Search Results (33)

Background: Artificial Intelligence (AI) and Machine Learning (ML) technologies, such as conversational agents, are becoming increasingly essential tools across multiple industries, particularly in healthcare. This paper presents a scoping review (PRISMA-ScR) of conversational agents (CAs) in mobile health coaching systems (MHCS). It examines existing applications of MHCS, focusing on development strategies, usage contexts, impacts on users, benefits, and research gaps, emphasizing the ability of explainable artificial intelligence (XAI) in making health guidance and decision-support recommendations transparent, trustworthy, and interpretable, if properly integrated. This scoping review identifies opportunities to maximize the use of conversational agents, explainable AI, and mobile technologies to make mobile health coaching systems more accessible and trustworthy, as well as further research gaps worth exploring. Objective: This scoping review maps the evidence on CAs and XAI-enabled technologies in MHCS, identifies trust-related design criteria, categorizes reported outcomes, and highlights opportunities for explainable conversational agents (XCA) in a mobile health context, especially in tackling general medical conditions pertinent in underserved settings. Eligibility criteria: Reported eligible resources evaluated, designed, or conceptually analyzed existing CAs, XAI techniques, and MHCS, AI-supported medical dialogue systems, e-coaching systems, and mobile health applications. We considered sources only relevant to healthcare, health coaching, trust, explainability, or patient engagement that were published between 2006 and 2025. Sources of Evidence: Searches were conducted in IEEE Xplore, Google Scholar, Springer, ScienceDirect/Elsevier, ProQuest, and ACM Digital Library, supplemented by targeted web searches and backward citation checks. Charting methods: Data were charted by system type, communication mode, health context, operational mode, technology used, XAI/trust features, degree of automation, study designs and outcome classification. We applied a revised outcome classification: generated desired outcome (GDO) and partially generated desired outcome (P-GDO), and did not generate desired outcome (DN-GDO). Results: A total of 201 resources were collected. Charted studies clustered around CAs in health, MHCS for chronic diseases and stress management, XAI methods such as LIME, SHAP, Prospector, and counterfactual explanations, and trust-related elements such as voice quality, communication style, appearance, social intelligence, privacy, and performance quality. Most health CAs and MHCS addressed chronic diseases, mental health, or behavior change; fewer addressed general medical diagnosis or autonomous mobile-based primary care support. Conclusions: Existing evidence suggests that CAs and MHCSs can support engagement, coaching, education, and selected decision-support tasks, but evidence for safe, autonomous, explainable general practice functionality remains limited. Future work should prioritize clinically supervised XCA designs, core safety assessment, interfaces with transparent explanation, data protection, culturally and linguistically responsive implementation, and future-oriented review in underserved mobile health settings. Full article

During pregnancy, women are more inclined to modify their habits and lifestyle to find a new balance and promote well-being for themselves and the child-to-be. However, the availability of nutritional and psychological support is often limited by stigma, geographic barriers, and a lack of services. Digital health tools are emerging as possible solutions to cover these needs. This study explores the acceptability, feasibility, and user experience of Demetra, a virtual coach based on Acceptance and Commitment Therapy (ACT), designed to promote healthy lifestyles and mental well-being. Fifty pregnant women will be enrolled in the feasibility study of the intervention. It starts with an educational part on the foundations of healthy eating and suggestions about lifestyle habits, followed by a six-week psychoeducational module. Content is delivered through text, audio, and video formats. User experience and engagement will be measured through validated questionnaires and semi-structured interviews. Psychological well-being will be evaluated both before and after the program. The intervention is expected to be well-received, with high levels of satisfaction and engagement, leading to a greater awareness of healthy behaviors, improved psychological flexibility, and enhanced overall well-being. Demetra offers an accessible solution to support women through the transformative experience of motherhood with a multidisciplinary and innovative approach. Full article

Background: A sedentary behavior and being overweight represent major public health issues associated with both physical and psychological risks. Based on self-determination theory (SDT), the psychoeducational intervention PsicoFIT—a component of the TIGREFIT program—aims to foster motivation toward physical activity, to promote healthy habits, and to reduce psychological ill-being in sedentary adults who are overweight and are fans of a football club. Methods: This protocol corresponds to a longitudinal comparative pragmatic clinical trial, designed in accordance with the recommendations of the SPIRIT Statement. The intervention, preceded by a training program for the coaches involved, will comprise 12 weekly modules delivered in two modalities: (1) face-to-face, through group sessions, and (2) semi face-to-face, through short video capsules hosted on a digital platform. Changes associated with the intervention will be evaluated using hierarchical multiple regression and pre-post comparisons, assessing baseline and post-intervention data within and between the intervention modalities. Primary outcomes will include changes in healthy lifestyle and burnout as indicators of well-being and ill-being, respectively. Secondary outcomes will assess basic psychological needs satisfaction and autonomous motivation as potential mediators of these effects, as well as the coach’s controlling interpersonal style as a possible contextual predictor. The modality of participation will be analyzed as a potential moderator of the observed changes. Finally, the acceptability and perceived contribution of the intervention will be explored through a focus group. Discussion: PsicoFIT will provide a methodological framework for designing interventions within multicomponent programs aimed at promoting healthy lifestyles and psychological well-being in sedentary adults who are overweight, considering the social context of football fandom and allowing for an exploration of the impact of the face-to-face and semi-face-to-face modalities. Future empirical application of the protocol will help verify its effectiveness, guide adaptations across contexts, and contribute to the development of evidence-based interventions. Conclusions: The implementation of PsicoFit will allow for the evaluation of its effectiveness, psychological mechanisms, and delivery modalities, thus guiding future evidence-based interventions in sport. Full article

Playing sports remains one of the most common avenues for youth engagement in physical activity. Yet mental health challenges, such as performance anxiety, depressive symptoms, reduced motivation, and burnout, place many young athletes at risk. As key mediators of sport participation, coaches’ roles are often underscored in recognizing shifts in athlete motivation, behavior, or well-being. Gaining better insight into athlete mental health status may enable coaches to provide timely support and strengthen athlete and team well-being. In this study protocol, we employ a mixed-methods design, evaluating the effectiveness of an AI-augmented mobile application (i.e., ThriveNudge) in promoting the mental health of youth athletes. ThriveNudge helps coaches monitor athlete mental health, flag mood disruptions, and practice supportive communication via simulated chats. A target sample of four interscholastic teams (with athletes aged 14–18 years) and their head coaches will be recruited. Teams will be cluster-randomized to either the intervention condition (n = 2), receiving pre-season training to implement ThriveNudge, or to a waitlist control condition (n = 2). Primary outcomes, including athlete burnout, motivation, coach–athlete relationships, and sport enjoyment, will be measured using psychometric scales administered online. Semi-structured interviews will be conducted with coaches and athletes in the experimental group to collect qualitative data on user interface and user experience. We hypothesize that teams using ThriveNudge will report lower athlete anxiety and burnout, higher intrinsic motivation and enjoyment, and stronger coach–athlete relationships than athletes in control teams. We aim to provide a scalable and accessible digital platform that safeguards youth mental health. Full article

Background: Obesity management is evolving with the integration of dual GIP/GLP-1 receptor agonists (Tirzepatide) into comprehensive Digital Weight-Loss Services (DWLSs). This model leverages virtual, app-based multidisciplinary care (MDT) to deliver continuous, supervised treatment, distinguishing it from traditional, intermittent clinic-based care. While clinical trials demonstrate high efficacy, real-world data are necessary to evaluate long-term adherence and identify predictive markers for patient persistence in these scalable care models. Specifically, there is a knowledge gap regarding the specific behavioral factors that govern 12-month persistence in these comprehensive, medicated DWLS settings. This study retrospectively assessed the 12-month effectiveness and adherence of a Tirzepatide-supported DWLS and identified demographic, clinical, and behavioral predictors of weight loss and program attrition. Methods: Data from 19,693 patients enrolled in the Juniper UK DWLS were analyzed. Adherence was defined by a minimum of 10 medication orders and 12-month weight submission. Weight loss in the full cohort was evaluated using the Last Observation Carried Forward (LOCF) method. Binary logistic and multiple linear regression models identified predictors of adherence and weight loss, respectively, using a comprehensive set of demographic, clinical (e.g., BMI, comorbidities), and behavioral variables. Results: The 12-month adherence rate was 27%. The adherent sub-cohort (n = 5322) achieved a mean weight loss of 22.60 (±7.46) percent, compared to 13.62 (±10.85) percent in the full cohort (LOCF). This difference in 12-month mean weight loss was statistically significant (p < 0.001). Consistent weekly weight tracking and health coach communication were the strongest positive predictors of long-term adherence and weight loss. Conversely, hyper-engagement, specifically intensive tracking frequency and high weight loss velocity in the first month, was a significant inverse predictor of 12-month adherence. Reporting side effects was positively correlated with adherence, suggesting a reporting bias among engaged patients. Conclusions: The DWLS model facilitates the maximum therapeutic effectiveness for adherent patients. However, patient persistence remains the primary translational challenge. As consistent weekly engagement (tracking, coaching) is the strongest predictor of success, clinical strategies should prioritize promoting sustainable, moderate behavioral pacing (i.e., emphasizing consistent weekly engagement over intensive daily tracking and rapid early weight loss) to mitigate attrition risk and optimize the public health effectiveness of medicated DWLSs. Full article

Background: Digital exclusion is a validated risk factor for cognitive decline in older adults. Digital interventions exhibit high dropout rates due to low digital literacy, technology anxiety, and limited adaptation to individual states, resulting in limited real-world transfer. Objective: This protocol aims to present the CTC Framework (Coach–Teacher–Companion), a tri-agent generative AI system proposed for exploring the feasibility of adaptive cognitive interventions in older adults with existing digital access. The protocol provides technical architecture, feasibility-stage implementation procedures, and methodological and ethical guidelines to assist clinicians in safely applying AI-based cognitive interventions in clinical research settings. Methods: The framework integrates three AI agents (Coach, Teacher, and Companion) designed to provide behavioral, cognitive, and emotional support. The system is designed to embed cognitive exercises in daily activities, monitor emotional states, and incorporate accessibility features for age-related limitations. Implementation safeguards include digital literacy assessment (MDPQ-16), technology anxiety monitoring (CARS), emotional safety protocols, and data privacy protections. The protocol specifies a six-week feasibility study (n$=14$, MMSE 18–25) to evaluate usability (System Usability Scale, primary outcome), user experience (UEQ-S), psychological needs satisfaction (BPNS), emotional safety (PANAS), adherence, and preliminary cognitive outcomes (MMSE, TMT-A/B, Digit Span). Conclusions: The CTC Framework is designed to provide methodological and ethical safeguards for clinical implementation, including standardized procedures for digital literacy assessment, technology anxiety management, emotional safety monitoring, and data privacy protections. Empirical validation of the framework’s feasibility and efficacy is required through future studies. Full article

Background: Plant-based diets are associated with reduced risk of chronic diseases and improved health outcomes. However, sustaining dietary changes remains challenging. Digital interventions—including virtual culinary medicine programs, web-based nutrition coaching, SMS and email reminders, mobile application–based self-management, and hybrid community programs—offer promising strategies to support behavior change, enhance cooking skills, and improve dietary adherence. These approaches are relevant for both healthy individuals and those living with chronic conditions. Methods: We conducted a narrative review of studies published between 2000 and 2025 in PubMed/MEDLINE, Scopus, and Web of Science, supplemented with manual searches. Included studies comprised randomized controlled trials, quasi-experimental designs, feasibility studies, and qualitative research. Interventions were categorized by modality (SMS, email, web platforms, mobile apps, virtual culinary programs, and hybrid formats) and population (healthy adults, patients with chronic diseases). Outcomes examined included dietary quality, self-efficacy, psychosocial well-being, and program engagement. Results: Most studies reported improvements in dietary quality, cooking skills, nutrition knowledge, and psychosocial outcomes. Virtual cooking programs enhanced dietary adherence and engagement, particularly among individuals at cardiovascular risk. Digital nutrition education supported behavior change in chronic disease populations, including patients with multiple sclerosis. SMS and email reminders improved self-monitoring and participation rates, while mobile applications facilitated real-time feedback and goal tracking. Hybrid programs combining online and in-person components increased motivation, social support, and long-term adherence. Reported barriers included limited technological access or skills, lack of personalization, and privacy concerns. Conclusions: Virtual culinary medicine programs and other digital microinterventions—including SMS, email, web, mobile, and hybrid formats—are effective tools to promote plant-based diets. Future interventions should focus on personalized, accessible, and hybrid strategies, with attention to underserved populations, to maximize engagement and sustain long-term dietary change. Full article

Background/Objectives: As global aging accelerates, there is a pressing and empirically substantiated demand for integrated and sustainable strategies, as evidenced by the rising prevalence rates of chronic conditions, social isolation, and digital exclusion among older adults worldwide. These factors underscore the urgent need for multidimensional interventions that simultaneously target physical, psychological, and social well-being. The HOPE-FIT (Hybrid Outreach Program for Exercise and Follow-up Integrated Training) model and the SAGE (Senior Active Guided Exercise) program were designed to address this need through a hybrid framework. These programs foster inclusive aging by explicitly bridging digitally underserved groups and mobility-restricted populations into mainstream health promotion systems through tailored exercise, psychosocial support, and smart-home technologies, thereby functioning as a scalable meta-model across healthcare, community, and policy domains. Methods: HOPE-FIT was developed through a formative, multi-phase process grounded in the RE-AIM framework and a Hybrid Type II effectiveness–implementation design. The program combines professional health coaching, home-based and digital exercise routines, Acceptance and Commitment Performance Training (ACPT)-based psychological strategies, and smart-home monitoring technologies. Empirical data from pilot studies, large-scale surveys (N = 1000), and in-depth user evaluations were incorporated to strengthen validity and contextual adaptation. Culturally tailored content and participatory feedback from older adults further informed ecological validity and program refinement. Implementation Strategy/Framework: The theoretical foundation integrates implementation science with behavioral and digital health. The RE-AIM framework guided reach, fidelity, and maintenance planning, while the Hybrid E–I design enabled the concurrent evaluation of effectiveness outcomes and contextual implementation strategies. Institutional partnerships with community centers, public health organizations, and welfare agencies further facilitated the translation of the model into real-world aging contexts. Dissemination Plan: The multi-pronged dissemination strategy includes international symposia, interdisciplinary academic networks, policy briefs, localized community deployment, and secure, authenticated data sharing for reproducibility. This design facilitates evidence-informed policy, empowers practitioners, and advances digital health equity. Ultimately, HOPE-FIT constitutes a scalable and inclusive model that concretely addresses health disparities and promotes active, dignified aging across systems and disciplines. Full article

Motor insurance can use telematics data not only to understand individual driving style but also to implement innovative coaching strategies that feed back to the drivers, through an app, the aggregated information extracted from the data. The purpose is to encourage an improvement in their driving style. A precondition for this improvement is that drivers are digitally engaged, that is, they interact with the app. This paper proposes a narrow understanding of the term engagement, referring to users’ interactions with the app. This interaction is also a behavior producing specific data that can be tracked and used by insurance companies. Based on the empirical investigation of the dataset of a company selling a telematics motor insurance policy, our research investigates if there is a correlation between engagement with the app and improvement of driving style. The analysis distinguishes different groups of users with different driving abilities, and takes into account time differences. Our findings contribute to clarifying the methodological challenges that must be addressed when exploring engagement and coaching effectiveness in proactive insurance policies. We conclude by discussing the possibility and difficulties of tracking and using second-order behavioral data related to policyholder engagement with the app. Full article

Background: Despite significant advancements in diabetes care, many individuals with type 2 diabetes (T2D) do not receive optimal care and treatment. Digital interventions promoting behavioral changes have shown promising long-term results in supporting healthier lifestyles but are not implemented in most healthcare offerings, maybe due to lack of general practice support and collaboration. This study evaluates the efficacy of the Digital, Individualized, and Collaborative Treatment of T2D in General Practice Based on Decision Aid (DICTA), a randomized controlled trial integrating a patient-centered smartphone application for lifestyle support in conjunction with a clinical decision support (CDS) tool to assist general practitioners (GPs) in optimizing antidiabetic treatment. Methods: The present randomized controlled trial aims to recruit 400 individuals with T2D from approximately 70 GP clinics (GPCs) in Denmark. The GPCs will be cluster-randomized in a 2:3 ratio to intervention or control groups. The intervention group will receive one year of individualized eHealth lifestyle coaching via a smartphone application, guided by patient-reported outcomes (PROs). Alongside this, the GPCs will have access to the CDS tool to optimize pharmacological decision-making through electronic health records. The control group will receive usual care for one year, followed by the same intervention in the second year. Results: The primary outcome is the one-year change in estimated ten-year cardiovascular risk, assessed by SCORE2-Diabetes calculated from age, smoking status, systolic blood pressure, total and high-density lipoprotein cholesterol, age at diabetes diagnosis, HbA1c, and eGFR. Conclusions: If effective, DICTA could offer a scalable, digital-first approach for improving T2D management in primary care by combining patient-centered lifestyle coaching with real-time pharmacological clinical decision support. Full article

Background: Obesity in adults is a growing health concern. The principal interventions used in obesity management are lifestyle-change interventions such as diet, exercise, and behavioral therapy. Although they are effective, current treatment options have not succeeded in halting the global rise in the prevalence of obesity or achieving sustained long-term weight maintenance at the population level. E-health and m-health are both integral components of digital health that focus on the use of technology to improve healthcare delivery and outcomes. The use of eHealth/mHealth might improve the management of some of these treatments. Several digital health interventions to manage obesity are currently in clinical trials. Objective: The aim of our systematic review is to evaluate whether digital health interventions (e-Health and m-Health) have effects on changes in anthropometric measures, such as weight, BMI, and waist circumference and behaviors such as energy intake, eating behaviors, and physical activity. Methods: A search was conducted for randomized controlled trials (RCTs) conducted through 4 October 2024 through three databases (Medline, Web of Science, and Scopus). Studies were included if they evaluated digital health interventions (e-Health and m-Health) compared to control groups in overweight or obese adults (BMI ≥ 25 kg/m²) and reported anthropometric or lifestyle behavioral outcomes. Study quality was assessed using the Cochrane Risk of Bias Tool (RoB 2). Meta-analyses were performed using random-effects or fixed-effects models as appropriate, with statistical significance set at p < 0.05. Results: Twenty-two RCTs involving diverse populations (obese adults, overweight individuals, postpartum women, patients with eating disorders) were included. Digital interventions included biofeedback devices, smartphone apps, e-coaching systems, web-based interventions, and mixed approaches. Only waist circumference showed a statistically significant reduction (WMD = −1.77 cm; 95% CI: −3.10 to −0.44; p = 0.009). No significant effects were observed for BMI (WMD = −0.43 kg/m²; p = 0.247), body weight (WMD = 0.42 kg; p = 0.341), or lifestyle behaviors, including physical activity (SMD = −0.01; p = 0.939) and eating behavior (SMD = −0.13; p = 0.341). Body-fat percentage showed a borderline-significant trend toward reduction (WMD = −0.79%; p = 0.068). High heterogeneity was observed across most outcomes (I² > 80%), indicating substantial variability between studies. Quality assessment revealed predominant judgments of “Some Concerns” and “High Risk” across the evaluated domains. Conclusions: Digital health interventions produce modest but significant benefits on waist circumference in overweight and obese adults, without significant effects on other anthropometric or behavioral parameters. The high heterogeneity observed underscores the need for more personalized approaches and future research focused on identifying the most effective components of digital interventions. Digital health interventions should be positioned as valuable adjuncts to, rather than replacements for, established obesity treatments. Their integration within comprehensive care models may enhance traditional interventions through continuous monitoring, real-time feedback, and improved accessibility, but interventions with proven efficacy such as behavioral counseling and clinical oversight should be maintained. Full article

Embodied Conversational Agents (ECAs) serve as digital twins (DTs), visually and behaviorally mirroring human counterparts in various roles, including healthcare coaching. While existing research primarily focuses on single-coach ECAs, our work explores the benefits of multi-coach virtual health sessions, where users engage with specialized diet, physical, and cognitive coaches simultaneously. ECAs require verbal relational cues—such as empowerment, affirmation, and empathy—to foster user engagement and adherence. Our study integrates Generative AI to automate the embedding of these cues into coaching dialogues, ensuring the advice remains unchanged while enhancing delivery. We employ ChatGPT to generate empathetic and collaborative dialogues, comparing their effectiveness against manually crafted alternatives. Using three participant cohorts, we analyze user perception of the helpfulness of AI-generated versus human-generated relational cues. Additionally, we investigate whether AI-generated dialogues preserve the original advice’s semantics and whether human or automated validation better evaluates their lexical meaning. Our findings contribute to the automation of digital health coaching. Comparing ChatGPT- and human-generated dialogues for helpfulness, users rated human dialogues as more helpful, particularly for working alliance and affirmation cues, whereas AI-generated dialogues were equally effective for empowerment. By refining relational cues in AI-generated dialogues, this research paves the way for automated virtual health coaching solutions. Full article

Digital sports, also known as online sports, are a new form of sport that users have tried in recent years. Despite the rapid growth of online sports, the factors influencing users’ willingness to sustain their use are currently unknown. Based on the theory of planned behavior (TPB) and expectation-confirmation theory (ECT), this study empirically investigates the factors influencing the persistent use of online sports videos. Questionnaires were administered to participants. A total of 305 participants completed the questionnaire. Structural equation modeling showed that all hypotheses’ paths were significant, except for H11 and H12. The results indicated that perceived usefulness, expectation confirmation, and coach social presence had a significant positive effect on users’ satisfaction in using online sports videos. Moreover, satisfaction, behavioral attitudes, subjective norms, and perceived behavioral control had a significant positive effect on users’ willingness to consistently use online sports videos, with gender moderating the impact of satisfaction and behavioral attitudes on the willingness to consistently use. We discuss the practical implications and recommendations for applying this study’s findings. Full article

The Metaverse and Natural Language Processing (NLP) technologies have combined to fundamentally change the nature of digital sociability. Our understanding of social interaction needs to be reevaluated as the Metaverse’s influence spreads into more areas of daily life, such as AI-driven gaming, interactive training companions, museum exhibits, personalized fitness coaching, virtual mental health assistance, language translation services, virtual tour guiding, and virtual conferencing. This study analyzes how NLP is changing social relationships in these Metaverse applications. We examine how NLP algorithms influence societal norms, individual behaviors, interpersonal connections, and improve the user experience using a multi-method approach incorporating user surveys and sentiment analysis. Our study’s findings show how NLP can enhance interactive experiences while also pointing out related issues like potential bias and moral problems. Our study provides a foundational analysis, shedding light on the challenges of negotiating a social environment in the Metaverse that is molded by cutting-edge NLP. It offers stakeholders in academia and public policy essential assistance that helps them understand and manage the complex ramifications of this changing socio-technological paradigm. Full article

In a randomized controlled trial including 340 people living with obesity, with and without type 2 diabetes, digital coaching has induced significant long-term weight loss compared to the usual methods of care. We investigated whether education level influenced this weight loss and which lifestyle changes supported the digital lifestyle coaching program. The intervention consisted of a 1 h face-to-face motivational interview followed by digital coaching using behavioral change techniques. At 6 months, the weight loss in the intervention group was significantly larger in participants with short education (6.0 vs. 2.2 kg, p < 0.01) (p = 0.006). Participants with long education experienced initially a modest weight loss, but the effect was maintained, leading to the largest weight loss at 24 months (5.06 [−11.98–1.86] kg), even though there were fewer coaching sessions in the maintenance period. In multiple regression analyses, the greater weight loss in the intervention group was associated with short education (β = 1.81, p = 0.02), improvements in everyday physical activity (β = 2.60, p = 0.014) and improvements in dietary habits (β = 3.84, p = 0.013). In conclusion, at 6 months, the effect of the intervention was more pronounced in people with short education through improvements in everyday physical activity and dietary habits. However, participants with long education sustained their weight loss at 24 months. Full article