Abstract BackgroundDigital health interventions (DHIs) using behavior change techniques (BCTs) show promise in addressing adolescent health behaviors, but evidence of their effectiveness across health behavior domains remains fragmented and poorly summarized. ObjectiveThis systematic umbrella review synthesized evidence from existing systematic reviews on the effectiveness of BCTs within DHI targeting key adolescent health behavior domains: alcohol consumption, tobacco use, physical activity, dietary habits, and obesity management. MethodsWe systematically searched PubMed, PsycInfo, Embase, and CINAHL in April 2024 for reviews of DHI for adolescents (10‐19 years old). We coded all identified BCTs using the Behavior Change Technique Taxonomy version 1 (BCTTv1). Data on BCT effectiveness, intervention characteristics, and review quality were extracted and narratively synthesized using AMSTAR-2 (A Measurement Tool to Assess Systematic Reviews 2). ResultsA total of 20 reviews, comprising 224,135 participants, were included. These examined DHIs targeting physical activity (7 reviews), dietary habits (3 reviews), alcohol consumption (2 reviews), combined alcohol and nicotine use (1 review), and obesity management (1 review), with an additional 6 reviews covering multiple health behaviors. Across reviews, 65% (13/20) reported statistically significant positive effects on at least one health behavior outcome. “Social support (unspecified)” was the most consistently adopted and effective BCT, especially with parental/peer involvement. The combination of “self-monitoring,” “goal setting,” and “feedback” also commonly appeared in successful interventions. Intervention effectiveness appeared linked to strategic BCT selection and individualization rather than the total number of techniques. The methodological quality of included reviews was predominantly low, with only 2 rated high. ConclusionsThis umbrella review identified “social support (unspecified)” as a consistently effective BCT across multiple adolescent health behavior domains, particularly with parental/peer involvement. Intervention success appears linked to targeted and individualized BCT use. Future research should prioritize clarifying the specific components and delivery methods of effective social support, rigorously evaluating BCT configurations in underexplored areas such as adolescent smoking cessation, and examining their long-term impact on behavior change.

Cancer remains a leading cause of mortality worldwide, with a substantial proportion of cases attributable to modifiable lifestyle-related risk factors that emerge during adolescence and often persist into adulthood. Despite the importance of this developmental period for habit formation, evidence on scalable, theory-driven, and sustainable school-based prevention interventions remains limited. The SUNRISE project addresses this gap by evaluating a co-created, digitally supported life-skills programme designed for routine school settings. SUNRISE is a pragmatic, multinational, cluster randomised controlled trial conducted in approximately 80 primary and secondary schools across eight European countries (Greece, Switzerland, Slovenia, Spain, Cyprus, Italy, Belgium, and Romania), recruiting around 4,000 students. Classes are randomised at the class level (3:1) to either a six-month digitally enhanced life-skills intervention or standard education. The primary aim of the study is to evaluate the feasibility, implementation, and sustainability of the intervention in real-world school settings, with secondary exploratory assessment of behavioural outcomes. The intervention integrates multiple digital components, including a mobile-based life-skills coaching programme, a conversational assistant, educational and serious games, influencer-led media literacy content, moderated social interaction platforms, and teacher-led educational modules. Intervention design is guided by the Capability–Opportunity–Motivation Behaviour (COM-B) model and developed through systematic co-creation with students, educators, parents, public health experts, and policymakers within a School Living Lab framework. Feasibility, implementation, and sustainability are evaluated using the RE-AIM and PRISM frameworks. Secondary behavioural outcomes include substance use, dietary and physical activity behaviours, mental well-being, stress, social skills, critical thinking towards media and advertising, and critical coping with food-related information, assessed at baseline, 6 months, and 18 months. SUNRISE integrates behavioural science, participatory design, and digital innovation to address adolescent health behaviours in real-world educational contexts. By embedding implementation and sustainability evaluation alongside behavioural outcomes, the study aims to generate actionable evidence on how multi-component digital interventions can be adopted, adapted, and maintained across diverse school systems. Findings are expected to inform future large-scale, theory-driven, equitable, and sustainable cancer prevention strategies targeting adolescents across Europe. NCT06931847 (registration date: 2025–04-09).

Co-creation is increasingly used in public health to strengthen the relevance, feasibility, and sustainability of interventions, yet many approaches remain either too generic to guide implementation or too rigid for multi-country adaptation. This paper presents the application of the MapStakes-PH framework as a practical, step-by-step roadmap for organizing co-creation processes in preventive public health, using Project Sunrise, a Horizon Europe–funded initiative on adolescent cancer prevention implemented across eight European countries, as an illustrative use case. Grounded in stakeholder theory, co-creation is a participatory approach requiring meaningful collaboration among diverse actors (e.g., young people, families, educators, practitioners, researchers, community representatives, and policymakers) throughout design and implementation to design, develop, and improve systems, policies, or experiences, with attention to local context and equity. The MapStakes-PH Framework, originally developed for environmental and urban planning, offers a five-step process to (1) identify, (2) analyze, (3) engage, (4) coordinate, and (5) evaluate stakeholder contributions, the centerpiece of co-creation. We describe how the project team transferred this framework into a health promotion setting to structure stakeholder mapping, convene local co-creation councils, support co-design of context-specific actions, and maintain iterative learning through light-touch feedback cycles. The framework’s strengths for qualitative, practice-based co-creation include its usability, explicit decision points, adaptability across settings, and capacity to make stakeholder dynamics actionable, without oversimplifying complexity. We detail the five steps, the assumptions required for use, and practical considerations for adoption (e.g., participation/selection effects, facilitation intensity, and scalability). Consistent with the manuscript’s scope, we focus on the process architecture and implementation roadmap rather than reporting empirical outcomes.

The rapid evolution of machine learning techniques, combined with the growing availability of large and diverse datasets, is poised to transform heart failure research and clinical care. This review first provides an overview of key machine learning and artificial intelligence concepts used in heart failure research and then examines how diverse data modalities-including electronic health records, patient registries, biobanks, imaging, telemonitoring, and synthetic data-are leveraged to develop machine learning applications for heart failure diagnosis, prognosis, risk stratification, and personalized treatment strategies. While the potential is considerable, we highlight key barriers to clinical translation, such as data heterogeneity, algorithmic bias, lack of interoperability, and privacy concerns. The review also examines the need for explainable and equitable artificial intelligence systems and evaluates emerging solutions, including Federated Learning and synthetic data generation to address fairness and data privacy challenges. Beyond technical innovations, we underscore the importance of human-centered design, stakeholder engagement, and regulatory readiness. We conclude by identifying future priorities and calling for interdisciplinary collaboration to ensure the scalable, ethical, and effective integration of AI in heart failure management.

Objective: Large Language Models (LLMs) are emerging as a key component for digital health systems based on Artificial Intelligence (AI). The objective of this paper is to systematically review the characteristics, effectiveness, and implementation challenges of LLM-based assistants targeting adolescent health and well-being. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. PubMed, Scopus, and Web of Science were searched in November 2025 for studies published from 2022 onwards. Eligible studies examined LLM-based assistants used directly by adolescents in health and well-being contexts and reported quantitative outcomes. Data was extracted independently by multiple reviewers and synthesised narratively. Risk of bias was assessed using the Mixed Methods Appraisal Tool (MMAT). Results: Nine studies met the inclusion criteria, involving between 3 and 40 participants and covering mental health support, physical activity promotion, treatment engagement, vaccination awareness, and academic self-efficacy. Most studies were proof-of-concept investigations or pilot studies. LLM-based assistants were associated with reductions in depression, anxiety, stress, and negative affect, improvements in emotional regulation, physical activity, treatment motivation, HPV knowledge, and academic self-efficacy. Risk of bias was generally moderate and the evidence base was limited by small samples, short follow-up periods, and heterogeneous methodologies. Conclusions: LLM-based assistants show promise as scalable and accessible tools for supporting adolescent health and well-being, particularly in mental health domains. However, the current evidence remains preliminary. Larger, long-term, and rigorously designed studies are required to establish effectiveness, safety, and implementation feasibility. Registration: This review was not pre-registered and no review protocol has been published prior to conducting the review.

Objective : A persistent gap separates the trustworthy AI principles articulated by consensus guidelines and regulatory instruments from the deterministic, verifiable specifications required to develop clinical decision-support systems. While frameworks such as FUTURE-AI operationalize trustworthiness through detailed sub-principles and lifecycle recommendations, the translation of these principles into formally structured engineering requirements remains under-specified. This paper presents a requirements engineering framework that systematically translates stakeholder needs, preferences, concerns, and regulatory constraints into formal, verifiable system specifications for clinical AI. Methods : The framework follows a three-phase methodology: (i) hybrid multi-stakeholder elicitation combining bottom-up clinical, patient, and ethical inputs with top-down regulatory and contractual constraints, followed by scoping to define the operational system boundary; (ii) formalization of scoped inputs into structured, verifiable requirements via the ISO/IEC/IEEE 29148 standard, applying its syntactic template, obligation levels (shall/should/may), functional and non-functional typing, and per-requirement means of verification (MoV); and (iii) systematic mapping of the formalized requirements to the FUTURE-AI taxonomy as a normative coverage criterion rather than a descriptive classification scheme. Results : Applied to the AI4HF project, a Horizon Europe initiative for personalized risk prediction in chronic heart failure, the framework yielded a fully specified, verifiable requirement corpus, demonstrating that it produces standards-compliant specifications with exhaustive FUTURE-AI coverage and per-requirement verification. The instantiation generated 173 requirements, each paired with a defined MoV; inter-rater validation of the FUTURE-AI mapping on a stratified subset yielded Cohen's κ = 0.72 (substantial agreement). The resulting corpus is publicly available, constituting, to our knowledge, the first openly available FUTURE-AI-aligned, ISO/IEC/IEEE 29148-compliant requirements dataset for a high-risk clinical AI system. Conclusion : The methodology is designed to be reproducible across clinical AI projects beyond the AI4HF instantiation and is directly applicable to multi-stakeholder development efforts subject to high-risk regulatory classification (EU AI Act, MDR/IVDR), supporting trustworthy-by-design specification of healthcare AI systems.

Objectives Primary cancer prevention through behavior change in adolescence, a crucial period for shaping lifelong health habits, presents a major public health challenge across Europe. Addressing this, the SUNRISE project aims to tackle the challenge of primary cancer prevention in adolescents by developing and implementing an innovative, digitally-enhanced life-skills program tailored to diverse socio-economic, cultural, and environmental backgrounds by incorporating various Digital Health Promotion (DHP) tools to foster sustainable health behavior change in adolescents. The present study aims to identify key requirements and features that should be considered while developing effective DHP tools, based on a multi-stakeholder survey conducted across seven European countries. Methods The survey was conducted on 505 stakeholders (students, parents, and educators), from seven European countries to assess a set of key features for effective DHP tools for their importance on a five-point likert scale. Results Our findings revealed that seven of the proposed DHP tools' features were identified as important considering all the stakeholder groups, while significant differences in the importance of certain features across different stakeholder groups and countries were identified. Students, as primary users, demonstrated distinct preferences, which often diverged from educators and parents, suggesting that stakeholders hold distinct priorities driven by their roles and contextual backgrounds. Additionally, country-level variations were notable; for example, Swiss participants rated the proposed features, in general, as of lower importance than the Spanish respondents. Conclusions These insights emphasize the necessity of developing adaptable and context-sensitive DHP tools that reflect the diverse needs and preferences of adolescents across Europe. The large-scale implementation and evaluation of this program will provide valuable data for shaping future digital health interventions aimed at cancer prevention in youth.

BACKGROUND: One of the most significant risk factors for cancer and several other adverse health outcomes is nicotine and tobacco use. Life-skills training programs conducted within the school curriculum are effective in preventing substance use, including nicotine and tobacco use, however, large-scale implementation is hindered by time, organizational and financial constraints. Providing life-skills training programs via smartphones may be a more economical and scalable approach. SUNRISE SmartCoach is the first life skills training program to use instant messaging and storytelling to present life-skills training in an emotional and engaging way. This study protocol outlines a cluster-randomized controlled trial testing the efficacy of SUNRISE SmartCoach among adolescents in eight European countries. METHODS: A two-arm, parallel-group, cluster-randomized, controlled trial will be conducted to test the efficacy of SUNRISE SmartCoach in comparison to an assessment only control group. The study participants will be assessed at baseline and at follow-ups after 6 and 18 months. The fully automated program is based on social cognitive theory and aims to improve self-management skills, social skills, and resistance to addictive behavior. Participants in the intervention group will receive online feedback on their life skills via Smartphone, as well as individually tailored coaching dialogues via WhatsApp or Viber over four months, to improve life skills. Active program engagement will be stimulated by interactive features such as quiz questions, message- and picture-contests, and integration of a friendly competition in which program users collect credits with each interaction. Study participants will be 3,500 secondary and upper secondary school students between the ages of 14 and 17 years from eight European countries: Switzerland, Greece, Slovenia, Spain, Cyprus, Italy, Belgium, and Romania. The primary outcome criterion will be nicotine or tobacco use within 30 days preceding the follow-up assessment at month 18. Secondary outcomes include the use of other substances, such as alcohol and cannabis, social skills, perceived stress, healthy eating habits, and quality of life. DISCUSSION: This is the first randomized controlled study testing the efficacy of an instant messenger- and storytelling-based life-skills training program to prevent nicotine and tobacco use as well as other behavioral risk factors among adolescents. If this intervention approach proves to be effective, it could be easily implemented in various settings and could reach large numbers of young people in a cost-effective way. TRIAL REGISTRATION: NCT06922201 (registration date: 2025-04-09).

Participant dropout from interventional studies targeting healthy lifestyles can significantly undermine the validity of study outcomes. Accurate dropout prediction can help mitigate this issue by enabling proactive participant engagement strategies. This study aims to develop a robust Machine Learning (ML) model to predict dropout from a school and community-based interventional study to promote a healthy lifestyle and prevent type 2 diabetes: The Feel4Diabetes study. Using data from 3274 participants across 790 variables, we aim to identify key dropout determinants and enhanceML predictive accuracy. We evaluated three individual machine learning models-Random Forest, XGBoost, and Support Vector Machine (SVM)-based on performance metrics including accuracy, precision, recall, and F1-score. Among these, the Random Forest model emerged as the most effective, achieving an accuracy of 0.80 on the test set, with balanced precision and recall scores. Our study highlights the effectiveness of machine learning methods in predicting dropout in interventional studies promoting healthy lifestyles and preventing type 2 diabetes. Future research will concentrate on refining these models further and exploring additional data sources to enhance their generalizability.

Embodied virtual agents (EVAs) are beginning to be researched to improve human–computer interaction. As EVAs become increasingly integrated into various aspects of daily life, understanding how to optimize their design to foster trust and likability among users is paramount. Leveraging insights from social psychology, particularly the concept of homophily, this study investigates the impact of perceived personality traits on user perceptions of EVAs. Specifically, we explore whether aligning the personality traits of EVAs with those of users increases engagement and fosters positive interactions. Drawing on a sample of 382 participants recruited through Amazon Mechanical Turk, we assessed participants' personality traits using the Big Five Inventory—2S, while the perceived extroversion of the agent was manipulated through facial expressions and body posture. Our findings suggest that participants were able to accurately identify the perceived extroversion of the agent (p = .014), and significant results indicate a homophily effect on trust, with participants exhibiting greater trust in agents perceived as having a similar level of extroversion (p < .01). However, no significant effect on likability was detected, suggesting a more nuanced relationship between perceived personality traits and user preferences. These findings highlight the potential of leveraging homophily in designing more engaging EVAs and underscore the importance of considering user–agent compatibility in human–computer interaction.

Background/Objective: The use of Large Language Models (LLMs) has recently gained significant interest from the research community toward the development and adoption of Generative Artificial Intelligence (GenAI) solutions for healthcare. The present work introduces the first meta-review (i.e., review of systematic reviews) in the field of LLMs for chronic diseases, focusing particularly on cardiovascular, cancer, and mental diseases, to identify their value in patient care, and challenges for their implementation and clinical application. Methods: A literature search in the bibliographic databases of PubMed and Scopus was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, to identify systematic reviews incorporating LLMs. The original studies included in the reviews were synthesized according to their target disease, specific application, LLMs used, data sources, accuracy, and key outcomes. Results: The literature search identified 5 systematic reviews respecting our inclusion and exclusion criteria, which examined 81 unique LLM-based solutions. The highest percentage of the solutions targeted mental disease (86%), followed by cancer (7%) and cardiovascular disease (6%), implying a large research focus in mental health. Generative Pre-trained Transformer (GPT)-family models were used most frequently (~55%), followed by Bidirectional Encoder Representations from Transformers (BERT) variants (~40%). Key application areas included depression detection and classification (38%), suicidal ideation detection (7%), question answering based on treatment guidelines and recommendations (7%), and emotion classification (5%). Study aims and designs were highly heterogeneous, and methodological quality was generally moderate with frequent risk-of-bias concerns. Reported performance varied widely across domains and datasets, and many evaluations relied on fictional vignettes or non-representative data, limiting generalisability. The most significant found challenges in the development and evaluation of LLMs include inconsistent accuracy, bias detection and mitigation, model transparency, data privacy, need for continual human oversight, ethical concerns and guidelines, as well as the design and conduction of high-quality studies. Conclusions: While LLMs show promise for screening, triage, decision support, and patient education-particularly in mental health-the current literature is descriptive and constrained by data, transparency, and safety gaps. We recommend prioritizing rigorous real-world evaluations, diverse benchmark datasets, bias-auditing, and governance frameworks before LLM clinical deployment and large adoption.

The rapid advancement of Artificial Intelligence (AI) in healthcare raises significant social and ethical concerns, particularly in cardiovascular care, the leading cause of death worldwide. Addressing these challenges requires a multidisciplinary, multi-stakeholder approach to ensure the responsible development and implementation of AI-driven solutions. First, a literature review examined how key ethical principles - namely, autonomy, confidentiality, data privacy, and equal treatment - are integrated into AI applications for heart failure care. These findings informed an online workshop with patient representatives, clinicians, and experts on ethical, legal, and social issues to discuss ethical concerns and practical implications. A team of requirements engineers and digital health experts synthesized insights from the literature review and workshop, specifying an initial set of requirements. Following multiple iterations with a multidisciplinary review team, the final set of 25 requirements was established. These were translated into software or system specifications where applicable or used to define guidelines for real-world implementation. This study provides a structured approach to embedding ethical and social considerations into AI-driven healthcare solutions. Its methods and key requirements are transferable to other AI applications in public health, promoting responsible and equitable adoption.

Hypoglycaemia is one of the most common complications in diabetes, which can be life threatening if not managed appropriately. So far, research on hypoglycaemia prediction has been scarce, focusing on small cohorts linked to specific geographical regions, thus limiting the generalizability of the findings. In this paper, we developed and validated different machine learning models for next-day hypoglycaemia prediction in type 2 diabetes. We used a large international cohort comprising 669 participants, who had been regular users (for over a couple of years) of a mobile app for diabetes self-management and used common portable commercial devices for measuring their blood glucose and blood pressure levels, collecting in total 96121 observations (from which we extracted a balanced dataset of 2998 observations). Random Forests (RF), Support Vector Machines, Adaptive Boosting and Feed-Forward Artificial Neural Networks were employed to train predictive models based on 10-day temporal sequences with blood glucose and blood pressure measurements towards estimating next day hypoglycaemic episodes. We used a leave-one-subject-out (LOSO) approach for model validation, and found that RF achieved the best accuracy (0.814) and F1-score (0.812) with sensitivity (0.805) and specificity (0.824) for next-day hypoglycaemia prediction. The results of this study provide an expedient and reliable app-based approach to accurately predict hypoglycaemia in day-to-day life, thereby facilitating patient and care provider awareness and potentially preventing other serious complications.

OBJECTIVE:Mobile Health (mHealth) refers to using mobile devices to support health. This study aimed to identify specific methodological challenges in systematic reviews (SRs) of mHealth interventions and to develop guidance for addressing selected challenges. STUDY DESIGN AND SETTING:Two-phase participatory research project. First, we sent an online survey to corresponding authors of SRs of mHealth interventions. On a five-category scale, survey respondents rated how challenging they found 24 methodological aspects in SRs of mHealth interventions compared to non-mHealth intervention SRs. Second, a subset of survey respondents participated in an online workshop to discuss recommendations to address the most challenging methodological aspects identified in the survey. Finally, consensus-based recommendations were developed based on the workshop discussion and subsequent interaction via email with the workshop participants and two external mHealth SR authors. RESULTS:We contacted 953 corresponding authors of mHealth intervention SRs, of whom 50 (5 %) completed the survey. All the respondents identified at least one methodological aspect as more or much more challenging in mHealth intervention SRs than in non-mHealth SRs. A median of 11 (IQR 7.25-15) out of 24 aspects (46 %) were rated as more or much more challenging. Those most frequently reported were: defining intervention intensity and components (85 %), extracting mHealth intervention details (71 %), dealing with dynamic research with evolving interventions (70 %), assessing intervention integrity (69 %), defining the intervention (66 %) and maintaining an updated review (65 %). Eleven survey respondents participated in the workshop (five had authored more than three mHealth SRs). Eighteen consensus-based recommendations were developed to address issues related to mHealth intervention integrity and to keep mHealth SRs up to date. CONCLUSION:mHealth SRs present specific methodological challenges compared to non-mHealth interventions, particularly related to intervention integrity and keeping SRs current. Our recommendations for addressing these challenges can improve mHealth SRs.

Objective The use of smartwatches has attracted considerable interest in developing smart digital health interventions and improving health and well-being during the past few years. This work presents a systematic review of the literature on smartwatch interventions in healthcare. The main characteristics and individual health-related outcomes of smartwatch interventions within research studies are illustrated, in order to acquire evidence of their benefit and value in patient care. Methods A literature search in the bibliographic databases of PubMed and Scopus was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, in order to identify research studies incorporating smartwatch interventions. The studies were grouped according to the intervention’s target disease, main smartwatch features, study design, target age and number of participants, follow-up duration, and outcome measures. Results The literature search identified 13 interventions incorporating smartwatches within research studies with people of middle and older age. The interventions targeted different conditions: cardiovascular diseases, diabetes, depression, stress and anxiety, metastatic gastrointestinal cancer and breast cancer, knee arthroplasty, chronic stroke, and allergic rhinitis. The majority of the studies (76%) were randomized controlled trials. The most used smartwatch was the Apple Watch utilized in 4 interventions (31%). Positive outcomes for smartwatch interventions concerned foot ulcer recurrence, severity of symptoms of depression, utilization of healthcare resources, lifestyle changes, functional assessment and shoulder range of motion, medication adherence, unplanned hospital readmissions, atrial fibrillation diagnosis, adherence to self-monitoring, and goal attainment for emotion regulation. Challenges in using smartwatches included frequency of charging, availability of Internet and synchronization with a mobile app, the burden of using a smartphone in addition to a patient’s regular phone, and data quality. Conclusion The results of this review indicate the potential of smartwatches to bring positive health-related outcomes for patients. Considering the low number of studies identified in this review along with their moderate quality, we implore the research community to carry out additional studies in intervention settings to show the utility of smartwatches in clinical contexts.

Digital screening programs and tools provide the potential for early detection of chronic diseases such as diabetes in the general population. The main purpose of the current paper is to present the findings of a multi-country study conducted with implementers (i.e., health professionals) and citizens (i.e., patients) to assess the usability and acceptance of a digital screening tool for type 2 diabetes screening. To this aim, 109 healthcare professionals and 71 citizens from four (4) European countries-Bulgaria, Albania, Spain, and Greece -participated in the study. The participants were requested to test the DigiCare4You tool, by completing instructed activities for user interaction, and were provided with questionnaires consisted of multiple sections that captured participants' characteristics, perceptions, attitudes, and testing experience. The perceived usability assessed through the System Usability Scale (SUS) was found to be satisfactory for both health professionals (SUS score=73.9) and citizens (SUS score=68.06), and the majority of the participants considered the tool as useful and easy to learn. The results show the digital tool's favorable usability among healthcare professionals and citizens in different regions, paving the way for its successful implementation and wider adoption in diabetes care.

Heart failure is a life-threatening disease with an increasing prevalence around the globe. Electronic health (eHealth) technologies provide a solution to enhance the monitoring and management of heart failure. In this direction, the CORRAL system utilizes user-friendly web and mobile-based components for heart failure integrated care management by multidisciplinary health professional teams, patients, and informal caregivers. CORRAL enables the co-design of the patient’s personalized care plan providing a detailed medical record, as well as risk prediction and decision-support capabilities. A conversational virtual assistant contributes to the empowerment of users, while it is optimized for data protection and sovereignty. With its patient-centric and holistic approach, CORRAL aims to optimize treatment adherence and self-management and to improve the quality of life of the patient.

Objective: Long term behavioural disturbances and interventions in healthy habits (mainly eating and physical activity) are the primary cause of childhood obesity. Current approaches for obesity prevention based on health information extraction lack the integration of multi-modal datasets and the provision of a dedicated Decision Support System (DSS) for health behaviour assessment and coaching of children. Methods: Continuous co-creation process has been applied in the frame of the Design Thinking Methodology, involving children, educators and healthcare professional in the whole process. Such considerations were used to derive the user needs and the technical requirements needed for the conception of the Internet of Things (IoT) platform based on microservices. Results: To promote the adoption of healthy habits and the prevention of the obesity onset for children (9-12 years old), the proposed solution empowers children -including families and educators- in taking control of their health by collecting and following-up real-time information about nutrition, physical activity data coming from IoT devices, and interconnecting healthcare professionals to provide a personalised coaching solution. The validation has two phases involving +400 children (control/intervention group), on four schools in three countries: Spain, Greece and Brazil. The prevalence of obesity decreased in 75.5% from baseline levels in the intervention group. The proposed solution created a positive impression and satisfaction from the technology acceptance perspective. Conclusions: Main findings confirm that this ecosystem can assess behaviours of children, motivating and guiding them towards achieving personal goals. Clinical and Translational Impact Statement—This study presents Early Research on the adoption of a smart childhood obesity caring solution adopting a multidisciplinary approach; it involves researchers from biomedical engineering, medicine, computer science, ethics and education. The solution has the potential to decrease the obesity rates in children aiming to impact to get a better global health.

Childhood obesity is a major public health challenge which is linked with the occurrence of diseases such as diabetes and cancer. The COVID-19 pandemic has forced changes to the lifestyle behaviors of children, thereby making the risk of developing obesity even greater. Novel preventive tools and approaches are required to fight childhood obesity. We present a social robot-based platform which utilizes an interactive motivational strategy in communication with children, collects self-reports through the touch of tangible objects, and processes behavioral data, aiming to: (a) screen and assess the behaviors of children in the dimensions of physical activity, diet, and education, and (b) recommend individualized goals for health behavior change. The platform was integrated through a microservice architecture within a multi-component system targeting childhood obesity prevention. The platform was evaluated in an experimental study with 30 children aged 9–12 years in a real-life school setting, showing children’s acceptance to use it, and an 80% success rate in achieving weekly personal health goals recommended by the social robot-based platform. The results provide preliminary evidence on the implementation feasibility and potential of the social robot-based platform toward the betterment of children’s health behaviors in the context of childhood obesity prevention. Further rigorous longer-term studies are required.