Smart approaches for assessing free-living energy expenditure following identification of types of physical activity

Raw Photoplethysmography as an Enhancement for Research-Grade Wearable Activity Monitors

Wearable monitors continue to play a critical role in scientific assessments of physical activity. Recently, research-grade monitors have begun providing raw data from photoplethysmography (PPG) alongside standard raw data from inertial sensors (accelerometers and gyroscopes). Raw PPG enables granular and transparent estimation of cardiovascular parameters such as heart rate, thus presenting a valuable alternative to standard PPG methodologies (most of which rely on consumer-grade monitors that provide only coarse output from proprietary algorithms). The implications for physical activity assessment are tremendous, since it is now feasible to monitor granular and concurrent trends in both movement and cardiovascular physiology using a single noninvasive device. However, new users must also be aware of challenges and limitations that accompany the use of raw PPG data. This viewpoint paper therefore orients new users to the opportunities and challenges of raw PPG data by presenting its mechanics, pitfalls, and availability, as well as its parallels and synergies with inertial sensors. This includes discussion of specific applications to the prediction of energy expenditure, activity type, and 24-hour movement behaviors, with an emphasis on areas in which raw PPG data may help resolve known issues with inertial sensing (eg, measurement during cycling activities). We also discuss how the impact of raw PPG data can be maximized through the use of open-source tools when developing and disseminating new methods, similar to current standards for raw accelerometer and gyroscope data. Collectively, our comments show the strong potential of raw PPG data to enhance the use of research-grade wearable activity monitors in science over the coming years.

Machine Learning Algorithms for Activity-Intensity Recognition Using Accelerometer Data

In pervasive healthcare monitoring, activity recognition is critical information for adequate management of the patient. Despite the great number of studies on this topic, a contextually relevant parameter that has received less attention is intensity recognition. In the present study, we investigated the potential advantage of coupling activity and intensity, namely, Activity-Intensity, in accelerometer data to improve the description of daily activities of individuals. We further tested two alternatives for supervised classification. In the first alternative, the activity and intensity are inferred together by applying a single classifier algorithm. In the other alternative, the activity and intensity are classified separately. In both cases, the algorithms used for classification are k-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF). The results showed the viability of the classification with good accuracy for Activity-Intensity recognition. The best approach was KNN implemented in the single classifier alternative, which resulted in 79% of accuracy. Using two classifiers, the result was 97% accuracy for activity recognition (Random Forest), and 80% for intensity recognition (KNN), which resulted in 78% for activity-intensity coupled. These findings have potential applications to improve the contextualized evaluation of movement by health professionals in the form of a decision system with expert rules.

Bidirectional Day-to-Day Associations of Reported Sleep Duration With Accelerometer Measured Physical Activity and Sedentary Time Among Dutch Adolescents: An Observational Study

Objectives

To examine the bidirectional association of sleep duration with proportions of time spent in physical behaviors among Dutch adolescents.

Methods

Adolescents (n = 294, 11-15 years) completed sleep diaries and wore an accelerometer (ActiGraph) over 1 week. With linear mixed-effects models, the authors estimated the association of sleep categories (short, optimal, and long) with the following day's proportion in physical behaviors. With generalized linear mixed models with binomial distribution, the authors estimated the association of physical behavior proportions on sleep categories. Physical behavior proportions were operationalized using percentages of wearing time and by applying a compositional approach. All analyses were stratified by gender accounting for differing developmental stages.

Results

For males (number of observed days: 345, n = 83), short as compared with optimal sleep was associated with the following day's proportion spent in sedentary (-2.57%, p = .03, 95% confidence interval [CI] [-4.95, -0.19]) and light-intensity activities (1.96%, p = .02, 95% CI [0.27, 3.65]), which was not significant in the compositional approach models. Among females (number of observed days: 427, n = 104), long sleep was associated with the proportions spent in moderate- to vigorous-intensity physical activity (1.69%, p < .001, 95% CI [0.75, 2.64]) and in sedentary behavior (-3.02%, p < .01, 95% CI [-5.09, -0.96]), which was replicated by the compositional approach models. None of the associations between daytime activity and sleep were significant (number of obs.: 844, n = 204).

Conclusions

Results indicate partial associations between sleep and the following day's physical behaviors, and no associations between physical behaviors and the following night's sleep.

Validity of Accelerometers for the Evaluation of Energy Expenditure in Obese and Overweight Individuals: A Systematic Review

OBJECTIVE

Even though the validity of accelerometers for the measurement of energy expenditure (EE) has been demonstrated for normal-weight individuals, the applicability of this instrument in obese individuals remains controversial. This review aims to summarize the level of agreement between accelerometers and the gold standards (indirect calorimetry and doubly labelled water) for the measurement of energy expenditure (EE) in obese or overweight individuals.

METHODS

The literature search was limited to comparison studies assessing agreement in EE determination between accelerometers and indirect calorimetry (IC) or doubly labelled water (DLW). We searched in PubMed and in Scopus until March 1, 2019. The analysis was restricted to obese or overweight adult individuals. The following descriptive information was extracted for each study: sample size, characteristics of participants (sex, age, BMI, fat mass percentage, any pathological conditions, modality of recruitment in the study, and exclusion criteria), accelerometer description (model, type and body position), and type of gold standard and validity protocol (duration, conditions, and requirements during and before the experiment). Three review authors independently screened the obtained results, and the quality of the selected articles was assessed by the QUADAS-2 tool.

RESULTS

We obtained seventeen eligible articles, thirteen of which showed concerns for the applicability section, due to the patient selection. Regarding the accelerometers, nine devices were validated in the included studies with the BodyMedia SenseWear® (SWA) being the most frequently validated. Although correlations between accelerometers and the gold standard were high in some studies, agreement between the two methods was low, as shown by the Bland-Altman plots.

CONCLUSIONS

Most accelerometer estimations of EE were inaccurate for obese/overweight subjects, and authors advise to improve the accuracy of algorithms for SWA software, or the predicted equations for estimating EE from other accelerometers.

Use of accelerometer-based activity monitoring in orthopaedics: benefits, impact and practical considerations

Studies of the effectiveness of orthopaedic interventions do not generally measure physical activity (PA). Applying accelerometer-based activity monitoring in orthopaedic studies will add relevant information to the generally examined physical function and pain assessment.Accelerometer-based activity monitoring is practically feasible in orthopaedic patient populations, since current day activity sensors have battery time and memory to measure continuously for several weeks without requiring technical expertise.The ongoing development in sensor technology has made it possible to combine functional tests with activity monitoring.For clinicians, the application of accelerometer-based activity monitoring can provide a measure of PA and can be used for clinical comparisons before and after interventions.In orthopaedic rehabilitation, accelerometer-based activity monitoring may be used to help patients reach their targets for PA and to coach patients towards a more active lifestyle through direct feedback. Cite this article: EFORT Open Rev 2019;4:678-685. DOI: 10.1302/2058-5241.4.180041.

Working against the biological clock: a review for the Occupational Physician

The master clock of the biological rhythm, located in the suprachiasmatic nucleus of the anterior hypothalamus, synchronizes the molecular biological clock found in every cell of most peripheral tissues. The human circadian rhythm is largely based on the light-dark cycle. In night shift workers, alteration of the cycle and inversion of the sleep-wake rhythm can result in disruption of the biological clock and induce adverse health effects. This paper offers an overview of the main physiological mechanisms that regulate the circadian rhythm and of the health risks that are associated with its perturbation in shift and night workers. The Occupational Physician should screen shift and night workers for clinical symptoms related to the perturbation of the biological clock and consider preventive strategies to reduce the associated health risks.

Thyroid Hormone Action and Energy Expenditure

Energy metabolism is one of the most recognized targets of thyroid hormone action, which indeed plays a critical role in modulating energy expenditure in all of its components. This is because thyroid hormone receptors are ubiquitous, and thyroid hormones interact and influence most metabolic pathways in virtually all systems throughout the entire life of the organism. The pleiotropic actions of thyroid hormone are the results of interaction between the local availability of T3 and the signal transduction machinery, which confer in physiologic conditions time and tissue specificity of the hormonal signal despite negligible variations in circulating levels. Historically, the measurement of energy expenditure has been used as the gold standard for the clinical assessment of the hormonal action until the advent of the immunoassays for TSH and thyroid hormone, which have since been used as proxy for measurement of thyroid hormone action. Although the clinical correlates between thyroid hormone action and energy expenditure in cases of extreme dysfunction (florid hyperthyroidism or hypothyroidism) are well recognized, there is still controversy on the effects of moderate, subclinical thyroid dysfunction on energy expenditure and, ultimately, on body weight trajectory. Moreover, little information is available on the effects of thyroid hormone replacement therapy on energy expenditure. This mini review is aimed to define the clinical relevance of thyroid hormone action in normal physiology and functional disorders, as well the effects of thyroid hormone therapy on energy expenditure and the effects of changes in energy status on the thyroid hormone axis.

Targeting lifestyle energy expenditure in the management of obesity and health: from biology to built environment

Increasing lifestyle energy expenditure has long been advocated in the prevention and treatment of obesity, as embodied in the ancient prescription of Hippocrates (the 'father of modern medicine') that people with obesity should eat less and exercise more. However, the long-term outcome of exercise alone or in combination with dieting in obesity management is poor. To understand the reasons underlying these failures and to develop novel strategies that target lifestyle energy expenditure in both prevention and treatment of obesity, research over the past decades has focused on (i) the interactions between physical activity and body weight (and its composition) throughout the lifespan; (ii) the influence of biology and potential compensatory changes in energy expenditure, food intake and food assimilation in response to energy deficits; and (iii) the impact of the built environment (outdoor and indoor) and smart technology on physical activity behaviours, thermoregulatory thermogenesis and metabolic health. It is against this background that recent advances relevant to the theme of 'Targeting Lifestyle Energy Expenditure in the Management of Obesity and Health: From Biology to Built Environment' are addressed in this overview and the nine review articles in this supplement, reporting the proceedings of the 9th Fribourg Obesity Research Conference.

Deep learning-based classification with improved time resolution for physical activities of children

Background

The proportion of overweight and obese people has increased tremendously in a short period, culminating in a worldwide trend of obesity that is reaching epidemic proportions. Overweight and obesity are serious issues, especially with regard to children. This is because obese children have twice the risk of becoming obese as adults, as compared to non-obese children. Nowadays, many methods for maintaining a caloric balance exist; however, these methods are not applicable to children. In this study, a new approach for helping children monitor their activities using a convolutional neural network (CNN) is proposed, which is applicable for real-time scenarios requiring high accuracy.

Methods

A total of 136 participants (86 boys and 50 girls), aged between 8.5 years and 12.5 years (mean 10.5, standard deviation 1.1), took part in this study. The participants performed various movement while wearing custom-made three-axis accelerometer modules around their waists. The data acquired by the accelerometer module was preprocessed by dividing them into small sets (128 sample points for 2.8 s). Approximately 183,600 data samples were used by the developed CNN for learning to classify ten physical activities : slow walking, fast walking, slow running, fast running, walking up the stairs, walking down the stairs, jumping rope, standing up, sitting down, and remaining still.

Results

The developed CNN classified the ten activities with an overall accuracy of 81.2%. When similar activities were merged, leading to seven merged activities, the CNN classified activities with an overall accuracy of 91.1%. Activity merging also improved performance indicators, for the maximum case of 66.4% in recall, 48.5% in precision, and 57.4% in f1 score . The developed CNN classifier was compared to conventional machine learning algorithms such as the support vector machine, decision tree, and k-nearest neighbor algorithms, and the proposed CNN classifier performed the best: CNN (81.2%) > SVM (64.8%) > DT (63.9%) > kNN (55.4%) (for ten activities); CNN (91.1%) > SVM (74.4%) > DT (73.2%) > kNN (65.3%) (for the merged seven activities).

Discussion

The developed algorithm distinguished physical activities with improved time resolution using short-time acceleration signals from the physical activities performed by children. This study involved algorithm development, participant recruitment, IRB approval, custom-design of a data acquisition module, and data collection. The self-selected moving speeds for walking and running (slow and fast) and the structure of staircase degraded the performance of the algorithm. However, after similar activities were merged, the effects caused by the self-selection of speed were reduced. The experimental results show that the proposed algorithm performed better than conventional algorithms. Owing to its simplicity, the proposed algorithm could be applied to real-time applicaitons.

Strength exercises during physical education classes in secondary schools improve body composition: a cluster randomized controlled trial

BACKGROUND

Metabolic health in people with obesity is determined by body composition. In this study, we examined the influence of a combined strength exercise and motivational programme -embedded in the school curriculum- on adolescents body composition and daily physical activity.

METHODS

A total of 695 adolescents (11-15y) from nine Dutch secondary schools participated in a one year cluster randomised controlled trial (RCT). In the intervention schools, physical education teachers were instructed to spend 15-30 min of all physical education lessons (2× per week) on strength exercises. Monthly motivational lessons were given to stimulate students to be more physically active. Control schools followed their usual curriculum. The primary outcome measure was body composition assessed by the deuterium dilution technique. Daily physical activity and sedentary behaviour measured by accelerometry served as a secondary outcome.

RESULTS

After 1 year, a 1.6% fat mass difference was found in favour of the intervention group (p = .007). This reflected a 0.9 kg difference in fat free mass (intervention>control; p = .041) and 0.7 kg difference in fat mass (intervention

CONCLUSION

In 11-15 year olds, the combination of strength exercises plus motivational lessons contributed to an improvement in body composition and a smaller decrease in physical activity level. TRIAL REGISTRATION ID: ( NTR5676 - retrospectively registered 8 February 2016; enrolment of first participant: 2 March 2015).

Collapse

Key Words

• Body composition
• Cluster randomised controlled trial
• Motivation
• Overweight and obesity
• Physical activity
• School-based
• Strength exercises

Collapse

MESH Headings

• Adolescent
• Adolescent Behavior
• Body Composition
• Child
• Cluster Analysis
• Curriculum
• Female
• Humans
• Male
• Motivation
• Muscle Strength
• Netherlands
• Obesity/prevention & control
• Physical Education and Training/methods
• Program Evaluation/methods
• Retrospective Studies
• School Health Services
• Schools
• Students

Collapse

Grants

• 525001004 ZonMw

Collapse

Affiliation(s)

G. A. Ten Hoor Department of Human Biology and Movement Sciences, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands Department of Work and Social Psychology, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
G. M. Rutten Department of Health Promotion, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands
G. J. P. Van Breukelen Department of Methodology and Statistics, CAPHRI, Care and Public Health Research Institute, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
G. Kok Department of Work and Social Psychology, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
R. A. C. Ruiter Department of Work and Social Psychology, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
K Meijer Department of Human Biology and Movement Sciences, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands
S. P. J. Kremers Department of Health Promotion, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands
F. J. M. Feron Department of Social Medicine, CAPHRI, Care and Public Health Research Institute, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
R. Crutzen Department of Health Promotion, CAPHRI, Care and Public Health Research Institute, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands
A. M. J. W. Schols Department of Respiratory Medicine, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands
G. Plasqui Department of Human Biology and Movement Sciences, NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University Medical Centre+, P.O. Box 616, 6200 MD Maastricht, The Netherlands

Collapse

Methods for Activity Monitor Validation Studies: An Example With the Fitbit Charge

Purpose: To advance research practices with consumer monitors, standard validation methods are needed. This study provides an example of best practices through systematically evaluating the validity of the Fitbit Charge (FBC) under free-living conditions using a strong reference measure and robust measurement agreement methods. Methods: 94 healthy participants (Mage 41.8 ±9.3 yrs) wore a FBC and two research grade accelerometers (Actigraph GT3X and activPAL) as they went about normal activities for a week. Estimated daily minutes of moderate to vigorous physical activity (MVPA) from the FBC were compared against reference estimates obtained from the Sojourns Including Posture (SIP) methodology, while daily step counts were compared against the activPAL. Results: Correlations with reference indicators were high for average daily MVPA (r = 0.8; p < .0001) and steps (r = 0.76; p < .0001), but the FBC overestimated time spent in MVPA by 56% and steps by 15%. The mean absolute percent errors of MVPA and steps estimated by FBC were 71.5% and 30.0%, respectively. Neither of the MVPA and step estimates from the FBC fell into the ±10% equivalence zone set by the criterion. The Kappa statistics of the classification agreement between the two MVPA assessment methods was 0.32 with a low sensitivity of 30.1% but a high specificity of 96.7%. Conclusion: The FBC overestimated minutes of MVPA and steps when compared to both reference assessments in free-living conditions. Standardized reporting in future studies will facilitate comparisons with other monitors and with future versions of the FBC.

Automatic energy expenditure measurement for health science

BACKGROUND AND OBJECTIVE

It is crucial to predict the human energy expenditure in any sports activity and health science application accurately to investigate the impact of the activity. However, measurement of the real energy expenditure is not a trivial task and involves complex steps. The objective of this work is to improve the performance of existing estimation models of energy expenditure by using machine learning algorithms and several data from different sensors and provide this estimation service in a cloud-based platform.

METHODS

In this study, we used input data such as breathe rate, and hearth rate from three sensors. Inputs are received from a web form and sent to the web service which applies a regression model on Azure cloud platform. During the experiments, we assessed several machine learning models based on regression methods.

RESULTS

Our experimental results showed that our novel model which applies Boosted Decision Tree Regression in conjunction with the median aggregation technique provides the best result among other five regression algorithms.

CONCLUSIONS

This cloud-based energy expenditure system which uses a web service showed that cloud computing technology is a great opportunity to develop estimation systems and the new model which applies Boosted Decision Tree Regression with the median aggregation provides remarkable results.

Nutrition, movement and sleep behaviours: their interactions in pathways to obesity and cardiometabolic diseases

Among the multitude of dietary and lifestyle behaviours that have been proposed to contribute to the obesity epidemic, those that have generated considerable research scrutiny in the past decade are centred upon sleep behaviours, sedentary behaviours (sitting or lying while awake) and diminished low-level physical activities of everyday life, with each category of behaviours apparently presenting an independent risk for obesity and/or cardiometabolic diseases. These behaviours are highly complex, operate in synergy with each other, disrupt the link between regulation of the circadian clock and metabolic physiology and impact on various components of daily energy expenditure and feeding behaviours to promote obesity and hinder the outcome of obesity therapy. As such, this behavioural triad (nutrition, movement and sleep) presents plenty of scope for intervention and optimization in the context of body weight regulation and lifestyle-related disease prevention. It is against this background that recent advances relevant to the theme of 'Nutrition, Movement & Sleep Behaviors: their interactions in pathways to obesity and cardiometabolic diseases' are addressed in this overview and the nine review articles in this supplement reporting the proceedings of the 8th Fribourg Obesity Research Conference.