scholarly journals Automatic Identification of Physical Activity Type and Duration by Wearable Activity Trackers: A Validation Study (Preprint)

2019 ◽  
Author(s):  
Diana Dorn ◽  
Jessica Gorzelitz ◽  
Ronald Gangnon ◽  
David Bell ◽  
Kelli Koltyn ◽  
...  
Keyword(s):  
Physical Activity ◽  
Treadmill Walking ◽  
Treadmill Running ◽  
Automatic Identification ◽  
Activity Type ◽  
Activity Duration ◽  
Activity Trackers ◽  
Outdoor Walking ◽  
Wearable Activity Trackers ◽  
Activity Types

BACKGROUND Activity trackers are now ubiquitous in certain populations, with potential applications for health promotion and monitoring and chronic disease management. Understanding the accuracy of this technology is critical to the appropriate and productive use of wearables in health research. Although other peer-reviewed validations have examined other features (eg, steps and heart rate), no published studies to date have addressed the accuracy of automatic activity type detection and duration accuracy in wearable trackers. OBJECTIVE The aim of this study was to examine the ability of 4 commercially available wearable activity trackers (Fitbits Flex 2, Fitbit Alta HR, Fitbit Charge 2, and Garmin Vívosmart HR), in a controlled setting, to correctly and automatically identify the type and duration of the physical activity being performed. METHODS A total of 8 activity types, including walking and running (on both a treadmill and outdoors), a run embedded in walking bouts, elliptical use, outdoor biking, and pool lap swimming, were tested by 28 to 34 healthy adult participants (69 total participants who participated in some to all activity types). Actual activity type and duration were recorded by study personnel and compared with tracker data using descriptive statistics and mean absolute percent error (MAPE). RESULTS The proportion of trials in which the activity type was correctly identified was 93% to 97% (depending on the tracker) for treadmill walking, 93% to 100% for treadmill running, 36% to 62% for treadmill running when preceded and followed by a walk, 97% to 100% for outdoor walking, 100% for outdoor running, 3% to 97% for using an elliptical, 44% to 97% for biking, and 87.5% for swimming. When activities were correctly identified, the MAPE of the detected duration versus the actual activity duration was between 7% and 7.9% for treadmill walking, 8.7% and 144.8% for treadmill running, 23.6% and 28.9% for treadmill running when preceded and followed by a walk, 4.9% and 11.8% for outdoor walking, 5.6% and 9.6% for outdoor running, 9.7% and 13% for using an elliptical, 9.5% and 17.7% for biking, and was 26.9% for swimming. CONCLUSIONS In a controlled setting, wearable activity trackers provide accurate recognition of the type of some common physical activities, especially outdoor walking and running and walking on a treadmill. The accuracy of measurement of activity duration varied considerably by activity type and tracker model and was poor for complex sets of activity, such as a run embedded within 2 walking segments.

scholarly journals Automatic Identification of Physical Activity Type and Duration by Wearable Activity Trackers: A Validation Study

10.2196/13547 ◽  
2019 ◽  
Vol 7 (5) ◽  
pp. e13547 ◽  
Author(s):  
Diana Dorn ◽  
Jessica Gorzelitz ◽  
Ronald Gangnon ◽  
David Bell ◽  
Kelli Koltyn ◽  
...  
Keyword(s):  
Physical Activity ◽  
Validation Study ◽  
Automatic Identification ◽  
Activity Type ◽  
Activity Trackers ◽  
Wearable Activity Trackers

scholarly journals The Acceptability, Feasibility and Effectiveness of Wearable Activity Trackers for Increasing Physical Activity in Children and Adolescents: A Systematic Review

2021 ◽  
Vol 18 (12) ◽  
pp. 6211
Author(s):  
Amy V. Creaser ◽  
Stacy A. Clemes ◽  
Silvia Costa ◽  
Jennifer Hall ◽  
Nicola D. Ridgers ◽  
...  
Keyword(s):  
Physical Activity ◽  
Systematic Review ◽  
Children And Adolescents ◽  
Behaviour Change Techniques ◽  
Physically Active ◽  
Self Monitoring ◽  
Start Date ◽  
Activity Trackers ◽  
Wearable Activity Trackers

Wearable activity trackers (wearables) embed numerous behaviour change techniques (BCTs) that have previously been shown to increase adult physical activity (PA). With few children and adolescents achieving PA guidelines, it is crucial to explore ways to increase their PA. This systematic review examined the acceptability, feasibility, and effectiveness of wearables and their potential mechanisms of action for increasing PA in 5 to 19-year-olds. A systematic search of six databases was conducted, including data from the start date of each database to December 2019 (PROSPERO registration: CRD42020164506). Thirty-three studies were included. Most studies (70%) included only adolescents (10 to 19 years). There was some—but largely mixed—evidence that wearables increase steps and moderate-to-vigorous-intensity PA and reduce sedentary behaviour. There were no apparent differences in effectiveness based on the number of BCTs used and between studies using a wearable alone or as part of a multi-component intervention. Qualitative findings suggested wearables increased motivation to be physically active via self-monitoring, goal setting, feedback, and competition. However, children and adolescents reported technical difficulties and a novelty effect when using wearables, which may impact wearables’ long-term use. More rigorous and long-term studies investigating the acceptability, feasibility, and effectiveness of wearables in 5 to 19-year-olds are warranted.

Who Uses Wearable Activity Trackers and Why? A Comparison of Former and Current Users in the United States

2020 ◽  
Vol 34 (7) ◽  
pp. 762-769
Author(s):  
Ciarán P. Friel ◽  
Carol Ewing Garber
Keyword(s):  
Physical Activity ◽  
Average Length ◽  
Physical Activity Behavior ◽  
The United States ◽  
Web Based ◽  
Shared Data ◽  
Activity Trackers ◽  
Wearable Activity Trackers ◽  
Average Current ◽  
Activity Behavior

Background: There has been an explosion in the use of wearable activity trackers (WATs), but we do not fully understand who wears them and why. This study’s purpose was to describe the characteristics of WAT users and to compare current and former users. Materials and Methods: A variety of internet-based resources (eg, Craigslist, Facebook) were used to recruit current and former WAT users. Respondents completed a web-based survey, where they provided information on sociodemographic characteristics, health, physical activity behavior, and about their WAT use. Results: Of the 2826 respondents who gave informed consent, 70.8% (n = 2002) met inclusion criteria for this analysis. Respondents ranged from 18 to 81 years old (mean 32.9 ± 12.2 standard deviation) with 73.8% women. Most were current WAT users (68.7%), and the average length of WAT use overall was 9.3 ± 9.7 months. On average, current users wore the device for 3.7 months longer than former users. Compared to current users, former users had a lower body mass index (1.2 kg/m2 less), reported fewer medical conditions, shared data from their device less often, and received the device as a gift more frequently. Conclusions: Current and former users varied in their reasons for using a WAT and how they used their device. Differences identified between these groups support further exploration of associations between WAT users’ profiles and their physical activity behavior.

scholarly journals Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4504 ◽  
Author(s):  
Petra Jones ◽  
Evgeny M. Mirkes ◽  
Tom Yates ◽  
Charlotte L. Edwardson ◽  
Mike Catt ◽  
...  
Keyword(s):  
Physical Activity ◽  
Cross Validation ◽  
Accelerometer Data ◽  
Activity Type ◽  
Free Living ◽  
Independent Dataset ◽  
Clustering Model ◽  
Activity Types ◽  
Unsupervised Approach ◽  
Viable Approach

Few methods for classifying physical activity from accelerometer data have been tested using an independent dataset for cross-validation, and even fewer using multiple independent datasets. The aim of this study was to evaluate whether unsupervised machine learning was a viable approach for the development of a reusable clustering model that was generalisable to independent datasets. We used two labelled adult laboratory datasets to generate a k-means clustering model. To assess its generalised application, we applied the stored clustering model to three independent labelled datasets: two laboratory and one free-living. Based on the development labelled data, the ten clusters were collapsed into four activity categories: sedentary, standing/mixed/slow ambulatory, brisk ambulatory, and running. The percentages of each activity type contained in these categories were 89%, 83%, 78%, and 96%, respectively. In the laboratory independent datasets, the consistency of activity types within the clusters dropped, but remained above 70% for the sedentary clusters, and 85% for the running and ambulatory clusters. Acceleration features were similar within each cluster across samples. The clusters created reflected activity types known to be associated with health and were reasonably robust when applied to diverse independent datasets. This suggests that an unsupervised approach is potentially useful for analysing free-living accelerometer data.

Wearable sensors and Mobile Health (mHealth) technologies to assess and promote physical activity in stroke: a narrative review

2016 ◽  
Vol 17 (1) ◽  
pp. 34-42 ◽  
Author(s):  
Shamala Thilarajah ◽  
Ross A Clark ◽  
Gavin Williams
Keyword(s):  
Physical Activity ◽  
Behaviour Change ◽  
Mobile Health ◽  
Wearable Sensors ◽  
Chronic Illnesses ◽  
Behaviour Change Techniques ◽  
Health Issues ◽  
Activity Trackers ◽  
Wearable Activity Trackers ◽  
Smartphone Technology

Stroke is a leading cause of disability worldwide, with approximately one third of people left with permanent deficits impacting on their function. This may contribute to a physically inactive lifestyle and further associated health issues. Current research suggests that people after stroke are not meeting the recommended levels of physical activity, and are less active than people with other chronic illnesses. Thus, it is important to understand how to support people after stroke to uptake and maintain physical activity. Wearable sensors and mobile health (mHealth) technologies are a potential platform to measure and promote physical activity. Some of these technologies may incorporate behaviour change techniques such as real-time feedback. Although wearable activity trackers and smartphone technology are widely available, the feasibility and applicability of these technologies for people after stroke is unclear. This article reviews the devices available for assessment of physical activity in stroke and discusses the potential for advances in technology to promote physical activity in this population.

scholarly journals P59 Monitoring the recovery time of children after elective tonsillectomies using commercial activity trackers, an prospective feasibility study

2019 ◽  
Vol 104 (6) ◽  
pp. e41.2-e42
Author(s):  
PIP Lambrechtse ◽  
VC Ziesenitz ◽  
A Atkinson ◽  
EJ Bos ◽  
T Welzel ◽  
...  
Keyword(s):  
Physical Activity ◽  
Feasibility Study ◽  
Recovery Time ◽  
List Type ◽  
Age Group ◽  
Validity And Reliability ◽  
Open Label ◽  
Activity Data ◽  
Activity Trackers ◽  
Wearable Activity Trackers

IntroductionWearable activity trackers are increasingly incorporated into daily life and are advancing in their technology in means of accuracy, validity and acceptability,1-6 however there is deficient knowledge on using these devices in a paediatric setting. The objective of this pilot study was to assess the feasibility of physical activity tracking in children7 before and after a standardized surgical intervention and to assess the recovery time after surgery.MethodsThis was a single centre, open-label, prospective feasibility study. We aimed at recruiting 24 children and adolescents 4–16 years of age undergoing elective tonsillectomy. The preoperative period was 10 days before surgery and the postoperative period was 28 days. Activity data were gathered with activity trackers.8 Reference activity was defined as the individual mean of daily steps preoperatively. Recovery time was defined as the number of days that the patient needed to reach reference activity postoperatively. The population was stratified according to age (4–7, 8–16 years).ResultsTwelve male and twelve female patients participated (mean age 6yr, mean BMI percentile 44.7). The age group 4–7 years had a mean recovery time of 11.2 days (SD 5.0) compared to 8.3 days (SD 1.7) in the age group 8–16. The difference was 2.9 days. The tracker datasets were 58% complete. The rate of technical failures of the trackers was 29.2% for the total study period.ConclusionsActivity trackers are a potential tool viable to assess recovery time after surgery in children. Recovery time after tonsillectomy seems to be age-dependent with older children recovering faster. For future studies, we recommend using trackers as a part of assessing physical activity as a parameter of general wellbeing of child during or after an intervention. Using wearable activity trackers is a more modern and appropriate method to assess physical activity,9-14 especially in a paediatric population.ReferencesBrooke SM, An HS, Kang SK, Noble JM, Berg KE, Lee JM. Concurrent validity of wearable activity trackers under free-living conditions. J Strength Cond Res 2017;31(4).Fokkema T, Kooiman TJM, Krijnen WP, Van Der Schans CP, De Groot M. Reliability and validity of ten consumer activity trackers depend on walking speed. Med Sci Sports Exerc. 2017;49(4).Evenson KR, Goto MM, Furberg RD. Systematic review of the validity and reliability of consumer-wearable activity trackers. Vol. 12, International Journal of Behavioral Nutrition and Physical Activity 2015.Huang Y, Xu J, Yu B, Shull PB. Validity of FitBit, Jawbone UP, Nike+ and other wearable devices for level and stair walking. Gait Posture 2016;Hein IM, Troost PW, De Vries MC, Knibbe CAJ, Van Goudoever JB, Lindauer RJL. Why do children decide not to participate in clinical research: A quantitative and qualitative study. Pediatr Res 2015;Van Berge Henegouwen MTH, Van Driel HF, Kasteleijn-Nolst Trenité DGA. A patient diary as a tool to improve medicine compliance. Pharm World Sci 1999;21(1):21–4.Stone AA. Patient non-compliance with paper diaries. BMJ 2002;Disclosure(s)Nothing to disclose

scholarly journals B.01 Impact of work-hours and sleep on well-being and burnout for physicians-in-training: the prospective RATE Study

2017 ◽  
Vol 44 (S2) ◽  
pp. S10-S10
Author(s):  
D Mendelsohn ◽  
I Despot ◽  
PA Gooderham ◽  
A Singhal ◽  
GJ Redekop ◽  
...  
Keyword(s):  
Physical Activity ◽  
Job Satisfaction ◽  
Well Being ◽  
Work Hours ◽  
Surgical Residents ◽  
Activity Trackers ◽  
Steps Per Day ◽  
Wearable Activity Trackers ◽  
Rate Study ◽  
The Impact

Background: Wearable activity trackers are an innovative tool for measuring sleep and physical activity. The Resident Activity Tracker Evaluation (RATE) is a prospective observational study evaluating the impact of work-hours, sleep, and physical activity on resident well-being, burnout, and job satisfaction. Methods: Residents were recruited from: 1. general surgery and orthopedics (SURG), 2. internal medicine and neurology (MED) and 3. anesthesia and radiology (RCD). Groups 1 and 2 do not enforce on-call duration restrictions and group 3 had 12-hour restricted-call durations (RCD). Participants wore FitBit activity trackers for 14 days and completed four validated surveys assessing self-reported health, sleepiness, burnout, and job satisfaction. Results: Fifty-nine residents completed the study. 778 days of activity and 244 on-call periods were tracked. Surgical residents worked 24 more hours per week than non-surgical residents (84.3 vs 60.7). Surgical residents had 7 less hours of sleep per week and reported significantly higher Epworth Sleepiness scores. Nearly two-thirds of participants (61%) scored high burnout on the Maslach depersonalization subscore. Total steps per day and self-reported well-being, burnout, and job satisfaction were comparable between the groups. Conclusions: Despite a positive correlation between work-hours and sleepiness, burnout and well-being were similar among residents. Physical activity did not prevent burnout. These findings are relevant to work-hours policies.

scholarly journals Group Outdoor Health Walks Using Activity Trackers: Measurement and Implementation Insight from a Mixed Methods Feasibility Study

2020 ◽  
Vol 17 (7) ◽  
pp. 2515 ◽  
Author(s):  
Katherine N. Irvine ◽  
Melissa R. Marselle ◽  
Alan Melrose ◽  
Sara L. Warber
Keyword(s):  
Physical Activity ◽  
Mixed Methods ◽  
Feasibility Study ◽  
Large Scale ◽  
Holistic Health ◽  
Physical Activity Guidelines ◽  
Health And Wellbeing ◽  
Activity Trackers ◽  
Outdoor Walking ◽  
Programme Delivery

Outdoor walking groups are nature-based interventions (NBIs) that promote health and wellbeing by modifying individual behaviour. The challenges of such NBIs include the motivation of inactive adults to participate and measurement issues. This feasibility study investigates a 12-week group outdoor health walk (GOHW) incorporating activity trackers and use of a holistic health and wellbeing measure, the Self-sasessment of Change (SAC) scale. A mixed methods design explored participant recruitment and retention, programme delivery, and measures of physical activity and health and wellbeing. Walker data included: pre-post questionnaires, daily step counts, and interviews. Programme delivery information included: weekly checklists, staff reflections, stakeholder meeting minutes, and a report. Thirteen adults (age 63–81, 76% female) joined and completed the activity tracker GOHW. Activity trackers motivated walkers to join and be more active but complicated programme delivery. Activity trackers allowed the quantification of physical activity and the SAC health and wellbeing measure was easy to use. By week 12, all participants met national physical activity guidelines. Clinically relevant changes on the SAC scale included: sleeping well, experiencing vibrant senses, and feeling energised, focused, joyful, calm and whole. Results illustrate the feasibility of using activity trackers to motivate engagement in and provide a measure of physical activity from GOHWs. The SAC scale offers a promising measure for nature–health research. A conceptual model is provided for the development of future large-scale studies of NBIs, such as group outdoor health walks.

Sign in / Sign up

Export Citation Format

Share Document