Dataset Information

MHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study.

ABSTRACT: INTRODUCTION:Depression and diabetes are highly disabling diseases with a high prevalence and high rate of comorbidity, particularly in low-income ethnic minority patients. Though comorbidity increases the risk of adverse outcomes and mortality, most clinical interventions target these diseases separately. Increasing physical activity might be effective to simultaneously lower depressive symptoms and improve glycaemic control. Self-management apps are a cost-effective, scalable and easy access treatment to increase physical activity. However, cutting-edge technological applications often do not reach vulnerable populations and are not tailored to an individual's behaviour and characteristics. Tailoring of interventions using machine learning methods likely increases the effectiveness of the intervention. METHODS AND ANALYSIS:In a three-arm randomised controlled trial, we will examine the effect of a text-messaging smartphone application to encourage physical activity in low-income ethnic minority patients with comorbid diabetes and depression. The adaptive intervention group receives messages chosen from different messaging banks by a reinforcement learning algorithm. The uniform random intervention group receives the same messages, but chosen from the messaging banks with equal probabilities. The control group receives a weekly mood message. We aim to recruit 276 adults from primary care clinics aged 18-75 years who have been diagnosed with current diabetes and show elevated depressive symptoms (Patient Health Questionnaire depression scale-8 (PHQ-8) >5). We will compare passively collected daily step counts, self-report PHQ-8 and most recent haemoglobin A1c from medical records at baseline and at intervention completion at 6-month follow-up. ETHICS AND DISSEMINATION:The Institutional Review Board at the University of California San Francisco approved this study (IRB: 17-22608). We plan to submit manuscripts describing our user-designed methods and testing of the adaptive learning algorithm and will submit the results of the trial for publication in peer-reviewed journals and presentations at (inter)-national scientific meetings. TRIAL REGISTRATION NUMBER:NCT03490253; pre-results.

SUBMITTER: Aguilera A

PROVIDER: S-EPMC7443305 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study.

Aguilera Adrian A Figueroa Caroline A CA Hernandez-Ramos Rosa R Sarkar Urmimala U Cemballi Anupama A Gomez-Pathak Laura L Miramontes Jose J Yom-Tov Elad E Chakraborty Bibhas B Yan Xiaoxi X Xu Jing J Modiri Arghavan A Aggarwal Jai J Jay Williams Joseph J Lyles Courtney R CR

BMJ open 20200820 8

<h4>Introduction</h4>Depression and diabetes are highly disabling diseases with a high prevalence and high rate of comorbidity, particularly in low-income ethnic minority patients. Though comorbidity increases the risk of adverse outcomes and mortality, most clinical interventions target these diseases separately. Increasing physical activity might be effective to simultaneously lower depressive symptoms and improve glycaemic control. Self-management apps are a cost-effective, scalable and easy ...[more]

PMID: 32819981

Similar Datasets

Project description:Backgrounde- and mHealth interventions using self-regulation techniques like action and coping planning have the potential to tackle the worldwide problem of physical inactivity. However, they often use one-week self-regulation cycles, providing support toward an active lifestyle on a weekly basis. This may be too long to anticipate on certain contextual factors that may fluctuate from day to day and may influence physical activity. Consequently, the formulated action and coping plans often lack specificity and instrumentality, which may decrease effectiveness of the intervention. The aim of this study was to evaluate effectiveness of a self-regulation, app-based intervention called 'MyDayPlan'. "MyDayPlan' provides an innovative daily cycle in which users are guided towards more physical activity via self-regulation techniques such as goal setting, action planning, coping planning and self-monitoring of behaviour.MethodsAn ABAB single-case design was conducted in 35 inactive adults between 18 and 58 years (M = 40 years). The A phases (A1 and A2) were the control phases in which the 'MyDayPlan' intervention was not provided. The B phases (B1 and B2) were the intervention phases in which 'MyDayPlan' was used on a daily basis. The length of the four phases varied within and between the participants. Each phase lasted a minimum of 5 days and the total study lasted 32 days for each participant. Participants wore a Fitbit activity tracker during waking hours to assess number of daily steps as an outcome. Single cases were aggregated and data were analysed using multilevel models to test intervention effects and possible carry-over effects.ResultsResults showed an average intervention effect with a significant increase in number of daily steps from the control to intervention phases for each AB combination. From A1 to B1, an increase of 1424 steps (95% CI [775.42, 2072.32], t (1082) = 4.31,p < .001), and from A2 to B2, an increase of 1181 steps (95% CI [392.98, 1968.16], t (1082) = 2.94, p = .003) were found. Furthermore, the number of daily steps decreased significantly (1134 steps) when going from the first intervention phase (B1) to the second control phase (A2) (95% CI [- 1755.60, - 512.38], t (1082) = - 3.58, p < .001). We found no evidence for a difference in trend between the two control (95% CI [- 114.59, 197.99], t (1078) = .52, p = .60) and intervention phases (95% CI [- 128.79,284.22], t (1078) = .74, p = .46). This reveals, in contrast to what was hypothesized, no evidence for a carry-over effect after removing the 'MyDayPlan' app after the first intervention phase (B1).ConclusionThis study adds evidence that the self-regulation mHealth intervention, 'MyDayPlan' has the capacity to positively influence physical activity levels in an inactive adult population. Furthermore, this study provides evidence for the potential of interventions adopting a daily self-regulation cycle in general.

Project description:BackgroundPhysical activity has shown beneficial effects in the treatment of breast cancer fatigue; nevertheless, a significant portion of patients remain insufficiently physically active after breast cancer. Currently most patients have a smartphone, and therefore mobile health (mHealth) holds the promise of promoting health behavior uptake for many of them.ObjectiveIn this study, we explored representations, levers, and barriers to physical activity and mHealth interventions among inactive breast cancer patients with fatigue.MethodsThis was an exploratory, qualitative study including breast cancer patients from a French cancer center. A total of 4 focus groups were conducted with 9 patients; 2 independent groups of patients (groups A and B) were interviewed at 2 consecutive times (sessions 1 to 4), before and after their participation in a 2-week mHealth group experience consisting of (1) a competitive virtual exercise group activity (a fictitious world tour), (2) participation in a daily chat network, and (3) access to physical activity information and world tour classification feedback. We used a thematic content analysis.ResultsSeveral physical activity levers emerged including (1) physical factors such as perception of physical benefit and previous practice, (2) psychological factors such as motivation increased by provider recommendations, (3) social factors such as group practice, and (4) organizational factors including preplanning physical activity sessions. The main barriers to physical activity identified included late effects of cancer treatment, lack of motivation, and lack of time. The lack of familiarity with connected devices was perceived as the main barrier to the use of mHealth as a means to promote physical activity. The tested mHealth group challenge was associated with several positive representations including well-being and good habit promotion and being a motivational catalyzer. Following feedback, modifications were implemented into the mHealth challenge.ConclusionsmHealth-based, easily accessed group challenges were perceived as levers for the practice of physical activity in this population. mHealth-based group challenges should be explored as options to promote physical activity in a population with fatigue after breast cancer.

Project description:Background: Healthy aging is critically important for several reasons, including economic impact and quality of life. As the population of older adults rapidly increases, identifying acceptable ways to promote healthy aging is a priority. Technologies that can facilitate health promotion and risk reduction behaviors may be a solution, but only if these mobile health (mHealth) tools can be used by the older adult population. Within the context of a physical activity intervention, this study gathered participant's opinions about the use of an mHealth device to learn about acceptance and to identify areas for improvement. Methods: The Independent Walking for Brain Health study (NCT03058146) was designed to evaluate the effectiveness of a wearable mHealth technology in facilitating adherence to a physical activity prescription among participants in free-living environments. An Exit Survey was conducted following intervention completion to gauge participant's perceptions and solicit feedback regarding the overall study design, including exercise promotion strategies and concerns specific to the technology (e.g., privacy), that could inform more acceptable mHealth interventions in the future. The Digital Health Checklist and Framework was used to guide the analysis focusing on the domains of Privacy, Access and Usability, and Data Management. Results: Participants (n = 41) were in their early 70's (mean = 71.6) and were predominantly female (75.6%) and White (92.7%). Most were college educated (16.9 years) and enjoyed using technology in their everyday life (85.4%). Key challenges included privacy concerns, device accuracy, usability, and data access. Specifically, participants want to know what is being learned about them and want control over how their identifiable data may be used. Overall, participants were able to use the device despite the design challenges. Conclusions: Understanding participant's perceptions of the challenges and concerns introduced by mHealth is important, as acceptance will influence adoption and adherence to the study protocol. While this study learned from participants at studycompletion, we recommend that researchers consider what might influence participant acceptance of the technology (access, data management, privacy, risks) and build these into the mHealth study design process. We provide recommendations for future mHealth studies with older adults.

Project description:BackgroundParticipation in regular physical activity holds key benefits for cancer survivors, yet few cancer survivors meet physical activity recommendations. This study aimed to develop and pilot test a mHealth app referral service aimed at assisting cancer survivors to increase their physical activity. In particular, the study sought to examine feasibility and acceptability of the service and determine preliminary efficacy for physical activity behaviour change.MethodsA systematic search identified potentially appropriate Apple (iOS) and Android mHealth apps. The apps were audited regarding the type of physical activity encouraged, evidence-based behavioural strategies and other characteristics, to help match apps to users' preferences and characteristics. A structured service was devised to deliver the apps and counselling, comprising two face-to-face appointments with a mid-week phone or email check-up. The mHealth app referral service was piloted using a pre-post design among 12 cancer survivors. Participants' feedback regarding the service's feasibility and acceptability was sought via purpose-designed questionnaire, and analysed using inductive thematic analysis and descriptive statistics. Change in physical activity was assessed using a valid and reliable self-report tool and analysed using paired t-tests. In line with recommendations for pilot studies, confidence intervals and effect sizes were reported to aid interpretation of clinical significance, with an alpha of 0.2 used to denote statistical significance.ResultsOf 374 mHealth apps identified during the systematic search, 54 progressed to the audit (iOS = 27, Android = 27). The apps consistently scored well for aesthetics, engagement and functionality, and inconsistently for gamification, social and behaviour change features. Ten participants completed the pilot evaluation and provided positive feedback regarding the service's acceptability and feasibility. On average, participants increased their moderate-vigorous physical activity by 236 min per week (d = 0.73; 95% CI = -49 to 522; p = 0.09).ConclusionThis study offered initial evidence that a mHealth app referral service for cancer survivors is feasible and acceptable and may increase physical activity levels. The large increase in physical activity is promising, but should be interpreted with caution given the small sample size and lack of control group. Further research is warranted on a larger scale to investigate generalisability, long-term compliance and application in clinical settings.

Project description:BackgroundElectronic health (eHealth) and mobile health (mHealth) interventions have the potential to tackle the worldwide problem of physical inactivity. However, they often suffer from large attrition rates. Consequently, feasibility and acceptability of interventions have become important matters in the creation of e- and mHealth interventions. The aim of this study was to evaluate participants' opinions regarding acceptability and feasibility of a self-regulation, app-based intervention called 'MyDayPlan'. 'MyDayPlan' provides an innovative daily cycle providing several self-regulation techniques throughout the day that guide users towards an active lifestyle via various self-regulation techniques.MethodsSemi-structured interviews were conducted with 20 adults after using the app for 2 weeks. A directed content analysis was performed using NVivo Software.Results'MyDayPlan' was well-received and seems to be feasible and acceptable with inactive adults. The straightforward lay out and ease of use of the app were appreciated. Furthermore, the incorporation of the techniques 'action planning', and 'prompting review of behavioral goals' was positively evaluated. However, the users gave some recommendations: implementation of activity trackers to self-monitor physical activity could be of added value. Furthermore, increasing intuitiveness by minimizing text input and providing more preprogrammed options could further increase the ease of use. Finally, users indicated that they would benefit from more guidance during the "coping planning" component (barrier identification/problem solving), for example by receiving more tailored examples.ConclusionsBased on these findings, adaptations will be made to the 'MyDayPlan' app before evaluating its effectiveness. Furthermore, involving potential end users and evaluating acceptability and feasibility during the development of an e- and mHealth intervention is key. Also, creating interventions with a large ease of use and straightforward layout that provides tailored support during action and coping planning is key.

Project description:BackgroundThe growing number of patients with type 2 diabetes and prediabetes is a major public health concern. Physical activity is a cornerstone of diabetes management and may prevent its onset in prediabetes patients. Despite this, many patients with (pre)diabetes remain physically inactive. Primary care physicians are well-situated to deliver interventions to increase their patients' physical activity levels. However, effective and sustainable physical activity interventions for (pre)diabetes patients that can be translated into routine primary care are lacking.MethodsWe describe the rationale and protocol for a 12-month pragmatic, multicentre, randomised, controlled trial assessing the effectiveness of an mHealth intervention delivered in general practice to increase physical activity and reduce sedentary behaviour of patients with prediabetes and type 2 diabetes (ENERGISED). Twenty-one general practices will recruit 340 patients with (pre)diabetes during routine health check-ups. Patients allocated to the active control arm will receive a Fitbit activity tracker to self-monitor their daily steps and try to achieve the recommended step goal. Patients allocated to the intervention arm will additionally receive the mHealth intervention, including the delivery of several text messages per week, with some of them delivered just in time, based on data continuously collected by the Fitbit tracker. The trial consists of two phases, each lasting six months: the lead-in phase, when the mHealth intervention will be supported with human phone counselling, and the maintenance phase, when the intervention will be fully automated. The primary outcome, average ambulatory activity (steps/day) measured by a wrist-worn accelerometer, will be assessed at the end of the maintenance phase at 12 months.DiscussionThe trial has several strengths, such as the choice of active control to isolate the net effect of the intervention beyond simple self-monitoring with an activity tracker, broad eligibility criteria allowing for the inclusion of patients without a smartphone, procedures to minimise selection bias, and involvement of a relatively large number of general practices. These design choices contribute to the trial's pragmatic character and ensure that the intervention, if effective, can be translated into routine primary care practice, allowing important public health benefits.Trial registrationClinicalTrials.gov (NCT05351359, 28/04/2022).

Project description:BackgroundDespite the ubiquity of smartphones, there is little guidance for how to design mobile health apps to increase use. Specifically, knowing what features users expect, grab their attention, encourage use (via predicted use or through positive app evaluations), and signal beneficial action possibilities can guide and focus app development efforts.ObjectiveWe investigated what features users expect and how the design (prototypicality) impacts app adoption.MethodsIn a web-based survey, we elicited expectations, including presence and placement, for 12 app features. Thereafter, participants (n=462) viewed 2 health apps (high prototypicality similar to top downloaded apps vs low prototypicality similar to research interventions) and reported willingness to download, attention, and predicted use of app features. Participants rated both apps (high and low) for aesthetics, ease of use, usefulness, perceived affordances, and intentions to use.ResultsMost participants (425/462, 92%) expected features for navigation or personal settings (eg, menu) in specific regions (eg, top corners). Features with summary graphs or statics were also expected by many (395-396 of 462, 86%), with a center placement expectation. A feature to "share with friends" was least expected among participants (203/462, 44%). Features fell into 4 unique categories based on attention and predicted use, including essential features with high (>50% or >231 of 462) predicted use and attention (eg, calorie trackers), flashy features with high attention but lower predicted use (eg, links to specific diets), functional features with modest attention and low use (eg, settings), and mundane features with low attention and use (eg, discover tabs). When given a choice, 347 of 462 (75%) participants would download the high-prototypicality app. High prototypicality apps (vs low) led to greater aesthetics, ease of use, usefulness, and intentions, (for all, P<.001). Participants thought that high prototypicality apps had more perceived affordances.ConclusionsIntervention designs that fail to meet a threshold of mHealth expectations will be dismissed as less usable or beneficial. Individuals who download health apps have shared expectations for features that should be there, as well as where these features should appear. Meeting these expectations can improve app evaluations and encourage use. Our typology should guide presence and placement of expected app features to signal value and increase use to impact preventive health behaviors. Features that will likely be used and are attention-worthy-essential, flashy, and functional-should be prioritized during app development.

Dataset Information

MHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study.

Publications

mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets