Background: Type 2 diabetes (T2D) tremendously affects patient health and health care globally. Changing lifestyle behaviors can help curb the burden of T2D. However, health behavior change is a complex interplay of medical, behavioral, and psychological factors. Personalized lifestyle advice and promotion of self-management can help patients change their health behavior and improve glucose regulation. Digital tools are effective in areas of self-management and have great potential to support patient self-management due to low costs, 24/7 availability, and the option of dynamic automated feedback. To develop successful eHealth solutions, it is important to include stakeholders throughout the development and use a structured approach to guide the development team in planning, coordinating, and executing the development process. Objective: The aim of this study is to develop an integrated, eHealth-supported, educational care pathway for patients with T2D. Methods: The educational care pathway was developed using the first 3 phases of the Center for eHealth and Wellbeing Research roadmap: the contextual inquiry, the value specification, and the design phase. Following this roadmap, we used a scoping review about diabetes self-management education and eHealth, past experiences of eHealth practices in our hospital, focus groups with health care professionals (HCPs), and a patient panel to develop a prototype of an educational care pathway. This care pathway is called the Diabetes Box (Leiden University Medical Center) and consists of personalized education, digital educational material, self-measurements of glucose, blood pressure, activity, and sleep, and a smartphone app to bring it all together. Results: The scoping review highlights the importance of self-management education and the potential of telemonitoring and mobile apps for blood glucose regulation in patients with T2D. Focus groups with HCPs revealed the importance of including all relevant lifestyle factors, using a tailored approach, and using digital consultations. The contextual inquiry led to a set of values that stakeholders found important to include in the educational care pathway. All values were specified in biweekly meetings with key stakeholders, and a prototype was designed. This prototype was evaluated in a patient panel that revealed an overall positive impression of the care pathway but stressed that the number of apps should be restricted to one, that there should be no delay in glucose value visualization, and that insulin use should be incorporated into the app. Both patients and HCPs stressed the importance of direct automated feedback in the Diabetes Box. Conclusions: After developing the Diabetes Box prototype using the Center for eHealth and Wellbeing Research roadmap, all stakeholders believe that the concept of the Diabetes Box is useful and feasible and that direct automated feedback and education on stress and sleep are essential. A pilot study is planned to assess feasibility, acceptability, and usefulness in more detail.

@en

Objective
Adopting healthy behavior is vital for preventing chronic diseases. Mobile health (mHealth) interventions utilizing virtual coaches (i.e., artificial intelligence conversational agents) can offer scalable and cost-effective solutions. Additionally, targeting multiple unhealthy behaviors, like low physical activity and smoking, simultaneously seems beneficial. We developed Perfect Fit, an mHealth intervention with a virtual coach providing personalized feedback to simultaneously promote smoking cessation and physical activity. Through innovative methods (e.g., sensor technology) and iterative development involving end-users, we strive to overcome challenges encountered by mHealth interventions, such as shortage of evidence-based interventions and insufficient personalization. This paper outlines the content of Perfect Fit and the protocol for evaluating its feasibility, acceptability, and preliminary effectiveness, the role of participant characteristics, and the study's feasibility.
Methods
A single-arm, mixed-method, real-world evaluation study will be conducted in the Netherlands. We aim to recruit 100 adult daily smokers intending to quit within 6 weeks. The personalized intervention will last approximately 16 weeks. Primary outcomes include Perfect Fit's feasibility and acceptability. Secondary outcomes are preliminary effectiveness and study feasibility, and we will measure participant characteristics. Quantitative data will be collected through questionnaires administered at baseline, post-intervention and 2, 6, and 12 months post-intervention. Qualitative data will be gathered via semi-structured interviews post-intervention. Data analysis will involve descriptive analyses, generalized linear mixed models (quantitative) and the Framework Approach (qualitative), integrating quantitative and qualitative data during interpretation.
Conclusions
This study will provide novel insight into the potential of interventions like Perfect Fit, as a multiple health behavior change strategy. Findings will inform further intervention development and help identify methods to foster feasibility and acceptability. Successful mHealth interventions with virtual coaches will prevent chronic diseases and promote public health.@en

Health care is under pressure due to an aging population with an increasing prevalence of chronic diseases, including cardiovascular disease. Smoking and physical inactivity are 2 key preventable risk factors for cardiovascular disease. Yet, as with most health behaviors, they are difficult to change. In the interdisciplinary Perfect Fit project, scientists from different fields join forces to develop an evidence-based virtual coach (VC) that supports smokers in quitting smoking and increasing their physical activity. In this Viewpoint paper, intervention content, design, and implementation, as well as lessons learned, are presented to support other research groups working on similar projects. A total of 6 different approaches were used and combined to support the development of the Perfect Fit VC. The approaches used are (1) literature reviews, (2) empirical studies, (3) collaboration with end users, (4) content and technical development sprints, (5) interdisciplinary collaboration, and (6) iterative proof-of-concept implementation. The Perfect Fit intervention integrates evidence-based behavior change techniques with new techniques focused on identity change, big data science, sensor technology, and personalized real-time coaching. Intervention content of the virtual coaching matches the individual needs of the end users. Lessons learned include ways to optimally implement and tailor interactions with the VC (eg, clearly explain why the user is asked for input and tailor the timing and frequency of the intervention components). Concerning the development process, lessons learned include strategies for effective interdisciplinary collaboration and technical development (eg, finding a good balance between end users’ wishes and legal possibilities). The Perfect Fit development process was collaborative, iterative, and challenging at times. Our experiences and lessons learned can inspire and benefit others. Advanced, evidence-based digital interventions, such as Perfect Fit, can contribute to a healthy society while alleviating health care burden.@en

Background: Smoking and physical inactivity are two key preventable risk factors of cardiovascular disease. Yet, as with most health behaviors, they are difficult to change. In the interdisciplinary Perfect Fit project, scientists from different fields join forces to develop an evidence-based virtual coach that supports smokers in quitting smoking and increasing their physical activity. Intervention content, design and implementation as well as lessons learnt are presented in the hopes of guiding other research groups working on similar projects. Methods: Numerous approaches were used and combined to support the development of the Perfect Fit virtual coach. Approaches include literature reviews, empirical studies, collaboration with end-users, content and technical development sprints, interdisciplinary collaboration and iterative proof-of-concept implementation. Findings: The Perfect Fit intervention integrates evidence-based behavioral change techniques as well as new techniques focused on identity change, big data science, sensor technology and personalized real-time coaching. Intervention content of the virtual coaching matches communication preferences and individual needs of end users. Lessons learnt include ways to optimally implement and tailor interactions from the virtual coach (e.g., ‘explain why user is asked for input’, ‘tailor timing and frequency of intervention components’). With regards to the development process, lessons learnt include strategies for effective interdisciplinary collaboration and technical development (e.g., ‘Find a good balance between wishes of end-users and legal possibilities’). Discussion: The Perfect Fit development process was interactive, iterative and challenging at times. We hope that our experiences and lessons learnt can inspire and benefit others.@en