Kerstin Denecke

BACKGROUND While digital health interventions (DHIs) have considerable potential to improve healthcare delivery, many fail to achieve sustained adoption beyond initial implementation. Sustainability has been suggested to be built through individual, social, economic, environmental, and technical factors, yet existing adoption frameworks address these dimensions only partially. Consequently, there is a need for a practical framework that enables stakeholders to systematically integrate sustainability considerations into the design, implementation, and evaluation of DHIs. OBJECTIVE To develop a structured planning and evaluation framework, the Digital Health Sustainability Canvas (DHSC) that is suitable for systematic assessment of the sustainability of DHIs. METHODS The DHSC was developed using an iterative three-step design science approach comprising: (1) identification of mechanisms that undermine the long-term sustainability of DHIs, (2) development of an initial version of the canvas, and (3) pilot application to three DHIs followed by iterative refinement. RESULTS The final DHSC comprises 21 assessment items organized into five sustainability dimensions: individual, social, environmental, economic, and technical. The individual dimension addresses psychosocial, usability, motivational, and behavioural determinants of sustained use. The social dimension evaluates user engagement within social contexts, including cultural adaptation, peer support, training, equity, ethics, privacy, governance, and social impact. The environmental dimension assesses how the DHI interacts with its physical and organizational environments. The economic dimension examines financial sustainability through business models, affordability, and long-term value. The technical dimension evaluates system reliability, interoperability, usability, and implementation capacity to support sustainable deployment and maintenance. Guiding questions for each item help users of the DHSC to assess their DHI regarding these sustainability aspects. CONCLUSIONS The DHSC provides a comprehensive and practical framework for integrating sustainability considerations throughout the planning, implementation, and evaluation of DHIs. By adopting a multidimensional perspective, the DHSC can support researchers, developers, healthcare organizations, and policymakers in designing DHIs that are not only effective but also sustainable over the long term.

Background: The transition from working life to retirement represents a life-course transition that can influence mental health of older adults. While retirement may provide opportunities for autonomy, leisure and personal development, it may also increase vulnerability to depression, loneliness, social isolation and loss of purpose. This scoping review aimed to identify and synthesize protective and risk factors that influence mental health during the transition to retirement. Methods: We conducted a scoping literature review following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and PRISMA-S checklist for literature search. PubMed, APA PsycINFO, CINAHL and Web of Science were searched for peer-reviewed studies published between 2015 and 2026. Studies focusing on adults aged 50 years and older that addressed factors influencing mental health during the transition from work to retirement were included. Data extraction was followed by thematic analysis and narrative synthesis to identify recurring themes, protective and risk factors. Results: Twenty seven studies were included in the review. Depression and depressive symptoms were the most frequently investigated mental health outcomes. The identified factors were grouped into socioeconomic, health-related, psychosocial, employment-related and retirement-related domains. Protective factors included financial security, good health, voluntary and planned retirement, social participation, volunteering, post-retirement employment, social relationships, optimism and maintenance of purpose and identity. Risk factors included involuntary or poorly planned retirement, financial insecurity, chronic illness, loneliness, social isolation, unemployment, loss of work-related identity and reduced perceived control over retirement. Across studies, maintaining control, social connectedness and meaningful engagement emerged as key determinants of positive mental health outcomes. Conclusions: Mental health during the retirement transition is influenced by interacting socioeconomic, health-related, psychosocial and retirement-related factors. The findings highlight the importance of financial stability, social participation, autonomy, health and meaningful engagement in supporting mental wellbeing. The existing evidence base remains fragmented, only partially grounded in theoretical frameworks and it lacks evidence on how digital health interventions can support the transition to retirement. This highlights an important gap in the literature and the need for future intervention-oriented research.

Introduction: Artificial intelligence (AI)-powered chatbots are increasingly used in healthcare for applications ranging from symptom triage to lifestyle guidance. Their effectiveness depends not only on their ability to provide reliable information but also on users engaging with their advice while remaining aware of potential inaccuracies. This study investigated how users perceive AI-generated medical advice, with a particular focus on the roles of accuracy, conversational tone, and disclaimers. Methods: A survey was conducted with 115 participants who evaluated 15 chatbot scenarios representing five common health problems. Participants assessed chatbot responses varying in accuracy, tone, and the presence of disclaimers. Associations between these factors, user trust, willingness to seek second opinions, and participant characteristics (including age, health literacy, and prior chatbot use) were examined. Results: Accuracy emerged as the strongest predictor of user trust, although participants did not consistently identify inaccurate advice. Individual characteristics, including age, health literacy, and prior chatbot experience, showed no significant associations with trust. Differences in chatbot tone had little influence on user perceptions, with chatbots generally being viewed as confident regardless of phrasing. The effects of disclaimers on willingness to seek second opinions were mixed and varied across scenarios, suggesting that disclaimers alone may not effectively prevent over-reliance on chatbot advice. Open-ended responses highlighted trust in healthcare professionals and the importance of clearly communicating AI limitations. Discussion: This exploratory study, based on self-reported intentions in hypothetical scenarios, suggests that the accuracy of AI-generated medical advice is the primary determinant of user trust. Conversational tone appears to have limited influence, while disclaimers may not consistently promote appropriate caution. These findings indicate that healthcare chatbots should prioritize accuracy, clearly communicate their limitations, and encourage critical evaluation to achieve an appropriate balance between user trust and scepticism.

BACKGROUND Recent advances in digital health, including Artificial Intelligence-driven interventions, offer new opportunities for remote monitoring, patient-reported outcomes, and even direct treatment. Despite the growing adoption of digital health interventions (DHI), the concept of sustainability in this context remains under-theorized and fragmented in the literature. A clear understanding of sustainability is essential to ensure that DHIs can deliver enduring clinical, organizational, and societal value beyond initial implementation. Here, sustainability refers to ensuring that DHIs remain ethically, equitably, and environmentally responsible while delivering lasting health benefits and minimizing negative societal and environmental impacts. OBJECTIVE To study which frameworks have been applied in digital health for measuring or ensuring sustainability of DHI as well as to assess which dimensions of sustainability have been currently considered and to what extent. METHODS We conducted a scoping review as a concise synthesis of how existing models and frameworks address sustainability in the context of DHI. We examined peer-reviewed papers from 5 databases that described a sustainability framework in the context of digital health. The process followed PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline and PRISMA-S (Preferred Reporting Items for Systematic Reviews and Meta-Analyses literature search extension) checklist. Information on the frameworks was extracted including the considered sustainability factors. RESULTS Of 292 records, 53 studies were included and considered for data synthesis. Sustainability was rarely defined in these papers but invoked the concept only implicitly. Sustainability was basically used as a synonym for continued use rather than a multidimensional construct. Correspondingly, frameworks typically addressed usability and user acceptance. The social and technological dimensions of sustainability were addressed most frequently by the included frameworks, while ecological and economic dimensions remained rarely considered. In particular, UTAUT and TAM frameworks were extended by concepts of trust, risk, individual and health-related factors and contextual influences. CONCLUSIONS The current landscape of frameworks applied for sustainability in DHI do not represent the multidimensionality of the concept of sustainability as it would be necessary for ensuring a sustained use of DHI. Future work should therefore focus on strengthening the multidimensional view for addressing sustainability aspects throughout the entire DHI lifecycle.

BACKGROUND Radiological reports are essential for clinical diagnosis. However, their preparation is laborious and time-consuming for radiologists. Artificial intelligence (AI) has the potential to help radiologists reduce this workload. OBJECTIVE This scoping review aims to map current research on AI-based radiological report generation, highlighting its applications, limitations, and future directions. METHODS We systematically retrieved 321 records from three major scientific databases (PubMed, Embase, Web of Science) and included 58 studies after screening. Benchmark datasets, radiological subspecialties, AI models, output formats, and evaluation methods were extracted and analyzed. RESULTS Nine public benchmark datasets and six radiological subspecialties were identified. Transformer-based architectures have become the dominant approach, with outputs primarily generated in natural language. Dataset diversity is limited, with most studies relying on chest X-ray images from two public datasets. Structured outputs for machine readability remain underexplored, and expert human evaluation is infrequently used as an assessment method. CONCLUSIONS Current AI research in radiological report generation is constrained by limited dataset diversity and evaluation practices. Future studies should expand imaging modalities and subspecialties, adopt unified vision-language Transformer models, generate more structured outputs for programmatic use, and incorporate expert human evaluation for quality assessment.

Introduction: Digital twin (DT) technologies have generated growing interest across healthcare stakeholders, including researchers, industry, clinicians, patients, and the general public. While previous studies have discussed potential benefits and risks, most are based on literature reviews or focus on specific clinical areas, limiting a broader understanding of DTs in healthcare. Objectives : This study aimed to gather expert perspectives on the benefits, risks, and potential clinical applications of DTs in healthcare practice. Methods : An expert panel study was conducted using an online survey. The survey included open-ended questions designed to collect qualitative insights into experts’ views on the use of DTs in clinical settings, focusing on perceived advantages, challenges, and areas of application. Results : Experts identified personalised and precision medicine as key benefits of DTs, highlighting their potential to support safer testing of therapeutic strategies and exploration of multiple clinical scenarios. DTs were also seen as valuable tools for drug and medical device development. However, participants raised concerns regarding technical limitations, legal and ethical issues, bias, transparency, and accountability. Oncology, cardiology, and surgery were considered the clinical fields most likely to benefit, along with immunology, rehabilitation, and chronic inflammatory or degenerative diseases. Experts agreed that DTs are likely to be integrated into clinical practice in specific use cases but emphasized the need to improve their credibility through human involvement in design, greater explainability and transparency, and more robust validation. Conclusions : Despite increasing interest, DTs in healthcare remain at an early stage of development. Their adoption faces challenges similar to other Artificial Intelligence-based technologies. Nevertheless, experts anticipate that DTs will play a significant future role in treatment optimisation, personalised care, and precision medicine.

Purpose: Artificial Intelligence (AI) has transformed various sectors, including healthcare, where it holds promises for improving early detection, personalized care, and decision-making. However, despite its potential, AI systems often exacerbate health inequalities, particularly among underrepresented communities, due to biased algorithms, limited accessibility, and data exclusion. This current study aims to examine inclusive AI in healthcare grounded on a patient-centered approach. Methods: We conducted a literature review following PRISMA 2020 guidelines, searching across online databases for publications from diverse geographic and cultural contexts. Articles were assessed for inclusion based on specific criteria, and data on healthcare, AI type, inclusivity frameworks, implementation methods, and SWOT analysis were extracted. The quality and risk of bias of included articles were assessed with the JBI Checklist for Expert Opinion; and the PROBAST tool. Results: Findings from the study suggest that various AI types were discussed, including machine learning, chatbots, and convolutional neural networks. Several key frameworks for ensuring inclusive AI were reported in the included articles, such as ACCEPT-AI, Bias Mitigation, and human rights values frameworks. However, some articles did not mention specific inclusivity frameworks. Our findings suggest that AI in healthcare has the potential to improve health outcomes but must be implemented inclusively and transparently to avoid exacerbating inequalities. Conclusions: This review emphasizes the need for ethical, regulated, and collaborative approaches to mitigate bias, enhance accessibility, and ensure patient-centered solutions. Future efforts should focus on stakeholder-inclusive design and standardized frameworks for equitable AI in healthcare. Registration: This literature review was not registered.

Although Small Language Models (SLMs) show promise for healthcare applications, their use also introduces ethical risks that must be evaluated to develop appropriate mitigation strategies. Within a group activity during the SLM4Health workshop with 13 participants, we assessed ethical risks using the Digital Ethics Canvas along five lenses (welfare, autonomy, privacy, fairness, and sustainability). The participants considered two SLMs application use-cases: clinical documentation and clinical decision support. For SLMs in clinical documentation, identified risks included documentation errors from hallucinations or omissions leading to potential medical mistakes, social and data biases that can affect underrepresented groups, and a potential erosion of clinicians’ skills. For clinical decision support, challenges included biases harming vulnerable groups, unequal data quality exacerbating healthcare disparities, and privacy risks due to exposure of sensitive data. In both use cases, SLMs were noted to have a smaller environmental footprint than large models, though they still require energy and resources. Participants recognized that SLMs enhance efficiency in clinical documentation and decision support but introduce ethical challenges concerning patient welfare, fairness, autonomy, and privacy.

Introduction: Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental condition characterized by inattention, hyperactivity and impulsivity. Analyzing registered clinical trials on digital interventions for ADHD can provide early insight into planned research directions. The study aims to review registered clinical trials to identify and characterize emerging research on digital interventions for ADHD. Methods: We systematically searched ClinicalTrials.gov, the EU Clinical Trials Registry and the WHO ICTRP for ongoing trials of digital interventions for ADHD. Results: Of 149 identified trials, 35 ongoing studies met inclusion criteria. The most common interventions were mobile apps (14), computerized training (6), virtual reality (5), and web-based programs (5). Intervention durations were typically 6–15 weeks (23), most commonly 12 weeks. Primary outcomes assessed included ADHD symptoms and neurocognitive functions (23), followed by emotional/psychological outcomes (18) and family-related outcomes (12). Discussion and conclusion: Registered trial protocols indicate a growing interest in digital approaches for ADHD, particularly app-based, medium-term interventions targeting both children and adults. However, as these findings are based on ongoing trials registrations rather than completed studies, conclusions regarding effectiveness cannot yet be drawn. The limited conclusion of safety-reported outcomes represents a critical gap that may constrain the future real-world applicability of these interventions.