Using Behavioral Analytics to Increase Exercise: A Randomized N-of-1 Study

Yoon, Sunmoo; Schwartz, Joseph E.; Burg, Matthew M.; Kronish, Ian M.; Alcántara, Carmela; Julian, Jacob; Parsons, Faith E.; Davidson, Karina W.; Diaz, Keith M.

doi:10.1016/j.amepre.2017.12.011

Cited by 68 publications

(16 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most commonly used Fitbit models were Fitbit Zip and Flex, which were used in 11 of the 20 studies [ 37 , 39 , 40 , 42 , 45 , 47 , 48 , 50 , 52 , 55 , 56 ]. Furthermore, 10 studies used Fitbits for both intervention and measurement purposes, 4 for intervention only, and 5 for measurement only.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Use of Fitbit Devices in Physical Activity Intervention Studies Across the Life Course: Narrative Review

Fleur¹,

George²,

Leite³

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background Commercial off-the-shelf activity trackers (eg, Fitbit) allow users to self-monitor their daily physical activity (PA), including the number of steps, type of PA, amount of sleep, and other features. Fitbits have been used as both measurement and intervention tools. However, it is not clear how they are being incorporated into PA intervention studies, and their use in specific age groups across the life course is not well understood. Objective This narrative review aims to characterize how PA intervention studies across the life course use Fitbit devices by synthesizing and summarizing information on device selection, intended use (intervention vs measurement tool), participant wear instructions, rates of adherence to device wear, strategies used to boost adherence, and the complementary use of other PA measures. This review provides intervention scientists with a synthesis of information that may inform future trials involving Fitbit devices. Methods We conducted a search of the Fitabase Fitbit Research Library, a database of studies published between 2012 and 2018. Of the 682 studies available on the Fitabase research library, 60 interventions met the eligibility criteria and were included in this review. A supplemental search in PubMed resulted in the inclusion of 15 additional articles published between 2019 and 2020. A total of 75 articles were reviewed, which represented interventions conducted in childhood; adolescence; and early, middle, and older adulthood. Results There was considerable heterogeneity in the use of Fitbit within and between developmental stages. Interventions for adults typically required longer wear periods, whereas studies on children and adolescents tended to have more limited device wear periods. Most studies used developmentally appropriate behavior change techniques and device wear instructions. Regardless of the developmental stage and intended Fitbit use (ie, measurement vs intervention tool), the most common strategies used to enhance wear time included sending participants reminders through texts or emails and asking participants to log their steps or synchronize their Fitbit data daily. The rates of adherence to the wear time criteria were reported using varying metrics. Most studies supplemented the use of Fitbit with additional objective or self-reported measures for PA. Conclusions Overall, the heterogeneity in Fitbit use across PA intervention studies reflects its relative novelty in the field of research. As the use of monitoring devices continues to expand in PA research, the lack of uniformity in study protocols and metrics of reported measures represents a major issue for comparability purposes. There is a need for increased transparency in the prospective registration of PA intervention studies. Researchers need to provide a clear rationale for the use of several PA measures and specify the source of their main PA outcome and how additional measures will be used in the context of Fitbit-based interventions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…A total of 10 studies asked participants to self-report their PA using instruments such as the International PA Questionnaire, the Stanford Brief PA Survey, and the 30-day PA Recall [37,39,40,42,[44][45][46][50][51][52][54][55][56]. Only 1 study used an additional objective measure of PA (ie, accelerometer [38]).…”

Section: Other Measures Of Pamentioning

confidence: 99%

Use of Fitbit Devices in Physical Activity Intervention Studies Across the Life Course: Narrative Review

Fleur¹,

George²,

Leite³

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

show abstract

“…Environmental variables were also shown to affect stress differently in different participants; for example, high temperatures predicted high stress in one individual but low stress in another. These predictors can be used to provide individuals with insights into what may contribute to their stress, as indicated by Yoon et al [20]. These models can also be operationalized to generate interventions or encouragements just before instances of high stress when the model predicts, with a sufficient degree of confidence, impending stress based on what is expected to be effective for that particular individual.…”

Section: Discussionmentioning

confidence: 99%

Using Machine Learning to Derive Just-In-Time and Personalized Predictors of Stress: Observational Study Bridging the Gap Between Nomothetic and Ideographic Approaches

Rozet¹,

Kronish²,

Schwartz³

et al. 2019

J Med Internet Res

View full text Add to dashboard Cite

Background Investigations into person-specific predictors of stress have typically taken either a population-level nomothetic approach or an individualized ideographic approach. Nomothetic approaches can quickly identify predictors but can be hindered by the heterogeneity of these predictors across individuals and time. Ideographic approaches may result in more predictive models at the individual level but require a longer period of data collection to identify robust predictors. Objective Our objectives were to compare predictors of stress identified through nomothetic and ideographic models and to assess whether sequentially combining nomothetic and ideographic models could yield more accurate and actionable predictions of stress than relying on either model. At the same time, we sought to maintain the interpretability necessary to retrieve individual predictors of stress despite using nomothetic models. Methods Data collected in a 1-year observational study of 79 participants performing low levels of exercise were used. Physical activity was continuously and objectively monitored by actigraphy. Perceived stress was recorded by participants via daily ecological momentary assessments on a mobile app. Environmental variables including daylight time, temperature, and precipitation were retrieved from the public archives. Using these environmental, actigraphy, and mobile assessment data, we built machine learning models to predict individual stress ratings using linear, decision tree, and neural network techniques employing nomothetic and ideographic approaches. The accuracy of the approaches for predicting individual stress ratings was compared based on classification errors. Results Across the group of patients, an individual’s recent history of stress ratings was most heavily weighted in predicting a future stress rating in the nomothetic recurrent neural network model, whereas environmental factors such as temperature and daylight, as well as duration and frequency of bouts of exercise, were more heavily weighted in the ideographic models. The nomothetic recurrent neural network model was the highest performing nomothetic model and yielded 72% accuracy for an 80%/20% train/test split. Using the same 80/20 split, the ideographic models yielded 75% accuracy. However, restricting ideographic models to participants with more than 50 valid days in the training set, with the same 80/20 split, yielded 85% accuracy. Conclusions We conclude that for some applications, nomothetic models may be useful for yielding higher initial performance while still surfacing personalized predictors of stress, before switching to ideographic models upon sufficient data collection.

show abstract

“…A commercial consumer accelerometer-based device, i.e., the FF-2, which has been largely used in several physical activity studies [26,27], was adopted. There have been studies showing that the FF-2 is accurate and reliable in assessing physical activity [19], demonstrating high agreement in steps with a research grade accelerometer such as Actigraph [28].…”

Section: Limitationsmentioning

confidence: 99%

Comparison between Self-Reported and Accelerometer-Measured Physical Activity in Young versus Older Children

Triantafyllidis

Alexiadis

Soutos

et al. 2021

Digital

View full text Add to dashboard Cite

Physical inactivity in children is a major public health challenge, for which valid physical activity assessment tools are needed. Wearable devices provide a means for objective assessment of children’s physical activity, but they are often not adopted because of issues such as cost, comfort, and privacy. In this context, self-reporting tools could be employed, but their validity in relation to a child’s age is understudied. We present the agreement of one of the most popular self-reporting tools, the Physical Activity Questionnaire for Children (PAQ-C) with accelerometer-measured physical activity in 9-year-old versus 12-year-old children, wearing an accelerometer-based wearable device for seven consecutive days. We study the relationship between the PAQ-C and accelerometer scores using Spearman’s rank correlation coefficients and Bland–Altman plots in a sample of 131 children included for analysis. Overall, there was correlation between PAQ-C score and physical activity measures for the 12-year-old children (rho = 0.47 for total physical activity, rho = 0.43 for moderate-to-vigorous physical activity, rho = 0.41 for steps, p < 0.01), but not for the 9-year-old children (rho = 0.08 for total physical activity, rho = 0.21 for moderate-to-vigorous physical activity, rho = 0.19 for steps, p > 0.05). All PAQ-C items other than item 3 (activity at recess) did not reach significance in correlation with accelerometry for the 9-year-old children (p > 0.05). Therefore, the use of wearable devices for more objective assessment of physical activity in younger children should be preferred.

show abstract

Using Behavioral Analytics to Increase Exercise: A Randomized N-of-1 Study

Abstract: This N-of-1 intervention study demonstrates that a one-time brief message conveying personalized exercise predictors had a beneficial effect on exercise behavior among urban adults.

Cited by 68 publications

References 35 publications

Use of Fitbit Devices in Physical Activity Intervention Studies Across the Life Course: Narrative Review

Use of Fitbit Devices in Physical Activity Intervention Studies Across the Life Course: Narrative Review

Using Machine Learning to Derive Just-In-Time and Personalized Predictors of Stress: Observational Study Bridging the Gap Between Nomothetic and Ideographic Approaches

Comparison between Self-Reported and Accelerometer-Measured Physical Activity in Young versus Older Children

Contact Info

Product

Resources

About