Mark Begale

Harnessing Context Sensing to Develop a Mobile Intervention for Depression

Background Mobile phone sensors can be used to develop context-aware systems that automatically detect when patients require assistance. Mobile phones can also provide ecological momentary interventions that deliver tailored assistance during problematic situations. However, such approaches have not yet been used to treat major depressive disorder. Objective The purpose of this study was to investigate the technical feasibility, functional reliability, and patient satisfaction with Mobilyze!, a mobile phone- and Internet-based intervention including ecological momentary intervention and context sensing. Methods We developed a mobile phone application and supporting architecture, in which machine learning models (ie, learners) predicted patients’ mood, emotions, cognitive/motivational states, activities, environmental context, and social context based on at least 38 concurrent phone sensor values (eg, global positioning system, ambient light, recent calls). The website included feedback graphs illustrating correlations between patients’ self-reported states, as well as didactics and tools teaching patients behavioral activation concepts. Brief telephone calls and emails with a clinician were used to promote adherence. We enrolled 8 adults with major depressive disorder in a single-arm pilot study to receive Mobilyze! and complete clinical assessments for 8 weeks. Results Promising accuracy rates (60% to 91%) were achieved by learners predicting categorical contextual states (eg, location). For states rated on scales (eg, mood), predictive capability was poor. Participants were satisfied with the phone application and improved significantly on self-reported depressive symptoms (betaweek = –.82, P < .001, per-protocol Cohen d = 3.43) and interview measures of depressive symptoms (betaweek = –.81, P < .001, per-protocol Cohen d = 3.55). Participants also became less likely to meet criteria for major depressive disorder diagnosis (bweek = –.65, P = .03, per-protocol remission rate = 85.71%). Comorbid anxiety symptoms also decreased (betaweek = –.71, P < .001, per-protocol Cohen d = 2.58). Conclusions Mobilyze! is a scalable, feasible intervention with preliminary evidence of efficacy. To our knowledge, it is the first ecological momentary intervention for unipolar depression, as well as one of the first attempts to use context sensing to identify mental health-related states. Several lessons learned regarding technical functionality, data mining, and software development process are discussed. Trial Registration Clinicaltrials.gov NCT01107041; http://clinicaltrials.gov/ct2/show/NCT01107041 (Archived by WebCite at http://www.webcitation.org/60CVjPH0n)

Multimodal e-mental health treatment for depression: a feasibility trial.

Background Internet interventions for depression have shown less than optimal adherence. This study describes the feasibility trial of a multimodal e-mental health intervention designed to enhance adherence and outcomes for depression. The intervention required frequent brief log-ins for self-monitoring and feedback as well as email and brief telephone support guided by a theory-driven manualized protocol. Objective The objective of this feasibility trial was to examine if our Internet intervention plus manualized telephone support program would result in increased adherence rates and improvement in depression outcomes. Methods This was a single arm feasibility trial of a 7-week intervention. Results Of the 21 patients enrolled, 2 (9.5%) dropped out of treatment. Patients logged in 23.2 ± 12.2 times over the 7 weeks. Significant reductions in depression were found on all measures, including the Patient Health Questionnaire depression scale (PHQ-8) (Cohen’s d = 1.96, P < .001), the Hamilton Rating Scale for Depression (d = 1.34, P < .001), and diagnosis of major depressive episode (P < .001). Conclusions The attrition rate was far lower than seen either in Internet studies or trials of face-to-face interventions, and depression outcomes were substantial. These findings support the feasibility of providing a multimodal e-mental health treatment to patients with depression. Although it is premature to make any firm conclusions based on these data, they do support the initiation of a randomized controlled trial examining the independent and joint effects of Internet and telephone administered treatments for depression.

A randomized controlled trial evaluating a manualized TeleCoaching protocol for improving adherence to a web-based intervention for the treatment of depression.

Background Web-based interventions for depression that are supported by coaching have generally produced larger effect-sizes, relative to standalone web-based interventions. This is likely due to the effect of coaching on adherence. We evaluated the efficacy of a manualized telephone coaching intervention (TeleCoach) aimed at improving adherence to a web-based intervention (moodManager), as well as the relationship between adherence and depressive symptom outcomes. Methods 101 patients with MDD, recruited from primary care, were randomized to 12 weeks moodManager+TeleCoach, 12 weeks of self-directed moodManager, or 6 weeks of a waitlist control (WLC). Depressive symptom severity was measured using the PHQ-9. Results TeleCoach+moodManager, compared to self-directed moodManager, resulted in significantly greater numbers of login days (p = 0.01), greater time until last use (p = 0.007), greater use of lessons (p = 0.03), greater variety of interactive tools used (p = 0.02), but total instances of tool use did not reach statistical significance. (p = 0.07). TeleCoach+moodManager produced significantly lower PHQ-9 scores relative to WLC at week 6 (p = 0.04), but there were no other significant differences in PHQ-9 scores at weeks 6 or 12 (ps>0.20) across treatment arms. Baseline PHQ-9 scores were no significantly related to adherence to moodManager. Conclusions TeleCoach produced significantly greater adherence to moodManager, relative to self-directed moodManager. TeleCoached moodManager produced greater reductions in depressive symptoms relative to WLC, however, there were no statistically significant differences relative to self-directed moodManager. While greater use was associated with better outcomes, most users in both TeleCoach and self-directed moodManager had dropped out of treatment by week 12. Even with telephone coaching, adherence to web-based interventions for depression remains a challenge. Methods of improving coaching models are discussed. Trial Registration Clinicaltrials.gov NCT00719979

Project onward: an innovative e-health intervention for cancer survivors.

This study examined the feasibility and acceptability of an Individual Internet Intervention (III) embedded and integrated into an Internet Support Group (ISG) with the ultimate goal of enhancing adherence and learning, compared with an individual internet invention alone.

Strategies for mHealth Research: Lessons from 3 Mobile Intervention Studies

The capacity of Mobile Health (mHealth) technologies to propel healthcare forward is directly linked to the quality of mobile interventions developed through careful mHealth research. mHealth research entails several unique characteristics, including collaboration with technologists at all phases of a project, reliance on regional telecommunication infrastructure and commercial mobile service providers, and deployment and evaluation of interventions “in the wild”, with participants using mobile tools in uncontrolled environments. In the current paper, we summarize the lessons our multi-institutional/multi-disciplinary team has learned conducting a range of mHealth projects using mobile phones with diverse clinical populations. First, we describe three ongoing projects that we draw from to illustrate throughout the paper. We then provide an example for multidisciplinary teamwork and conceptual mHealth intervention development that we found to be particularly useful. Finally, we discuss mHealth research challenges (i.e. evolving technology, mobile phone selection, user characteristics, the deployment environment, and mHealth system “bugs and glitches”), and provide recommendations for identifying and resolving barriers, or preventing their occurrence altogether.

mHealth for Schizophrenia: Patient Engagement With a Mobile Phone Intervention Following Hospital Discharge

Background mHealth interventions that use mobile phones as instruments for illness management are gaining popularity. Research examining mobile phone‒based mHealth programs for people with psychosis has shown that these approaches are feasible, acceptable, and clinically promising. However, most mHealth initiatives involving people with schizophrenia have spanned periods ranging from a few days to several weeks and have typically involved participants who were clinically stable. Objective Our aim was to evaluate the viability of extended mHealth interventions for people with schizophrenia-spectrum disorders following hospital discharge. Specifically, we set out to examine the following: (1) Can individuals be engaged with a mobile phone intervention program during this high-risk period?, (2) Are age, gender, racial background, or hospitalization history associated with their engagement or persistence in using a mobile phone intervention over time?, and (3) Does engagement differ by characteristics of the mHealth intervention itself (ie, pre-programmed vs on-demand functions)? Methods We examined mHealth intervention use and demographic and clinical predictors of engagement in 342 individuals with schizophrenia-spectrum disorders who were given the FOCUS mobile phone intervention as part of a technology-assisted relapse prevention program during the 6-month high-risk period following hospitalization. Results On average, participants engaged with FOCUS for 82% of the weeks they had the mobile phone. People who used FOCUS more often continued using it over longer periods: 44% used the intervention over 5-6 months, on average 4.3 days a week. Gender, race, age, and number of past psychiatric hospitalizations were associated with engagement. Females used FOCUS on average 0.4 more days a week than males. White participants engaged on average 0.7 days more a week than African-Americans and responded to prompts on 0.7 days more a week than Hispanic participants. Younger participants (age 18-29) had 0.4 fewer days of on-demand use a week than individuals who were 30-45 years old and 0.5 fewer days a week than older participants (age 46-60). Participants with fewer past hospitalizations (1-6) engaged on average 0.2 more days a week than those with seven or more. mHealth program functions were associated with engagement. Participants responded to prompts more often than they self-initiated on-demand tools, but both FOCUS functions were used regularly. Both types of intervention use declined over time (on-demand use had a steeper decline). Although mHealth use declined, the majority of individuals used both on-demand and system-prompted functions regularly throughout their participation. Therefore, neither function is extraneous. Conclusions The findings demonstrated that individuals with schizophrenia-spectrum disorders can actively engage with a clinically supported mobile phone intervention for up to 6 months following hospital discharge. mHealth may be useful in reaching a clinical population that is typically difficult to engage during high-risk periods.

Purple: A Modular System for Developing and Deploying Behavioral Intervention Technologies

The creation, deployment, and evaluation of Web-based and mobile-based applications for health, mental health, and wellness within research settings has tended to be siloed, with each research group developing their own systems and features. This has led to technological features and products that are not sharable across research teams, thereby limiting collaboration, reducing the speed of dissemination, and raising the bar for entry into this area of research. This paper provides an overview of Purple, an extensible, modular, and repurposable system created for the development of Web-based and mobile-based applications for health behavior change. Purple contains features required to construct applications and to manage and evaluate research trials using these applications. Core functionality of Purple includes elements that support user management, content authorship, content delivery, and data management. We discuss the history and development of the Purple system guided by the rationale of producing a system that allows greater collaboration and understanding across research teams interested in investigating similar questions and using similar methods. Purple provides a useful tool to meet the needs of stakeholders involved in the creation, provision, and usage of eHealth and mHealth applications. Housed in a non-profit, academic institution, Purple also offers the potential to facilitate the diffusion of knowledge across the research community and improve our capacity to deliver useful and usable applications that support the behavior change of end users.

Skin Self-Examination Education for Early Detection of Melanoma: A Randomized Controlled Trial of Internet, Workbook, and In-Person Interventions

Background Early detection of melanoma improves survival. Since many melanoma patients and their spouses seek the care of a physician after discovering their melanoma, an ongoing study will determine the efficacy of teaching at-risk melanoma patients and their skin check partner how to conduct skin self-examinations (SSEs). Internet-based health behavior interventions have proven efficacious in creating behavior change in patients to better prevent, detect, or cope with their health issues. The efficacy of electronic interactive SSE educational intervention provided on a tablet device has not previously been determined. Objective The electronic interactive educational intervention was created to develop a scalable, effective intervention to enhance performance and accuracy of SSE among those at-risk to develop melanoma. The intervention in the office was conducted using one of the following three methods: (1) in-person through a facilitator, (2) with a paper workbook, or (3) with a tablet device used in the clinical office. Differences related to method of delivery were elucidated by having the melanoma patient and their skin check partner provide a self-report of their confidence in performing SSE and take a knowledge-based test immediately after receiving the intervention. Methods The three interventions used 9 of the 26 behavioral change techniques defined by Abraham and Michie to promote planning of monthly SSE, encourage performing SSE, and reinforce self-efficacy by praising correct responses to knowledge-based decision making and offering helpful suggestions to improve performance. In creating the electronic interactive SSE educational intervention, the educational content was taken directly from both the scripted in-person presentation delivered with Microsoft PowerPoint by a trained facilitator and the paper workbook training arms of the study. Enrollment totaled 500 pairs (melanoma patient and their SSE partner) with randomization of 165 pairs to the in-person, 165 pairs to the workbook, and 70 pairs to electronic interactive SSE educational intervention. Results The demographic survey data showed no significant mean differences between groups in age, education, or income. The tablet usability survey given to the first 30 tablet pairs found that, overall, participants found the electronic interactive intervention easy to use and that the video of the doctor-patient-partner dialogue accompanying the dermatologist’s examination was particularly helpful in understanding what they were asked to do for the study. The interactive group proved to be just as good as the workbook group in self-confidence of scoring moles, and just as good as both the workbook and the in-person intervention groups in self-confidence of monitoring their moles. While the in-person intervention performed significantly better on a skill-based quiz, the electronic interactive group performed significantly better than the workbook group. The electronic interactive and in-person interventions were more efficient (30 minutes), while the workbook took longer (45 minutes). Conclusions This study suggests that an electronic interactive intervention can deliver skills training comparable to other training methods, and the experience can be accommodated during the customary outpatient office visit with the physician. Further testing of the electronic interactive intervention’s role in the anxiety of the pair and pair-discovered melanomas upon self-screening will elucidate the impact of these tools on outcomes in at-risk patient populations. Trial Registration ClinicalTrials.gov NCT01013844; http://clinicaltrials.gov/show/NCT01013844 (Archived by WebCite at http://www.webcitation.org/6LvGGSTKK).

Feasibility, acceptability, and preliminary efficacy of a technology-assisted psychosocial intervention for racially diverse men with advanced prostate cancer.

The utility of psychosocial interventions in reducing symptom burden and improving health‐related quality of life (HRQOL) for men with localized prostate cancer has been demonstrated. However, studies have yet to demonstrate the efficacy of interventions in advanced prostate cancer (APC). This study examined the feasibility, acceptability, and preliminary efficacy of a technology‐assisted, 10‐week, group‐based psychosocial intervention for diverse men with APC.

Uptake and Usage of IntelliCare: A Publicly Available Suite of Mental Health and Well-Being Apps.

Background Treatments for depression and anxiety have several behavioral and psychological targets and rely on varied strategies. Digital mental health treatments often employ feature-rich approaches addressing several targets and strategies. These treatments, often optimized for desktop computer use, are at odds with the ways people use smartphone applications. Smartphone use tends to focus on singular functions with easy navigation to desired tools. The IntelliCare suite of apps was developed to address the discrepancy between need for diverse behavioral strategies and constraints imposed by typical app use. Each app focuses on one strategy for a limited subset of clinical aims all pertinent to depression and anxiety. This study presents the uptake and usage of apps from the IntelliCare suite following an open deployment on a large app marketplace. Methods Thirteen lightweight apps, including 12 interactive apps and one Hub app that coordinates use across those interactive apps, were developed and made free to download on the Google Play store. De-identified app usage data from the first year of IntelliCare suite deployment were analyzed for this study. Results In the first year of public availability, 5210 individuals downloaded one or more of the IntelliCare apps, for a total of 10,131 downloads. Nearly a third of these individuals (31.8%) downloaded more than one of these apps. The modal number of launches for each of the apps was 1, however the mean number of app launches per app ranged from 3.10 to 16.98, reflecting considerable variability in the use of each app. Conclusions The use rate of the IntelliCare suite of apps is higher than public deployments of other comparable digital resources. Our findings suggest that people will use multiple apps and provides support for the concept of app suites as a useful strategy for providing diverse behavioral strategies.