5 years, height 173 ± 7 cm and body mass 72 ± 11 kg) performed a 2 h laboratory-based protocol simulating six low to moderate intensity physical activities. Each activity lasted 8 min and was interspersed with 8 min supine rest. Activities included treadmill walking at 4.8 km.h−1, sweeping, digging in sand, simulated watering of plants, treadmill walking at 5.6 km.h−1 whilst carrying 4% body mass in each hand and folding and stacking sheets. These activities were chosen as they range from low to moderate intensity physical activity according to assigned values (2–5 metabolic equivalents). These activities include movements where the use of accelerometry and heart rate may be most limited and therefore provide data that may represent a worst-case scenario. Energy expenditure was estimated throughout using indirect calorimetry (COSMED, Italy) and AHR (Cambridge Neurotechnology Ltd., UK). Established default equations for AHR were used to estimate energy expenditure and we also developed new calibration equations derived from both group and individual data. RESULTS Mean energy expenditure across all six physical activities determined using indirect calorimetry was 3.6 ± 0.3 kcal·min−1. The comparison between methods was conducted using ordinary least-products regression. The standard error of the estimate for the prediction of energy expenditure from AHR was 0.4 kcal·min−1 for default equations, new group equations and individual calibration equations during the period of observation. If this were extrapolated to a typical day where an individual was active for 16h, this would be equivalent to 384 kcal (this represents approximately 15% of total energy expenditure if energy expenditure was 2500 kcal.day−1). CONCLUSION These results demonstrate that AHR is a promising tool for the estimation of energy expenditure during low to moderate intensity physical activities. It appears that deriving new group equations or individual calibration equations may not be necessary.

We present a multi-device and multi-modal dataset, called WEEE, collected from 17 participants while they were performing different physical activities. WEEE contains: (1) sensor data collected using seven wearable devices placed on four body locations (head, ear, chest, and wrist); (2) respiratory data collected with an indirect calorimeter serving as ground-truth information; (3) demographics and body composition data (e.g., fat percentage); (4) intensity level and type of physical activities, along with their corresponding metabolic equivalent of task (MET) values; and (5) answers to questionnaires about participants’ physical activity level, diet, stress and sleep. Thanks to the diversity of sensors and body locations, we believe that the dataset will enable the development of novel human energy expenditure (EE) estimation techniques for a diverse set of application scenarios. EE refers to the amount of energy an individual uses to maintain body functions and as a result of physical activity. A reliable estimate of people’s EE thus enables computing systems to make inferences about users’ physical activity and help them promoting a healthier lifestyle.

Energy Expenditure (EE) Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardiovascular diseases. Accurate and online EE estimation using small wearable sensors is a difficult task, primarily because most existing schemes work offline or using heuristics. In this work, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs or downstairs) of individuals wearing mobile sensors. We use Convolution Neural Networks (CNNs) to automatically detect important features from data collected from triaxial accelerometer and heart rate sensors. Using CNNs, we find a significant improvement in EE estimation compared to other state-of-the-art models. We compare our results against state-of-the-art Activity-Specific Linear Regression as well as Artificial Neural Networks (ANN) based models. Using a universal CNN model, we obtain an overall low Root Mean Square Error (RMSE) of 1.12 which is 30% and 35% lower than existing models. The results were calibrated against a COSMED K4b2 indirect calorimeter readings.

Wearable devices continuously measure multiple physiological variables to inform users of health and behavior indicators. The computed health indicators must rely on informative signals obtained by processing the raw physiological variables with powerful noise- and artifacts-filtering algorithms. In this study, we aimed to elucidate the effects of signal processing techniques on the accuracy of detecting and discriminating physical activity (PA) and acute psychological stress (APS) using physiological measurements (blood volume pulse, heart rate, skin temperature, galvanic skin response, and accelerometer) collected from a wristband. Data from 207 experiments involving 24 subjects were used to develop signal processing, feature extraction, and machine learning (ML) algorithms that can detect and discriminate PA and APS when they occur individually or concurrently, classify different types of PA and APS, and estimate energy expenditure (EE). Training data were used to generate feature variables from the physiological variables and develop ML models (naïve Bayes, decision tree, k-nearest neighbor, linear discriminant, ensemble learning, and support vector machine). Results from an independent labeled testing data set demonstrate that PA was detected and classified with an accuracy of 99.3%, and APS was detected and classified with an accuracy of 92.7%, whereas the simultaneous occurrences of both PA and APS were detected and classified with an accuracy of 89.9% (relative to actual class labels), and EE was estimated with a low mean absolute error of 0.02 metabolic equivalent of task (MET).The data filtering and adaptive noise cancellation techniques used to mitigate the effects of noise and artifacts on the classification results increased the detection and discrimination accuracy by 0.7% and 3.0% for PA and APS, respectively, and by 18% for EE estimation. The results demonstrate the physiological measurements from wristband devices are susceptible to noise and artifacts, and elucidate the effects of signal processing and feature extraction on the accuracy of detection, classification, and estimation of PA and APS.

Movement sensing using accelerometers is commonly used for the measurement of physical activity (PA) and estimating energy expenditure (EE) under free-living conditions. The major limitation of this approach is lack of accuracy and precision in estimating EE, especially in low-intensity activities. Thus the objective of this study was to investigate benefits of a distributed lag spline (DLS) modeling approach for the prediction of total daily EE (TEE) and EE in sedentary (1.0-1.5 metabolic equivalents; MET), light (1.5-3.0 MET), and moderate/vigorous (> or = 3.0 MET) intensity activities in 10- to 17-year-old youth (n = 76). We also explored feasibility of the DLS modeling approach to predict physical activity EE (PAEE) and METs. Movement was measured by Actigraph accelerometers placed on the hip, wrist, and ankle. With whole-room indirect calorimeter as the reference standard, prediction models (Hip, Wrist, Ankle, Hip+Wrist, Hip+Wrist+Ankle) for TEE, PAEE, and MET were developed and validated using the fivefold cross-validation method. The TEE predictions by these DLS models were not significantly different from the room calorimeter measurements (all P > 0.05). The Hip+Wrist+Ankle predicted TEE better than other models and reduced prediction errors in moderate/vigorous PA for TEE, MET, and PAEE (all P < 0.001). The Hip+Wrist reduced prediction errors for the PAEE and MET at sedentary PA (P = 0.020 and 0.021) compared with the Hip. Models that included Wrist correctly classified time spent at light PA better than other models. The means and standard deviations of the prediction errors for the Hip+Wrist+Ankle and Hip were 0.4 +/- 144.0 and 1.5 +/- 164.7 kcal for the TEE, 0.0 +/- 84.2 and 1.3 +/- 104.7 kcal for the PAEE, and -1.1 +/- 97.6 and -0.1 +/- 108.6 MET min for the MET models. We conclude that the DLS approach for accelerometer data improves detailed EE prediction in youth.

9164 Background: Physical activity is an important component of the physical and social domains of quality of life (QL); therefore any restoration of physical activity level (PAL) towards a normal level may translate into an improvement in QL of cachectic cancer patients. Purpose: We carried out a phase III randomized study to establish which was the most effective and safest treatment to improve the primary endpoints of cancer cachexia and among them we have selected as the most relevant PAL. Patient total daily PAL and associated energy expenditure was assessed with an electronic device (SenseWear PRO2 Armband), shown in some validation studies to be able to assess appropriately the total energy expenditure (TEE) and its specific components, resting energy expenditure (REE) and active energy expenditure (AEE). AEE was recorded at an intensity ≥ 3.0 metabolic equivalents corresponding to a moderate physical activity. The armband is able to identify the specific type of patient physical activity in such a way to attribute to it a “functional quality.” Methods: Seventy out of 332 patients with cancer cachexia enrolled in the study were assessed for total daily PAL before and after treatment. The study design planned to randomly assign eligible patients to 1 of 5 arms of treatment: 1) medroxyprogesterone 500 mg/d or megestrol acetate 320 mg/d; 2) oral supplementation with 2 g EPA; 3) L-carnitine 4 g/d; 4) thalidomide 200 mg/d; 5) a combination of the above. Treatment duration: 4 months. Results: Total daily PAL showed that TEE and AEE increased significantly in arm 5 (TEE from 1291 kcal/die to 1649 kcal/die, p=0.04 and AEE from 93.8 kcal/die to 155 kcal/die, p=0.032) with a concomitant significant decrease of REE (from 1227 ± 439 to 1067 ± 181 kcal/die, p=0.044). The primary endpoints LBM (by DEXA) and fatigue improved significantly in arm 5. Toxicity was substantially negligible, comparable between treatment arms. Conclusions: The present study showed that the combination regimen was the only effective treatment in improving patient total daily PAL. Our trial shows that PAL monitoring provides a new dimension in the assessment of the comprehensive quality of life of cachectic cancer patients. No significant financial relationships to disclose.