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

2020 ◽  
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 A Neural Network Based Algorithm for Dynamically Adjusting Activity Targets to Sustain Exercise Engagement Among People Using Activity Trackers

2019 ◽  
Author(s):  
Ramin Mohammadi ◽  
Amanda Jayne Centi ◽  
Mursal Atif ◽  
Stephen Agboola ◽  
Kamal Jethwani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Absolute Error ◽  
Learning Model ◽  
Step Count ◽  
Entropy Measure ◽  
Daily Step ◽  
Activity Trackers ◽  
Machine Learning Model ◽  
Daily Step Count

AbstractIt is well established that lack of physical activity is detrimental to overall health of an individual. Modern day activity trackers enable individuals to monitor their daily activity to meet and maintain targets and to promote activity encouraging behavior. However, the benefits of activity trackers are attenuated over time due to waning adherence. One of the key methods to improve adherence to goals is to motivate individuals to improve on their historic performance metrics. In this work we developed a machine learning model to dynamically adjust the activity target for the forthcoming week that can be realistically achieved by the activity-tracker users. This model prescribes activity target for the forthcoming week. We considered individual user-specific personal, social, and environmental factors, daily step count through the current week (7 days). In addition, we computed an entropy measure that characterizes the pattern of daily step count for the current week. Data for training the machine learning model was collected from 30 participants over a duration of 9 weeks. The model predicted target daily count with mean absolute error of 1545 steps. The proposed work can be used to set personalized goals in accordance with the individual’s level of activity and thereby improving adherence to fitness tracker.

scholarly journals Examining physical activity and quality of life in adults with autism spectrum disorder and intellectual disability

2021 ◽  
pp. 174462952110334
Author(s):  
Brianne Tomaszewski ◽  
Melissa N Savage ◽  
Kara Hume
Keyword(s):  
Quality Of Life ◽  
Physical Activity ◽  
Intellectual Disability ◽  
Step Count ◽  
Daily Step ◽  
Adults With Autism ◽  
Activity Tracker ◽  
Daily Step Count ◽  
The Relationship

Adults with autism and co-occurring intellectual disability engage in low levels of physical activity and are at increased risk of developing secondary health conditions attributed to physical inactivity compared to adults in the general population. Few studies have examined the use of objective measures to characterize physical activity levels for adults with autism and intellectual disability. The current study aimed to examine the relationship between physical activity, using an activity tracker, and quality of life in adults with autism and intellectual disability. In the current study, 38 adults with autism and intellectual disability, ages 18–55, wore a Fitbit Flex 2® activity tracker for 1 week, and completed the Quality of Life Questionnaire. The relationship between average daily step count quality of life was examined. Most adults in the sample were overweight and taking fewer daily steps than recommended guidelines. Increased average daily step count was significantly associated with quality of life.

scholarly journals Combining Activity Trackers With Motivational Interviewing and Mutual Support to Increase Physical Activity in Parent-Adolescent Dyads: Longitudinal Observational Feasibility Study (Preprint)

2017 ◽  
Author(s):  
Josette Bianchi-Hayes ◽  
Elinor Schoenfeld ◽  
Rosa Cataldo ◽  
Wei Hou ◽  
Catherine Messina ◽  
...  
Keyword(s):  
Physical Activity ◽  
Weight Management ◽  
Rank Order ◽  
Adolescent Obesity ◽  
Step Count ◽  
Daily Step ◽  
Management Interventions ◽  
Phone Calls ◽  
Activity Trackers ◽  
Daily Step Count

BACKGROUND An essential component of any effective adolescent weight management program is physical activity (PA). PA levels drop dramatically in adolescence, contributing to the rising prevalence of adolescent obesity. Therefore, finding innovative interventions to address this decline in PA may help adolescents struggling with weight issues. The growing field of health technology provides potential solutions for addressing chronic health issues and lifestyle change, such as adolescent obesity. Activity trackers, used in conjunction with smartphone apps, can engage, motivate, and foster support among users while simultaneously providing feedback on their PA progress. OBJECTIVE The objective of our study was to evaluate the effect of a 10-week pilot study using smartphone-enabled activity tracker data to tailor motivation and goal setting on PA for overweight and obese adolescents and their parents. METHODS We queried enrolled adolescents, aged 14 to 16 years, with a body mass index at or above the 85th percentile, and 1 of their parents as to behaviors, barriers to change, and perceptions about exercise and health before and after the intervention. We captured daily step count and active minutes via activity trackers. Staff made phone calls to dyads at weeks 1, 2, 4, and 8 after enrollment to set daily personalized step-count and minutes goals based on their prior data and age-specific US national guidelines. We evaluated dyad correlations using nonparametric Spearman rank order correlations. RESULTS We enrolled 9 parent-adolescent dyads. Mean adolescent age was 15 (SD 0.9) years (range 14-16 years; 4 female and 5 male participants); mean parent age was 47 (SD 8.0) years (range 36-66 years). On average, adolescents met their personalized daily step-count goals on 35% (range 11%-62%) of the days they wore their trackers; parents did so on 39% (range 3%-68%) of the days they wore their trackers. Adolescents met their active-minutes goals on 55% (range 27%-85%) of the days they wore their trackers; parents did so on 83% (range 52%-97%) of the days. Parent and adolescent success was strongly correlated (step count: r=.36, P=.001; active minutes: r=.30, P=.007). Parental age was inversely correlated with step-count success (r=–.78, P=.01). CONCLUSIONS Our findings illustrate that parent-adolescent dyads have highly correlated PA success rates. This supports further investigation of family-centered weight management interventions for adolescents, particularly those that involve the parent and the adolescent working together.

The translation of preschoolers’ physical activity guidelines into a daily step count target

2014 ◽  
Vol 33 (10) ◽  
pp. 1051-1057 ◽  
Author(s):  
Marieke De Craemer ◽  
Ellen De Decker ◽  
Ilse De Bourdeaudhuij ◽  
Maïté Verloigne ◽  
Yannis Manios ◽  
...  
Keyword(s):  
Physical Activity ◽  
Step Count ◽  
Daily Step ◽  
Physical Activity Guidelines ◽  
Daily Step Count

Abstract 11: mActive: A Blinded, Randomized mHealth Trial Supporting Digital Tracking and Smart Texting for Promotion of Physical Activity

Circulation ◽  
2015 ◽  
Vol 131 (suppl_1) ◽  
Author(s):  
Seth S Martin ◽  
David I Feldman ◽  
Roger S Blumenthal ◽  
Steven R Jones ◽  
Wendy S Post ◽  
...  
Keyword(s):  
Physical Activity ◽  
Phase I ◽  
Real Time ◽  
Phase Ii ◽  
The United States ◽  
Step Count ◽  
Daily Step ◽  
Baseline Activity ◽  
Daily Step Count ◽  
Digital Tracking

Introduction: The recent advent of smartphone-linked wearable pedometers offers a novel opportunity to promote physical activity using mobile health (mHealth) technology. Hypothesis: We hypothesized that digital activity tracking and smart (automated, real-time, personalized) texting would increase physical activity. Methods: mActive (NCT01917812) was a 5-week, blinded, sequentially-randomized, parallel group trial that enrolled patients at an academic preventive cardiovascular center in Baltimore, MD, USA from January 17 th to May 20 th , 2014. Eligible patients were 18-69 year old smartphone users who reported low leisure-time physical activity by a standardized survey. After establishing baseline activity during a 1-week blinded run-in, we randomized 2:1 to unblinded or blinded tracking in phase I (2 weeks), then randomized unblinded participants 1:1 to receive or not receive smart texts in phase II (2 weeks). Smart texts provided automated, personalized, real-time coaching 3 times/day towards a daily goal of 10,000 steps. The primary outcome was change in daily step count. Results: Forty-eight patients (22 women, 26 men) enrolled with a mean (SD) age of 58 (8) years, body mass index of 31 (6), and baseline daily step count of 9670 (4350). The phase I change in activity was non-significantly higher in unblinded participants versus blinded controls by 1024 steps/day (95% CI -580-2628, p=0.21). In phase II, smart text receiving participants increased their daily steps over those not receiving texts by 2534 (1318-3750, p<0.001) and over blinded controls by 3376 (1951-4801, p<0.001). The unblinded-texts group had the highest proportion attaining the 10,000 steps/day goal (p=0.02) (Figure). Conclusions: In present-day adult smartphone users receiving preventive cardiovascular care in the United States, a technologically-integrated mHealth strategy combining digital tracking with automated, personalized, real-time text message coaching resulted in a large short-term increase in physical activity.

scholarly journals An Activity Tracker–Guided Physical Activity Program for Patients Undergoing Radiotherapy: Protocol for a Prospective Phase III Trial (OnkoFit I and II Trials) (Preprint)

2021 ◽  
Author(s):  
Franziska Hauth ◽  
Barbara Gehler ◽  
Andreas Michael Nieß ◽  
Katharina Fischer ◽  
Andreas Toepell ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Physical Activity ◽  
Functional Assessment ◽  
Exercise Program ◽  
Daily Step ◽  
Patients With Cancer ◽  
Activity Tracker ◽  
Cancer Related Fatigue ◽  
Daily Step Count

BACKGROUND The positive impact that physical activity has on patients with cancer has been shown in several studies over recent years. However, supervised physical activity programs have several limitations, including costs and availability. Therefore, our study proposes a novel approach for the implementation of a patient-executed, activity tracker–guided exercise program to bridge this gap. OBJECTIVE Our trial aims to investigate the impact that an activity tracker–guided, patient-executed exercise program for patients undergoing radiotherapy has on cancer-related fatigue, health-related quality of life, and preoperative health status. METHODS Patients receiving postoperative radiotherapy for breast cancer (OnkoFit I trial) or neoadjuvant, definitive, or postoperative treatment for other types of solid tumors (OnkoFit II trial) will be randomized (1:1:1) into 3-arm studies. Target accrual is 201 patients in each trial (50 patients per year). After providing informed consent, patients will be randomized into a standard care arm (arm A) or 1 of 2 interventional arms (arms B and C). Patients in arms B and C will wear an activity tracker and record their daily step count in a diary. Patients in arm C will receive personalized weekly targets for their physical activity. No further instructions will be given to patients in arm B. The target daily step goals for patients in arm C will be adjusted weekly and will be increased by 10% of the average daily step count of the past week until they reach a maximum of 6000 steps per day. Patients in arm A will not be provided with an activity tracker. The primary end point of the OnkoFit I trial is cancer-related fatigue at 3 months after the completion of radiotherapy. This will be measured by the Functional Assessment of Chronic Illness Therapy-Fatigue questionnaire. For the OnkoFit II trial, the primary end point is the overall quality of life, which will be assessed with the Functional Assessment of Cancer Therapy-General sum score at 6 months after treatment to allow for recovery after possible surgery. In parallel, blood samples from before, during, and after treatment will be collected in order to assess inflammatory markers. RESULTS Recruitment for both trials started on August 1, 2020, and to date, 49 and 12 patients have been included in the OnkoFit I and OnkoFit II trials, respectively. Both trials were approved by the institutional review board prior to their initiation. CONCLUSIONS The OnkoFit trials test an innovative, personalized approach for the implementation of an activity tracker–guided training program for patients with cancer during radiotherapy. The program requires only a limited amount of resources. CLINICALTRIAL ClinicalTrials.gov NCT04506476; https://clinicaltrials.gov/ct2/show/NCT04506476. ClinicalTrials.gov NCT04517019; https://clinicaltrials.gov/ct2/show/NCT04517019. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/28524

scholarly journals Feedback From Activity Trackers Improves Daily Step Count After Knee and Hip Arthroplasty: A Randomized Controlled Trial

2018 ◽  
Vol 33 (11) ◽  
pp. 3422-3428 ◽  
Author(s):  
Neill Van der Walt ◽  
Lucy J. Salmon ◽  
Benjamin Gooden ◽  
Matthew C. Lyons ◽  
Michael O'Sullivan ◽  
...  
Keyword(s):  
Randomized Controlled Trial ◽  
Hip Arthroplasty ◽  
Controlled Trial ◽  
Step Count ◽  
Daily Step ◽  
Randomized Controlled ◽  
Activity Trackers ◽  
Daily Step Count ◽  
Knee And Hip Arthroplasty

scholarly journals Adding team-based financial incentives to the Carrot Rewards physical activity app increases daily step count on a population scale: a 24-week matched case control study

2020 ◽  
Vol 17 (1) ◽  
Author(s):  
Emma Pearson ◽  
Harry Prapavessis ◽  
Christopher Higgins ◽  
Robert Petrella ◽  
Lauren White ◽  
...  
Keyword(s):  
Physical Activity ◽  
Financial Incentives ◽  
Step Count ◽  
Daily Step ◽  
Individual Level ◽  
Significant Difference ◽  
Daily Step Count ◽  
Steps Per Day ◽  
The Impact ◽  
Experimental Group

Abstract Background Mobile health applications (mHealth apps) targeting physical inactivity have increased in popularity yet are usually limited by low engagement. This study examined the impact of adding team-based incentives (Step Together Challenges, STCs) to an existing mHealth app (Carrot Rewards) that rewarded individual physical activity achievements. Methods A 24-week quasi-experimental study (retrospective matched pairs design) was conducted in three Canadian provinces (pre-intervention: weeks 1–12; intervention: weeks 13–24). Participants who used Carrot Rewards and STCs (experimental group) were matched with those who used Carrot Rewards only (controls) on age, gender, province and baseline mean daily step count (±500 steps/d). Carrot Rewards users earned individual-level incentives (worth $0.04 CAD) each day they reached a personalized daily step goal. With a single partner, STC users could earn team incentives ($0.40 CAD) for collaboratively reaching individual daily step goals 10 times in seven days (e.g., Partner A completes four goals and Partner B completes six goals in a week). Results The main analysis included 61,170 users (mean age = 32 yrs.; % female = 64). Controlling for pre-intervention mean daily step count, a significant difference in intervention mean daily step count favoured the experimental group (p < 0.0001; ηp2 = 0.024). The estimated marginal mean group difference was 537 steps per day, or 3759 steps per week (about 40 walking min/wk). Linear regression suggested a dose-response relationship between the number of STCs completed (app engagement) and intervention mean daily step count (adjusted R2 = 0.699) with each new STC corresponding to approximately 200 more steps per day. Conclusion Despite an explosion of physical activity app interest, low engagement leading to small or no effects remains an industry hallmark. In this paper, we found that adding modest team-based incentives to the Carrot Rewards app increased mean daily step count, and importantly, app engagement moderated this effect. Others should consider novel small-teams based approaches to boost engagement and effects.

Sign in / Sign up

Export Citation Format

Share Document