Frontiers in digital health最新文献

{"title":"Real-world deployment and longitudinal evaluation of a human-in-the-loop telemedicine communication support system.","authors":"Roland Roller, Ajay Madhavan Ravichandran, Tillmann-Leonhard Breitenstein, Marcel Naik, Bianca Zukunft, Bilgin Osmanodja, Matthias Pfefferkorn, Tim Gielsdorf, Judith Schleder, Sinem Karaterzi, Kristina Boss, Philipp Winnekens, Mario A Cypko, Aditya Kumar, Ulrich Kunze, Lisa Raithel, Oliver Witzke, Oliver Amft, Lars Pape, Sebastian Möller, Mario Schiffer, Klemens Budde, Wiebke Duettmann","doi":"10.3389/fdgth.2026.1864704","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1864704","url":null,"abstract":"<p><strong>Background: </strong>Telemedicine platforms are increasingly used to support the long-term monitoring of chronically ill patients. However, continuous streams of patient-reported data and messages may impose substantial workload on telemedicine teams. To address this challenge, we developed a human-in-the-loop communication support system for telemedicine monitoring of kidney transplant recipients.</p><p><strong>Methods: </strong>The system was integrated into the telemedicine program of the nephrology department at Charité - Universitätsmedizin Berlin. It analyzes telemedicine data in combination with locally stored electronic health record (EHR) data and generates suggested responses and reminders for clinical staff. All suggestions are reviewed by telemedicine personnel and can be accepted, modified, or discarded before being sent to patients. System usage was evaluated based on routine operation data collected since deployment.</p><p><strong>Results: </strong>The system has been in productive use since May 15, 2024. During the observation period, more than 22,000 message suggestions were generated, of which over 16,000 were sent without modification. Overall, approximately 76% of all generated suggestions resulted in patient communication. Usage increased steadily over time, indicating successful integration into routine telemedicine workflows. Standardized reminders and routine communication tasks showed particularly high utilization.</p><p><strong>Conclusions: </strong>Our findings demonstrate the potential of automated communication support systems to assist routine telemedicine workflows while maintaining human oversight of patient communication. At the same time, practical challenges related to system integration, data timeliness, and context awareness remain important considerations for successful deployment in clinical environments.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1864704"},"PeriodicalIF":5.2,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658540/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186408","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":"Evaluating artificial intelligence-generated clinical guidance for patellar dislocation: accuracy, readability and qualitative appraisal of DeepSeek-R1 responses.","authors":"Shuo Liu, Xiyang Sun, Yunfei Ma, Zhenzhong Yang, Hanyuan Zhang, Hongbo Mao, Bin Xu","doi":"10.3389/fdgth.2026.1719101","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1719101","url":null,"abstract":"<p><strong>Introduction: </strong>Large language models (LLMs) are increasingly used to answer patient questions, but the readability and information quality of patellar dislocation guidance remain unclear.</p><p><strong>Methods: </strong>A series of clinical questions covering etiopathogenesis, mechanisms, clinical manifestations, diagnosis, treatment, complications, and postoperative rehabilitation of patellar dislocation were posed to DeepSeek-R1 v2.3.1 and ChatGPT-4o. Readability was assessed using the Flesch Reading Ease score (FRES), Flesch-Kincaid Grade Level (FKGL), Automated Readability Index (ARI), SMOG Index, and Gunning Fog Score (GFS). Three sports medicine surgeons rated responses using DISCERN. Wilcoxon signed-rank tests compared models; Inter-rater reliability (IRR) for DISCERN was assessed with intraclass correlation coefficient (ICC). Additionally, we analysed DeepSeek's responses based on the current literature and therapeutic standards.</p><p><strong>Results: </strong>Readability favored ChatGPT-4o across all indices (between-model <i>P</i> < 0.05): DeepSeek-R1 vs. ChatGPT-4o medians (Q1-Q3) were ARI 15.62 (13.90-16.60) vs. 12.54 (10.15-13.41), FKGL 14.39 (12.38-15.24) vs. 11.27 (9.44-12.76), GFS 18.25 (15.20-19.43) vs. 14.55 (13.73-16.53), SMOG 11.02 (9.72-12.18) vs. 9.55 (8.14-10.67), and FRES 9.50 (6.75-25.00) vs. 33.00 (19.75-41.50). Both models exceeded the NIH-recommended sixth-grade reading level (all <i>P</i> < 0.05). DISCERN scores were similar [median (Q1-Q3)] for DeepSeek-R1 vs. ChatGPT-4o: 49.17 (40.25-59.17) vs. 50.33 (38.92-58.42), corresponding to \"Fair\" quality (<i>P</i> = 0.767). DISCERN agreement was high (single-measure ICC 0.860-0.950).</p><p><strong>Conclusions: </strong>Although both AI platforms can generate clinically relevant responses of moderate quality, they should be regarded as adjunctive information rather than stand-alone clinical guidance, particularly given the high incidence of patellar instability and developmental characteristics of children and adolescents. Exploratory qualitative assessment of DeepSeek-R1 responses identified strengths in clinical explanation and reasoning, while also revealing limitations in citation reliability and readability. Future work should incorporate multi-turn, multi-generation frameworks, more samples with repeated sampling and longitudinal assessment, enforced citation standards, and expanded evaluation to better quantify both clinical utility and reliability.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1719101"},"PeriodicalIF":5.2,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658195/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186664","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":"A scoping review of generative AI and digital twins in tackling loneliness during hospital-to-home transitions.","authors":"Yuqing Zhang, Shengfeng Qin","doi":"10.3389/fdgth.2026.1802931","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1802931","url":null,"abstract":"<p><p>Loneliness is an important psychosocial concern for older adults and may be intensified during the transition from hospital to home, when established routines, professional contact, functional capacity, and social participation can change simultaneously. This scoping review examined how generative artificial intelligence (GenAI), AI-enabled technologies, and digital twins (DTs) have been investigated in relation to loneliness, social connectedness, and psychosocial support for older adults, with particular attention to their relevance to hospital-to-home transitions. Following Joanna Briggs Institute guidance and PRISMA-ScR reporting principles, six interdisciplinary databases were searched for English-language peer-reviewed studies published between 2020 and 2026. Thirty-two primary studies were included in the final synthesis. Review-level publications were excluded from the primary synthesis and used separately to contextualize the broader technology landscape. The evidence revealed two largely separate research streams. Loneliness-focused studies predominantly investigated conversational agents, smart speakers, voice assistants, social and companion robots, large-language-model-supported systems, generative reminiscence, and AI-based loneliness detection, mainly in community, home, and long-term-care settings. In contrast, hospital-to-home studies primarily addressed continuity of care, rehabilitation, symptom communication, monitoring, personalized assistance, and service coordination, with loneliness rarely assessed as a primary outcome. Digital-twin applications relevant to loneliness were particularly limited and remained largely conceptual or design-oriented. No included study evaluated an integrated GenAI-DT intervention that continuously interpreted changing post-discharge context and used this information to personalize relational support within an accountable hospital-to-home care pathway. The principal gap is therefore not the absence of AI-enabled support, but the lack of integration between relational GenAI capabilities, context-aware sensing and digital-twin representations, and transitional-care services. Based on these findings, this review proposes a Relational Intelligence Ecosystem as an evidence-derived and theory-informed framework to guide the future design and evaluation of personalized, context-aware, and human-supervised smart services for older adults during hospital-to-home recovery.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1802931"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13655533/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186702","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":"Recommendations for the development, implementation, and evaluation of technology-assisted physical activity interventions to support healthy aging: insights from PhysAgeNet.","authors":"Nadja Schott, Jana Pelclová, Eleftheria Giannouli, Antoine Langeard, Christopher McCrum, Rosemary Dubbeldam, Rafael A Bernardes, Arben Boshnjaku, David Beckwée","doi":"10.3389/fdgth.2026.1913687","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1913687","url":null,"abstract":"<p><p>Digital health technologies offer substantial potential to support physical activity among older adults, yet their development and implementation often remain driven by technological possibilities rather than clinical evidence and user needs. This position paper, developed within the PhysAgeNet COST Action, synthesizes current evidence and expert consensus to provide recommendations for designing, evaluating, and implementing technology-assisted physical activity interventions for older adults. We first outline key technology categories and functions relevant to physical activity promotion, including wearables, exergames, mobile applications, telehealth platforms, and smart environments, and highlight critical technical requirements such as accuracy, reliability, connectivity, interoperability, and data security. We then emphasize the need to align digital interventions with established clinical guidelines for physical activity, falls prevention, frailty, and sarcopenia, including explicit specification of exercise dose according to FITT-VP principles and robust monitoring of dual adherence to both physical activity and technology use. Building on technology acceptance models and behavior change theories, we describe how user-centered and co-creative design processes can translate theoretical constructs into concrete digital features that enhance motivation, enjoyment, and long-term engagement. Finally, we propose stakeholder-specific guidance for developers, researchers, and clinicians, including recommendations on user assessment, recruitment of vulnerable groups, implementation frameworks, and clinically grounded evaluation of outcomes and usability. Together, these recommendations provide a pragmatic roadmap for moving from a technology-push paradigm toward evidence-based, acceptable, and equitable technology-assisted physical activity interventions that can be sustainably integrated into routine practice for older adults.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1913687"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13655530/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186366","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":"Patient-level evaluation of smartwatch-based pain and dehydration detection in nursing home residents: a prospective observational study.","authors":"Lorenz Kapral, Fred Bucek, Lisa Lichtenegger, Aylin Albrecht, Oliver Kimberger, Laurenz Berger, Francesco Moscato, Harald Willschke","doi":"10.3389/fdgth.2026.1930008","DOIUrl":"10.3389/fdgth.2026.1930008","url":null,"abstract":"<p><strong>Introduction: </strong>Nursing home residents are at high risk for underrecognized pain and dehydration, particularly those with cognitive impairment who cannot reliably self-report symptoms. Consumer-grade smartwatches capable of continuous physiological monitoring may help detect these conditions, but their feasibility in frail older adults remains underexplored, and evaluation strategies based on random splits of repeated time windows can yield optimistically biased estimates. We therefore evaluated the feasibility of continuous smartwatch monitoring in nursing home residents and explored whether machine learning models using smartwatch-derived data can detect pain and dehydration under patient-independent evaluation.</p><p><strong>Methods: </strong>In a prospective, observational feasibility study (VIENNESE) conducted at three Caritas nursing homes in Vienna, Austria (February to November 2024), 24 residents were enrolled, 16 began smartwatch monitoring and 13 completed the protocol and contributed sufficient data for analysis (1,414 labelled 120 min windows). Matched XGBoost classifiers were evaluated with nested leave-one-patient-out cross-validation, with hyperparameters tuned inside each fold on training participants only.</p><p><strong>Results: </strong>Pain detection showed a weak signal, with a mean per-patient AUC of 0.557 (range 0.533 to 0.599 across random seeds) and a pooled window-level AUC of 0.736 (0.662 to 0.784). For dehydration, discrimination remained at chance level (mean per-patient AUC 0.513, range 0.468 to 0.550; pooled 0.484, range 0.393 to 0.593).</p><p><strong>Discussion: </strong>Continuous smartwatch monitoring was operationally feasible in this population. The exploratory models point to a weak pain-related signal that merits evaluation in larger cohorts with stronger reference standards, whereas hydration status may require different sensing modalities.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1930008"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13654990/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149167754","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":"Digital health literacy in safety-net primary care: a needs assessment and call to action for health equity.","authors":"Julie Glickstein, Jessica O Idumonyi, Tina Ting, Ines Robles-Aponte, Matthew Ramey, Robert Fullilove, Jessica Singer","doi":"10.3389/fdgth.2026.1907871","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1907871","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Digital literacy is a crucial social determinant of health. The COVID-19 pandemic's rapid shift to digital health services has widened disparities for older adults, racial and ethnic minorities, and low-income populations. Understanding barriers to electronic medical record (EMR) use is essential for equitable care in safety-net settings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a cross-sectional needs assessment survey (&lt;i&gt;N&lt;/i&gt; = 204) at an urban primary care clinic in Washington Heights, New York City, serving predominantly Latino (83%), Spanish-speaking (31%), and older adult (67% aged ≥65) patients. We assessed demographics, EMR use frequency, digital health literacy [eHealth Literacy Scale (eHEALS)], patient portal (MyChart) functional competency, and learning interest using chi-square tests for categorical variables and t-tests for continuous variables. Pairwise comparisons with &lt;i&gt;post-hoc&lt;/i&gt; correction were conducted for multi-category variables. EMR patterns were operationalized as self-reported frequency of patient-initiated digital communication with healthcare providers using the clinic's electronic patient portal system within the past 6 months.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;EMR use varied significantly by age among stable age groups, &lt;i&gt;χ&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; (2) = 12.34, &lt;i&gt;p&lt;/i&gt; = 0.002: 63.9% of ages 31-64 and 53.7% of ages ≥65 reported EMR use. [Note: Adults ages 18-30 comprised only &lt;i&gt;n&lt;/i&gt; = 7 (3.4% of sample); 100% EMR use in this group, 95% CI: 59-100%, is underpowered and excluded from primary interpretation.] Employment status was significantly associated with EMR use [&lt;i&gt;χ&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; (2) = 10.89, &lt;i&gt;p&lt;/i&gt; = 0.003], with full-time employed individuals showing 95.5% usage, compared to 54.6% among retired and 57.7% among unemployed respondents. Bonferroni-corrected pairwise comparisons (adjusted &lt;i&gt;α&lt;/i&gt;=0.017) confirmed significant differences between full-time employed and retired individuals (&lt;i&gt;p&lt;/i&gt; &lt; 0.001) and between full-time employed and unemployed individuals (&lt;i&gt;p&lt;/i&gt; = 0.002). Mean eHEALS score was 25.33 (SD = 6.83) out of 40, indicating moderate digital literacy. Approximately half of participants demonstrated proficiency with individual MyChart functional tasks: viewing lab results (47% correct), reading physician notes (43% correct), messaging providers (50% correct), requesting refills (46% correct), and scheduling appointments (42% correct). Despite this lower EMR engagement, 71.6% expressed interest in learning EMR skills overall [83.1% among ages ≥65, 83.1% among Spanish speakers, &lt;i&gt;χ&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; (2) = 18.76, &lt;i&gt;p&lt;/i&gt; &lt; 0.0001, these representing separate subgroup analyses]. Women showed significantly higher interest than men [76.8% vs. 47.2%; &lt;i&gt;χ&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; (1) = 14.32, &lt;i&gt;p&lt;/i&gt; = 0.0004].&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study highlights a key tension: EMR engagement is lowest among older, retired, and Medicare-only patients, yet these grou","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1907871"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186632","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":"Awareness, attitudes, and experiences of using digital health services among patients with chronic diseases at King Abdulaziz Medical City.","authors":"Seham A Elgamal, Rahmah Alalawi, Neama Y Hantira, Rana Alsulami, Suzan Abdulsubhan, Danah Abutaleb, Batool Althobaiti, Rafa Binzagr, Shahad Almehmadi, Dareen Alqhtani","doi":"10.3389/fdgth.2026.1887874","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1887874","url":null,"abstract":"<p><strong>Background: </strong>Digital health technologies have transformed chronic disease management by supporting remote monitoring, personalized care, and improved communication between patients and healthcare providers. Applications such as mobile health platforms, telemedicine, and wearable devices can enhance self-management and continuity of care for individuals with chronic illnesses. In Saudi Arabia, digital health platforms, including Sehhaty, have been introduced to improve healthcare accessibility; however, patient utilization remains suboptimal.</p><p><strong>Aim: </strong>This study aimed to assess patients' awareness, attitudes, and experiences regarding the use of digital health services among individuals living with chronic diseases.</p><p><strong>Methods: </strong>A descriptive cross-sectional study was conducted among patients with confirmed chronic illnesses attending outpatient clinics at King Abdulaziz Medical City. Data were collected using a structured questionnaire assessing sociodemographic characteristics, awareness, experience, digital health utilization patterns, and attitudes toward digital health application use. Descriptive and inferential statistical analyses were performed to identify factors associated with awareness and attitudes.</p><p><strong>Results: </strong>Nearly half of the participants (45.5%) demonstrated low digital health awareness, while 50.6% exhibited positive attitudes toward digital health applications. Sehhaty was the most commonly used application (38.9%), and 68.5% used the internet to obtain health-related information. Digital health awareness was strongly positively correlated with attitudes toward digital health applications (<i>r</i> = 0.693, <i>p</i> < 0.001). Higher awareness, use of digital health applications, internet use for health information, and younger age were significant predictors of more positive attitudes (<i>p</i> < 0.05).</p><p><strong>Conclusion: </strong>Nearly half of the patients with chronic illnesses demonstrated low digital health awareness, although attitudes toward digital health applications were generally positive. Enhancing digital literacy and integrating digital health education into routine care may improve the adoption and effective use of digital health technologies in chronic disease management.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1887874"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186637","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 for pneumonia diagnosis: a systematic review of multimodal learning, fusion strategies, and explainability.","authors":"K G Sruthy, T M Navamani","doi":"10.3389/fdgth.2026.1949796","DOIUrl":"10.3389/fdgth.2026.1949796","url":null,"abstract":"<p><p>Pneumonia remains a major global public health challenge, particularly among children, older adults, and individuals with weakened immune systems. Although deep learning has made great progress in automated pneumonia diagnosis, most current methods are unimodal, using only chest X-ray images. This results in limited robustness, cross-institutional generalization and clinical applicability. Moreover, the current reviews mainly focus on summarising single data modalities or model architectures and lack comparative analysis of multimodal fusion strategies, explainability methods, benchmark datasets, and new artificial intelligence paradigms. To fill these gaps, this systematic review offers a common analytical framework for systematically comparing multimodal deep learning architectures, fusion strategies, explainability methods, benchmark datasets, and emerging technologies in the field of artificial intelligence for pneumonia diagnosis. Research articles were systematically reviewed to identify the latest developments, technological challenges, and future research directions. Evidence suggests that multimodal models can provide information from different sources and may improve diagnostic performance in specific settings. However, direct comparisons between studies are limited by differences in datasets, clinical tasks, and validation protocols. Attention-based and hybrid fusion strategies can learn useful information from various modalities. Explainable artificial intelligence methods provide mechanisms for improving the transparency and interpretability of model predictions.The clinical translation is still limited, however, due to the lack of large-scale multimodal datasets, data heterogeneity, missing modalities, inconsistent evaluation protocols, and lack of external validation. In summary, this review summarizes the current research trends, outlines important technological challenges, and provides a research agenda for the future to build strong, interpretable, and clinically viable artificial intelligence systems for next-generation pneumonia diagnosis.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1949796"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13655001/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149170305","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":"Public health communication and information quality of knee osteoarthritis-related short videos on TikTok, Kwai, and Bilibili: a cross-sectional study.","authors":"Yundong Xu, Qianqian Yang, Jian Zhang, Jin Xu, Niqin Xiao, Heguo Yan, Sanjin Zeng, Shengyi Zhao, Rong Wang, Zhaohu Xie, Zhaofu Li","doi":"10.3389/fdgth.2026.1868584","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1868584","url":null,"abstract":"<p><strong>Background: </strong>Knee osteoarthritis (KOA) is a prevalent musculoskeletal disorder and a major cause of pain and disability. As short-video platforms increasingly shape how the public accesses health information, concerns have grown regarding the quality, reliability, and completeness of KOA-related content. This study evaluated KOA-related videos on three major Chinese short-video platforms, TikTok, Kwai, and Bilibili, to compare information quality, user engagement, and implications for digital public health communication.</p><p><strong>Methods: </strong>In this cross-sectional study, standardized Chinese keywords were used to retrieve KOA-related videos from TikTok, Kwai, and Bilibili on December 24, 2025. After deduplication and screening, 300 videos were included, 100 from each platform. Video characteristics and engagement indicators were recorded. Information quality was assessed using the DISCERN reliability section, Global Quality Score (GQS), content completeness score (CS, range 0-10), and engagement score (ES, range 0-4). Uploaders were categorized by source type. Statistical analyses included the Kruskal-Wallis H test, chi-square test, and Spearman correlation analysis.</p><p><strong>Results: </strong>Substantial cross-platform differences were identified. Bilibili videos had the longest duration (median 402 s) and the highest information quality, with superior DISCERN scores (median 32), GQS (mean 4.3), and CS (mean 7), and had the highest proportion of certified medical professionals among uploaders (38.0%). TikTok videos were the shortest (median 86 s) but showed the highest user engagement, including likes, comments, shares, and the highest ES (median 3.6). TikTok and Kwai videos were generally less complete, focusing mainly on symptoms and treatment while providing limited information on etiology and prognosis. Correlation analysis showed that higher information quality and completeness were negatively associated with user interaction metrics, whereas ES was positively associated with engagement.</p><p><strong>Conclusions: </strong>The three major short-video platforms in China represent distinct digital health information ecosystems for KOA, revealing a consistent trade-off between scientific rigor and audience engagement. Platform recommendation mechanisms may may preferentially surface content that is more attractive and interactive rather than more accurate and comprehensive. These findings highlight an important public health challenge in the governance of online health information and suggest that improving chronic disease communication on social media will require both stronger platform-level quality prioritization and more engaging evidence-based content produced by health professionals.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1868584"},"PeriodicalIF":5.2,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186382","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":"Short-form video exposure characteristics and respiratory symptom severity among patients with chronic obstructive pulmonary disease: a cross-sectional study.","authors":"Haihong Zhang, Wenxue Zhang, Li Tang","doi":"10.3389/fdgth.2026.1955608","DOIUrl":"https://doi.org/10.3389/fdgth.2026.1955608","url":null,"abstract":"<p><strong>Background: </strong>Short-form video platforms have become a dominant health information source for COPD patients, yet the relationship between content characteristics of exposure and respiratory symptom severity remains unexplored. Given China's 1.02 billion short-form video users with daily viewing exceeding 150 min, understanding differential health impacts of various content types is critical, particularly for older adults vulnerable to algorithmic misinformation.</p><p><strong>Objective: </strong>This study investigated associations between multidimensional short-form video exposure characteristics-content type (health preservation, illness prevention, daily exercise), viewing duration, and user acceptance-and respiratory symptom severity measured by the BCSS among outpatients with COPD.</p><p><strong>Methods: </strong>A multi-center cross-sectional study enrolled 207 GOLD-confirmed COPD patients (mean age 63.0 ± 12.9 years; 55.1% male) from January to July 2025. Short-form video exposure was assessed using a validated self-designed questionnaire (Cronbach's <i>α</i>=0.78, CVI=0.85). Respiratory symptoms were measured using the BCSS. Analyses included t-tests, ANOVA, and hierarchical multiple linear regression, with established clinical confounders forced into multivariable models per STROBE guidelines. Multicollinearity and model assumptions were verified.</p><p><strong>Results: </strong>Mean BCSS was 7.86 ± 2.24, indicating moderate-to-severe symptom burden. Health preservation content exposure was independently associated with higher BCSS (B = 1.163, <i>β</i>=0.227, <i>P</i> = 0.003), while daily exercise content showed an inverse association (B = -0.876, <i>β</i>=-0.196, <i>P</i> = 0.007). Daily viewing duration was not independently associated with BCSS (B = 0.059, <i>P</i> = 0.377). Acceptance showed a significant non-linear pattern suggestive of an inverted U-shaped relationship with BCSS (P for non-linearity=0.025), warranting cautious interpretation. Content and acceptance variables improved model fit beyond clinical covariates and duration (<i>Δ</i>R² = 0.108, <i>P</i> = 0.001), whereas duration alone did not (<i>Δ</i>R² = 0.009, <i>P</i> = 0.155). The final model explained 22.0% of BCSS variance.</p><p><strong>Conclusion: </strong>Content type-not duration alone-was significantly associated with respiratory symptom severity in COPD patients. Health preservation content (often non-evidence-based) was linked to worse symptoms, while daily exercise content showed protective associations. The non-linear acceptance-symptom relationship suggests that the association between content acceptance and symptom severity is complex and not simply monotonic; the underlying mechanisms merit further investigation. These findings support content-aware digital health literacy interventions and integration of social media exposure assessment into nursing-led COPD management.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"8 ","pages":"1955608"},"PeriodicalIF":5.2,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13650011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149171577","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}