Determinants for Sustained Use of an Activity Tracker: Observational Study

Abstract

Background: A lack of physical activity is considered to cause 6% of deaths globally. Feedback from wearables such as activity trackers has the potential to encourage daily physical activity. To date, little research is available on the natural development of adherence to activity trackers or on potential factors that predict which users manage to keep using their activity tracker during the first year (and thereby increasing the chance of healthy behavior change) and which users discontinue using their trackers after a short time.

Objective: The aim of this study was to identify the determinants for sustained use in the first year after purchase. Specifically, we look at the relative importance of demographic and socioeconomic, psychological, health-related, goal-related, technological, user experience-related, and social predictors of feedback device use. Furthermore, this study tests the effect of these predictors on physical activity.

Methods: A total of 711 participants from four urban areas in France received an activity tracker (Fitbit Zip) and gave permission to use their logged data. Participants filled out three Web-based questionnaires: at start, after 98 days, and after 232 days to measure the aforementioned determinants. Furthermore, for each participant, we collected activity data tracked by their Fitbit tracker for 320 days. We determined the relative importance of all included predictors by using Random Forest, a machine learning analysis technique.

Results: The data showed a slow exponential decay in Fitbit use, with 73.9% (526/711) of participants still tracking after 100 days and 16.0% (114/711) of participants tracking after 320 days. On average, participants used the tracker for 129 days. Most important reasons to quit tracking were technical issues such as empty batteries and broken trackers or lost trackers (21.5% of all Q3 respondents, 130/601). Random Forest analysis of predictors revealed that the most influential determinants were age, user experience-related factors, mobile phone type, household type, perceived effect of the Fitbit tracker, and goal-related factors. We explore the role of those predictors that show meaningful differences in the number of days the tracker was worn.

Conclusions: This study offers an overview of the natural development of the use of an activity tracker, as well as the relative importance of a range of determinants from literature. Decay is exponential but slower than may be expected from existing literature. Many factors have a small contribution to sustained use. The most important determinants are technical condition, age, user experience, and goal-related factors. This finding suggests that activity tracking is potentially beneficial for a broad range of target groups, but more attention should be paid to technical and user experience-related aspects of activity trackers.

Keywords: habits; mHealth; machine learning; mobile health; physical activity.

Figure 1

Distribution of participants’ total number of days of activity tracker use.

Figure 2

Usage decline over time. The horizontal axis shows the number of days since the first day of use. The percentage of participants who used the activity tracker for any number of days after a particular day is indicated with a solid line. The other lines indicate habitual use: the percentage of participants who used the tracker for at least 3, 5, and 7 days in the preceding 7 days. Note that this includes participants who stop using the tracker and later start using it again. The early dip in use is due to the summer holiday.

Figure 3

Distribution of participants’ mean number of daily steps.

Figure 4

Plot of relative importance of predictors of sustained use in questionnaire 1 (Q1); BMI: body mass index, MSE: mean squared error.

Figure 5

Boxplots of the distributions of Age levels. Older participants have longer sustained use.

Figure 6

Boxplots of the distributions of iPhone type levels. Holders of iPhones show less sustained use than those of other smartphones.

Figure 7

Boxplots of the distributions of Having the goal to quit smoking. Those not wanting to quit smoking (including non-smokers) have longer sustained use than those who do.

Figure 8

Boxplots of the distributions of Household type. Single parents show shorter sustained use than other household types.

Figure 9

Boxplots of the distributions of Sports in company of others. Those who practice individual sports or with relatives, have longer sustained use of the tracker than those who participate in sports with friends or acquaintances.

Figure 10

Plot of the relative importance of predictors in all questionnaires (Q1 + Q2 + Q3).

Figure 11

Boxplots of the distributions of the marginal means for participant age. The under-25 use the Fitbit less long than the other groups. There are no participants older than 65 in this sample.

Figure 12

Boxplots of the distributions of having the goal to change eating habits. The stronger the goal, the less sustained use of the tracker.

Figure 13

Plot of the partial dependence of sustained tracker use on the perceived effect of the tracker on goal attainment. A larger perceived effect leads to longer sustained use.

Figure 14

Plot of the partial dependence of sustained tracker use on user experience of the valence of the tracker. A better user experience leads to longer sustained use.

Figure 15

Plot of the partial dependence of sustained tracker use on user experience of the efficacy of the tracker. A better user experience leads to longer sustained use.