Frontiers in digital health最新文献

{"title":"TICD: a novel thermal imaging cats' dataset for non-invasive health monitoring.","authors":"Mohammad Abdulghafar, Adnan Nadeem, Anas Alhindi, Hudhaifa Gburi, Saifullah Abdulghaffar, Emad Nabil","doi":"10.3389/fdgth.2025.1650223","DOIUrl":"10.3389/fdgth.2025.1650223","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1650223"},"PeriodicalIF":3.2,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12394521/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144980876","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":"Unveiling practical insights of eHealth implementation in Europe: a grey literature review on legal, ethical, financial, and technological (LEFT) considerations.","authors":"B E Bente, N Beerlage-de Jong, R M Verdaasdonk, J E W C van Gemert-Pijnen","doi":"10.3389/fdgth.2025.1575620","DOIUrl":"10.3389/fdgth.2025.1575620","url":null,"abstract":"<p><strong>Background: </strong>The implementation of eHealth technologies can improve healthcare efficiency, accessibility, and affordability. However, it involves complex legal, ethical, financial, and technological (LEFT) challenges that can impede success. While our previous scoping review identified barriers such as balancing compliance with innovation, funding gaps, and unclear business models, there remains a significant gap in understanding how these challenges manifest in real-world settings. This study uses grey literature to explore practical experiences and strategies in addressing LEFT challenges during eHealth implementation.</p><p><strong>Objective: </strong>This study aims to explore real-world experiences and perspectives on the legal, ethical, financial, and technological (LEFT) challenges encountered during eHealth implementation.</p><p><strong>Methods: </strong>A grey literature review was conducted by querying databases BASE and Policy Commons, consulting expert references for relevant reports, and using snowball sampling to identify additional relevant grey literature.</p><p><strong>Results: </strong>While the aim of this study was to explore practical experiences, the grey literature mainly reflects policy-level concerns, including strategic and regulatory challenges, with limited insight into how organizations navigate eHealth implementation in practice. Legal barriers include navigating complex regulatory frameworks, interpreting regulations, and concerns about data privacy. Facilitators focus on centralized governance and Europe's role in the global data market. Ethical barriers address inequalities in access, while facilitators emphasize patient autonomy, clear consent processes, and digital literacy. Financial barriers stem from inadequate funding structures and unclear financial requirements, with public-private partnerships as facilitators. Technological barriers revolve around interoperability issues due to national IT infrastructure limitations, with facilitators working to improve data exchange.</p><p><strong>Conclusions: </strong>This study highlights a disconnect between the strategic focus of available grey literature and the need for actionable, practice-based insights. The limited presence of real-world implementation experiences underscores the necessity for more operational documentation to support stakeholders facing interrelated LEFT barriers. Key challenges include the need for actionable legal and ethical frameworks, clearer ethical discussions aligned with legal requirements, sustainable financial infrastructures, and enhanced stakeholder involvement to address interoperability challenges. These challenges require cross-sector investment in IT infrastructures, harmonized data standards, and stronger collaboration among stakeholders. Coordinated efforts across all LEFT domains are crucial for effective eHealth implementation.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1575620"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12390996/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144980962","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":"Editorial: VR, AR, MR in healthcare: the role of immersive technologies in medical training.","authors":"Serena Ricci, Veronica Penza, Francesco Neri","doi":"10.3389/fdgth.2025.1669899","DOIUrl":"10.3389/fdgth.2025.1669899","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1669899"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12390970/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981068","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":"Professionals' perspectives on the challenges of implementing digital solutions in rehabilitation settings in Rwanda.","authors":"Kaisa Jokinen, Michael Oduor, Gerard Urimubenshi, Juliette Gasana, Jean Damascene Bigirimana, David K Tumusiime, Eeva Aartolahti, Kari-Pekka Murtonen, Katariina Korniloff","doi":"10.3389/fdgth.2025.1489288","DOIUrl":"10.3389/fdgth.2025.1489288","url":null,"abstract":"<p><p>The need for rehabilitation is unmet, especially in low- and middle-income countries such as Rwanda. Digital rehabilitation offers significant potential for delivering rehabilitation services in low-resource settings, and this study examines the challenges affecting the digitalization of rehabilitation. Semi-structured interviews and a survey were conducted in Rwanda with rehabilitation professionals to collect data for two different projects. The different datasets were analyzed using thematic analysis and inductive content analysis. As a result, three main concepts were formed: context-related factors, individual-related factors, and technology-related factors. Results suggest that the challenges in implementing digital solutions in rehabilitation settings in Rwanda encompass various domains, including socioeconomic factors, infrastructure, digital competency, regulatory frameworks, and user-related factors. In conclusion, because of multifaceted challenges, systemic-level change is needed to realize the potential of the digitalization of rehabilitation and other health care services in Rwanda.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1489288"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12391195/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144980866","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":"Investigating lightweight and interpretable machine learning models for efficient and explainable stress detection.","authors":"Debasish Ghose, Ayan Chatterjee, Indika A M Balapuwaduge, Yuan Lin, Soumya P Dash","doi":"10.3389/fdgth.2025.1523381","DOIUrl":"10.3389/fdgth.2025.1523381","url":null,"abstract":"<p><p>Stress is a common human reaction to demanding circumstances, and prolonged and excessive stress can have detrimental effects on both mental and physical health. Heart rate variability (HRV) is widely used as a measure of stress due to its ability to capture variations in the time intervals between heartbeats. However, achieving high accuracy in stress detection through machine learning (ML), using a reduced set of statistical features extracted from HRV, remains a significant challenge. In this study, we aim to address these challenges by proposing lightweight ML models that can effectively detect stress using minimal HRV features and are computationally efficient enough for IoT deployment. We have developed ML models incorporating efficient feature selection techniques and hyper-parameter tuning. The publicly available SWELL-KW dataset has been utilized for evaluating the performance of our models. Our results demonstrate that lightweight models such as <math><mi>k</mi></math> -NN and Decision Tree can achieve competitive accuracy while ensuring lower computational demands, making them ideal for real-time applications. Promisingly, among the developed models, the <math><mi>k</mi></math> -nearest neighbors ( <math><mi>k</mi></math> -NN) algorithm has emerged as the best-performing model, achieving an accuracy score of 99.3 <math><mi>%</mi></math> using only three selected features. To confirm real-world deployability, we benchmarked the best model on an 8 GB NVIDIA Jetson Orin Nano edge device, where it retained 99.26% accuracy and completed training in 31 s. Furthermore, our study has incorporated local interpretable model-agnostic explanations to provide comprehensive insights into the predictions made by the <math><mi>k</mi></math> -NN-based architecture.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1523381"},"PeriodicalIF":3.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380676/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981111","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":"Convergence of disciplines: a systematic review of multidisciplinary development approaches in artificial intelligence.","authors":"Giusi Antonia Toto, Luca Grilli, Luigi Traetta, Rosanna Villani, Annamaria Petito, Gaetano Serviddio","doi":"10.3389/fdgth.2025.1400338","DOIUrl":"10.3389/fdgth.2025.1400338","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) across multiple disciplines is fostering a transformative shift in research and practice. This paper explores how multidisciplinary collaboration with AI is reshaping traditional methodologies and catalyzing innovation in diverse fields such as medicine, psychology, agriculture, mathematics, physics, and economics. A systematic review was conducted following the PRISMA 2020 guidelines. Relevant literature was identified through searches in PubMed, Scopus, and Google Scholar, covering publications from 2013 to August 2023. Inclusion criteria focused on English-language articles examining the intersection of AI and multidisciplinary applications. Additional studies were identified by screening reference lists of included articles. The analysis revealed that AI's multidisciplinary integration has significantly influenced practices across multiple domains. In medicine, AI supports diagnosis and treatment planning; in psychology, it enhances mental health interventions; and in agriculture, it contributes to addressing global food security challenges. The reviewed literature highlights how AI collaboration with fields such as physics, economics, and history is leading to innovative problem-solving strategies and paradigm shifts. The findings underscore the substantial potential of a multidisciplinary approach to AI. This convergence is not only accelerating technological advancement but also fostering more comprehensive and effective solutions to complex global issues. The results suggest that ongoing interdisciplinary collaboration will be critical in maximizing AI's societal impact and shaping its future development.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1400338"},"PeriodicalIF":3.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981095","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":"Advancements and challenges of artificial intelligence in dermatology: a review of applications and perspectives in China.","authors":"Jiaao Yu, Io Hong Cheong, Zisis Kozlakidis, Hui Wang","doi":"10.3389/fdgth.2025.1544520","DOIUrl":"10.3389/fdgth.2025.1544520","url":null,"abstract":"<p><p>The diagnosis of skin diseases can be challenging due to their diverse manifestations, while early detection of malignant skin cancers greatly improves the prognosis, highlighting the pressing need for efficient screening methods. In recent years, advancements in AI have paved the way for AI-aided diagnosis of skin lesions. Furthermore, the COVID-19 pandemic has spurred the demand of telemedicine, accelerating the integration of AI into medical domains, particularly in China. This article aims to provide an overview of the progress of AI-aided diagnosis in Chinese dermatology. Given the widespread use of public datasets in the reviewed studies, we compared the performance of AI models in segmentation and classification on public datasets. Despite the promising results of AI in experimental settings, we recognize the limitations of these public datasets in representing clinical scenarios in China. To address this gap, we reviewed the studies that used clinical datasets and conducted comparative analyses between AI and dermatologists. Although AI demonstrated comparable results to human experts, AI still cannot replace dermatologists due to limitations in generalizability and interpretability. We attempt to provide insights into improving the performance of AI through advancements in dataset quality, image pre-processing techniques, and integration of medical data. Finally, the role that AI will play in the medical practice and the relationship between AI and dermatologists are discussed. This systematic review addresses the gap in evaluating AI applications in Chinese dermatology, with a focus on dermatological datasets and real-world application.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1544520"},"PeriodicalIF":3.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380682/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981118","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-centered AI.","authors":"Shamie Kumar","doi":"10.3389/fdgth.2025.1638098","DOIUrl":"10.3389/fdgth.2025.1638098","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1638098"},"PeriodicalIF":3.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380751/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144980677","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 the impact of engaging healthcare providers in an AI-based gamified mHealth intervention for improving maternal health outcomes among disadvantaged pregnant women in Lebanon.","authors":"Shadi Saleh, Nour El Arnaout, Nadine Sabra, Asmaa El Dakdouki, Khaled El Iskandarani, Zahraa Chamseddine, Randa Hamadeh, Abed Shanaa, Mohamad Alameddine","doi":"10.3389/fdgth.2025.1574946","DOIUrl":"10.3389/fdgth.2025.1574946","url":null,"abstract":"<p><strong>Introduction: </strong>Maternal health in Lebanon faces significant challenges, particularly among disadvantaged populations, due to limited access to antenatal care (ANC) and a strained healthcare system. While mHealth interventions have improved maternal outcomes globally, few engage healthcare providers (HCPs) or incorporate advanced tools like artificial intelligence (AI) and gamification. This study evaluated the effectiveness of an AI-based, gamified mHealth intervention, Gamification and AI and mHealth Network for Maternal Health Improvement (GAIN MHI), on ANC utilization and maternal and neonatal outcomes in Lebanon.</p><p><strong>Methods and materials: </strong>The intervention included two arms: one targeting pregnant women and their spouses without HCP engagement and another involving HCPs. A post-intervention analysis was conducted with 2,880 pregnant women divided into three groups: control (<i>n</i> = 1,315), non-HCP intervention (<i>n</i> = 668), and HCP intervention (<i>n</i> = 897). Intervention components included AI-driven, gamified HCP professional development via the GAIN MHI app, weekly WhatsApp-based educational messages, and ANC visit reminders. Data on healthcare access (ANC visits, supplement intake, ultrasounds, and lab tests) and outcomes (term delivery, maternal/neonatal complications) were analyzed using logistic regression to calculate adjusted odds ratios (OR).</p><p><strong>Results: </strong>The HCP arm significantly improved healthcare access, with higher odds of attending ≥4 ANC visits (OR = 1.968, 95% CI: 1.575-2.459), completing ≥2 ultrasounds (OR = 3.026, 95% CI: 2.301-3.981), lab test completion (OR = 2.828, 95% CI: 1.894-4.221), and supplement intake (OR = 1.467, 95% CI: 1.221-1.762). Term deliveries were more likely in the HCP arm (OR = 1.360, 95% CI: 1.011-1.289), and neonatal morbidity decreased by 52.15% (OR = 1.521, 95% CI: 1.127-2.051). No improvements were seen in abortion rates, and normal deliveries decreased across intervention arms. Significant baseline demographic differences, including nationality and chronic disease prevalence, were observed between groups.</p><p><strong>Discussion: </strong>Integrating HCPs into an mHealth intervention significantly enhanced ANC uptake and maternal and neonatal outcomes in disadvantaged populations in Lebanon. These findings underscore the importance of combining digital tools with clinical support to address systemic barriers and improve maternal health in resource-limited settings. Future interventions should address delivery practices and broader social determinants of health to achieve sustainable impacts.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1574946"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379028/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981109","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":"Voice as a biomarker: exploratory analysis for benign and malignant vocal fold lesions.","authors":"Phillip Jenkins, Rylan Harrison, Steven Bedrick, Lisa Karstens, William Hersh","doi":"10.3389/fdgth.2025.1609811","DOIUrl":"10.3389/fdgth.2025.1609811","url":null,"abstract":"<p><p>Benign and malignant vocal fold lesions can alter voice quality and lead to significant morbidity or, in the case of malignancy, mortality. Early, noninvasive identification of these lesions using voice as a biomarker may improve diagnostic access and outcomes. In this study, we analyzed data from the initial release of the Bridge2AI-Voice dataset to evaluate which acoustic features best distinguish laryngeal cancer and benign vocal fold lesions from other vocal pathologies and healthy voice function. Seven diagnostic cohorts were grouped into two analyses: the first included participants with laryngeal cancer, benign lesions, or no voice disorder; the second included those with laryngeal cancer or benign lesions without other voice disorders, as well as individuals with spasmodic dysphonia or vocal fold paralysis. Acoustic features including fundamental frequency, jitter, shimmer, and harmonic-to-noise ratio (HNR) were extracted from standardized speech recordings and compared using nonparametric statistical methods. Among the overall sample, significant differences were identified in HNR and fundamental frequency between benign lesions and both healthy controls and laryngeal cancer. In cisgender men, these distinctions were also observed, particularly in HNR and its variability. No statistically significant differences were observed among cisgender women, likely due to the limited sample size. These findings suggest that HNR, particularly its variability, may hold promise as a voice-based marker for early detection and monitoring of vocal fold lesions. Further research with larger, more diverse populations is needed to refine these features and validate their clinical utility.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1609811"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12378753/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981043","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}