Frontiers in digital health最新文献

{"title":"Critical activities for successful implementation and adoption of AI in healthcare: towards a process framework for healthcare organizations.","authors":"Monika Nair, Jens Nygren, Per Nilsen, Fabio Gama, Margit Neher, Ingrid Larsson, Petra Svedberg","doi":"10.3389/fdgth.2025.1550459","DOIUrl":"10.3389/fdgth.2025.1550459","url":null,"abstract":"<p><strong>Introduction: </strong>Absence of structured guidelines to navigate the complexities of implementing AI-based applications in healthcare is recognized by clinicians, healthcare leaders, and policy makers. AI implementation presents challenges beyond the technology development which necessitates standardized approaches to implementation. This study aims to explore the activities typical to implementation of AI-based systems to develop an AI implementation process framework intended to guide healthcare professionals. The Quality Implementation Framework (QIF) was considered as an initial reference framework.</p><p><strong>Methods: </strong>This study employed a qualitative research design and included three components: (1) a review of 30 scientific articles describing differences empirical cases of real-world AI implementation in healthcare, (2) analysis of qualitative interviews with healthcare representatives possessing first-hand experience in planning, running, and sustaining AI implementation projects, (3) analysis of qualitative interviews with members of the research group´s network and purposively sampled for their AI literacy and academic, technical or managerial leadership roles.</p><p><strong>Results: </strong>The data were deductively mapped onto the steps of QIF using direct qualitative content analysis. All the phases and steps in QIF are relevant to AI implementation in healthcare, but there are specificities in the context of AI that require incorporation of additional activities and phases. To effectively support the AI implementations, the process frameworks should include a dedicated phase to implementation with specific activities that occur after planning, ensuring a smooth transition from AI's design to deployment, and a phase focused on governance and sustainability, aimed at maintaining the AI's long-term impact. The component of continuous engagement of diverse stakeholders should be incorporated throughout the lifecycle of the AI implementation.</p><p><strong>Conclusion: </strong>The value of this study is the identified processual phases and activities specific and typical to AI implementations to be carried out by an adopting healthcare organization when AI systems are deployed. The study advances previous research by outlining the types of necessary comprehensive assessments and legal preparations located in the implementation planning phase. It also extends prior understanding of what the staff's training should focus on throughout different phases of implementation. Finally, the overall processual, phased structure is discussed in order to incorporate activities that lead to a successful deployment of AI systems in healthcare.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1550459"},"PeriodicalIF":3.2,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12122488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200984","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":"Role of digital health technologies in improving health financing and universal health coverage in Sub-Saharan Africa: a comprehensive narrative review.","authors":"Olutola Vivian Awosiku, Ibrahim Nafisa Gbemisola, Oluwafiponmile Thomas Oyediran, Oluwaseyi Muyiwa Egbewande, Jibril Habibah Lami, Daniel Afolabi, Melody Okereke, Fortune Effiong","doi":"10.3389/fdgth.2025.1391500","DOIUrl":"10.3389/fdgth.2025.1391500","url":null,"abstract":"<p><p>Digital technologies play a key role in developing a comprehensive and resilient healthcare delivery system in many low and middle-income countries in Sub-Saharan Africa. These technologies aim not only to address the financial accessibility gap for health needs but also to enhance innovation, partnerships, data management, and performance across healthcare stakeholders. By bridging gaps in access and reducing inequities, digital health technologies have the potential to mitigate socioeconomic disparities in healthcare delivery, particularly in resource-limited settings. This paper explores existing data on health challenges, financing, and universal health coverage in sub-Saharan Africa, along with examining digital health technologies, their adoption, and implementation. Case studies from initiatives such as M-TIBA in Kenya, JAMII in Tanzania, and L'UNION TECHNIQUE DE LA MUTUALITÉ MALIENNE in Mali are presented, along with recommendations for scale-up, policy enhancement, collaboration, support, and identification of research gaps and areas for further exploration.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1391500"},"PeriodicalIF":3.2,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12122447/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200986","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":"Developing a transparent reporting tool for AI-based diagnostic prediction models of disease and syndrome in Chinese medicine: a Delphi protocol.","authors":"Jieyun Li, Wei Song Seetoh, Jiekee Lim, Xin'ang Xiao, Kehu Yang, Si Yong Yeo, Boyun Sun, Jinhua Liu, Zhaoxia Xu, Linda L D Zhong","doi":"10.3389/fdgth.2025.1575320","DOIUrl":"10.3389/fdgth.2025.1575320","url":null,"abstract":"<p><strong>Introduction: </strong>The application of artificial intelligence in diagnostic prediction models for diseases and syndromes in Chinese Medicine (CM) has been rapidly expanding, accompanied by a significant increase in related research publications. However, existing reporting guidelines for diagnostic prediction models are primarily tailored to Western medicine, which differs fundamentally from CM in its theoretical framework, terminology, and classification systems. To address this gap, it is essential to establish a transparent and standardized reporting tool specifically designed for CM diagnostic and syndrome prediction models. This will enhance the transparency, reproducibility, and clinical relevance of research findings in this emerging field.</p><p><strong>Methods: </strong>This study adopts a structured, multi-phase Delphi protocol. A core working group will first conduct a comprehensive review of published studies on CM diagnostic prediction models to develop an initial item pool for the Transparent Reporting Tool for AI-based Diagnostic Prediction Models of Disease and Syndrome in Chinese Medicine (TRAPODS-CM). Delphi questionnaires will then be distributed via email to a multidisciplinary panel of experts in CM, computer science, and evidence-based methodology who meet the inclusion criteria. The number of Delphi rounds will be determined by evaluating the active coefficient, expert authority, and expert consensus. Final consensus on the TRAPODS-CM checklist will be achieved through online meetings. The study will be governed by a Steering Committee, with the core working group responsible for implementation. After publication, the finalized checklist will be disseminated via multimedia platforms, seminars, and academic conferences to maximize its academic and clinical impact.</p><p><strong>Ethics and dissemination: </strong>This project has received ethical approval from the National Natural Science Foundation of China (Grant No. 82374336) and the Institutional Review Board of Nanyang Technological University (IRB-2024-1007). The study findings will be disseminated through peer-reviewed publications.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1575320"},"PeriodicalIF":3.2,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12122445/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200985","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":"Data, dialogue, and design: patient and public involvement and engagement for natural language processing with real-world cancer data.","authors":"Wuraola Oyewusi, Eliana M Vasquez Osorio, Goran Nenadic, Issy MacGregor, Gareth Price","doi":"10.3389/fdgth.2025.1560757","DOIUrl":"10.3389/fdgth.2025.1560757","url":null,"abstract":"<p><strong>Introduction: </strong>This study describes the process and outcomes of a Patient and Public Involvement and Engagement (PPIE) event designed to incorporate patient perspectives into the application of Natural Language Processing (NLP) for analyzing unstructured free-text cancer medical notes. The analysis of routinely collected data aims to provide evidence to support clinical decision making in patient groups that are often under-represented in conventional clinical trials, highlighting the critical role of PPIE in responsibly implementing AI within healthcare. The study focuses on ensuring that NLP research reflects patient-centered and clinically relevant considerations.</p><p><strong>Methods: </strong>The event involved 13 participants: nine cancer survivors and caregivers, acting as contributors, and four researchers. These participants engaged in focus group discussions on three key topics: data use, consent preferences, and communication strategies for this type of research.</p><p><strong>Results: </strong>Some key findings included that two-thirds (6/9) of contributors preferred a national opt-out consent model for data use, while one-third (3/9) favored project-specific consent. They offered perspectives on data use, including how it is processed and stored. They also highlighted the importance of clear, accessible information about the research process to build trust and facilitate informed decision-making.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1560757"},"PeriodicalIF":3.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12119481/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144180618","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":"Governance for anti-racist AI in healthcare: integrating racism-related stress in psychiatric algorithms for Black Americans.","authors":"Christopher T Fields, Carmen Black, Jannat K Thind, Oluwole Jegede, Damla Aksen, Matthew Rosenblatt, Shervin Assari, Chyrell Bellamy, Elijah Anderson, Avram Holmes, Dustin Scheinost","doi":"10.3389/fdgth.2025.1492736","DOIUrl":"10.3389/fdgth.2025.1492736","url":null,"abstract":"<p><p>While the world is aware of America's history of enslavement, the ongoing impact of anti-Black racism in the United States remains underemphasized in health intervention modeling. This Perspective argues that algorithmic bias-manifested in the worsened performance of clinical algorithms for Black vs. white patients-is significantly driven by the failure to model the cumulative impacts of racism-related stress, particularly racial heteroscedasticity. Racial heteroscedasticity refers to the unequal variance in health outcomes and algorithmic predictions across racial groups, driven by differential exposure to racism-related stress. This may be particularly salient for Black Americans, where anti-Black bias has wide-ranging impacts that interact with differing backgrounds of generational trauma, socioeconomic status, and other social factors, promoting unaccounted for sources of variance that are not easily captured with a blanket \"race\" factor. Not accounting for these factors deteriorates performance for these clinical algorithms for all Black patients. We outline key principles for anti-racist AI governance in healthcare, including: (1) mandating the inclusion of Black researchers and community members in AI development; (2) implementing rigorous audits to assess anti-Black bias; (3) requiring transparency in how algorithms process race-related data; and (4) establishing accountability measures that prioritize equitable outcomes for Black patients. By integrating these principles, AI can be developed to produce more equitable and culturally responsive healthcare interventions. This anti-racist approach challenges policymakers, researchers, clinicians, and AI developers to fundamentally rethink how AI is created, used, and regulated in healthcare, with profound implications for health policy, clinical practice, and patient outcomes across all medical domains.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1492736"},"PeriodicalIF":3.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12119476/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144180489","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":"Personalization variables in digital mental health interventions for depression and anxiety in adolescents and youth: a scoping review.","authors":"Vajisha Udayangi Wanniarachchi, Chris Greenhalgh, Adrien Choi, James R Warren","doi":"10.3389/fdgth.2025.1500220","DOIUrl":"10.3389/fdgth.2025.1500220","url":null,"abstract":"<p><strong>Introduction: </strong>The impact of personalization on user engagement and adherence in digital mental health interventions (DMHIs) has been widely explored. However, there is a lack of clarity regarding the prevalence of its application, as well as the dimensions and mechanisms of personalization within DMHIs for adolescents and youth.</p><p><strong>Methods: </strong>To understand how personalization has been applied in DMHIs for adolescents and young people, a scoping review was conducted. Empirical studies on DMHIs for adolescents and youth with depression and anxiety, published between 2013 and July 2024, were extracted from PubMed and Scopus. A total of 67 studies were included in the review. Additionally, we expanded an existing personalization framework, which originally classified personalization into four dimensions (content, order, guidance, and communication) and four mechanisms (user choice, provider choice, rule-based, and machine learning), by incorporating non-therapeutic elements.</p><p><strong>Results: </strong>The adapted framework includes therapeutic and non-therapeutic content, order, guidance, therapeutic and non-therapeutic communication, interfaces (customization of non-therapeutic visual or interactive components), and interactivity (personalization of user preferences), while retaining the original mechanisms. Half of the interventions studied used only one personalization dimension (51%), and more than two-thirds used only one personalization mechanism. This review found that personalization of therapeutic content (51% of the interventions) and interfaces (25%) were favored. User choice was the most prevalent personalization mechanism, present in 60% of interventions. Additionally, machine learning mechanisms were employed in a substantial number of cases (30%), but there were no instances of generative artificial intelligence (AI) among the included studies.</p><p><strong>Discussion: </strong>The findings of the review suggest that although personalization elements of the interventions are reported in the articles, their impact on younger people's experience with DMHIs and adherence to mental health protocols is not thoroughly addressed. Future interventions may benefit from incorporating generative AI, while adhering to standard clinical research practices, to further personalize user experiences.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1500220"},"PeriodicalIF":3.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12119569/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144182499","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":"Interpretable AI-driven multi-objective risk prediction in heart failure patients with thyroid dysfunction.","authors":"Massimo Iacoviello, Vito Santamato, Alessandro Pagano, Agostino Marengo","doi":"10.3389/fdgth.2025.1583399","DOIUrl":"10.3389/fdgth.2025.1583399","url":null,"abstract":"<p><strong>Introduction: </strong>Heart Failure (HF) complicated by thyroid dysfunction presents a complex clinical challenge, demanding more advanced risk stratification tools. In this study, we propose an AI-driven machine learning (ML) approach to predict mortality and hospitalization risk in HF patients with coexisting thyroid disorders.</p><p><strong>Methods: </strong>Using a retrospective cohort of 762 HF patients (including euthyroid, hypothyroid, hyperthyroid, and low T3 syndrome cases), we developed and optimized several ML models-including Random Forest, Gradient Boosting, Support Vector Machines, and others-to identify high-risk individuals.</p><p><strong>Results: </strong>The best-performing model, a Random Forest classifier, achieved robust predictive accuracy for both 1-year mortality and HF-related hospitalization (area under the ROC curve ∼0.80 for each). We further employed model interpretability techniques (Local Interpretable Model-agnostic Explanations, LIME) to elucidate key predictors of risk at the individual level. This interpretability revealed that factors such as atrial fibrillation, absence of cardiac resynchronization therapy, amiodarone use, and abnormal thyroid-stimulating hormone (TSH) levels strongly influenced model predictions, providing clinicians with transparent insights into each prediction. Additionally, a multi-objective risk stratification analysis across thyroid status subgroups highlighted that patients with hypothyroidism and low T3 syndrome are particularly vulnerable under high-risk conditions, indicating a need for closer monitoring and tailored interventions in these groups.</p><p><strong>Discussion: </strong>In summary, our study demonstrates an innovative AI methodology for medical risk prediction: interpretable ML models can accurately stratify mortality and hospitalization risk in HF patients with thyroid dysfunction, offering a novel tool for personalized medicine. These findings suggest that integrating explainable AI into clinical workflows can improve prognostic precision and inform targeted management, though prospective validation is warranted to confirm realworld applicability.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1583399"},"PeriodicalIF":3.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12104302/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144153034","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":"Optimizing patient check-in process for telehealth visits: a data-driven perspective.","authors":"Kunal Khashu","doi":"10.3389/fdgth.2025.1554762","DOIUrl":"10.3389/fdgth.2025.1554762","url":null,"abstract":"","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1554762"},"PeriodicalIF":3.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144152178","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 the design of simulated exercising peers: insights from a participatory design study.","authors":"Alessandro Silacci, Mauro Cherubini, Maurizio Caon","doi":"10.3389/fdgth.2025.1551966","DOIUrl":"10.3389/fdgth.2025.1551966","url":null,"abstract":"<p><strong>Background: </strong>To fight sedentary lifestyles, researchers have introduced various technological interventions aimed at promoting physical activity through social support. These interventions encourage people to exercise together, maintaining high levels of motivation. However, the unpredictable nature of human peers makes it challenging to control behavior and balance these interventions effectively. Artificial intelligence agents, on the other hand, can provide consistent social support and are more controllable. Hence, we propose Simulated Exercising Peers (SEPs) as a promising solution for providing agent-based social support for physical activity.</p><p><strong>Method: </strong>Participatory design sessions were conducted, involving young adults in the creation of SEP-based interventions. Sixteen participants generated four prototypes that varied in aesthetics, behavior, and communication style, with outcomes analyzed through the lens of Self-Determination Theory to better understand the motivational implications of each design.</p><p><strong>Results: </strong>Findings highlight key components crucial for designing SEPs that enhance acceptance and efficiently integrate into physical activity interventions. Additionally, the study revealed how the aesthetics and behavior of SEPs could potentially deceive users, which can lead to user disengagement from interventions involving SEPs. Participants also defined two distinct social roles for the SEPs, i.e., coach, and companion, each associated with unique communication styles.</p><p><strong>Conclusion: </strong>This study offers five design guidelines for the development of SEPs, AI agents aimed at promoting physical activity through social support, and highlights opportunities for their integration into broader physical activity interventions.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1551966"},"PeriodicalIF":3.2,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105049/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144151808","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":"ArcTEX-a novel clinical data enrichment pipeline to support real-world evidence oncology studies.","authors":"Keiran Tait, Joseph Cronin, Olivia Wiper, Jamie Wallis, Jim Davies, Robert Dürichen","doi":"10.3389/fdgth.2025.1561358","DOIUrl":"10.3389/fdgth.2025.1561358","url":null,"abstract":"<p><p>Data stored within electronic health records (EHRs) offer a valuable source of information for real-world evidence (RWE) studies in oncology. However, many key clinical features are only available within unstructured notes. We present ArcTEX, a novel data enrichment pipeline developed to extract oncological features from NHS unstructured clinical notes with high accuracy, even in resource-constrained environments where availability of GPUs might be limited. By design, the predicted outcomes of ArcTEX are free of patient-identifiable information, making this pipeline ideally suited for use in Trust environments. We compare our pipeline to existing discriminative and generative models, demonstrating its superiority over approaches such as Llama3/3.1/3.2 and other BERT based models, with a mean accuracy of 98.67% for several essential clinical features in endometrial and breast cancer. Additionally, we show that as few as 50 annotated training examples are needed to adapt the model to a different oncology area, such as lung cancer, with a different set of priority clinical features, achieving a comparable mean accuracy of 95% on average.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1561358"},"PeriodicalIF":3.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12098606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144144618","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}