-
PloS One 2016Metabolic syndrome (MetS) has been diagnosed in adolescents and among the associated factors are low levels of physical activity, sedentary behavior over long periods... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Metabolic syndrome (MetS) has been diagnosed in adolescents and among the associated factors are low levels of physical activity, sedentary behavior over long periods and low cardiorespiratory fitness. However, specifically in adolescents, studies present conflicting results. The aim of the present study was to conduct a systematic review and meta-analysis of observational studies, in order to map the association between physical activity, sedentary behavior, cardiorespiratory fitness and MetS in adolescents.
METHODS
A search was performed in the databases PubMed, SPORTDiscus, LILACS and the Cochrane Library. For the meta-analysis, the odds ratio (OR) was calculated together with the respective confidence intervals (95% CI), in which the measures of effect were analyzed by dichotomous data (exposure variables) with MetS used as events.
RESULTS
Eighteen studies were included in the meta-analysis. Primary analysis demonstrated that low levels of physical activity (OR = 1.35 [1.03 to 1.79]; p = 0.03) and low cardiorespiratory fitness (OR = 4.05 [2.09 to 7.87]; p < 0.01) were significantly associated with the development of MetS, while for sedentary behavior, represented by screen time > 2 hours/day, a significant association was not identified (OR = 1.20 [0.91 to 1.59]; p = 0.20). Subgroup analyses demonstrated that the association between low physical activity and MetS was dependent on the use of the accelerometry technique (OR = 2.93 [1.56 to 5.47]; p < 0.01). Screen time > 2 hours/day was significantly associated with MetS only on weekends (OR = 2.05 [1.13 to 3.73]; p = 0.02). With respect to cardiorespiratory fitness, a significant association with MetS was found independent of the maximal oxygen uptake (VO2max) measurement method.
CONCLUSIONS
Low levels of physical activity, low indices of cardiorespiratory fitness and sedentary behavior, represented by screen time > 2 hours/day on weekends, were significantly associated with the development of MetS in adolescence.
Topics: Adolescent; Cardiorespiratory Fitness; Exercise; Female; Humans; Male; Metabolic Syndrome; Sedentary Behavior
PubMed: 27997601
DOI: 10.1371/journal.pone.0168503 -
Journal of Medical Internet Research Jul 2023Wearable sensor technologies have the potential to improve monitoring in people with multiple sclerosis (MS) and inform timely disease management decisions. Evidence of... (Review)
Review
BACKGROUND
Wearable sensor technologies have the potential to improve monitoring in people with multiple sclerosis (MS) and inform timely disease management decisions. Evidence of the utility of wearable sensor technologies in people with MS is accumulating but is generally limited to specific subgroups of patients, clinical or laboratory settings, and functional domains.
OBJECTIVE
This review aims to provide a comprehensive overview of all studies that have used wearable sensors to assess, monitor, and quantify motor function in people with MS during daily activities or in a controlled laboratory setting and to shed light on the technological advances over the past decades.
METHODS
We systematically reviewed studies on wearable sensors to assess the motor performance of people with MS. We scanned PubMed, Scopus, Embase, and Web of Science databases until December 31, 2022, considering search terms "multiple sclerosis" and those associated with wearable technologies and included all studies assessing motor functions. The types of results from relevant studies were systematically mapped into 9 predefined categories (association with clinical scores or other measures; test-retest reliability; group differences, 3 types; responsiveness to change or intervention; and acceptability to study participants), and the reporting quality was determined through 9 questions. We followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) reporting guidelines.
RESULTS
Of the 1251 identified publications, 308 were included: 176 (57.1%) in a real-world context, 107 (34.7%) in a laboratory context, and 25 (8.1%) in a mixed context. Most publications studied physical activity (196/308, 63.6%), followed by gait (81/308, 26.3%), dexterity or tremor (38/308, 12.3%), and balance (34/308, 11%). In the laboratory setting, outcome measures included (in addition to clinical severity scores) 2- and 6-minute walking tests, timed 25-foot walking test, timed up and go, stair climbing, balance tests, and finger-to-nose test, among others. The most popular anatomical landmarks for wearable placement were the waist, wrist, and lower back. Triaxial accelerometers were most commonly used (229/308, 74.4%). A surge in the number of sensors embedded in smartphones and smartwatches has been observed. Overall, the reporting quality was good.
CONCLUSIONS
Continuous monitoring with wearable sensors could optimize the management of people with MS, but some hurdles still exist to full clinical adoption of digital monitoring. Despite a possible publication bias and vast heterogeneity in the outcomes reported, our review provides an overview of the current literature on wearable sensor technologies used for people with MS and highlights shortcomings, such as the lack of harmonization, transparency in reporting methods and results, and limited data availability for the research community. These limitations need to be addressed for the growing implementation of wearable sensor technologies in clinical routine and clinical trials, which is of utmost importance for further progress in clinical research and daily management of people with MS.
TRIAL REGISTRATION
PROSPERO CRD42021243249; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=243249.
Topics: Humans; Reproducibility of Results; Sclerosis; Wearable Electronic Devices; Gait; Exercise; Multiple Sclerosis
PubMed: 37498655
DOI: 10.2196/44428 -
Journal of Neuroengineering and... Mar 2017The development of interactive rehabilitation technologies which rely on wearable-sensing for upper body rehabilitation is attracting increasing research interest. This... (Review)
Review
BACKGROUND
The development of interactive rehabilitation technologies which rely on wearable-sensing for upper body rehabilitation is attracting increasing research interest. This paper reviews related research with the aim: 1) To inventory and classify interactive wearable systems for movement and posture monitoring during upper body rehabilitation, regarding the sensing technology, system measurements and feedback conditions; 2) To gauge the wearability of the wearable systems; 3) To inventory the availability of clinical evidence supporting the effectiveness of related technologies.
METHOD
A systematic literature search was conducted in the following search engines: PubMed, ACM, Scopus and IEEE (January 2010-April 2016).
RESULTS
Forty-five papers were included and discussed in a new cuboid taxonomy which consists of 3 dimensions: sensing technology, feedback modalities and system measurements. Wearable sensor systems were developed for persons in: 1) Neuro-rehabilitation: stroke (n = 21), spinal cord injury (n = 1), cerebral palsy (n = 2), Alzheimer (n = 1); 2) Musculoskeletal impairment: ligament rehabilitation (n = 1), arthritis (n = 1), frozen shoulder (n = 1), bones trauma (n = 1); 3) Others: chronic pulmonary obstructive disease (n = 1), chronic pain rehabilitation (n = 1) and other general rehabilitation (n = 14). Accelerometers and inertial measurement units (IMU) are the most frequently used technologies (84% of the papers). They are mostly used in multiple sensor configurations to measure upper limb kinematics and/or trunk posture. Sensors are placed mostly on the trunk, upper arm, the forearm, the wrist, and the finger. Typically sensors are attachable rather than embedded in wearable devices and garments; although studies that embed and integrate sensors are increasing in the last 4 years. 16 studies applied knowledge of result (KR) feedback, 14 studies applied knowledge of performance (KP) feedback and 15 studies applied both in various modalities. 16 studies have conducted their evaluation with patients and reported usability tests, while only three of them conducted clinical trials including one randomized clinical trial.
CONCLUSIONS
This review has shown that wearable systems are used mostly for the monitoring and provision of feedback on posture and upper extremity movements in stroke rehabilitation. The results indicated that accelerometers and IMUs are the most frequently used sensors, in most cases attached to the body through ad hoc contraptions for the purpose of improving range of motion and movement performance during upper body rehabilitation. Systems featuring sensors embedded in wearable appliances or garments are only beginning to emerge. Similarly, clinical evaluations are scarce and are further needed to provide evidence on effectiveness and pave the path towards implementation in clinical settings.
Topics: Accelerometry; Biomechanical Phenomena; Clothing; Humans; Movement; Posture; Range of Motion, Articular; Rehabilitation
PubMed: 28284228
DOI: 10.1186/s12984-017-0229-y -
The Cochrane Database of Systematic... Jun 2023Although exercise is recommended as part of the cystic fibrosis (CF) therapeutic routine, adherence to exercise is still limited. Digital health technologies can provide... (Review)
Review
BACKGROUND
Although exercise is recommended as part of the cystic fibrosis (CF) therapeutic routine, adherence to exercise is still limited. Digital health technologies can provide easy-to-access health information and may help improve healthcare and outcomes in individuals with long-term conditions. However, its effects for delivering and monitoring exercise programs in CF have not yet been synthesized.
OBJECTIVES
To evaluate the benefits and harms of digital health technologies for delivering and monitoring exercise programs, increasing adherence to exercise regimens, and improving key clinical outcomes in people with CF.
SEARCH METHODS
We used standard, extensive Cochrane search methods. The latest search date was 21 November 2022.
SELECTION CRITERIA
We included randomized controlled trials (RCTs) or quasi-RCTs of digital health technologies for delivering or monitoring exercise programs in CF.
DATA COLLECTION AND ANALYSIS
We used standard Cochrane methods. Our primary outcomes were 1. physical activity, 2. self-management behavior, and 3. pulmonary exacerbations. Our secondary outcomes were 4. usability of technologies, 5. quality of life, 6. lung function, 7. muscle strength, 8. exercise capacity, 9. physiologic parameters, and 10.
ADVERSE EVENTS
We used GRADE to assess certainty of evidence.
MAIN RESULTS
We identified four parallel RCTs (three single-center and one multicenter with 231 participants aged six years or older). The RCTs evaluated different modes of digital health technologies with distinct purposes, combined with diverse interventions. We identified important methodologic concerns in the RCTs, including insufficient information on the randomization process, blinding of outcome assessors, balance of non-protocol interventions across groups, and whether the analyses performed corrected for bias due to missing outcome data. Non-reporting of results may also be a concern, especially because some planned outcome results were reported incompletely. Furthermore, each trial had a small number of participants, resulting in imprecise effects. These limitations on the risk of bias, and on the precision of effect estimates resulted in overall low- to very low-certainty evidence. We undertook four comparisons and present the findings for our primary outcomes below. There is no information on the effectiveness of other modes of digital health technologies for monitoring physical activity or delivering exercise programs in people with CF, on adverse events related to the use of digital health technologies either for delivering or monitoring exercise programs in CF, and on their long-term effects (more than one year). Digital health technologies for monitoring physical activity Wearable fitness tracker plus personalized exercise prescription compared to personalized exercise prescription alone One trial (40 adults with CF) evaluated this outcome, but did not report data for any of our primary outcomes. Wearable fitness tracker plus text message for personalized feedback and goal setting compared to wearable fitness tracker alone The evidence is very uncertain about the effects of a wearable fitness tracker plus text message for personalized feedback and goal setting, compared to wearable technology alone on physical activity measured by step count at six-month follow-up (mean difference [MD] 675.00 steps, 95% confidence interval [CI] -2406.37 to 3756.37; 1 trial, 32 participants). The same study measured pulmonary exacerbation rates and reported finding no difference between groups. Web-based application to record, monitor, and set goals on physical activity plus usual care compared to usual care alone Using a web-based application to record, monitor, and set goals on physical activity plus usual care may result in little to no difference on time spent in moderate-to-vigorous physical activity measured via accelerometry compared to usual care alone at six-month follow-up (MD -4 minutes/day, 95% CI -37 to 29; 1 trial, 63 participants). Low certainty-evidence from the same trial suggests that the intervention may result in little to no difference on pulmonary exacerbations during 12 months of follow-up (median 1 respiratory hospitalization, interquartile range [IQR] 0 to 3) versus control (median 1 respiratory hospitalization, IQR 0 to 2; P = 0.6). Digital health technologies for delivering exercise programs Web-based versus face-to-face exercise delivery The evidence is very uncertain about the effects of web-based compared to face-to-face exercise delivery on adherence to physical activity as assessed by the number of participants who completed all exercise sessions after three months of intervention (risk ratio 0.92, 95% CI 0.69 to 1.23; 1 trial, 51 participants).
AUTHORS' CONCLUSIONS
The evidence is very uncertain about the effects of an exercise program plus the use of a wearable fitness tracker integrated with a social media platform compared with exercise prescription alone and on the effects of receiving a wearable fitness tracker plus text message for personalized feedback and goal setting, compared to a wearable fitness tracker alone. Low-certainty evidence suggests that using a web-based application to record, monitor, and set goals on physical activity plus usual care may result in little to no difference in time spent in moderate-to-vigorous physical activity, total time spent in activity, pulmonary exacerbations, quality of life, lung function, and exercise capacity compared to usual care alone. Regarding the use of digital health technologies for delivering exercise programs in CF, the evidence is very uncertain about the effects of using a wearable fitness tracker plus personalized exercise prescription compared to personalized exercise prescription alone. Further high-quality RCTs, with blinded outcome assessors, reporting the effects of digital health technologies on clinically important outcome measures, such as physical activity participation and intensity, self-management behavior, and the occurrence of pulmonary exacerbations in the long term are needed. The results of six ongoing RCTs identified through our searches may help clarify the effects of different modes of digital health technologies for delivering and monitoring exercise programs in people with CF.
Topics: Adult; Humans; Cystic Fibrosis; Digital Technology; Exercise; Exercise Therapy; Multicenter Studies as Topic; Muscle Strength; Quality of Life
PubMed: 37294546
DOI: 10.1002/14651858.CD014605.pub2 -
Sensors (Basel, Switzerland) Sep 2023Measurement of real-world physical activity (PA) data using accelerometry in older adults is informative and clinically relevant, but not without challenges. This review... (Review)
Review
Measurement of real-world physical activity (PA) data using accelerometry in older adults is informative and clinically relevant, but not without challenges. This review appraises the reliability and validity of accelerometry-based PA measures of older adults collected in real-world conditions. Eight electronic databases were systematically searched, with 13 manuscripts included. Intraclass correlation coefficient (ICC) for were: walking duration (0.94 to 0.95), lying duration (0.98 to 0.99), sitting duration (0.78 to 0.99) and standing duration (0.98 to 0.99). ICCs for ranged from 0.24 to 0.82 for step counts and 0.48 to 0.86 for active calories. ranged from 5864 to 10,832 steps and for active calories from 289 to 597 kcal. ICCs for for step count were 0.02 to 0.41, and for active calories 0.07 to 0.93. for step count ranged from 0.83 to 0.98. Percentage of agreement for walking ranged from 63.6% to 94.5%; for lying 35.6% to 100%, sitting 79.2% to 100%, and standing 38.6% to 96.1%. between step count and criteria for moderate-to-vigorous PA was = 0.68 and 0.72. Inter-rater reliability and criterion validity for walking, lying, sitting and standing duration are established. Criterion validity of step count is also established. Clinicians and researchers may use these measures with a limited degree of confidence. Further work is required to establish these properties and to extend the repertoire of PA measures beyond "volume" counts to include more nuanced outcomes such as intensity of movement and duration of postural transitions.
Topics: Independent Living; Reproducibility of Results; Exercise; Walking; Accelerometry
PubMed: 37688071
DOI: 10.3390/s23177615 -
Journal of Biomedical Informatics Jan 2018To review published empirical literature on the use of smartphone-based passive sensing for health and wellbeing.
OBJECTIVE
To review published empirical literature on the use of smartphone-based passive sensing for health and wellbeing.
MATERIAL AND METHODS
A systematic review of the English language literature was performed following PRISMA guidelines. Papers indexed in computing, technology, and medical databases were included if they were empirical, focused on health and/or wellbeing, involved the collection of data via smartphones, and described the utilized technology as passive or requiring minimal user interaction.
RESULTS
Thirty-five papers were included in the review. Studies were performed around the world, with samples of up to 171 (median n = 15) representing individuals with bipolar disorder, schizophrenia, depression, older adults, and the general population. The majority of studies used the Android operating system and an array of smartphone sensors, most frequently capturing accelerometry, location, audio, and usage data. Captured data were usually sent to a remote server for processing but were shared with participants in only 40% of studies. Reported benefits of passive sensing included accurately detecting changes in status, behavior change through feedback, and increased accountability in participants. Studies reported facing technical, methodological, and privacy challenges.
DISCUSSION
Studies in the nascent area of smartphone-based passive sensing for health and wellbeing demonstrate promise and invite continued research and investment. Existing studies suffer from weaknesses in research design, lack of feedback and clinical integration, and inadequate attention to privacy issues. Key recommendations relate to developing passive sensing strategies matching the problem at hand, using personalized interventions, and addressing methodological and privacy challenges.
CONCLUSION
As evolving passive sensing technology presents new possibilities for health and wellbeing, additional research must address methodological, clinical integration, and privacy issues. Doing so depends on interdisciplinary collaboration between informatics and clinical experts.
Topics: Behavior Observation Techniques; Confidentiality; Data Accuracy; Health Behavior; Health Status; Humans; Mental Health; Mobile Applications; Monitoring, Ambulatory; Smartphone
PubMed: 29248628
DOI: 10.1016/j.jbi.2017.12.008 -
Sensors (Basel, Switzerland) Oct 2021The emergence of physiological monitoring technologies has produced exceptional opportunities for real-time collection and analysis of workers' physiological... (Review)
Review
The emergence of physiological monitoring technologies has produced exceptional opportunities for real-time collection and analysis of workers' physiological information. To benefit from these safety and health prognostic opportunities, research efforts have explored the applicability of these devices to control workers' wellbeing levels during occupational activities. A systematic review is proposed to summarise up-to-date progress in applying physiological monitoring systems for occupational groups. Adhering with the PRISMA Statement, five databases were searched from 2014 to 2021, and 12 keywords were combined, concluding with the selection of 38 articles. Sources of risk of bias were assessed regarding randomisation procedures, selective outcome reporting and generalisability of results. Assessment procedures involving non-invasive methods applied with health and safety-related goals were filtered. Working-age participants from homogeneous occupational groups were selected, with these groups primarily including firefighters and construction workers. Research objectives were mainly directed to assess heat stress and physiological workload demands. Heart rate related variables, thermal responses and motion tracking through accelerometry were the most common approaches. Overall, wearable sensors proved to be valid tools for assessing physiological status in working environments. Future research should focus on conducting sensor fusion assessments, engaging wearables in real-time evaluation methods and giving continuous feedback to workers and practitioners.
Topics: Accelerometry; Heart Rate; Heat Stress Disorders; Humans; Monitoring, Physiologic; Workplace
PubMed: 34770556
DOI: 10.3390/s21217249 -
Osteoporosis International : a Journal... Jun 2022Positive associations have been identified between bone outcomes and accelerometer-derived moderate (MPA) and vigorous (VPA) physical activity (PA) in youth; however, it... (Review)
Review
A comparison of the associations between bone health and three different intensities of accelerometer-derived habitual physical activity in children and adolescents: a systematic review.
Positive associations have been identified between bone outcomes and accelerometer-derived moderate (MPA) and vigorous (VPA) physical activity (PA) in youth; however, it remains unclear which intensity is most beneficial. This systematic review aimed to summarise accelerometer-derived methods used to estimate habitual PA in children and adolescents and determine whether the magnitude of association was consistently stronger for a particular intensity (MPA/MVPA/VPA). Observational studies assessing associations between accelerometer-derived MPA and/or MVPA and VPA with bone outcomes in children and adolescents (≤ 18 years) were identified in MEDLINE, EMBASE, Web of Science, SPORTDiscus and the Cochrane Central Register of Controlled Trials. Thirty articles were included (total n = 20,613 (10,077 males), 4-18 years). Chi-square tests determined whether the proportion of significant associations and strongest within-study associations differed significantly between intensities. Results demonstrated that accelerometer methods were highly variable between studies. Of the 570 associations analysed, 186 were significant (p < 0.05). The proportion of within-study strongest associations differed by PA intensity (3 × 2 χ = 86.6, p < 0.001) and was significantly higher for VPA (39%) compared to MVPA (5%; 2 × 2 χ = 55.3, p < 0.001) and MPA (9%, 2 × 2 χ = 49.1, p < 0.001). Results indicated a greater benefit of VPA over MPA/MVPA; however, variability in accelerometer-derived methods used prevents the precise bone-benefitting amount of VPA from being identified. Long epochs and numerous intensity cut-point definitions mean that bone-relevant PA has likely been missed or misclassified in this population. Future research should explore the use of shorter epochs (1 s) and identify bone-specific activity intensities, rather than using pre-defined activity classifications more relevant to cardiovascular health.
Topics: Accelerometry; Adolescent; Bone Density; Child; Exercise; Humans; Male
PubMed: 35089364
DOI: 10.1007/s00198-021-06218-5 -
The International Journal of Behavioral... Feb 2020Early experiences in physical activity (PA) are important to shape healthy movement behaviours long-term; as such, it is critical that PA is promoted from infancy, and... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Early experiences in physical activity (PA) are important to shape healthy movement behaviours long-term; as such, it is critical that PA is promoted from infancy, and that detrimental behaviours (e.g., prolonged sedentary time [ST]) are minimized. The purpose of this systematic review and meta-analysis was to examine infants' and toddlers' movement behaviours across daytime hours.
METHODS
Seven online databases were searched for terms related to infants (< 12 months), toddlers (12-35.9 months), PA, ST, and accelerometry. Two independent reviewers examined 4873 articles for peer-reviewed original research, published in English, that assessed infants' (counts/min) and/or toddlers' PA or ST (min/day) using accelerometry across daytime hours. Infants' mean PA level (counts/min) was averaged across studies, and ranges were produced. Estimates of toddlers' movement behaviours were aggregated meta-analytically to produce average daily rates, and accelerometer placement, cut-point validity, device type, and epoch length were tested as a moderating variables.
RESULTS
Twenty-four studies from 16 countries (published 2011-2019), representing 3699 participants, were included in the systematic review. Five studies reported on infants' PA, which ranged from 78.2 to 2580.5 cpm. Across 20 studies, toddlers' total PA, light PA, moderate-to vigorous-intensity PA, and ST ranged from 72.9 to 636.5, 48.5 to 582.4, 6.5 to 89.9, and 172.7 to 545.0 min/day, respectively. After taking into account accelerometer placement, cut-point validity, device type, and epoch length, we found that toddlers engaged in 246.19 min/day (SE = 28.50; 95% CI: 190.34, 302.04) of total PA, 194.10 min/day (SE = 28.76; 95% CI: 137.73, 250.47) of light PA, and 60.16 min/day (SE = 5.88; 95% CI: 48.64, 71.69) of moderate-to vigorous-intensity PA. Toddlers engaged in 337.04 min/day (SE = 32.67; 95% CI: 273.01, 401.07) of ST.
CONCLUSIONS
With limited studies conducted in infants (n = 5), PA estimates are inconclusive and largely heterogeneous. Overall, toddlers tend to exceed the total PA recommendation of 180 min/day; however, very little of this time is spent at higher movement intensities. Even with high PA rates, toddlers still engage in substantial ST. More consistent and valid measurement protocols are needed to improve comparability across studies.
Topics: Accelerometry; Child, Preschool; Exercise; Humans; Infant; Monitoring, Ambulatory; Sedentary Behavior
PubMed: 32028975
DOI: 10.1186/s12966-020-0912-4 -
Gait & Posture Feb 2019Objective measures using accelerometer-based activity monitors have been extensively used in physical activity (PA) and sedentary behavior (SB) research. To measure PA...
BACKGROUND
Objective measures using accelerometer-based activity monitors have been extensively used in physical activity (PA) and sedentary behavior (SB) research. To measure PA and SB precisely, the field is shifting towards machine learning-based (ML) approaches for calibration and validation of accelerometer-based activity monitors. Nevertheless, various parameters regarding the use and development of ML-based models, including data type (raw acceleration data versus activity counts), sampling frequency, window size, input features, ML technique, accelerometer placement, and free-living settings, affect the predictive ability of ML-based models. The effects of these parameters on ML-based models have remained elusive, and will be systematically reviewed here. The open challenges were identified and recommendations are made for future studies and directions.
METHOD
We conducted a systematic search of PubMed and Scopus databases to identify studies published before July 2017 that used ML-based techniques for calibration and validation of accelerometer-based activity monitors. Additional articles were manually identified from references in the identified articles.
RESULTS
A total of 62 studies were eligible to be included in the review, comprising 48 studies that calibrated and validated ML-based models for predicting the type and intensity of activities, and 22 studies for predicting activity energy expenditure.
CONCLUSIONS
It appears that various ML-based techniques together with raw acceleration data sampled at 20-30 Hz provide the opportunity of predicting the type and intensity of activities, as well as activity energy expenditure with comparable overall predictive accuracies regardless of accelerometer placement. However, the high predictive accuracy of laboratory-calibrated models is not reproducible in free-living settings, due to transitive and unseen activities together with differences in acceleration signals.
Topics: Accelerometry; Calibration; Energy Metabolism; Exercise; Humans; Machine Learning; Sedentary Behavior
PubMed: 30579037
DOI: 10.1016/j.gaitpost.2018.12.003