Assessing User Retention of a Mobile App: Survival Analysis.
Ontology highlight
ABSTRACT: Background
A mobile app generates passive data, such as GPS data traces, without any direct involvement from the user. These passive data have transformed the manner of traditional assessments that require active participation from the user. Passive data collection is one of the most important core techniques for mobile health development because it may promote user retention, which is a unique characteristic of a software medical device.Objective
The primary aim of this study was to quantify user retention for the "Staff Hours" app using survival analysis. The secondary aim was to compare user retention between passive data and active data, as well as factors associated with the survival rates of user retention.Methods
We developed an app called "Staff Hours" to automatically calculate users' work hours through GPS data (passive data). "Staff Hours" not only continuously collects these passive data but also sends an 11-item mental health survey to users monthly (active data). We applied survival analysis to compare user retention in the collection of passive and active data among 342 office workers from the "Staff Hours" database. We also compared user retention on Android and iOS platforms and examined the moderators of user retention.Results
A total of 342 volunteers (224 men; mean age 33.8 years, SD 7.0 years) were included in this study. Passive data had higher user retention than active data (P=.011). In addition, user retention for passive data collected via Android devices was higher than that for iOS devices (P=.015). Trainee physicians had higher user retention for the collection of active data than trainees from other occupations, whereas no significant differences between these two groups were observed for the collection of passive data (P=.700).Conclusions
Our findings demonstrated that passive data collected via Android devices had the best user retention for this app that records GPS-based work hours.
SUBMITTER: Lin YH
PROVIDER: S-EPMC7728530 | biostudies-literature | 2020 Nov
REPOSITORIES: biostudies-literature
Publications
Assessing User Retention of a Mobile App: Survival Analysis.
Lin Yu-Hsuan YH Chen Si-Yu SY Lin Pei-Hsuan PH Tai An-Shun AS Pan Yuan-Chien YC Hsieh Chang-En CE Lin Sheng-Hsuan SH
JMIR mHealth and uHealth 20201126 11
<h4>Background</h4>A mobile app generates passive data, such as GPS data traces, without any direct involvement from the user. These passive data have transformed the manner of traditional assessments that require active participation from the user. Passive data collection is one of the most important core techniques for mobile health development because it may promote user retention, which is a unique characteristic of a software medical device.<h4>Objective</h4>The primary aim of this study wa ...[more]
Similar Datasets
Project description:Promising first results for Kaia, a mobile app digitalizing multidisciplinary rehabilitation for low back pain, were recently published. It remains unclear whether the implementation of user feedback in an updated version of this app leads to desired effects in terms of increased app usage and clinical outcomes.The aim is to elucidate the effect on user retention and clinical outcomes of an updated version of the Kaia app where user feedback was included during development.User feedback of the initial app versions (0.x) was collected in a quality management system and systematically analyzed to define requirements of a new version. For this study, the anonymized data of Kaia users was analyzed retrospectively and users were grouped depending on the available version at the time of the sign-up (0.x vs 1.x). The effect on the duration of activity of users in the app, the number of completed exercises of each type, and user-reported pain levels were compared.Overall, data of 1251 users fulfilled the inclusion criteria, of which 196 users signed up using version 0.x and 1055 users signed up with version 1.x. There were significant differences in the demographic parameters for both groups. A log-rank test showed no significant differences for the duration of activity in the app between groups (P=.31). Users signing up during availability of the 1.x version completed significantly more exercises of each type in the app (physical exercises: 0.x mean 1.99, SD 1.61 units/week vs 1.x mean 3.15, SD1.72 units/week; P<.001; mindfulness exercises: 0.x mean 1.36, SD 1.43 units/week vs 1.x mean 2.42, SD 1.82 units/week; P<.001; educational content: 0.x mean 1.51, SD 1.42 units/week vs 1.x mean 2.71, SD 1.89 units/week; P<.001). This translated into a stronger decrease in user-reported pain levels in versions 1.x (F1,1233=7.084, P=.008).Despite the limitations of retrospective cohort studies, this study indicates that the implementation of systematically collected user feedback during development of updated versions can contribute to improvements in terms of frequency of use and potentially even clinical endpoints such as pain level. The clinical efficiency of the Kaia app needs to be validated in prospective controlled trials to exclude bias.
| S-EPMC6010841 | biostudies-literature
Project description:BACKGROUND:Despite the growing number of mental health apps available for smartphones, the perceived usability of these apps from the perspectives of end users or health care experts has rarely been reported. This information is vital, particularly for self-guided mHealth interventions, as perceptions of navigability and quality of content are likely to impact participant engagement and treatment compliance. OBJECTIVE:The aim of this study was to conduct a usability evaluation of a personalized, self-guided, app-based intervention for depression. METHODS:Participants were administered the System Usability Scale and open-ended questions as part of a semistructured interview. There were 15 participants equally divided into 3 groups: (1) individuals with clinical depression who were the target audience for the app, (2) mental health professionals, and (3) researchers who specialize in the area of eHealth interventions and/or depression research. RESULTS:The end-user group rated the app highly, both in quantitative and qualitative assessments. The 2 expert groups highlighted the self-monitoring features and range of established psychological treatment options (such as behavioral activation and cognitive restructuring) but had concerns that the amount and layout of content may be difficult for end users to navigate in a self-directed fashion. The end-user data did not confirm these concerns. CONCLUSIONS:Encouraging participant engagement via self-monitoring and feedback, as well as personalized messaging, may be a viable way to maintain participation in self-guided interventions. Further evaluation is necessary to determine whether levels of engagement with these features enhance treatment effects.
| S-EPMC6127496 | biostudies-literature
Project description:BACKGROUND:The MedFit app is designed to facilitate participation of people with cardiovascular disease (CVD) in an exercise-based rehabilitation program remotely. This paper details the development for the MedFit app. OBJECTIVE:The aim of this research was to develop a behavior change, theoretically informed exercise rehabilitation mobile app for adults with CVD by following the early stages of the formative research: development and feasibility testing. METHODS:Adhering to the mobile health (mHealth) development evaluation framework, the stages of the formative research process including (1) development and (2) feasibility were undertaken. The content and format of the MedFit app were developed based on (1) theory, (2) usability testing, and (3) content design. RESULTS:A systematic review of the literature was undertaken to identify the most appropriate theories from which to develop the app. This led to the creation of the MedFit app. The app went through iterative rounds of usability focus group testing with adults with CVD to provide feedback on the app. This process was framed by the unified theory of acceptance and use of technology model. Feedback was then translated into feasible technical improvements to be executed through close collaboration with the technical team, who adapted and made modifications to the app based on this codesign process. CONCLUSIONS:The formative research process of the app development involved theoretical underpinning, usability testing, and content design. mHealth interventions may play a key role in the future of health care, potentially addressing the barriers to participation in cardiac rehabilitation. This work will provide guidance for future research aiming to develop mobile apps by incorporating a best practice framework for mHealth intervention development and a user-centered design approach.
| S-EPMC6334713 | biostudies-literature
Project description:BackgroundDespite the worldwide growth in mobile health (mHealth) tools and the possible benefits for both patients and health care providers, the overall adoption levels of mHealth tools by health professionals remain relatively low.ObjectiveThis study aimed (1) to investigate attitudes of health care providers and mHealth experts toward mHealth tools in the health context in general, and this study aimed (2) to test the acceptability and feasibility of a specific mHealth tool for patients with an eating disorder (ED), called TCApp, among patients and ED specialists.MethodsTo this purpose, we conducted an explorative qualitative study with 4 in-depth group discussions with several groups of stakeholders: our first focus group was conducted with 11 experts on mHealth from the Catalan Association of Health Entities; the second focus group included 10 health care professionals from the Spanish College of Doctors of Barcelona; the third focus group involved 9 patients with an ED who had used the TCApp over a 12-week period, and the fourth and last focus group involved 8 ED specialists who had monitored such ED patients on the Web.ResultsThe focus groups showed that health care providers and mHealth experts reported barriers for mHealth adoption more often than facilitators, indicating that mHealth techniques are difficult to obtain and use. Most barriers were attributed to external factors relating to the human or organizational environment (ie, lack of time because of workload, lack of direct interest on a legislative or political level) rather than being attributed to internal factors relating to individual obstacles. The results of the mHealth intervention study indicate that the TCApp was considered as easy to use and useful, although patients and the ED specialists monitoring them on the Web reported different adoption problems, such as the inability to personalize the app, a lack of motivational and interactive components, or difficulties in adhering to the study protocol.ConclusionsIn general, this paper indicates that both health professionals and patients foresee difficulties that need to be addressed before comprehensive adoption and usage of mHealth techniques can be effectively implemented. Such findings are in line with previous studies, suggesting that although they acknowledge their possible benefits and cost-effectiveness, health care providers are quite resistant and conservative about integrating mHealth technologies in their daily practice.
| S-EPMC6592393 | biostudies-literature
Project description:BackgroundMental health in general, and depression in particular, remain undertreated conditions. Mobile health (mHealth) apps offer tremendous potential to overcome the barriers to accessing mental health care and millions of depression apps have been installed and used. However, little is known about the effect of these apps on a potentially vulnerable user population and the emotional reactions that they generate, even though emotions are a key component of mental health. App reviews, spontaneously posted by the users on app stores, offer up-to-date insights into the experiences and emotions of this population and are increasingly decisive in influencing mHealth app adoption.ObjectiveThis study aims to investigate the emotional reactions of depression app users to different app features by systematically analyzing the sentiments expressed in app reviews.MethodsWe extracted 3261 user reviews of depression apps. The 61 corresponding apps were categorized by the features they offered (psychoeducation, medical assessment, therapeutic treatment, supportive resources, and entertainment). We then produced word clouds by features and analyzed the reviews using the Linguistic Inquiry Word Count 2015 (Pennebaker Conglomerates, Inc), a lexicon-based natural language analytical tool that analyzes the lexicons used and the valence of a text in 4 dimensions (authenticity, clout, analytic, and tone). We compared the language patterns associated with the different features of the underlying apps.ResultsThe analysis highlighted significant differences in the sentiments expressed for the different features offered. Psychoeducation apps exhibited more clout but less authenticity (ie, personal disclosure). Medical assessment apps stood out for the strong negative emotions and the relatively negative ratings that they generated. Therapeutic treatment app features generated more positive emotions, even though user feedback tended to be less authentic but more analytical (ie, more factual). Supportive resources (connecting users to physical services and people) and entertainment apps also generated fewer negative emotions and less anxiety.ConclusionsDevelopers should be careful in selecting the features they offer in their depression apps. Medical assessment features may be riskier as users receive potentially disturbing feedback on their condition and may react with strong negative emotions. In contrast, offering information, contacts, or even games may be safer starting points to engage people with depression at a distance. We highlight the necessity to differentiate how mHealth apps are assessed and vetted based on the features they offer. Methodologically, this study points to novel ways to investigate the impact of mHealth apps and app features on people with mental health issues. mHealth apps exist in a rapidly changing ecosystem that is driven by user satisfaction and adoption decisions. As such, user perceptions are essential and must be monitored to ensure adoption and avoid harm to a fragile population that may not benefit from traditional health care resources.
| S-EPMC8715360 | biostudies-literature
Project description:BackgroundPostfracture acute pain is often inadequately managed in older adults. Mobile health (mHealth) technologies can offer opportunities for self-management of pain; however, insufficient apps exist for acute pain management after a fracture, and none are designed for an older adult population.ObjectiveThis study aims to design, develop, and evaluate an mHealth app prototype using a human-centered design approach to support older adults in the self-management of postfracture acute pain.MethodsThis study used a multidisciplinary and user-centered design approach. Overall, 7 stakeholders (ie, 1 clinician-researcher specialized in internal medicine, 2 user experience designers, 1 computer science researcher, 1 clinical research assistant researcher, and 2 pharmacists) from the project team, together with 355 external stakeholders, were involved throughout our user-centered development process that included surveys, requirement elicitation, participatory design workshops, mobile app design and development, mobile app content development, and usability testing. We completed this study in 3 phases. We analyzed data from prior surveys administered to 305 members of the Canadian Osteoporosis Patient Network and 34 health care professionals to identify requirements for designing a low-fidelity prototype. Next, we facilitated 4 participatory design workshops with 6 participants for feedback on content, presentation, and interaction with our proposed low-fidelity prototype. After analyzing the collected data using thematic analysis, we designed a medium-fidelity prototype. Finally, to evaluate our medium-fidelity prototype, we conducted usability tests with 10 participants. The results informed the design of our high-fidelity prototype. Throughout all the phases of this development study, we incorporated inputs from health professionals to ensure the accuracy and validity of the medical content in our prototypes.ResultsWe identified 3 categories of functionalities necessary to include in the design of our initial low-fidelity prototype: the need for support resources, diary entries, and access to educational materials. We then conducted a thematic analysis of the data collected in the design workshops, which revealed 4 themes: feedback on the user interface design and usability, requests for additional functionalities, feedback on medical guides and educational materials, and suggestions for additional medical content. On the basis of these results, we designed a medium-fidelity prototype. All the participants in the usability evaluation tests found the medium-fidelity prototype useful and easy to use. On the basis of the feedback and difficulties experienced by participants, we adjusted our design in preparation for the high-fidelity prototype.ConclusionsWe designed, developed, and evaluated an mHealth app to support older adults in the self-management of pain after a fracture. The participants found our proposed prototype useful for managing acute pain and easy to interact with and navigate. Assessment of the clinical outcomes and long-term effects of our proposed mHealth app will be evaluated in the future.
| S-EPMC9635443 | biostudies-literature
Project description:BACKGROUND:Mobile health apps are commonly used to support diabetes self-management (DSM). However, there is limited research assessing whether such apps are able to meet the basic requirements of retaining and engaging users. OBJECTIVE:This study aimed to evaluate participants' retention and engagement with My Care Hub, a mobile app for DSM. METHODS:The study employed an explanatory mixed methods design. Participants were people with type 1 or type 2 diabetes who used the health app intervention for 3 weeks. Retention was measured by completion of the postintervention survey. Engagement was measured using system log indices and interviews. Retention and system log indices were presented using descriptive statistics. Transcripts were analyzed using content analysis to develop themes interpreted according to the behavioral intervention technology theory. RESULTS:Of the 50 individuals enrolled, 42 (84%) adhered to the study protocol. System usage data showed multiple and frequent interactions with the app by most of the enrolled participants (42/50, 84%). Two-thirds of participants who inputted data during the first week returned to use the app after week 1 (36/42, 85%) and week 2 (30/42, 71%) of installation. Most daily used features were tracking of blood glucose (BG; 28/42, 68%) and accessing educational information (6/42, 13%). The interview results revealed the app's potential as a behavior change intervention tool, particularly because it eased participants' self-care efforts and improved their engagement with DSM activities such as BG monitoring, physical exercise, and healthy eating. Participants suggested additional functionalities such as extended access to historical analytic data, automated data transmission from the BG meter, and periodic update of meals and corresponding nutrients to further enhance engagement with the app. CONCLUSIONS:The findings of this short-term intervention study suggested acceptable levels of participant retention and engagement with My Care Hub, indicating that it may be a promising tool for extending DSM support and education beyond the confines of a physical clinic.
| S-EPMC7317626 | biostudies-literature
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.
| S-EPMC5529741 | biostudies-other
Project description:BACKGROUND:Without effective self-care, people with diabetic foot ulcers (DFUs) are at risk of prolonged healing times, hospitalization, amputation, and reduced quality of life. Despite these consequences, adherence to DFU self-care remains low. New strategies are needed to engage people in the self-care of their DFUs. OBJECTIVE:This study aimed to evaluate the usability and potential usefulness of a new mobile phone app to engage people with DFUs in self-care. METHODS:We developed a new mobile phone app, MyFootCare, to engage people with DFUs through goals, progress monitoring, and reminders in self-care. Key features included novel visual analytics that automatically extract and monitor DFU size information from mobile phone photos of the foot. A functional prototype of MyFootCare was created and evaluated through a user-centered design process with 11 participants with DFUs. Data were collected through semistructured interviews discussing existing self-care practices and observations of MyFootCare with participants. Data were analyzed qualitatively through thematic analysis. RESULTS:Key themes were as follows: (1) participants already used mobile phone photos to monitor their DFU progress; (2) participants had limited experience with using mobile phone apps; (3) participants desired the objective DFU size data provided by the tracking feature of MyFootCare to monitor their DFU progress; (4) participants were ambivalent about the MyFootCare goal image and diary features, commenting that these features were useful but also that it was unlikely that they would use them; and (5) participants desired to share their MyFootCare data with their clinicians to demonstrate engagement in self-care and to reflect on their progress. CONCLUSIONS:MyFootCare shows promising features to engage people in DFU self-care. Most notably, ulcer size data are useful to monitor progress and engage people. However, more work is needed to improve the usability and accuracy of MyFootCare, that is, by refining the process of taking and analyzing photos of DFUs and removing unnecessary features. These findings open the door for further work to develop a system that is easy to use and functions in everyday life conditions and to test it with people with DFUs and their carers.
| S-EPMC6238831 | biostudies-other
Project description:BackgroundTo address the obesity epidemic, there is a need for novel paradigms, including those that address the timing of eating and sleep in relation to circadian rhythms. Electronic health records (EHRs) are an efficient way to identify potentially eligible participants for health research studies. Mobile health (mHealth) apps offer available and convenient data collection of health behaviors, such as timing of eating and sleep.ObjectiveThe aim of this descriptive analysis was to report on recruitment, retention, and app use from a 6-month cohort study using a mobile app called Daily24.MethodsUsing an EHR query, adult patients from three health care systems in the PaTH clinical research network were identified as potentially eligible, invited electronically to participate, and instructed to download and use the Daily24 mobile app, which focuses on eating and sleep timing. Online surveys were completed at baseline and 4 months. We described app use and identified predictors of app use, defined as 1 or more days of use, versus nonuse and usage categories (ie, immediate, consistent, and sustained) using multivariate regression analyses.ResultsOf 70,661 patients who were sent research invitations, 1021 (1.44%) completed electronic consent forms and online baseline surveys; 4 withdrew, leaving a total of 1017 participants in the analytic sample. A total of 53.79% (n=547) of the participants were app users and, of those, 75.3% (n=412), 50.1% (n=274), and 25.4% (n=139) were immediate, consistent, and sustained users, respectively. Median app use was 28 (IQR 7-75) days over 6 months. Younger age, White race, higher educational level, higher income, having no children younger than 18 years, and having used 1 to 5 health apps significantly predicted app use (vs nonuse) in adjusted models. Older age and lower BMI predicted early, consistent, and sustained use. About half (532/1017, 52.31%) of the participants completed the 4-month online surveys. A total of 33.5% (183/547), 29.3% (157/536), and 27.1% (143/527) of app users were still using the app for at least 2 days per month during months 4, 5, and 6 of the study, respectively.ConclusionsEHR recruitment offers an efficient (ie, high reach, low touch, and minimal participant burden) approach to recruiting participants from health care settings into mHealth research. Efforts to recruit and retain less engaged subgroups are needed to collect more generalizable data. Additionally, future app iterations should include more evidence-based features to increase participant use.
| S-EPMC9233254 | biostudies-literature