Dataset Information

Characterizing user engagement with health app data: a data mining approach.

ABSTRACT: The use of mobile health applications (apps) especially in the area of lifestyle behaviors has increased, thus providing unprecedented opportunities to develop health programs that can engage people in real-time and in the real-world. Yet, relatively little is known about which factors relate to the engagement of commercially available apps for health behaviors. This exploratory study examined behavioral engagement with a weight loss app, Lose It! and characterized higher versus lower engaged groups. Cross-sectional, anonymized data from Lose It! were analyzed (n = 12,427,196). This dataset was randomly split into 24 subsamples and three were used for this study (total n = 1,011,008). Classification and regression tree methods were used to identify subgroups of user engagement with one subsample, and descriptive analyses were conducted to examine other group characteristics associated with engagement. Data mining validation methods were conducted with two separate subsamples. On average, users engaged with the app for 29 days. Six unique subgroups were identified, and engagement for each subgroup varied, ranging from 3.5 to 172 days. Highly engaged subgroups were primarily distinguished by the customization of diet and exercise. Those less engaged were distinguished by weigh-ins and the customization of diet. Results were replicated in further analyses. Commercially-developed apps can reach large segments of the population, and data from these apps can provide insights into important app features that may aid in user engagement. Getting users to engage with a mobile health app is critical to the success of apps and interventions that are focused on health behavior change.

SUBMITTER: Serrano KJ

PROVIDER: S-EPMC5526821 | biostudies-other | 2017 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Pain is one of the most prevalent health-related concerns and is among the top 3 most common reasons for seeking medical help. Scientific publications of data collected from pain tracking and monitoring apps are important to help consumers and healthcare professionals select the right app for their use.The main objectives of this paper were to (1) discover user engagement patterns of the pain management app, Manage My Pain, using data mining methods; and (2) identify the association between several attributes characterizing individual users and their levels of engagement.User engagement was defined by 2 key features of the app: longevity (number of days between the first and last pain record) and number of records. Users were divided into 5 user engagement clusters employing the k-means clustering algorithm. Each cluster was characterized by 6 attributes: gender, age, number of pain conditions, number of medications, pain severity, and opioid use. Z tests and chi-square tests were used for analyzing categorical attributes. Effects of gender and cluster on numerical attributes were analyzed using 2-way analysis of variances (ANOVAs) followed up by pairwise comparisons using Tukey honest significant difference (HSD).The clustering process produced 5 clusters representing different levels of user engagement. The proportion of males and females was significantly different in 4 of the 5 clusters (all P ≤.03). The proportion of males was higher than females in users with relatively high longevity. Mean ages of users in 2 clusters with high longevity were higher than users from other 3 clusters (all P <.001). Overall, males were significantly older than females (P <.001). Across clusters, females reported more pain conditions than males (all P <.001). Users from highly engaged clusters reported taking more medication than less engaged users (all P <.001). Females reported taking a greater number of medications than males (P =.04). In 4 of 5 clusters, the percentage of males taking an opioid was significantly greater (all P ≤.05) than that of females. The proportion of males with mild pain was significantly higher than that of females in 3 clusters (all P ≤.008).Although most users of the app reported being female, male users were more likely to be highly engaged in the app. Users in the most engaged clusters self-reported a higher number of pain conditions, a higher number of current medications, and a higher incidence of opioid usage. The high engagement by males in these clusters does not appear to be driven by pain severity which may, in part, be the case for females. Use of a mobile pain app may be relatively more attractive to highly-engaged males than highly-engaged females, and to those with relatively more complex chronic pain problems.

Project description:Software development is an iterative process from designing to implementation, and to testing, in which product development staff should be closely integrated with users. Satisfying user needs effectively is often the pain point for developers. In order to alleviate this, this paper manages to establish the quantitative connection between users' online reviews and APP (Application Program) downloads. By analyzing user online comments, companies can dig out user needs and preferences. This could benefit them by making accurate market positioning of their APP products, and therefore iteratively innovating products based on user needs, which hopefully will increase the volume of APP downloads. This paper regards WeChat APP during 47 updates periods as the research object. Based on Grounded Theory, user needs are extracted after data cleaning. Next, by using semantic analysis and word frequency analysis, we are able to obtain the implicit feedbacks such as emotion tendency, satisfaction and requirements lie under online reviews. Then, we construct a quantile regression model to study the impact of users' online reviews on downloads based on the influencing factors we extracted so as to provide a decision basis for enterprises to iteratively update their products. Results show that: (1) Generally speaking, needs of WeChat users mainly focus on performance, reliability, usability, functional deficiency, functional insufficiency, and system adaptability; (2) For those APP versions with relatively fewer downloads, user needs are mostly about functional deficiency, followed by functional insufficiency, performance, usability, and system adaptability. At this stage, it is found out that users' emotion tendency and user satisfaction significantly affect the volume of downloads; (3) When the volume of APP downloads is moderate, the user needs are functional deficiency, functional insufficiency, and system adaptability. While under this circumstances, users' star ratings have a significant impact on downloads; (4) In addition, when the volume of App downloads is high, user needs are performance, usability, and system adaptability. Our methods effectively extract users' requirements from online reviews and then successfully build up the quantitative connection between the implicit feedbacks from those requirements and APP downloads.

Project description:BackgroundThere is growing interest in using mobile apps and online tools to support postsecondary student mental health, but most of these solutions have suboptimal user engagement in real-world settings. Poor engagement can limit long-term effectiveness and usefulness of these tools. Previous literature has proposed several theories that link factors such as low usability and poor user-centered design to app disengagement. However, few studies provide direct evidence showing what factors contribute to suboptimal user engagement in the context of mobile mental health apps for postsecondary students.ObjectiveThis study focuses on understanding postsecondary students' attitudes and behaviors when using Thought Spot, a co-designed mental health app and online platform, to understand factors related to engagement and user experience.MethodsStudents who were given access to Thought Spot for 6 months during a randomized trial of the intervention were invited to participate in one-on-one semistructured interviews. The interviews explored participants' overall experiences and perceptions of the app, along with factors that affected their usage of various features. All interviews were recorded, and template analysis was used to analyze transcripts.ResultsUser satisfaction was mixed among users of Thought Spot. The degree of engagement with the app appeared to be affected by factors that can be grouped into 5 themes: (1) Students valued detailed, inclusive, and relevant content; (2) Technical glitches and a lack of integration with other apps affected the overall user experience and satisfaction with the app; (3) Using the app to support peers or family can increase engagement; (4) Crowdsourced information from peers about mental health resources drove user engagement, but was difficult to obtain; and (5) Users often turned to the app when they had an immediate need for mental health information, rather than using it to track mental health information over time.ConclusionsContent, user experience, user-centeredness, and peer support are important determinants of user engagement with mobile mental health apps among postsecondary students. In this study, participants disengaged when the app did not meet their expectations on these determinants. Future studies on user engagement should further explore the effectiveness of different features and the relative importance of various criteria for high-quality apps. Further focus on these issues may inform the creation of interventions that increase student engagement and align with their mental health needs.Trial registrationClinicalTrials.gov NCT03412461; https://clinicaltrials.gov/ct2/show/NCT03412461.International registered report identifier (irrid)RR2-10.2196/resprot.6446.

Project description:BackgroundEvaluating engagement with an intervention is a key component of understanding its efficacy. With an increasing interest in developing behavioral interventions in the mobile health (mHealth) space, appropriate methods for evaluating engagement in this context are necessary. Data collected to evaluate mHealth interventions are often collected much more frequently than those for clinic-based interventions. Additionally, missing data on engagement is closely linked to level of engagement resulting in the potential for informative missingness. Thus, models that can accommodate intensively collected data and can account for informative missingness are required for unbiased inference when analyzing engagement with an mHealth intervention.ObjectiveThe objectives of this paper are to discuss the utility of the joint modeling approach in the analysis of longitudinal engagement data in mHealth research and to illustrate the application of this approach using data from an mHealth intervention designed to support illness management among people with schizophrenia.MethodsEngagement data from an evaluation of an mHealth intervention designed to support illness management among people with schizophrenia is analyzed. A joint model is applied to the longitudinal engagement outcome and time-to-dropout to allow unbiased inference on the engagement outcome. Results are compared to a naïve model that does not account for the relationship between dropout and engagement.ResultsThe joint model shows a strong relationship between engagement and reduced risk of dropout. Using the mHealth app 1 day more per week was associated with a 23% decreased risk of dropout (P<.001). The decline in engagement over time was steeper when the joint model was used in comparison with the naïve model.ConclusionsNaïve longitudinal models that do not account for informative missingness in mHealth data may produce biased results. Joint models provide a way to model intensively collected engagement outcomes while simultaneously accounting for the relationship between engagement and missing data in mHealth intervention research.

Project description:BackgroundChildhood obesity is an ongoing problem in developed countries that needs targeted prevention in the youngest age groups. Children in socioeconomically disadvantaged families are most at risk. Mobile health (mHealth) interventions offer a potential route to target these families because of its relatively low cost and high reach. The Growing healthy program was developed to provide evidence-based information on infant feeding from birth to 9 months via app or website. Understanding user engagement with these media is vital to developing successful interventions. Engagement is a complex, multifactorial concept that needs to move beyond simple metrics.ObjectiveThe aim of our study was to describe the development of an engagement index (EI) to monitor participant interaction with the Growing healthy app. The index included a number of subindices and cut-points to categorize engagement.MethodsThe Growing program was a feasibility study in which 300 mother-infant dyads were provided with an app which included 3 push notifications that was sent each week. Growing healthy participants completed surveys at 3 time points: baseline (T1) (infant age ≤3 months), infant aged 6 months (T2), and infant aged 9 months (T3). In addition, app usage data were captured from the app. The EI was adapted from the Web Analytics Demystified visitor EI. Our EI included 5 subindices: (1) click depth, (2) loyalty, (3) interaction, (4) recency, and (5) feedback. The overall EI summarized the subindices from date of registration through to 39 weeks (9 months) from the infant's date of birth. Basic descriptive data analysis was performed on the metrics and components of the EI as well as the final EI score. Group comparisons used t tests, analysis of variance (ANOVA), Mann-Whitney, Kruskal-Wallis, and Spearman correlation tests as appropriate. Consideration of independent variables associated with the EI score were modeled using linear regression models.ResultsThe overall EI mean score was 30.0% (SD 11.5%) with a range of 1.8% - 57.6%. The cut-points used for high engagement were scores greater than 37.1% and for poor engagement were scores less than 21.1%. Significant explanatory variables of the EI score included: parity (P=.005), system type including "app only" users or "both" app and email users (P<.001), recruitment method (P=.02), and baby age at recruitment (P=.005).ConclusionsThe EI provided a comprehensive understanding of participant behavior with the app over the 9-month period of the Growing healthy program. The use of the EI in this study demonstrates that rich and useful data can be collected and used to inform assessments of the strengths and weaknesses of the app and in turn inform future interventions.

Project description:BackgroundMobile health (mHealth) apps represent a promising approach for improving health outcomes in patients with chronic illness, but surprisingly few mHealth interventions have investigated the association between user engagement and health outcomes. We aimed to examine the efficacy of a recommended, commercially available gout self-management app for improving self-care behaviors and to assess self-reported user engagement of the app in a sample of adults with gout.ObjectiveOur objective was to examine differences in self-reported user engagement between a recommended gout app (treatment group) and a dietary app (active control group) over 2 weeks as well as to examine any differences in self-care behaviors and illness perceptions.MethodsSeventy-two adults with gout were recruited from the community and three primary and secondary clinics. Participants were randomized to use either Gout Central (n=36), a self-management app, or the Dietary Approaches to Stop Hypertension Diet Plan (n=36), an app based on a diet developed for hypertension, for 2 weeks. The user version of the Mobile Application Rating Scale (uMARS, scale: 1 to 5) was used after the 2 weeks to assess self-reported user engagement, which included an open-ended question. Participants also completed a self-report questionnaire on self-care behaviors (scale: 1-5 for medication adherence and diet and 0-7 for exercise) and illness perceptions (scale: 0-10) at baseline and after the 2-week trial. Independent samples t tests and analysis of covariance were used to examine differences between groups at baseline and postintervention.ResultsParticipants rated the gout app as more engaging (mean difference -0.58, 95% CI -0.96 to -0.21) and more informative (mean difference -0.34, 95% CI -0.67 to -0.01) than the dietary app at the 2-week follow-up. The gout app group also reported a higher awareness of the importance of gout (mean difference -0.64, 95% CI -1.27 to -0.003) and higher knowledge/understanding of gout (mean difference -0.70, 95% CI -1.30 to -0.09) than the diet app group at follow-up. There were no significant differences in self-care behaviors between the two groups postintervention. The gout app group also demonstrated stronger negative beliefs regarding the impact of gout (mean difference -2.43, 95% CI -3.68 to -1.18), stronger beliefs regarding the severity of symptoms (mean difference -1.97, 95% CI -3.12 to -0.82), and a stronger emotional response to gout (mean difference -2.38, 95% CI -3.85 to -0.90) at follow-up. Participant feedback highlighted the importance of tracking health-related information, customizing to the target group/individual, providing more interactive features, and simplifying information.ConclusionsParticipants found the commercially available gout app more engaging. However, these findings did not translate into differences in self-care behaviors. The gout app group also demonstrated stronger negative illness perceptions at the follow-up. Overall, these findings suggest that the development of gout apps would benefit from a user-centered approach with a focus on daily, long-term self-care behaviors as well as modifying illness beliefs.Trial registrationAustralian New Zealand Clinical Trials Registry ACTRN12617001052325; https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=373217.

Project description:The See Me Smoke-Free (SMSF) mobile health (mHealth) app was developed to help women quit smoking by targeting concerns about body weight, body image, and self-efficacy through cognitive behavioral techniques and guided imagery audio files addressing smoking, diet, and physical activity. A feasibility trial found associations between SMSF usage and positive treatment outcomes. This paper reports a detailed exploration of program use among eligible individuals consenting to study participation and completing the baseline survey (participants) and ineligible or nonconsenting app installers (nonparticipants), as well as the relationship between program use and treatment outcomes.The aim of this study was to determine whether (1) participants were more likely to set quit dates, be current smokers, and report higher levels of smoking at baseline than nonparticipants; (2) participants opened the app and listened to audio files more frequently than nonparticipants; and (3) participants with more app usage had a higher likelihood of self-reported smoking abstinence at follow up.The SMSF feasibility trial was a single arm, within-subjects, prospective cohort study with assessments at baseline and 30 and 90 days post enrollment. The SMSF app was deployed on the Google Play Store for download, and basic profile characteristics were obtained for all app installers. Additional variables were assessed for study participants. Participants were prompted to use the app daily during study participation. Crude differences in baseline characteristics between trial participants and nonparticipants were evaluated using t tests (continuous variables) and Fisher exact tests (categorical variables). Exact Poisson tests were used to assess group-level differences in mean usage rates over the full study period using aggregate Google Analytics data on participation and usage. Negative binomial regression models were used to estimate associations of app usage with participant baseline characteristics after adjustment for putative confounders. Associations between app usage and self-reported smoking abstinence were assessed using separate logistic regression models for each outcome measure.Participants (n=151) were more likely than nonparticipants (n=96) to report female gender (P<.02) and smoking in the 30 days before enrollment (P<.001). Participants and nonparticipants opened the app and updated quit dates at the same average rate (rate ratio [RR] 0.98; 95% CI 0.92-1.04; P=.43), but participants started audio files (RR 1.07; 95% CI 1.00-1.13; P<.04) and completed audio files (RR 1.11; 95% CI 1.03-1.18; P<.003) at significantly higher rates than nonparticipants. Higher app usage among participants was positively associated with some smoking cessation outcomes.This study suggests potential efficacy of the SMSF app, as increased usage was generally associated with higher self-reported smoking abstinence. A planned randomized controlled trial will assess the SMSF app's efficacy as an intervention tool to help women quit smoking.

Dataset Information

Characterizing user engagement with health app data: a data mining approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets