Frontiers in digital health最新文献

{"title":"The evolution of barriers and facilitators to using a COPD app among older adults: results from a pilot study.","authors":"Jeff Brady, Rachel F McCloud, Erin Higgins, Aishwarya Mahesh, Keith LeJeune, Jon Black, Anil Singh","doi":"10.3389/fdgth.2025.1557590","DOIUrl":"10.3389/fdgth.2025.1557590","url":null,"abstract":"<p><strong>Purpose: </strong>Although older adults are more frequently adopting smartphone technologies, factors influencing decisions for uptake and continued use remain complex. This study explored how perceptions and use of a smartphone app changed from pre-adoption through initial use.</p><p><strong>Methods: </strong>Participants were interviewed before, during, and after being introduced to a COPD app to assess their experiences with and perceptions of the app over a 4-month period.</p><p><strong>Results: </strong>Prior to app introduction, participants reported technology, health behavior, and contextual barriers to engaging with health technology. After app introduction, many technology-based barriers lessened over time as participants became more familiar with the app. Other barriers, such as perceived lack of relevance and competing health and life concerns, remained as challenges to use.</p><p><strong>Discussion: </strong>Results point to the need for apps that can cater to the diverse needs and other life challenges of older adults. Opportunities for assistance from technical support lines, family, friends, and/or community are required.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1557590"},"PeriodicalIF":3.2,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12301334/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144735858","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":"Physicians' attitudes and acceptance towards artificial intelligence in medical care: a qualitative study in Germany.","authors":"Sarah Negash, Jana Gundlack, Charlotte Buch, Timo Apfelbacher, Jan Schildmann, Thomas Frese, Jan Christoph, Rafael Mikolajczyk","doi":"10.3389/fdgth.2025.1616827","DOIUrl":"10.3389/fdgth.2025.1616827","url":null,"abstract":"<p><strong>Background: </strong>The role of artificial intelligence (AI) in medicine is rapidly expanding, with the potential to transform physicians' working practices across various areas of medical care. As part of the PEAK project (Perspectives on the Use and Acceptance of Artificial Intelligence in Medical Care) this study aimed to investigate physicians' attitudes towards and acceptance of AI in medical care.</p><p><strong>Methods: </strong>Between June 2022 and January 2023 eight semi-structured focus groups (FGs) were conducted with general practitioners (GPs) recruited from practices in the region of Halle/Leipzig, Germany, via email and postal mail, as well as with university hospital physicians from Halle and Erlangen, recruited via email. To conduct the FGs, a topic guide and a video stimulus were developed, including a definition of AI and three potential applications in medical care. Transcribed FGs and field notes were analyzed using qualitative content analysis.</p><p><strong>Results: </strong>39 physicians participated in eight FGs, including 15 GPs [80% male, mean age 44 years, standard deviation (SD) 10.4] and 24 hospital physicians (67% male, mean age 42 years, SD 8.6) from specialties including anesthesiology, neurosurgery, and occupational medicine. Physicians' statements were categorized into four themes: acceptance, physician-patient relationship, AI development and implementation, and application areas. Each theme was illustrated with selected participant quotations to highlight key aspects. Key factors promoting AI acceptance included human oversight, reliance on scientific evidence and non-profit funding. Concerns about AI's impact on the physician-patient relationship focused on reduced patient interaction time, with participants emphasizing the importance of maintaining a human connection. Key prerequisites for AI implementation included legal standards, like clarifying responsibilities and robust data protection measures. Most physicians were skeptical about the use of AI in tasks requiring empathy and human attention, like psychotherapy and caregiving. Potential areas of application included early diagnosis, screening, and repetitive, data-intensive processes.</p><p><strong>Conclusion: </strong>Most participants expressed openness to the use of AI in medicine, provided that human oversight is ensured, data protection measures are implemented, and regulatory barriers are addressed. Physicians emphasized interpersonal relationships as irreplaceable by AI. Understanding physicians' perspectives is essential for developing effective and practical AI applications for medical care settings.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1616827"},"PeriodicalIF":3.2,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12301400/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144735857","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":"Exploring Mexican psychotherapist's attitudes towards knowledge and use of serious games in clinical practice.","authors":"Marcela Tiburcio, Nora Angélica Martínez-Vélez, Rosalía Pilar Bernal-Pérez, Jessica Huss, Christiane Eichenberg","doi":"10.3389/fdgth.2025.1584171","DOIUrl":"10.3389/fdgth.2025.1584171","url":null,"abstract":"<p><strong>Objective: </strong>To explore the perceptions, attitudes, and use of serious games (SG) in psychotherapeutic intervention from the perspective of psychotherapists in Mexico.</p><p><strong>Methods: </strong>An online survey was conducted using snowball sampling through social media. The participation of psychotherapists was sought, regardless of their theoretical approach. The questionnaire, available through SurveyMonkey, explored demographics, experience with electronic devices and computer games, experience with SG, and attitudes toward SG use. Two hundred and sixteen health professionals participated, yielding 135 (62.5%) complete questionnaires; 74.1% of the respondents were women. Participants had an average age of 35 (SD + 11) and 9.5 (SD + 8.5) years of clinical experience. The most common psychotherapeutic approach was cognitive-behavioral (66.7%).</p><p><strong>Results: </strong>Nearly all respondents used a technological modality as part of psychotherapy but only nine (6.6%) reported using SG. Participants considered that SG could be used to treat anxiety and emotional and impulse control disorders with a mild to moderate degree of severity. A total of 4.8% of therapists showed unfavorable attitudes and 9.8% highly favorable attitudes towards SG; no statistically significant differences were observed by sex, age, years of experience, or psychotherapeutic approach. Although SG are a little-known care modality in Mexico, some potential benefits have been acknowledged, particularly in the care of adolescents and young people, for specific skills training. More information on their advantages and disadvantages should be made available to those seeking care and health professionals.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1584171"},"PeriodicalIF":3.2,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12289558/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144735790","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":"LarynxFormer: a transformer-based framework for processing and segmenting laryngeal images.","authors":"Rune Mæstad, Abdul Hanan, Haakon Kristian Kvidaland, Hege Clemm, Reza Arghandeh","doi":"10.3389/fdgth.2025.1459136","DOIUrl":"10.3389/fdgth.2025.1459136","url":null,"abstract":"<p><p>Manual diagnostic methods for assessing exercise-induced laryngeal obstruction (EILO) contain human bias and can lead to subjective decisions. Several studies have proposed machine learning methods for segmenting laryngeal structures to automate and make diagnostic outcomes more objective. Four state-of-the-art models for laryngeal image segmentation are implemented, trained, and compared using our pre-processed dataset containing laryngeal images derived from continuous laryngoscopy exercise-test (CLE-test) data. These models include both convolutional-based and transformer-based methods. We propose a new framework called LarynxFormer, consisting of a pre-processing pipeline, transformer-based segmentation, and post-processing of laryngeal images. This study contributes to the investigation of using machine learning as a diagnostic tool for EILO. Furthermore, we show that a transformer-based approach for larynx segmentation outperforms conventional state-of-the-art image segmentation methods in terms of performance metrics and computational speed, demonstrating up to 2x faster inference time compared to the other methods.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1459136"},"PeriodicalIF":3.2,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12289634/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144735856","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":"An evidence-based digital prescription opioid safety toolkit for national dissemination: co-design and user testing.","authors":"Alex Waddell, Jessica L Watterson, Dhruv Basur, Christopher Owen Prawira, Louisa Picco, Tina Lam, Patrick Olivier, Joshua Paolo Seguin, Liam Kay, Suzanne Nielsen","doi":"10.3389/fdgth.2025.1600836","DOIUrl":"10.3389/fdgth.2025.1600836","url":null,"abstract":"<p><strong>Introduction: </strong>Australia has one of the highest rates of opioid prescribing and prescription opioid-related harm in the world. Although effective for pain relief, the use of prescription opioids is a leading cause of preventable morbidity and mortality. Barriers exist for consumers identifying their own risk factors, accessing naloxone (opioid overdose antidote) and overdose prevention education. This study aimed to co-design a digital Opioid Safety Toolkit for national dissemination through pharmacies to encourage three consumer opioid safety behaviours: (1) uptake of naloxone, (2) creating a safety plan, and (3) discussing their use of opioids, including any concerns with their healthcare professional.</p><p><strong>Methods: </strong>The digital Toolkit was co-designed and developed using a novel approach to digital health intervention design combining the Theoretical Domains Framework (TDF) and Double-Diamond design process. Co-design involved a series of seven iterative workshops with consumers (4) and professionals (3). Workshops focused on identifying factors influencing opioid safety behaviours, exploring design preferences, sense-checking, and ideation of the user flow. User testing was conducted with the penultimate version of the Toolkit.</p><p><strong>Results: </strong>13 consumers with lived experience of prescription opioid use and 14 professionals including prescribers, pharmacists, pain specialists, researchers and consumer advocates participated in up to three separate workshops. 15 consumers participated in user testing interviews. Analysis of workshops identified factors promoting safety behaviours including increased public awareness of naloxone, understanding personal risk (TDF domain of Knowledge); healthcare professional's role in education and consumers' experience of stigma (Social/professional role and identity); use of conversational aids to scaffold conversations, material resources and data ownership (Environment, context and resources). User testing elicited feedback pertaining to the information and resources on the website and the overall user interface and experience.</p><p><strong>Discussion: </strong>The Toolkit was co-designed with consumers and professionals to facilitate opioid safety behaviours. The Toolkit includes evidence-based information, tools for risk assessment and screening, opioid use monitoring, conversation aids, and a safety plan. The Toolkit is being disseminated nationally through Australian pharmacies following a randomized controlled trial that demonstrated the Toolkit promotes safety behaviours, is easy to use and acceptable to those with lived experience of prescription opioid use and professionals.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1600836"},"PeriodicalIF":3.2,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12291169/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144735788","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":"Rare diseases: ethical challenges in the era of digital health.","authors":"Liesbeth Siderius, Sahan Damsiri Perera, Lina Jankauskaite, Anjan Bhattacharya, Paulo Gonçalves","doi":"10.3389/fdgth.2025.1539841","DOIUrl":"10.3389/fdgth.2025.1539841","url":null,"abstract":"<p><p>To improve the health and wellbeing outcomes of people with rare conditions, it is necessary to integrate all aspects of health and wellbeing. Digital health technologies can appropriately capture and share harmonised data between care providers and the individuals concerned. The quality of digital health is dependent on defined data points reflecting the actual medical and societal situation and register changes when new diagnostics or therapies become available. The life experiences of individuals living with a condition, individually or as a group, are underrepresented in the digitalising world. This narrative review addresses rare conditions as an entity, public health strategies, digital health opportunities, and ethical considerations. The challenge is illustrated by comparing data gathered by manually selected data points with advanced artificial intelligence systems. In this new digital era, we consider the philosopher Kant's notion of noumena: \"Only individuals with rare disabling conditions can genuinely convey the reality of living with those conditions\". In conclusion, there is a pressing demand to embed the needs and experiences of people in all new technologies.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1539841"},"PeriodicalIF":3.2,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12283590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144700526","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":"Transfer learning with class activation maps in compositions driving plaque classification in carotid ultrasound.","authors":"Georgia D Liapi, Christos P Loizou, Maura Griffin, Constantinos S Pattichis, Andrew Nicolaides, Efthyvoulos Kyriacou","doi":"10.3389/fdgth.2025.1484231","DOIUrl":"10.3389/fdgth.2025.1484231","url":null,"abstract":"<p><strong>Introduction: </strong>Carotid B-mode ultrasound (U/S) imaging provides more than the degree of stenosis in stroke risk assessment. Plaque morphology and texture have been extensively investigated in U/S images, revealing plaque components, such as juxtaluminal black areas close to lumen (JBAs), whose size is linearly related to the risk of stroke. Convolutional neural networks (CNNs) have joined the battle for the identification of high-risk plaques, although the ways they perceive asymptomatic (ASY) and symptomatic (SY) plaque features need further investigation. In this study, the objective was to assess whether class activations maps (CAMs) can reveal which U/S grayscale-(GS)-based plaque compositions (lipid cores, fibrous content, collagen, and/or calcified areas) <i>influence</i> the model's understanding of the ASY and SY cases.</p><p><strong>Methods: </strong>We used Xception via transfer learning, as a base for <i>feature extraction</i> (all layers frozen), whose output we fed into a new dense layer, followed by a new classification layer, which we trained with standardized B-mode U/S longitudinal plaque images. From a total of 236 images (118 ASY and 118 SY), we used 168 in training (84 ASY and 84 SY), 22 in internal validation (11 ASY and 11 SY), and 46 in testing (23 ASY and 23 SY).</p><p><strong>Results: </strong>In testing, the model reached an accuracy, sensitivity, specificity, and area under the curve at 80.4%, 82.6%, 78.3%, and 0.80, respectively. Precision and the F1 score were found at 81.8% and 80.0%, and 79.2% and 80.9%, for the ASY and SY cases, respectively. We used faster-Score-CAM to produce a <i>heatmap</i> for each tested image, quantifying each plaque composition area overlapping with the heatmap to find compositions areas related to ASY and SY cases. Dark areas (GS ≤ 25) or JBAs (whose presence was verified priorly, by an experienced vascular surgeon) were found <i>influential</i> for the understanding of both the ASY and the SY plaques. Calcified areas, fibrous content, and lipid cores, <i>together</i>, were more related to ASY plaques.</p><p><strong>Conclusions: </strong>These findings indicate the need for further investigation on how the GS ≤ 25 plaque areas affect the learning process of the CNN models, and they will be further validated.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1484231"},"PeriodicalIF":3.2,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12283640/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144700527","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":"Ethical dilemmas and the reconstruction of subjectivity in digital mourning in the age of AI: an empirical study on the acceptance intentions of bereaved family members of cancer patients.","authors":"Kun Fu, Chenxi Ye, Zeyu Wang, Miaohui Wu, Zhen Liu, Yuan Yuan","doi":"10.3389/fdgth.2025.1618169","DOIUrl":"10.3389/fdgth.2025.1618169","url":null,"abstract":"<p><strong>Introduction: </strong>With the rapid advancement of AI replication, virtual memorials, and affective computing technologies, digital mourning has emerged as a prevalent mode of psychological reconstruction for families coping with the loss of terminally ill patients. For family members of cancer patients, who often shoulder prolonged caregiving and complex ethical decisions, this process entails not only emotional trauma but also profound ethical dilemmas.</p><p><strong>Methods: </strong>This study adopts the Unified Theory of Acceptance and Use of Technology (UTAUT) as its analytical framework, further integrating Foucauldian subjectivation theory and emotional-cognitive models. A structural path model was constructed to examine how ethical identification and grief perception influence the acceptance of AI-based digital mourning technologies. A total of 129 valid survey responses were collected and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM).</p><p><strong>Results: </strong>The findings indicate that performance expectancy, effort expectancy, social influence, and ethical concern significantly predict users' intention to adopt digital mourning technologies. Additionally, grief perception not only influences adoption intention but also directly affects actual usage behavior.</p><p><strong>Discussion: </strong>This study highlights that the acceptance of AI-based digital mourning technologies extends beyond instrumental rationality. It is shaped by the interplay of emotional vulnerability and moral tension. The results contribute to a deeper understanding of the ethical and psychological dimensions of posthumous AI applications and provide valuable insights for future human-AI interaction design, digital commemoration systems, and the governance of end-of-life technologies.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1618169"},"PeriodicalIF":3.2,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12278142/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144683731","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":"Bridging AI innovation and healthcare: scalable clinical validation methods for voice biomarkers.","authors":"Agnieszka Ewa Krautz, Jörg Langner, Florian Helmhold, Julia Volkening, Alina Hoffmann, Claudio Hasler","doi":"10.3389/fdgth.2025.1575753","DOIUrl":"10.3389/fdgth.2025.1575753","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) in voice biomarker analysis presents a transformative opportunity for objective and non-invasive diagnostics in healthcare. However, clinical adoption remains limited due to challenges such as data scarcity, model generalizability, and regulatory hurdles. This perspective article explores effective and scalable methods for clinical validation of voice biomarkers, emphasizing the importance of proprietary technology, high-quality, diverse datasets, strong clinical partnerships, and regulatory compliance. We propose a multifaceted approach leveraging proprietary AI technology (Musicology AI) to enhance voice analysis, large-scale data collection initiatives to improve model robustness, and medical device certification to ensure clinical applicability. Addressing technical, ethical, and regulatory challenges is crucial for establishing trust in AI-driven diagnostics. By combining technological innovation with rigorous clinical validation, this work aims to bridge the gap between research and real-world implementation, paving the way for AI-powered voice biomarkers to become a reliable tool in digital healthcare.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1575753"},"PeriodicalIF":3.2,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12267164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144661178","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":"An AI-mediated framework for recursive learning: transforming individual experiences into organizational knowledge and autonomous engagement in elderly care.","authors":"Naoki Mitsugi, Koki Ijuin, Chiaki Oshiyama, Eri Hara, Takuichi Nishimura","doi":"10.3389/fdgth.2025.1529072","DOIUrl":"10.3389/fdgth.2025.1529072","url":null,"abstract":"<p><strong>Introduction: </strong>The elderly care industry in Japan is currently facing significant challenges, including chronic labor shortages, high staff turnover, and low levels of IT utilization. Effective human resource development is crucial to address these issues.</p><p><strong>Methods: </strong>In this study, we propose an AI-supported method to facilitate both individual and organizational development in elderly care settings. This approach integrates Kolb's experiential learning theory and Huber's organizational learning framework. Staff members use digital tools to record their daily observations, which are then processed by an AI system. The AI organizes and visualizes the data to promote structured reflection and behavioral improvement.</p><p><strong>Results: </strong>The visualized data serve as a basis for personalized guidance provided by managers and senior staff, tailored to each employee's personality and situation. This process fosters cooperation and knowledge sharing within the organization. The demonstration study showed that AI-supported reflection enhanced organizational collaboration, improved work procedures, and increased staff's goal awareness and proactive behavior.</p><p><strong>Discussion: </strong>Furthermore, individual experiences were transformed into structured, purpose-oriented organizational knowledge through AI-driven analysis and were utilized as manuals. The method ensures cost efficiency and adaptability for small-scale care facilities through the use of digital infrastructure. It provides a practical and scalable solution to enhance care quality and workforce development.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1529072"},"PeriodicalIF":3.2,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12267155/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144661177","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}