scholarly journals The validity of activity trackers is affected by walking speed: the criterion validity of Garmin Vivosmart® HR and StepWatch™ 3 for measuring steps at various walking speeds under controlled conditions

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e9381
Author(s):  
Frederik Rose Svarre ◽  
Mads Møller Jensen ◽  
Josephine Nielsen ◽  
Morten Villumsen
Keyword(s):  
Criterion Validity ◽  
Step Count ◽  
Healthcare Personnel ◽  
Percentage Error ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Controlled Conditions ◽  
Healthcare It ◽  
Graded Activity ◽  
Walking Speeds

Introduction The use of activity trackers has increased both among private consumers and in healthcare. It is therefore relevant to consider whether a consumer-graded activity tracker is comparable to or may substitute a research-graded activity tracker, which could further increase the use of activity trackers in healthcare and rehabilitation. Such use will require knowledge of their accuracy as the clinical implications may be significant. Studies have indicated that activity trackers are not sufficiently accurate, especially at lower walking speeds. The present study seeks to inform decision makers and healthcare personnel considering implementing physical activity trackers in clinical practice. This study investigates the criterion validity of the consumer-graded Garmin Vivosmart® HR and the research-graded StepWatch™ 3 compared with manual step count (gold standard) at different walking speeds under controlled conditions. Methods Thirty participants, wearing Garmin Vivosmart® HR at the wrist and StepWatch™ 3 at the ankle, completed six trials on a treadmill at different walking speeds: 1.6 km/h, 2.4 km/h, 3.2 km/h, 4.0 km/h, 4.8 km/h, and 5.6 km/h. The participants were video recorded, and steps were registered by manual step count. Medians and inter-quartile ranges (IQR) were calculated for steps and differences in steps between manually counted steps and the two devices. In order to assess the clinical relevance of the tested devices, the mean absolute percentage error (MAPE) was determined at each speed. A MAPE ≤3% was considered to be clinically irrelevant. Furthermore, differences between manually counted steps and steps recorded by the two devices were presented in Bland–Altman style plots. Results The median of differences in steps between Garmin Vivosmart® HR and manual step count ranged from −49.5 (IQR = 101) at 1.6 km/h to −1 (IQR = 4) at 4.0 km/h. The median of differences in steps between StepWatch™ 3 and manual step count were 4 (IQR = 14) at 1.6 km/h and 0 (IQR = 1) at all other walking speeds. The results of the MAPE showed that differences in steps counted by Garmin Vivosmart® HR were clinically irrelevant at walking speeds 3.2–4.8 km/h (MAPE: 0.61–1.27%) as the values were below 3%. Differences in steps counted by StepWatch™ 3 were clinically irrelevant at walking speeds 2.4–5.6 km/h (MAPE: 0.08–0.35%). Conclusion Garmin Vivosmart® HR tended to undercount steps compared with the manual step count, and StepWatch™ 3 slightly overcounted steps compared with the manual step count. Both the consumer-graded activity tracker (Garmin Vivosmart® HR) and the research-graded (StepWatch™ 3) are valid in detecting steps at selected walking speeds in healthy adults under controlled conditions. However, both activity trackers miscount steps at slow walking speeds, and the consumer graded activity tracker also miscounts steps at fast walking speeds.

scholarly journals Neural Network–Based Algorithm for Adjusting Activity Targets to Sustain Exercise Engagement Among People Using Activity Trackers: Retrospective Observation and Algorithm Development Study

10.2196/18142 ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. e18142
Author(s):  
Ramin Mohammadi ◽  
Mursal Atif ◽  
Amanda Jayne Centi ◽  
Stephen Agboola ◽  
Kamal Jethwani ◽  
...  
Keyword(s):  
Neural Network ◽  
Physical Activity ◽  
Machine Learning ◽  
Learning Model ◽  
Step Count ◽  
Daily Step ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Machine Learning Model ◽  
Daily Step Count

Background It is well established that lack of physical activity is detrimental to the overall health of an individual. Modern-day activity trackers enable individuals to monitor their daily activities to meet and maintain targets. This is expected to promote activity encouraging behavior, but the benefits of activity trackers attenuate over time due to waning adherence. One of the key approaches to improving adherence to goals is to motivate individuals to improve on their historic performance metrics. Objective The aim of this work was to build a machine learning model to predict an achievable weekly activity target by considering (1) patterns in the user’s activity tracker data in the previous week and (2) behavior and environment characteristics. By setting realistic goals, ones that are neither too easy nor too difficult to achieve, activity tracker users can be encouraged to continue to meet these goals, and at the same time, to find utility in their activity tracker. Methods We built a neural network model that prescribes a weekly activity target for an individual that can be realistically achieved. The inputs to the model were user-specific personal, social, and environmental factors, daily step count from the previous 7 days, and an entropy measure that characterized the pattern of daily step count. Data for training and evaluating the machine learning model were collected over a duration of 9 weeks. Results Of 30 individuals who were enrolled, data from 20 participants were used. The model predicted target daily count with a mean absolute error of 1545 (95% CI 1383-1706) steps for an 8-week period. Conclusions Artificial intelligence applied to physical activity data combined with behavioral data can be used to set personalized goals in accordance with the individual’s level of activity and thereby improve adherence to a fitness tracker; this could be used to increase engagement with activity trackers. A follow-up prospective study is ongoing to determine the performance of the engagement algorithm.

scholarly journals Precision and Accuracy of a Simple Consumer-oriented Wristband Activity Tracker During Walking at Different Speeds

2021 ◽  
Author(s):  
Shozo Konishi ◽  
Daisaku Nakatani ◽  
Kiminobu Nishimura ◽  
Maki Shigyo ◽  
Keita Yamasaki ◽  
...  
Keyword(s):  
Patient Monitoring ◽  
Measurement Accuracy ◽  
Step Count ◽  
Percentage Error ◽  
Concordance Correlation ◽  
Walking Test ◽  
Activity Tracker ◽  
Precision And Accuracy ◽  
Lightweight Core

Abstract Objective: FAIT Tag is a wrist-worn consumer-oriented pedometer composed of a small and lightweight core and silicone wrist band. The aim of this study was to validate the measurement precision and accuracy of the FAIT Tag during walking.Results: To assess intra-subject precision, five subjects wearing a FAIT Tag performed a repeated 200-step walking test in which they walked 200 steps a total of 10 times. To assess inter-subject accuracy, 30 subjects wearing a FAIT Tag and ActiGraph walked for 3 minutes at two different speeds. Step count measured by these devices was compared with the actual step count counted visually and simultaneously by an investigator. The average intra-subject precision was 2.2. For the inter-subject precision of FAIT Tag, the concordance correlation coefficient and the absolute percentage error ranged from 0.35 to 0.39 and 5.4% to 10.0%, respectively. In conclusion, the FAIT Tag is a practical pedometer with low intra-subject error and acceptable measurement accuracy. It may be a useful tool for long-term patient monitoring and digital biomarker acquisition.

scholarly journals Criterion validity of a wrist-worn activity tracker in laboratory and free-living setting in patients with chronic pain (Preprint)

2020 ◽  
Author(s):  
Veronica Sjöberg ◽  
Jens Westergren ◽  
Andreas Monnier ◽  
Ricardo LoMartire ◽  
Maria Hagströmer ◽  
...  
Keyword(s):  
Chronic Pain ◽  
Criterion Validity ◽  
Step Count ◽  
Fair Agreement ◽  
Laboratory Setting ◽  
Poor Agreement ◽  
Activity Tracking ◽  
Free Living ◽  
Activity Tracker ◽  
Tracking Devices

BACKGROUND Physical Activity (PA) is evidently a crucial part of the rehabilitation process for patients suffering from chronic pain. Modern wrist-worn activity tracking devices seemingly have a great potential to provide objective feedback and assist in the adoption of healthy PA behavior by supplying data of energy expenditure expressed as Metabolic Equivalents (METS). However, no studies have been found of any wrist-worn activity tracking devices’ criterion validity in estimating METS, heart rate (HR), or step count in patients with chronic pain. OBJECTIVE The aim was to determine the criterion validity of wrist-worn activity tracking devices for estimations of METS, HR, and step count in a controlled laboratory setting and free-living settings for patients with chronic pain. METHODS In this combined laboratory and field validation study, METS, HR, and step count were simultaneously estimated by a wrist-worn activity tracker (Fitbit Versa), indirect calorimetry (Jaeger Oxycon Pro), and a research-grade hip-worn accelerometer (ActiGraph GT3X) during a treadmill walk at three speeds (3.0, 4.5, and 6.0 km/h) in a laboratory setting. METS and step count were also estimated by the wrist-worn activity tracker in free-living settings for 72 hours. The criterion validity was determined by conventional statistics (ICC and Spearman rho) and graphical plots (Bland-Altman Plots) as well as by Mean Absolute Percentage Error (MAPE). Analysis of Variance (ANOVA) was used to determine any significant systematic differences between estimations. RESULTS A total of 42 patients (76% females), 25-66 years of age, with chronic pain, were included. Results showed that the wrist-worn activity tracking devices (Fitbit Versa) systematically overestimated METS when compared to the criterion measurement (Jaeger Oxycon Pro) and the relative criterion measurement (ActiGraph GT3X). Poor agreement and correlation was shown in estimated METS between Fitbit Versa and both Jaeger Oxycon Pro and ActiGraph GT3X at all treadmill speeds. Estimations of HR emerged with poor to fair agreement during laboratory-based treadmill walks. For step count, the wrist-worn devices showed a fair agreement and fair correlation at most treadmill speeds. In free-living settings, however, the agreement of step count between wrist-worn devices and waist-worn accelerometer was good, and the correlation was excellent. CONCLUSIONS The wrist-worn device systematically overestimated METS and showed poor agreement and correlation compared to the criterion measurement (Jaeger Oxycon Pro) and the relative criterion measurement (ActiGraph GT3X), which needs to be considered when used clinically. Step count measured from the wrist, however, seemed to be a valid estimation, suggesting that future guidelines could include such variables in this group with chronic pain. CLINICALTRIAL Not applicable in this study

The remote monitoring of gastrointestinal cancer patients’ performance status and burden of symptoms via a consumer-based activity tracker (Preprint)

2020 ◽  
Author(s):  
Alireza Ghods ◽  
Armin Shahrokni ◽  
Hassan Ghasemzadeh ◽  
Diane Cook
Keyword(s):  
Cancer Patients ◽  
Remote Monitoring ◽  
Gastrointestinal Cancer ◽  
Performance Status ◽  
Step Count ◽  
Remote Monitoring System ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Steps Per Day ◽  
Ecog Ps

BACKGROUND Patients with cancer spend most of their time in their homes, but their condition is under constant change as a result of the treatment they receive. Patients' performance status (PS) and their symptoms assessments have typically only been collected during clinic visits. Developing a secure and reliable remote monitoring system is a necessity that can be achieved with an inexpensive consumer-based activity tracker. The real-time data captured by wearable activity trackers could provide a dynamic view of patients for clinicians to make an informed treatment. OBJECTIVE This study aims to assess the practicality of a consumer-based activity tracker for remote monitoring of gastrointestinal cancer patients. METHODS Twenty-seven consenting patients (63% male, median age 58 years) wore a consumer-based activity tracker seven days before chemotherapy, and fourteen days after receiving their first treatment. The clinician assessed patients' ECOG-PS and Memorial Symptom Assessment Checklist-Short Form (MSAS-SF) for patients pre- and post-chemotherapy. The statistical correlation between ECOG-PS and MSAS-SF of patients with their step count was assessed. RESULTS The daily step count had the highest correlation with the patients' ECOG-PS after chemotherapy (P = 6.4e-11). The patients with higher ECOG-PS experienced a higher fluctuation in their step count. The patients who walked more (mean: 6071 steps per day) pre-chemotherapy and (mean: 5930 steps per day) post-chemotherapy had a lower MSAS score (less burden of symptoms) compared to patients who walked less (mean: 5205 steps per day) pre-chemotherapy and (mean: 4437 steps per day) post-chemotherapy. CONCLUSIONS This study demonstrates the feasibility of inexpensive, consumer-based activity trackers in monitoring patients’ PS and MSAS in the gastrointestinal cancer population. The findings need to be validated in a larger population for generalizability.

scholarly journals The Validation of a Pocket Worn Activity Tracker for Step Count and Physical Behavior in Older Adults during Simulated Activities of Daily Living

2020 ◽  
Vol 6 ◽  
pp. 233372142095173
Author(s):  
Darcy Ummels ◽  
Wouter Bijnens ◽  
Jos Aarts ◽  
Kenneth Meijer ◽  
Anna J. Beurskens ◽  
...  
Keyword(s):  
Older Adults ◽  
Daily Living ◽  
Sedentary Time ◽  
Correlation Coefficients ◽  
Step Count ◽  
Percentage Error ◽  
Cross Sectional ◽  
Physical Behavior ◽  
Activity Tracker ◽  
The Mean

Purpose: The purpose of this study was to validate optimized algorithm parameter settings for step count and physical behavior for a pocket worn activity tracker in older adults during ADL. Secondly, for a more relevant interpretation of the results, the performance of the optimized algorithm was compared to three reference applications Methods: In a cross-sectional validation study, 20 older adults performed an activity protocol based on ADL with MOXMissActivity versus MOXAnnegarn, activPAL, and Fitbit. The protocol was video recorded and analyzed for step count and dynamic, standing, and sedentary time. Validity was assessed by percentage error (PE), absolute percentage error (APE), Bland-Altman plots and correlation coefficients. Results: For step count, the optimized algorithm had a mean APE of 9.3% and a correlation coefficient of 0.88. The mean APE values of dynamic, standing, and sedentary time were 15.9%, 19.9%, and 9.6%, respectively. The correlation coefficients were 0.55, 0.91, and 0.92, respectively. Three reference applications showed higher errors and lower correlations for all outcome variables. Conclusion: This study showed that the optimized algorithm parameter settings can more validly estimate step count and physical behavior in older adults wearing an activity tracker in the trouser pocket during ADL compared to reference applications.

Sign in / Sign up

Export Citation Format

Share Document