Toward Impactful Collaborations on Computing and Mental Health

A Mental Health and Well-Being Chatbot: User Event Log Analysis

BACKGROUND

Conversational user interfaces, or chatbots, are becoming more popular in the realm of digital health and well-being. While many studies focus on measuring the cause or effect of a digital intervention on people's health and well-being (outcomes), there is a need to understand how users really engage and use a digital intervention in the real world.

OBJECTIVE

In this study, we examine the user logs of a mental well-being chatbot called ChatPal, which is based on the concept of positive psychology. The aim of this research is to analyze the log data from the chatbot to provide insight into usage patterns, the different types of users using clustering, and associations between the usage of the app's features.

METHODS

Log data from ChatPal was analyzed to explore usage. A number of user characteristics including user tenure, unique days, mood logs recorded, conversations accessed, and total number of interactions were used with k-means clustering to identify user archetypes. Association rule mining was used to explore links between conversations.

RESULTS

ChatPal log data revealed 579 individuals older than 18 years used the app with most users being female (n=387, 67%). User interactions peaked around breakfast, lunchtime, and early evening. Clustering revealed 3 groups including "abandoning users" (n=473), "sporadic users" (n=93), and "frequent transient users" (n=13). Each cluster had distinct usage characteristics, and the features were significantly different (P<.001) across each group. While all conversations within the chatbot were accessed at least once by users, the "treat yourself like a friend" conversation was the most popular, which was accessed by 29% (n=168) of users. However, only 11.7% (n=68) of users repeated this exercise more than once. Analysis of transitions between conversations revealed strong links between "treat yourself like a friend," "soothing touch," and "thoughts diary" among others. Association rule mining confirmed these 3 conversations as having the strongest linkages and suggested other associations between the co-use of chatbot features.

CONCLUSIONS

This study has provided insight into the types of people using the ChatPal chatbot, patterns of use, and associations between the usage of the app's features, which can be used to further develop the app by considering the features most accessed by users.

Preferences for a Mental Health Support Technology Among Chinese Employees: Mixed Methods Approach

BACKGROUND

Workplace mental health is under-studied in China, making it difficult to design effective interventions. To encourage the engagement with interventions, it is crucial to understand employees' motivation toward seeking help through technologies.

OBJECTIVE

This study aimed to understanding how Chinese employees view digital mental health support technology and how mental health support technology could be designed to boost the motivation of Chinese employees to use it.

METHODS

A mixed methods approach was used. In total, 458 Chinese employees (248/458, 54% female) in 5 industries (manufacturing, software, medical, government, and education) responded to a survey, and 14 employees and 5 managers were interviewed.

RESULTS

Government data and employee responses showed that mental health support in China is limited. In the workplace, Chinese employees experience a lower sense of autonomy satisfaction compared with competence and relatedness. Although managers and employees try to empathize with those who have mental health issues, discrimination and the stigma of mental illness are rife in Chinese workplaces. Digital technologies are perceived as a potential medium for mental health interventions; however, privacy is a major concern.

CONCLUSIONS

The results of this study demonstrated the potential of self-help digital mental health support for Chinese employees. Interdisciplinary cooperation between design engineers and mental health researchers can contribute toward understanding the issues that engage or disengage users with digital mental health interventions.

Human-Computer Interaction in Digital Mental Health

Human-computer interaction (HCI) has contributed to the design and development of some efficient, user-friendly, cost-effective, and adaptable digital mental health solutions. But HCI has not been well-combined into technological developments resulting in quality and safety concerns. Digital platforms and artificial intelligence (AI) have a good potential to improve prediction, identification, coordination, and treatment by mental health care and suicide prevention services. AI is driving web-based and smartphone apps; mostly it is used for self-help and guided cognitive behavioral therapy (CBT) for anxiety and depression. Interactive AI may help real-time screening and treatment in outdated, strained or lacking mental healthcare systems. The barriers for using AI in mental healthcare include accessibility, efficacy, reliability, usability, safety, security, ethics, suitable education and training, and socio-cultural adaptability. Apps, real-time machine learning algorithms, immersive technologies, and digital phenotyping are notable prospects. Generally, there is a need for faster and better human factors in combination with machine interaction and automation, higher levels of effectiveness evaluation and the application of blended, hybrid or stepped care in an adjunct approach. HCI modeling may assist in the design and development of usable applications, and to effectively recognize, acknowledge, and address the inequities of mental health care and suicide prevention and assist in the digital therapeutic alliance.

Chatbots to Support Mental Wellbeing of People Living in Rural Areas: Can User Groups Contribute to Co-design?

Digital technologies such as chatbots can be used in the field of mental health. In particular, chatbots can be used to support citizens living in sparsely populated areas who face problems such as poor access to mental health services, lack of 24/7 support, barriers to engagement, lack of age appropriate support and reductions in health budgets. The aim of this study was to establish if user groups can design content for a chatbot to support the mental wellbeing of individuals in rural areas. University students and staff, mental health professionals and mental health service users (N = 78 total) were recruited to workshops across Northern Ireland, Ireland, Scotland, Finland and Sweden. The findings revealed that participants wanted a positive chatbot that was able to listen, support, inform and build a rapport with users. Gamification could be used within the chatbot to increase user engagement and retention. Content within the chatbot could include validated mental health scales and appropriate response triggers, such as signposting to external resources should the user disclose potentially harmful information or suicidal intent. Overall, the workshop participants identified user needs which can be transformed into chatbot requirements. Responsible design of mental healthcare chatbots should consider what users want or need, but also what chatbot features artificial intelligence can competently facilitate and which features mental health professionals would endorse.

Care Managers and Role Ambiguity: The Challenges of Supporting the Mental Health Needs of Patients with Chronic Conditions

As U.S. healthcare organizations transition to value-based healthcare, they are increasingly focusing on supporting patients who have difficulties managing chronic care, including mental health, through the growing role of care managers (CMs). CMs communicate with patients, provide access to resources, and coach them toward healthy behaviors. CMs also coordinate patient-related issues internally with healthcare practitioners and externally with community organizations and insurance providers. While there have been many interaction design studies regarding the work of clinical and non-clinical healthcare providers and how best to design support systems for them, we know little about the work of CMs. In this study, we examine the role of CMs, particularly focusing on their work to support patient mental health, through interviews with 11 CMs who are part of a large Midwestern U.S. health system. Workflow observations were conducted to supplement the interview data. We describe the role of CMs and identify challenges that they face in supporting patient mental health. A key challenge is a high degree of role ambiguity in this professional role. We discuss sociotechnical implications to better support care delivery processes and technologies for the delivery of mental health services by CMs.

From development to exploitation of digital health solutions: lessons learnt through multidisciplinary research and consultancy

Purpose

This viewpoint paper provides an overview of lessons learnt throughout the whole cycle of development to exploitation of digital solutions in health and wellbeing settings. This paper aims to address learnings that can be applied to all digital health technologies, including assistive technologies, apps, wearables, medical devices and serious games.

Design/methodology/approach

Based on the knowledge and experiences of working within a multidisciplinary team, the authors discuss lessons learnt through research and consultancy projects in digital health and translate these into pragmatic suggestions and recommendations.

Findings

Firstly, the importance of collaborating and co-creating with multidisciplinary stakeholders and end users throughout the whole project lifecycle is emphasised. Secondly, digital health solutions are not a means to an end, nor a panacea; decisions should be evidence-based and needs-driven. Thirdly, whenever possible, research designs and tools need to be more adaptive and personalised. Fourthly, the use of a mixed-method system approach and continuous evaluation throughout the project’s lifecycle is recommended to build up the evidence base. Fifthly, to ensure successful exploitation and implementation, a business case and timely bottom-up approach is recommended. Finally, to prevent research waste, it is our shared responsibility to collaborate with existing consortia and create an awareness of existing solutions and approaches.

Originality/value

In conclusion, collaborating in the field of digital health offered insights into how to be more purposeful and effective in development, evaluation and exploitation of digital health solutions. Moving this diverse and dynamic field forward is challenging but will contribute to greater long-term impact on society.

Characteristics of Neuropsychiatric Mobile Health Trials: Cross-Sectional Analysis of Studies Registered on ClinicalTrials.gov

BACKGROUND

The development of mobile health (mHealth) technologies is progressing at a faster pace than that of the science to evaluate their validity and efficacy. Under the International Committee of Journal Medical Editors (ICMJE) guidelines, clinical trials that prospectively assign people to interventions should be registered with a database before the initiation of the study.

OBJECTIVE

The aim of this study was to better understand the smartphone mHealth trials for high-burden neuropsychiatric conditions registered on ClinicalTrials.gov through November 2018, including the number, types, and characteristics of the studies being conducted; the frequency and timing of any outcome changes; and the reporting of results.

METHODS

We conducted a systematic search of ClinicalTrials.gov for the top 10 most disabling neuropsychiatric conditions and prespecified terms related to mHealth. According to the 2016 World Health Organization Global Burden of Disease Study, the top 10 most disabling neuropsychiatric conditions are (1) stroke, (2) migraine, (3) major depressive disorder, (4) Alzheimer disease and other dementias, (5) anxiety disorders, (6) alcohol use disorders, (7) opioid use disorders, (8) epilepsy, (9) schizophrenia, and (10) other mental and substance use disorders. There were no date, location, or status restrictions.

RESULTS

Our search identified 135 studies. A total of 28.9% (39/135) of studies evaluated interventions for major depressive disorder, 14.1% (19/135) of studies evaluated interventions for alcohol use disorders, 12.6% (17/135) of studies evaluated interventions for stroke, 11.1% (15/135) of studies evaluated interventions for schizophrenia, 8.1% (11/135) of studies evaluated interventions for anxiety disorders, 8.1% (11/135) of studies evaluated interventions for other mental and substance use disorders, 7.4% (10/135) of studies evaluated interventions for opioid use disorders, 3.7% (5/135) of studies evaluated interventions for Alzheimer disease or other dementias, 3.0% (4/135) of studies evaluated interventions for epilepsy, and 3.0% (4/135) of studies evaluated interventions for migraine. The studies were first registered in 2008; more than half of the studies were registered from 2016 to 2018. A total of 18.5% (25/135) of trials had results reported in some publicly accessible location. Across all the studies, the mean estimated enrollment (reported by the study) was 1078, although the median was only 100. In addition, across all the studies, the actual reported enrollment was lower, with a mean of 249 and a median of 80. Only about a quarter of the studies (35/135, 25.9%) were funded by the National Institutes of Health.

CONCLUSIONS

Despite the increasing use of health-based technologies, this analysis of ClinicalTrials.gov suggests that only a few apps for high-burden neuropsychiatric conditions are being clinically evaluated in trials.

Untold Stories in User-Centered Design of Mobile Health: Practical Challenges and Strategies Learned From the Design and Evaluation of an App for Older Adults With Heart Failure

Background

User-centered design (UCD) is a powerful framework for creating useful, easy-to-use, and satisfying mobile health (mHealth) apps. However, the literature seldom reports the practical challenges of implementing UCD, particularly in the field of mHealth.

Objective

This study aims to characterize the practical challenges encountered and propose strategies when implementing UCD for mHealth.

Methods

Our multidisciplinary team implemented a UCD process to design and evaluate a mobile app for older adults with heart failure. During and after this process, we documented the challenges the team encountered and the strategies they used or considered using to address those challenges.

Results

We identified 12 challenges, 3 about UCD as a whole and 9 across the UCD stages of formative research, design, and evaluation. Challenges included the timing of stakeholder involvement, overcoming designers’ assumptions, adapting methods to end users, and managing heterogeneity among stakeholders. To address these challenges, practical recommendations are provided to UCD researchers and practitioners.

Conclusions

UCD is a gold standard approach that is increasingly adopted for mHealth projects. Although UCD methods are well-described and easily accessible, practical challenges and strategies for implementing them are underreported. To improve the implementation of UCD for mHealth, we must tell and learn from these traditionally untold stories.

Beyond the Impact Factor: Reflecting on Twenty Years of Leading Efforts in Research, Innovation in Publishing, and Investment in People

This viewpoint celebrates the accomplishments of the Journal of Medical Internet Research on its twentieth anniversary and reviews accomplishments around research publications, journal innovation, and supporting people.

Veterans' Perspectives on Fitbit Use in Treatment for Post-Traumatic Stress Disorder: An Interview Study

BACKGROUND

The increase in availability of patient data through consumer health wearable devices and mobile phone sensors provides opportunities for mental health treatment beyond traditional self-report measurements. Previous studies have suggested that wearables can be effectively used to benefit the physical health of people with mental health issues, but little research has explored the integration of wearable devices into mental health care. As such, early research is still necessary to address factors that might impact integration including patients' motivations to use wearables and their subsequent data.

OBJECTIVE

The aim of this study was to gain an understanding of patients' motivations to use or not to use wearables devices during an intensive treatment program for post-traumatic stress disorder (PTSD). During this treatment, they received a complementary Fitbit. We investigated the following research questions: How did the veterans in the intensive treatment program use their Fitbit? What are contributing motivators for the use and nonuse of the Fitbit?

METHODS

We conducted semistructured interviews with 13 veterans who completed an intensive treatment program for PTSD. We transcribed and analyzed interviews using thematic analysis.

RESULTS

We identified three major motivations for veterans to use the Fitbit during their time in the program: increase self-awareness, support social interactions, and give back to other veterans. We also identified three major reasons certain features of the Fitbit were not used: lack of clarity around the purpose of the Fitbit, lack of meaning in the Fitbit data, and challenges in the veteran-provider relationship.

CONCLUSIONS

To integrate wearable data into mental health treatment programs, it is important to understand the patient's perspectives and motivations in using wearables. We also discuss how the military culture and PTSD may have contributed to our participants' behaviors and attitudes toward Fitbit usage. We conclude with possible approaches for integrating patient-generated data into mental health treatment settings that may address the challenges we identified.