Development of “LvL UP 1.0”: a smartphone-based, conversational agent-delivered holistic lifestyle intervention for the prevention of non-communicable diseases and common mental disorders

Castro, Óscar; Mair, Jacqueline L.; Salamanca-Sanabria, Alicia; Alattas, Aishah; Keller, Roman; Zheng, Shenglin; Jabir, Ahmad Ishqi; Lin, Xiaowen; Frese, Bea Franziska; Lim, Chang Siang; Santhanam, Prabhakaran; Dam, Rob M. van; Car, Josip; Lee, Jimmy; Tai, E. Shyong; Fleisch, Elgar; Wangenheim, Florian von; Car, Lorainne Tudor; Müller‐Riemenschneider, Falk; Kowatsch, Tobias

doi:10.3389/fdgth.2023.1039171

Cited by 10 publications

(8 citation statements)

References 169 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible that the fully automated social components in the CanRelax app 2.0, such as the weekly coaching sessions with Lumy, compensated for the lack of human support. This aligns with recent research underscoring the potential of conversational agents to positively impact engagement with mHealth apps [3,[72][73][74][75][76][77]. We demonstrated this potential by combining a conversational agent with a theoretical foundation and incorporating key design principles inspired by highly engaging commercial apps (eg, inclusive avatar and visuals).…”

Section: Comparison With Prior Worksupporting

confidence: 84%

Engagement With a Relaxation and Mindfulness Mobile App Among People With Cancer: Exploratory Analysis of Use Data and Self-Reports From a Randomized Controlled Trial

Schläpfer,

Schneider,

Santhanam

et al. 2024

JMIR Cancer

Self Cite

View full text Add to dashboard Cite

Background Mobile health (mHealth) apps offer unique opportunities to support self-care and behavior change, but poor user engagement limits their effectiveness. This is particularly true for fully automated mHealth apps without any human support. Human support in mHealth apps is associated with better engagement but at the cost of reduced scalability. Objective This work aimed to (1) describe the theory-informed development of a fully automated relaxation and mindfulness app to reduce distress in people with cancer (CanRelax app 2.0), (2) describe engagement with the app on multiple levels within a fully automated randomized controlled trial over 10 weeks, and (3) examine whether engagement was related to user characteristics. Methods The CanRelax app 2.0 was developed in iterative processes involving input from people with cancer and relevant experts. The app includes evidence-based relaxation exercises, personalized weekly coaching sessions with a rule-based conversational agent, 39 self-enactable behavior change techniques, a self-monitoring dashboard with gamification elements, highly tailored reminder notifications, an educational video clip, and personalized in-app letters. For the larger study, German-speaking adults diagnosed with cancer within the last 5 years were recruited via the web in Switzerland, Austria, and Germany. Engagement was analyzed in a sample of 100 study participants with multiple measures on a micro level (completed coaching sessions, relaxation exercises practiced with the app, and feedback on the app) and a macro level (relaxation exercises practiced without the app and self-efficacy toward self-set weekly relaxation goals). Results In week 10, a total of 62% (62/100) of the participants were actively using the CanRelax app 2.0. No associations were identified between engagement and level of distress at baseline, sex assigned at birth, educational attainment, or age. At the micro level, 71.88% (3520/4897) of all relaxation exercises and 714 coaching sessions were completed in the app, and all participants who provided feedback (52/100, 52%) expressed positive app experiences. At the macro level, 28.12% (1377/4897) of relaxation exercises were completed without the app, and participants’ self-efficacy remained stable at a high level. At the same time, participants raised their weekly relaxation goals, which indicates a potential relative increase in self-efficacy. Conclusions The CanRelax app 2.0 achieved promising engagement even though it provided no human support. Fully automated social components might have compensated for the lack of human involvement and should be investigated further. More than one-quarter (1377/4897, 28.12%) of all relaxation exercises were practiced without the app, highlighting the importance of assessing engagement on multiple levels.

show abstract

Section: Comparison With Prior Worksupporting

confidence: 84%

Engagement With a Relaxation and Mindfulness Mobile App Among People With Cancer: Exploratory Analysis of Use Data and Self-Reports From a Randomized Controlled Trial

Schläpfer,

Schneider,

Santhanam

et al. 2024

JMIR Cancer

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, reliance on human support within DHIs vastly reduces their scalability and cost-effectiveness potential. Given that personalized support appears to be crucial for effective behavior change, alternative delivery strategies, such as using conversational agents [ 114 , 115 , 116 , 117 ], should be explored as a matter of priority to develop scalable and effective DHI solutions.…”

Section: Discussionmentioning

confidence: 99%

Effective Behavior Change Techniques in Digital Health Interventions for the Prevention or Management of Noncommunicable Diseases: An Umbrella Review

Mair,

Salamanca-Sanabria,

Augsburger

et al. 2023

Annals of Behavioral Medicine

Self Cite

View full text Add to dashboard Cite

Background Despite an abundance of digital health interventions (DHIs) targeting the prevention and management of noncommunicable diseases (NCDs), it is unclear what specific components make a DHI effective. Purpose This narrative umbrella review aimed to identify the most effective behavior change techniques (BCTs) in DHIs that address the prevention or management of NCDs. Methods Five electronic databases were searched for articles published in English between January 2007 and December 2022. Studies were included if they were systematic reviews or meta-analyses of DHIs targeting the modification of one or more NCD-related risk factors in adults. BCTs were coded using the Behavior Change Technique Taxonomy v1. Study quality was assessed using AMSTAR 2. Results Eighty-five articles, spanning 12 health domains and comprising over 865,000 individual participants, were included in the review. We found evidence that DHIs are effective in improving health outcomes for patients with cardiovascular disease, cancer, type 2 diabetes, and asthma, and health-related behaviors including physical activity, sedentary behavior, diet, weight management, medication adherence, and abstinence from substance use. There was strong evidence to suggest that credible source, social support, prompts and cues, graded tasks, goals and planning, feedback and monitoring, human coaching and personalization components increase the effectiveness of DHIs targeting the prevention and management of NCDs. Conclusions This review identifies the most common and effective BCTs used in DHIs, which warrant prioritization for integration into future interventions. These findings are critical for the future development and upscaling of DHIs and should inform best practice guidelines.

show abstract

“…LLM CAs are, therefore, not yet appropriate for safe and ethical delivery of several-week health interventions [47]. We therefore, decided for an established, save and transparent approach to CAs and employed a rule-based CA [39,40,[48][49][50][51].…”

Section: Misha -A Chatbot-delivered Stress Management Coaching For St...mentioning

confidence: 99%

A Chatbot-Delivered Stress Management Coaching for Students (MISHA App): Pilot Randomized Controlled Trial

Ulrich,

Lienhard,

Künzli

et al. 2024

JMIR Mhealth Uhealth

Self Cite

View full text Add to dashboard Cite

Background: Globally, students face increasing mental health challenges, including elevated stress levels and declining wellbeing, leading to academic performance issues and mental health disorders. However, due to stigma and symptom underestimation, students rarely seek effective stress management solutions. Conversational agents (CAs) in the health sector have shown promise in reducing stress, depression, and anxiety. Nevertheless, research on their effectiveness for stressed students remains limited.Objective: This study aimed to develop a CA-delivered stress-management coaching intervention for students called MISHA, and to evaluate the effectiveness, engagement, and acceptance. Methods:In an unblinded randomized controlled trial, Swiss students experiencing stress were recruited online. By a 1.1 randomization, participants (N=140) were allocated to the intervention or wait-list control group. Treatment effectiveness on changes on primary outcome perceived stress, and secondary outcomes depression, anxiety, psychosomatic symptoms, and active coping, were evaluated using analyses of variance (ANOVA) and general estimating equations (GEE). Results:The per protocol (PP) analysis revealed evidence for improvement of stress, depression, and somatic symptoms with effects ranging from medium to medium-large (d=0.54 to d=0.67), while anxiety, and active coping did not change significantly (d=0.37; d=0.39). In the intention to treat (ITT) analysis, we found evidence for reduced stress (?=-0.13, 95% CI -0.20 to -0.05, P<.001), depressive symptoms (?=-0.23, 95% CI -0.38 to -0.08, P=.003), and psychosomatic symptoms (?=-0.16, 95% CI = -0.27 to -0.06, P=.003), while anxiety, and active comping did change. Overall, 60% of participants in the intervention group completed the coaching by completing the outro. The particularly appreciated the quality, quantity, credibility, and visual representation of information. While individual customization was rated lowest, the target group fitting was perceived high. Conclusions:Findings indicate that MISHA is feasible, acceptable and effective in reducing perceived stress among students in Switzerland. Future research is needed for different populations, for example in students with high stress levels or compared to active controls.

show abstract

Development of “LvL UP 1.0”: a smartphone-based, conversational agent-delivered holistic lifestyle intervention for the prevention of non-communicable diseases and common mental disorders

Cited by 10 publications

References 169 publications

Engagement With a Relaxation and Mindfulness Mobile App Among People With Cancer: Exploratory Analysis of Use Data and Self-Reports From a Randomized Controlled Trial

Engagement With a Relaxation and Mindfulness Mobile App Among People With Cancer: Exploratory Analysis of Use Data and Self-Reports From a Randomized Controlled Trial

Effective Behavior Change Techniques in Digital Health Interventions for the Prevention or Management of Noncommunicable Diseases: An Umbrella Review

A Chatbot-Delivered Stress Management Coaching for Students (MISHA App): Pilot Randomized Controlled Trial

Contact Info

Product

Resources

About