Frontiers in digital health最新文献

{"title":"Lessons to be learned from an attempted RCT: iCHIMPS-an online intervention for adolescents with mentally Ill parents.","authors":"P Dülsen, K Barck, S Wiegand-Grefe, A Leidger, T Paumen, H Baumeister","doi":"10.3389/fdgth.2025.1526995","DOIUrl":"10.3389/fdgth.2025.1526995","url":null,"abstract":"<p><strong>Background: </strong>Children and adolescents with mentally ill parents represent an at-risk population for developing mental disorders themselves. Internet- and mobile-based interventions (IMIs) have been demonstrated to be an effective, scalable, and temporally and geographically independent method of treatment delivery. However, evidence for IMIs aimed at children and adolescents remains limited and inconclusive, especially for children of mentally ill parents. Therefore, the present trial aimed to evaluate the effectiveness of a mental health IMI (iCHIMPS) for children of parents with a mental illness. Due to insufficient recruitment, however, this article will primarily focus on lessons learned from the challenges encountered during the study's implementation.</p><p><strong>Methods: </strong>The IMI was targeted at children aged 12-18 years, regardless of whether they exhibited symptoms of mental disorders, provided that at least one parent had a diagnosed mental illness. To evaluate the effectiveness, the IMI was provided to one group [intervention group (IG)] while the control group received treatment as usual (TAU). At four measurement timepoints, the primary outcome (Youth Self-Report-YSR 11-18R) and various secondary outcomes were assessed. Recruitment from May 2021 to April 2023 initially took place at 21 participating mental health clinics throughout Germany and was later supplemented by various additional clinics as well as recruitment pathways.</p><p><strong>Results: </strong>In total, <i>n</i> = 22 participants were recruited. This result was far off the needed number of participants to meaningfully conduct any analyses. Therefore, no quantitative analyses were conducted, and this trial is discussed as a failed trial, providing important insights into ineffective strategies for reaching adolescents of parents with mental illnesses, in particular, and adolescents through digital interventions more generally.</p><p><strong>Conclusion: </strong>The identified reasons for the failed recruitment include the complex study design, particularly the presence of multiple concurrent trials recruiting from the same population, the inherent difficulty of reaching families with mentally ill parents, and the limitation of targeting the IMI solely at adolescents rather than involving families more broadly. Additionally, the design may not have been sufficiently engaging or appealing to adolescents. These reasons are discussed along with the implications for future IMI research involving children and adolescents.</p><p><strong>Clinical trial registration: </strong>identifier (DRKS00025158).</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1526995"},"PeriodicalIF":3.2,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12331599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144818398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Navigating online health information: empowerment vs. misinformation.","authors":"Alan Silburn","doi":"10.3389/fdgth.2025.1555290","DOIUrl":"10.3389/fdgth.2025.1555290","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1555290"},"PeriodicalIF":3.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12328366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in personalized rehabilitation: current applications and a SWOT analysis.","authors":"Elpidio Attoh-Mensah, Arnaud Boujut, Mikaël Desmons, Anaick Perrochon","doi":"10.3389/fdgth.2025.1606088","DOIUrl":"10.3389/fdgth.2025.1606088","url":null,"abstract":"<p><p>Artificial intelligence (AI) is transforming personalized rehabilitation by introducing innovative methods to enhance care across diverse medical specialties. Despite its potential, widespread implementation remains limited, largely due to a lack of comprehensive analyses on its benefits and barriers. This mini narrative review examines current applications of AI in personalized rehabilitation and provide a SWOT (Strengths, Weaknesses, Opportunities, Threats) analysis AI is already being used to develop personalized treatment plans, support ongoing patient management, and adapt therapy sessions in real-time. One of its key strengths is the capacity to process vast datasets and monitor real-time information, thereby elevating the level of personalization. Automation of certain tasks can reduce human error and alleviate clinician workload, allowing more time for direct patient care. Opportunities for AI lie in leveraging rapidly advancing technologies to meet the rising demand for rehabilitation services, particularly with aging populations. Collaborations with industry can accelerate innovation, while data sharing can promote best practices across institutions. However, notable challenges persist. High implementation costs, ethical concerns such as algorithmic bias, and risks of increasing healthcare disparities remain major barriers. Additionally, threats such as data privacy breaches and security vulnerabilities emphasize the need for robust, balanced regulatory frameworks. In conclusion, AI holds immense promise for transforming personalized rehabilitation. While current applications are largely in early stages or proof-of-concept phases, ongoing research, ethical foresight, and strategic collaboration are essential to maximize benefits and minimize risks for optimal patient outcomes.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1606088"},"PeriodicalIF":3.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12328449/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure latent Dirichlet allocation.","authors":"Thijs Veugen, Vincent Dunning, Michiel Marcus, Bart Kamphorst","doi":"10.3389/fdgth.2025.1610228","DOIUrl":"10.3389/fdgth.2025.1610228","url":null,"abstract":"<p><p>Topic modelling refers to a popular set of techniques used to discover hidden topics that occur in a collection of documents. These topics can, for example, be used to categorize documents or label text for further processing. One popular topic modelling technique is Latent Dirichlet Allocation (LDA). In topic modelling scenarios, the documents are often assumed to be in one, centralized dataset. However, sometimes documents are held by different parties, and contain privacy- or commercially-sensitive information that cannot be shared. We present a novel, decentralized approach to train an LDA model securely without having to share any information about the content of the documents. We preserve the privacy of the individual parties using a combination of privacy enhancing technologies. Next to the secure LDA protocol, we introduce two new cryptographic building blocks that are of independent interest; a way to efficiently convert between secret-shared- and homomorphic-encrypted data as well as a method to efficiently draw a random number from a finite set with secret weights. We show that our decentralized, privacy preserving LDA solution has a similar accuracy compared to an (insecure) centralised approach. With 1024-bit Paillier keys, a topic model with 5 topics and 3000 words can be trained in around 16 h. Furthermore, we show that the solution scales linearly in the total number of words and the number of topics.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1610228"},"PeriodicalIF":3.2,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12328381/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Gen3 for clinical trial time series analytics and data discovery: a data commons framework for NIH clinical trials.","authors":"Meredith C B Adams, Colin Griffin, Hunter Adams, Stephen Bryant, Robert W Hurley, Umit Topaloglu","doi":"10.3389/fdgth.2025.1570009","DOIUrl":"10.3389/fdgth.2025.1570009","url":null,"abstract":"<p><p>This work presents a framework for enhancing Gen3, an open-source data commons platform, with temporal visualization capabilities for clinical trial research. We describe the technical implementation of cloud-native architecture and integrated visualization tools that enable standardized analytics for longitudinal clinical trial data while adhering to FAIR principles. The enhancement includes Kubernetes-based container orchestration, Kibana-based temporal analytics, and automated ETL pipelines for data harmonization. Technical validation demonstrates reliable handling of varied time-based data structures, while maintaining temporal precision and measurement context. The framework's implementation in NIH HEAL Initiative networks studying chronic pain and substance use disorders showcases its utility for real-time monitoring of longitudinal outcomes across multiple trials. This adaptation provides a model for research networks seeking to enhance their data commons capabilities while ensuring findable, accessible, interoperable, and reusable clinical trial data.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1570009"},"PeriodicalIF":3.2,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326274/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144796306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness of mHealth interventions targeting physical activity, sedentary behaviour, sleep or nutrition on emotional, behavioural and eating disorders in adolescents: a systematic review and meta-analysis.","authors":"H Baumann, B Singh, A E Staiano, C Gough, M Ahmed, J Fiedler, I Timm, K Wunsch, A Button, Z Yin, M F Vasiloglou, B Sivakumar, J M Petersen, J Dallinga, C Huong, S Schoeppe, C L Kracht, K Spring, C Maher, C Vandelanotte","doi":"10.3389/fdgth.2025.1593677","DOIUrl":"10.3389/fdgth.2025.1593677","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Introduction: &lt;/strong&gt;Mental health conditions are highly prevalent among adolescents, affecting one in seven individuals and accounting for 15% of the global disease burden in this age group. The promotion of health behaviours including physical activity, nutrition, and sleep, and reduction of sedentary behaviour, has been shown to significantly improve symptoms of mental health conditions in adolescents. However, addressing this public health challenge at a population level requires scalable interventions, such as mobile health (mHealth) interventions. However, the effectiveness of mHealth interventions in achieving clinically meaningful mental health improvements for adolescents with emotional, behavioural, or eating disorders remains unclear. Therefore, this systematic review and meta-analysis evaluated the effectiveness of mHealth behaviour change interventions aimed at improving physical activity (PA), sedentary behaviour (SB), nutrition, or sleep on outcomes related to emotional, behavioural, and eating disorders in adolescents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A systematic review and meta-analysis were conducted in accordance with PRISMA guidelines (PROSPERO ID: CRD42024591285). Eight databases were searched for randomized controlled trials (RCTs) published up to September 2024. Eligible studies included participants in early (11-14 years), middle (15-17 years) and late (18-21 years) adolescence with clinical diagnosis or self-report of emotional, behavioural, or eating disorders, where interventions targeted physical activity, sedentary behaviour, nutrition, or sleep. The cochrane risk of bias 2.0 (ROB2) and cochrane grading of recommendations assessment, development and evaluation tool (GRADE) were applied. Pooled effect sizes were calculated as standardized mean differences (SMD) with 95% confidence intervals using random-effect models.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Nine RCTs involving 3,703 participants were analysed across emotional, behavioural, and eating disorders. The meta-analysis yielded a significant reduction in anxiety (6 Studies, 2086 participants, SMD [95% CI] = -0.19 [-0.37, -0.01], &lt;i&gt;I&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; = 71%, with positive effects for sleep focussed interventions as well as multimodal interventions (PA, SB, diet, sleep) and eating disorders (3 studies, 732 participants, SMD [95% CI] = -0.23 [-0.44, -0.02], &lt;i&gt;I&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; = 38%, with positive effects for diet and combined diet/PA interventions). In contrast, depressive (7 Studies, 1855 participants, SMD [95%CI] of -0.12 [-0.28, -0.04], I&lt;sup&gt;2&lt;/sup&gt; 59%) and behavioural disorders symptoms (2 studies, 560 participants, SMD [95%CI] = -0.71 [1.77, 0.36], &lt;i&gt;I&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; = 95) showed no significant pooled effect. The cumulative evidence was weakened by high heterogeneity of trial design and low overall certainty of evidence as indicated by ROB2 and GRADE assessments. Across interventions, trials characterized by higher session frequency, greater int","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1593677"},"PeriodicalIF":3.2,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12318977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144786093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating machine-readable user interface requirements into open networked operating rooms.","authors":"Okan Yilmaz, Dominik Stegemann, Klaus Radermacher, Miriam Lange, Armin Janß","doi":"10.3389/fdgth.2025.1520584","DOIUrl":"10.3389/fdgth.2025.1520584","url":null,"abstract":"<p><p>Comprehensive risk management (<b>RM</b>) and usability engineering (<b>UE</b>) must be performed to enable safe and usable interoperable medical device systems (according to IEEE 11073 SDC). This has to be fulfilled by applying recognized standards such as ISO 14971 (RM) and IEC 62366-1 (UE). Addressing the complexity of use cases with multiple network participants requires defining use context, hazardous situations, user profiles, user interfaces, system function contributions, limitations, configurations, and required conditions for safe use. We propose extending the categories mentioned in IEEE 11073-10700 with standardized user interface requirements provided by medical device manufacturers. A consumer of networked services can consider those UI Profiles containing design-, risk-, and process-related UI requirements during its design phase, usability engineering process, and risk management. This allows a systematic deficiency analysis prior to device usage, encompassing human-induced risks and thereby enhancing usability, patient safety, and finally operational efficiency. Using benchmarked, verified, and tested UI controls to create user interfaces that fulfill those requirements automatically might also be a solution for the future. This work presents an architectural overview incorporating ISO IEEE 11073-10700 standard requirements. Significantly, it extends these standards by introducing categories that enhance support for the usability engineering and risk management process, emphasizing the role of UI Profiles in achieving safe and usable operating room environments with more flexibility regarding interoperability and enabling a human-induced risk analysis prior to device usage. The number of surveyed manufacturers (8) and the need for real-world validation are limitations of this work, which should be validated by future work.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1520584"},"PeriodicalIF":3.2,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12319011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144786094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stakeholder perspectives on skills required for health technology developers: a qualitative study in Thailand.","authors":"Sranya Phaisawang, Thanyaphong Na Nakorn, Prasert Trivijitsilp, Anan Srikiatkhachorn","doi":"10.3389/fdgth.2025.1578782","DOIUrl":"10.3389/fdgth.2025.1578782","url":null,"abstract":"<p><strong>Background: </strong>Throughout history, medical education has developed in response to societal changes and advances in biological research and technology. Health technology, encompassing devices, medicines, vaccines, and digital health systems, is transforming healthcare with increased effectiveness and efficiency. Thailand, a popular medical tourism destination, intends to shift its focus to high-quality healthcare services and advanced technologies for long-term economic sustainability. This study identifies necessary skills for health technology developers to help create a technology-driven healthcare ecosystem and prepare human capital in the field.</p><p><strong>Methods: </strong>In this qualitative study, in-depth interviews with diverse stakeholders in health and health technology industries were conducted to investigate the role of health technology in future healthcare and the skills required for health technology developers. Qualitative Content Analysis was carried out. Participants included national health policy makers, university presidents, hospital directors, and health technology company administrators. The study utilized the electronic Delphi method for ranking skills through multiple interview rounds, ensuring thorough evaluation of significant topics.</p><p><strong>Results: </strong>This study involved interviews with sixteen stakeholders in health technology, focusing on its importance and impact on future healthcare. Participants discussed three major areas of technology: molecular technologies, biomedical engineering technologies, and health information technologies. Delocalization, personalization, and digitalization are key components of healthcare transformation. The challenges and skills needed for health technology developers were categorized into four domains including, Health Science, Health Technology, Product Development & Design and Marketing & Entrepreneurship.</p><p><strong>Conclusion: </strong>Our study revealed the significance of technology in healthcare transformation. We identified four skill categories that health technology developers must possess. (1) Health Science, (2) Health Technology, (3) Product Development & Design, and (4) Marketing & Entrepreneurship were among these domains. A systematic strategy for developing these skills is a crucial success factor in human capital preparation for future technology-driven healthcare.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1578782"},"PeriodicalIF":3.2,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12313557/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144777064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Diagnostic efficacy of large language models in the pediatric emergency department: a pilot study.","authors":"Francesco Del Monte, Roberta Barolo, Maria Circhetta, Angelo Giovanni Delmonaco, Emanuele Castagno, Emanuele Pivetta, Letizia Bergamasco, Matteo Franco, Gabriella Olmo, Claudia Bondone","doi":"10.3389/fdgth.2025.1658635","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1658635","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.3389/fdgth.2025.1624786.].</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1658635"},"PeriodicalIF":3.2,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12308998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144755263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perspective: advancing public health education by embedding AI literacy.","authors":"Jose A Acosta","doi":"10.3389/fdgth.2025.1584883","DOIUrl":"10.3389/fdgth.2025.1584883","url":null,"abstract":"<p><p>Artificial intelligence (AI) fundamentally reshaping public health practice, yet formal training in AI literacy remains scarce in most public health educational programs. The rapid emergence of large language models and other AI-driven technologies such as computer vision, predictive analytics, and natural language processing tools-used in applications ranging from epidemiological modeling and policy analysis to real-time health communication-highlights the urgent need to bridge a persistent knowledge gap in structured, competency-based AI training for public health students and professionals. This <i>Perspective</i> article introduces the growing role of AI in public health, examines challenges in diverse global settings, outlines current gaps in AI literacy training, and proposes a framework for integrating AI competencies into undergraduate, graduate, and continuing public health curricula. In doing so, it emphasizes the importance of equipping tomorrow's public health workforce with the ethical, technical, and critical-thinking skills needed to harness AI's potential to improve health outcomes and support public health practice across diverse and underserved communities.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1584883"},"PeriodicalIF":3.2,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12307283/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144755264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}