scholarly journals Classification Accuracy of a Wearable Activity Tracker for Assessing Sedentary Behavior and Physical Activity in 3–5-Year-Old Children

2018 ◽  
Vol 15 (4) ◽  
pp. 594 ◽  
Author(s):  
Wonwoo Byun ◽  
Jung-Min Lee ◽  
Youngwon Kim ◽  
Timothy Brusseau
Keyword(s):  
Physical Activity ◽  
Sedentary Behavior ◽  
Classification Accuracy ◽  
Activity Tracker ◽  
Wearable Activity Tracker

scholarly journals Consumer-Based Wearable Activity Trackers Increase Physical Activity Participation: Systematic Review and Meta-Analysis (Preprint)

2018 ◽  
Author(s):  
Katie-Jane Brickwood ◽  
Greig Watson ◽  
Jane O'Brien ◽  
Andrew D Williams
Keyword(s):  
Physical Activity ◽  
Sedentary Behavior ◽  
Physical Activity Participation ◽  
Activity Participation ◽  
Activity Levels ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Wearable Activity Trackers ◽  
Wearable Activity Tracker ◽  
Meta Analyses

BACKGROUND The range of benefits associated with regular physical activity participation is irrefutable. Despite the well-known benefits, physical inactivity remains one of the major contributing factors to ill-health throughout industrialized countries. Traditional lifestyle interventions such as group education or telephone counseling are effective at increasing physical activity participation; however, physical activity levels tend to decline over time. Consumer-based wearable activity trackers that allow users to objectively monitor activity levels are now widely available and may offer an alternative method for assisting individuals to remain physically active. OBJECTIVE This review aimed to determine the effects of interventions utilizing consumer-based wearable activity trackers on physical activity participation and sedentary behavior when compared with interventions that do not utilize activity tracker feedback. METHODS A systematic review was performed searching the following databases for studies that included the use of a consumer-based wearable activity tracker to improve physical activity participation: Cochrane Controlled Register of Trials, MEDLINE, PubMed, Scopus, Web of Science, Cumulative Index of Nursing and Allied Health Literature, SPORTDiscus, and Health Technology Assessments. Controlled trials of adults comparing the use of a consumer-based wearable activity tracker with other nonactivity tracker–based interventions were included. The main outcome measures were physical activity participation and sedentary behavior. All studies were assessed for risk of bias, and the Grades of Recommendation, Assessment, Development, and Evaluation system was used to rank the quality of evidence. The guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement were followed. A random-effects meta-analysis was completed on the included outcome measures to estimate the treatment effect of interventions that included an activity tracker compared with a control group. RESULTS There was a significant increase in daily step count (standardized mean difference [SMD] 0.24; 95% CI 0.16 to 0.33; P<.001), moderate and vigorous physical activity (SMD 0.27; 95% CI 0.15 to 0.39; P<.001), and energy expenditure (SMD 0.28; 95% CI 0.03 to 0.54; P=.03) and a nonsignificant decrease in sedentary behavior (SMD −0.20; 95% CI −0.43 to 0.03; P=.08) following the intervention versus control comparator across all studies in the meta-analyses. In general, included studies were at low risk of bias, except for performance bias. Heterogeneity varied across the included meta-analyses ranging from low (I2=3%) for daily step count through to high (I2=67%) for sedentary behavior. CONCLUSIONS Utilizing a consumer-based wearable activity tracker as either the primary component of an intervention or as part of a broader physical activity intervention has the potential to increase physical activity participation. As the effects of physical activity interventions are often short term, the inclusion of a consumer-based wearable activity tracker may provide an effective tool to assist health professionals to provide ongoing monitoring and support.

A personalised smartphone-delivered just-in-time adaptive intervention (JITABug) to increase physical activity in older adults: A feasibility pilot study (Preprint)

2021 ◽  
Author(s):  
Jacqueline Louise Mair ◽  
Lawrence Hayes ◽  
Amy Campbell ◽  
Duncan Buchan ◽  
Chris Easton ◽  
...  
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
Data Collection ◽  
Real Time ◽  
Behaviour Change ◽  
Time Of Day ◽  
Activity Level ◽  
Just In Time ◽  
Activity Tracker ◽  
Wearable Activity Tracker

BACKGROUND Just-in-time-adaptive-interventions (JITAIs) provide real-time ‘in the moment’ behaviour change support to people when they need it most. JITAIs could be a viable way to provide personalised physical activity support to older adults in the community. However, it is unclear how feasible it is to remotely deliver a physical activity intervention via a smartphone to older adults, or how acceptable older adults would find a JITAI targeting physical activity in everyday life. OBJECTIVE (1) to describe the development of “JITABug”, a personalised smartphone and activity tracker delivered JITAI designed to support older adults to increase or maintain their physical activity level; (2) to explore the acceptability of JITABug in a free-living setting, and (3) to assess the feasibility of conducting an effectiveness trial of the JITABug intervention. METHODS The intervention development process was underpinned by the Behaviour Change Wheel. The intervention consisted of a wearable activity tracker (Fitbit) and a companion smartphone app (JITABug) which delivered goal setting, planning, reminders, and just-in-time adaptive messages to encourage achievement of personalised physical activity goals. Message delivery was tailored based on time of day, real-time physical activity tracker data, and weather conditions. We tested the feasibility of remotely delivering the JITAI with older adults in a 6-week trial using a mixed-methods approach. Data collection involved assessment of physical activity by accelerometery and activity tracker, self-reported mood and mental wellbeing via ecological momentary assessment, and contextual information on physical activity via voice memos. Feasibility and acceptability outcomes included: (1) recruitment capability and adherence to the intervention; (2) intervention delivery ‘in the wild’; (3) appropriateness of data collection methodology; (4) adverse events and; (5) participant satisfaction. RESULTS Of 46 recruited older adults (aged 56-72 years old), 65% completed the intervention. The intervention was successfully delivered as intended; 27 participants completed the intervention independently, 94% of physical activity messages were successfully delivered, and 99% of Fitbit and 100% of weather data calls were successful. Wrist-worn accelerometer data were obtained from 96% at baseline and 96% at follow up. On average, participants recorded 8/16 (50%) voice memos, 3/8 (38%) mood assessments, and 2/4 (50%) wellbeing assessments via the app. Overall acceptability of the intervention was very good (77% satisfaction). Participant feedback suggested that more diverse and tailored physical activity messages, app usage reminders, technical refinements regarding real-time data syncing, and an improved user interface could improve the intervention and make it more appealing. CONCLUSIONS This study suggests that a smartphone delivered JITAI utilizing a wearable activity tracker is an acceptable way to support physical activity in older adults in the community. Overall, the intervention is feasible, however based on user feedback, the JITABug app requires further technical refinements that may enhance usage, engagement, and user satisfaction before moving to effectiveness trials. CLINICALTRIAL Non-Applicable

scholarly journals Using a consumer-based wearable activity tracker for physical activity goal setting and measuring steps in pregnant women with gestational diabetes mellitus: exploring acceptance and validity

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Samantha F. Ehrlich ◽  
Jill M. Maples ◽  
Cristina S. Barroso ◽  
Kathleen C. Brown ◽  
David R. Bassett ◽  
...  
Keyword(s):  
Physical Activity ◽  
Gestational Diabetes ◽  
Goal Setting ◽  
Equivalence Testing ◽  
Structured Interviews ◽  
Self Monitoring ◽  
Activity Tracker ◽  
Wearable Activity Tracker ◽  
Stepping In Place ◽  
Monitoring Devices

Abstract Background Activity monitoring devices may be used to facilitate goal-setting, self-monitoring, and feedback towards a step-based physical activity (PA) goal. This study examined the performance of the wrist-worn Fitbit Charge 3™ (FC3) and sought opinions on walking and stepping-in-place from women with gestational diabetes (GDM). Methods Participants completed six 2-min metronome-assisted over ground bouts that varied by cadence (67, 84, or 100 steps per minute) and mode (walking or stepping-in-place; N = 15), with the sequence randomized. Steps were estimated by FC3 and measured, in duplicate, by direct observation (hand-tally device, criterion). Equivalence testing by the two one-sided tests (TOST) method assessed agreement within ± 15%. Mean absolute percent error (MAPE) of steps were compared to 10%, the accuracy standard of the Consumer Technology Association (CTA)™. A subset (n = 10) completed a timed, 200-m self-paced walk to assess natural walking pace and cadence. All participants completed semi-structured interviews, which were transcribed and analyzed using descriptive and interpretive coding. Results Mean age was 27.0 years (SD 4.2), prepregnancy BMI 29.4 kg/m2 (8.3), and gestational age 32.8 weeks (SD 2.6). The FC3 was equivalent to hand-tally for bouts of metronome-assisted walking and stepping-in-place at 84 and 100 steps per minute (i.e., P < .05), although walking at 100 steps per minute (P = .01) was no longer equivalent upon adjustment for multiple comparisons (i.e., at P < .007). The FC3 was equivalent to hand-tally during the 200-m walk (i.e., P < .001), in which mean pace was 68.2 m per minute (SD 10.7), or 2.5 miles per hour, and mean cadence 108.5 steps per minute (SD 6.5). For walking at 84 and 100 steps per minute, stepping-in-place at 100 steps per minute, and the 200-m walk, MAPE was within 10%, the accuracy standard of the CTA™. Interviews revealed motivation for PA, that stepping-in-place was an acceptable alternative to walking, and competing responsibilities made it difficult to find time for PA. Conclusions The FC3 appears to be a valid step counter during the third trimester, particularly when walking or stepping-in-place at or close to women’s preferred cadence.

scholarly journals Calibrating Wrist-Worn Accelerometers for Physical Activity Assessment in Preschoolers: Machine Learning Approaches (Preprint)

2019 ◽  
Author(s):  
Shiyu Li ◽  
Jeffrey T Howard ◽  
Erica T Sosa ◽  
Alberto Cordova ◽  
Deborah Parra-Medina ◽  
...  
Keyword(s):  
Physical Activity ◽  
Machine Learning ◽  
Cluster Analysis ◽  
Sedentary Behavior ◽  
Classification Accuracy ◽  
Characteristic Curve ◽  
Learning Approaches ◽  
Cut Points ◽  
Activity Intensity ◽  
Vector Magnitude

BACKGROUND Physical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency in the methods for quantification of PA levels among preschoolers remains a problem. OBJECTIVE This study aimed to develop PA intensity cut points for wrist-worn accelerometers by using machine learning (ML) approaches to assess PA in preschoolers. METHODS Wrist- and hip-derived acceleration data were collected simultaneously from 34 preschoolers on 3 consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut points to classify accelerometer counts into sedentary behavior, light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). Physical activity intensity levels identified by hip-worn accelerometer VM cut points were used as reference to train the supervised ML models. Vector magnitude counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Daily estimates of PA were compared to the hip-reference criterion. RESULTS In total, 3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut points for wrist-worn accelerometers. Among the three ML models, k-means cluster analysis derived the following cut points: ≤2556 counts per minute (cpm) for sedentary behavior, 2557-7064 cpm for LPA, 7065-14532 cpm for MPA, and ≥14533 cpm for VPA; in addition, k-means cluster analysis had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories, as examined by the hip reference. Additionally, k-means cut points exhibited the most accurate estimates on sedentary behavior, LPA, and VPA as the hip reference. None of the three wrist methods were able to accurately assess MPA. CONCLUSIONS This study demonstrates the potential of ML approaches in establishing cut points for wrist-worn accelerometers to assess PA in preschoolers. However, the findings from this study warrant additional validation studies.

scholarly journals A Wearable Activity Tracker Intervention With and Without Weekly Behavioral Support Emails to Promote Physical Activity Among Women Who Are Overweight or Obese: Randomized Controlled Trial

10.2196/28128 ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. e28128
Author(s):  
Melissa Black ◽  
Jennifer Brunet
Keyword(s):  
Physical Activity ◽  
Psychological Needs ◽  
Behavioral Support ◽  
Activity Tracker ◽  
Wearable Activity Tracker ◽  
Group 3 ◽  
Vigorous Intensity ◽  
Group 2 ◽  
Group 1

Background Physical activity (PA) plays a fundamental role in combating the current obesity epidemic; however, most women who are overweight or obese are generally physically inactive. Wearable activity tracker interventions can help increase the PA levels in this population. Supplementing such interventions with behavioral support emails may further improve their effectiveness, but this remains to be confirmed. Objective This study aims to determine if adding behavioral support emails to a wearable activity tracker intervention can further increase PA levels among women who are overweight or obese in comparison to a wearable activity tracker–only intervention and a control condition. Methods Women with a BMI ≥25 kg/m2 who were not meeting the Canadian PA guidelines for aerobic and strength training were randomized into 1 of 3 groups. Group 1 received 6 weekly behavioral support emails, a wearable activity tracker, and a copy of the Canadian PA guidelines. Group 2 received a wearable activity tracker and a copy of the Canadian PA guidelines, and group 3 (control condition) received a copy of the Canadian PA guidelines. Self-reported data for walking and moderate to vigorous intensity PA were collected preintervention (week 0; prerandomization), postintervention (7 weeks postrandomization), and at follow-up (21 weeks postrandomization) and analyzed as metabolic equivalent of task minutes per week. In addition, potential mechanisms of behavior change (ie, basic psychological needs satisfaction and motivational regulations) were assessed for within- and between-group differences at all 3 time points. Data were analyzed using nonparametric statistical tests. Results A total of 49 women were recruited; data from 47 women (mean age 37.57 years, SD 11.78 years; mean BMI 31.69 kg/m2, SD 5.97 kg/m2) were available for analysis. Group 1 reported a significant increase in walking from preintervention to postintervention (χ22=7.5; P=.02) but not in moderate to vigorous intensity PA (P=.24). Group 1 also reported significant increases in perceptions of competence from preintervention to follow-up (χ22=7.6; P=.02) and relatedness from preintervention to follow-up (χ22=8.7; P=.005). Increases in perceived autonomy were observed for group 2 (χ22=7.0) and group 3 (χ22=10.6). There were no significant changes in the motivational regulations within the groups. The difference between the groups was not significant for any outcome variable. Conclusions The results suggest that adding behavioral support emails to a wearable activity tracker intervention may help to increase time spent walking and perceptions of competence and relatedness for PA among women who are overweight or obese. Trial Registration ClinicalTrials.gov NCT03601663; http://clinicaltrials.gov/ct2/show/NCT03601663

scholarly journals Daily Physical Activity and Sleep Measured by Wearable Activity Trackers during the Coronavirus Disease 2019 Pandemic: A Lesson for Preventing Physical Inactivity during Future Pandemics

2021 ◽  
Vol 11 (21) ◽  
pp. 9956
Author(s):  
Hidetaka Hamasaki
Keyword(s):  
Physical Activity ◽  
Physical Inactivity ◽  
The Body ◽  
Daily Physical Activity ◽  
Healthcare Organizations ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Wearable Activity Trackers ◽  
Wearable Activity Tracker ◽  
The Impact

Wearable activity trackers are devices that are comfortably worn on the body and are designed to be effective in monitoring daily physical activity and improving physical fitness of the wearer. This review aimed to investigate the impact of the coronavirus disease 2019 (COVID-19) pandemic on physical activity measured using wearable activity trackers and discuss future perspectives on wearable activity trackers during pandemics. Daily physical activity was significantly decreased during the COVID-19 pandemic. The implementation of strict public health measures, such as total lockdown, can decrease people’s physical activity by 50% or more of that prior to the lockdown. Physical inactivity is significantly associated with several health problems, including obesity, diabetes, cardiovascular disease, and cancers; therefore, an effective healthcare system to prevent physical inactivity during pandemics should be established. It is essential to create a network between healthcare organizations and wearable activity tracker users to monitor real-time health status and prepare for the future pandemic.

scholarly journals Parental Perspectives of a Wearable Activity Tracker for Children Younger Than 13 Years: Acceptability and Usability Study

10.2196/13858 ◽  
2019 ◽  
Vol 7 (11) ◽  
pp. e13858 ◽  
Author(s):  
Kelly A Mackintosh ◽  
Stephanie E Chappel ◽  
Jo Salmon ◽  
Anna Timperio ◽  
Kylie Ball ◽  
...  
Keyword(s):  
Physical Activity ◽  
Activity Levels ◽  
Distance Information ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Activity Promotion ◽  
Parental Perspectives ◽  
Physical Activity Levels ◽  
Wearable Activity Trackers ◽  
Wearable Activity Tracker

Background There is increasing availability of, and interest in, wearable activity trackers for children younger than 13 years. However, little is known about how children and parents use these activity trackers or perceive their acceptability. Objective This study primarily aimed to ascertain parental perspectives on the acceptability and usability of wearables designed to monitor children’s physical activity levels. Secondary aims were to (1) identify practical considerations for future use in physical activity interventions and promotion initiatives; (2) determine use of different features and functions incorporated into the accompanying app; and (3) identify parents’ awareness of their child’s current physical activity levels. Methods In total, 36 children (18 boys and 18 girls) aged 7-12 years were asked to wear a wrist-worn activity tracker (KidFit) for 4 consecutive weeks and to use the accompanying app with parental assistance and guidance. Each week, one parent from each family (n=25; 21 mothers and 4 fathers) completed a Web-based survey to record their child’s activity tracker use, app interaction, and overall experiences. At the end of the 4-week period, a subsample of 10 parents (all mothers) participated in face-to-face interviews exploring perceptions of the acceptability and usability of wearable activity trackers and accompanying apps. Quantitative and qualitative data were analyzed descriptively and thematically, respectively. Thematic data are presented using pen profiles, which were constructed from verbatim transcripts. Results Parents reported that they and their children typically found the associated app easy to use for activity tracking, though only step or distance information was generally accessed and some difficulties interpreting the data were reported. Children were frustrated with not being able to access real-time feedback, as the features and functions were only available through the app, which was typically accessed by, or in the presence of, parents. Parents identified that children wanted additional functions including a visual display to track and self-monitor activity, access to the app for goal setting, and the option of undertaking challenges against schools or significant others. Other barriers to the use of wearable activity trackers included discomfort of wearing the monitor because of the design and the inability to wear for water- or contact-based sports. Conclusions Most parents reported that the wearable activity tracker was easy for their child or children to use and a useful tool for tracking their children’s daily activity. However, several barriers were identified, which may impact sustained use over time; both the functionality and wearability of the activity tracker should therefore be considered. Overall, wearable activity trackers for children have the potential to be integrated into targeted physical activity promotion initiatives.

Sign in / Sign up

Export Citation Format

Share Document