DIGITAL HEALTH最新文献

{"title":"Do engagement metrics reflect educational value in short-form diabetes videos?","authors":"Varshitha Hantur Dinakar, Neeraj Singh, Monika Srivastav","doi":"10.1177/20552076261481592","DOIUrl":"https://doi.org/10.1177/20552076261481592","url":null,"abstract":"","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261481592"},"PeriodicalIF":3.9,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13490780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intervention structure and effectiveness in digital health interventions for childhood and adolescent obesity: A scoping review.","authors":"Sung-Hyo Seo, Yujin Kim, Yoolwon Jeong","doi":"10.1177/20552076261480966","DOIUrl":"https://doi.org/10.1177/20552076261480966","url":null,"abstract":"<p><strong>Background: </strong>Digital health interventions for childhood and adolescent obesity have shown mixed effectiveness, with prior studies largely focusing on stand-alone mobile-based approaches. Limited attention has been given to how the structural characteristics of interventions influence outcomes. This study aimed to examine the structural characteristics of contemporary digital health interventions, including wearable devices, artificial intelligence, web-based platforms, exergames, and virtual or augmented reality, and to assess how these factors relate to intervention effectiveness.</p><p><strong>Methods: </strong>We conducted a scoping review of digital health interventions beyond stand-alone mobile-based approaches for obesity prevention and management among children and adolescents, following PRISMA-ScR guidelines. Interventions were analyzed using a structured framework across three dimensions: modality, behavioral mechanisms, and integration, along with family engagement and digital role.</p><p><strong>Results: </strong>Of the twenty-three studies included in the review, ten (43.4%) showed significant or partially significant effects. Interventions incorporating exergame-based modalities, behavioral activation, social support, and family engagement showed higher effectiveness. Hybrid-integrated interventions demonstrated greater effectiveness compared to fully digital or parallel approaches. In contrast, interventions using digital components primarily as adjunct tools showed lower effectiveness.</p><p><strong>Conclusion: </strong>The effectiveness of digital health interventions cannot be explained by modality alone but is shaped by how interventions are structured and integrated. Interventions embedded within interconnected digital, social, and care delivery systems appear more effective, highlighting the importance of system-level design in obesity prevention and management. Future digital health interventions should be designed as adaptive, integrated systems that leverage data and coordinated support across family, school, and healthcare contexts to enhance real-world effectiveness.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261480966"},"PeriodicalIF":3.9,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13490797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and preliminary evaluation of a mobile-based situational simulation retraining system for patients undergoing peritoneal dialysis: A pilot study.","authors":"Jun-Ming Su, Chia-Ching Liao, I-Kuan Wang, Chih-Jung Wu, Ya-Fang Ho","doi":"10.1177/20552076261481014","DOIUrl":"https://doi.org/10.1177/20552076261481014","url":null,"abstract":"<p><strong>Objective: </strong>Peritoneal dialysis (PD) is a home-based therapy that requires sustained technical competence; however, technique degradation and infection risk may occur over time. This pilot study aimed to examine the preliminary effects of a developed mobile-based situational simulation peritoneal dialysis training system (Mbs-PDTS) as a retraining intervention for adult patients undergoing PD.</p><p><strong>Methods: </strong>An exploratory, two-arm, open-label cluster trial was conducted at a university hospital in Taiwan, with PD nurses serving as the unit of allocation. The intervention group received Mbs-PDTS in addition to usual care, whereas the control group received usual care alone. PD-related knowledge and technical skills were assessed at baseline and at 1 and 2 months. Infection-related outcomes, including peritonitis and PD catheter-related infection, were monitored over a 6-month follow-up. Linear mixed-effects models, generalized estimating equations, and exploratory time-to-event analyses were used.</p><p><strong>Results: </strong>Thirty participants completed the study, with 15 in each group. Compared with usual care, the Mbs-PDTS intervention was associated with significant group × time interactions for PD-related knowledge and technical skills (both p < 0.001), with improvements observed in the intervention group. No statistically significant differences were observed in infection-related outcomes. Given the small number of infection-related events, these analyses were interpreted descriptively.</p><p><strong>Conclusions: </strong>This pilot study provides preliminary evidence that the Mbs-PDTS may improve PD-related knowledge and technical skills in adult patients undergoing PD. Larger multicenter studies with longer follow-up are needed to confirm its effects and evaluate its potential impact on infection-related outcomes.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261481014"},"PeriodicalIF":3.9,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13490787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TextRank-based healthcare big data analysis system for text network analysis and trend phase identification.","authors":"Soo-Kyoung Lee, Jinhyun Ahn","doi":"10.1177/20552076261480208","DOIUrl":"https://doi.org/10.1177/20552076261480208","url":null,"abstract":"<p><strong>Purpose: </strong>The demand for scalable healthcare knowledge extraction is increasing. To address this demand, this study developed a TextRank-based big data analysis system focused on reusable, system-level implementation for the automation of keyword extraction, text network analysis, and trend phase identification from large-scale textual data.</p><p><strong>Methods: </strong>The proposed system was developed based on a system engineering framework that included requirement analysis, modular architecture design, and system implementation. Healthcare-related textual documents were collected and preprocessed using domain-specific normalisation and noise-reduction procedures. Keywords were extracted using a graph-based TextRank algorithm, and weighted keyword co-occurrence networks were constructed for each analysis period. Trend phase identification was performed by calculating the weighted Jaccard similarity between consecutive periods and detecting structural changes in keyword distributions. All analytical components were integrated into an end-to-end healthcare big data analysis system with interactive visualisation capabilities.</p><p><strong>Results: </strong>The proposed system successfully extracted representative keywords, constructed keyword co-occurrence networks, and identified distinct trend phases reflecting changes in healthcare research topics over time. The system automated the analytical workflow from keyword extraction to trend phase identification and provided visualizations to support the exploration and interpretation of healthcare research trends.</p><p><strong>Conclusion: </strong>The results confirmed that the proposed system provides a scalable, interpretable, and reusable platform for continuous healthcare knowledge monitoring, supporting data-driven research, policy formulation, and strategic decision-making. The automated functions of the system thereby enable researchers to efficiently monitor evolving healthcare topics and discover meaningful insights over time.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261480208"},"PeriodicalIF":3.9,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487071/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148800562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early detection of infectious diseases using wearable sensor data through personalized baseline deviation modelling.","authors":"Fidel Cacheda, Víctor Carneiro, Marco A Álvarez, Manuel F López-Vizcaíno","doi":"10.1177/20552076261477919","DOIUrl":"https://doi.org/10.1177/20552076261477919","url":null,"abstract":"<p><strong>Objective: </strong>Early detection of infectious diseases using physiological and behavioural signals from wearable devices could enable earlier intervention and help reduce disease transmission. This study proposes and evaluates a framework specifically designed for sequential early-warning aimed at detecting infectious disease episodes prior to clinical diagnosis.</p><p><strong>Methods: </strong>In this retrospective observational cohort study, we used the Evidation 2019-2020 Fitbit dataset to formulate infection detection as an episode-level prediction problem. We designed augmented features that capture short-term deviations from each individual's healthy baseline over sliding windows and evaluated several machine learning models. The framework incorporates probability calibration, validation-based threshold selection, and an optional persistent two-day alarm rule to reduce false-positive alerts.</p><p><strong>Results: </strong>Experiments on data from 435 participants showed that personalized deviation-based features substantially outperformed basic wearable features. The best-performing configuration achieved an episode-level F1-score of 0.784 with an Average Earliness (AE) of 0.555, corresponding to approximately 5.5 days before diagnosis. Additionally, combining step and sleep features provided a favourable trade-off between timeliness (AE = 0.69) and accuracy (F1 = 0.75).</p><p><strong>Conclusions: </strong>Personalized baseline-deviation features, combined with calibrated probabilities and persistent alarm mechanisms, enable accurate and timely early detection of infectious disease episodes from wearable data. The results indicate that recent individualized baselines and step-derived signals provide the most robust predictive information, supporting the potential of wearable devices as scalable tools for population-level infectious disease surveillance.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261477919"},"PeriodicalIF":3.9,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487130/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a deep learning-based model for estimating stroke volume and blood pressures simultaneously using electrocardiogram and photoplethysmogram.","authors":"Hyun-Lim Yang, Seong-A Park, Hyeonhoon Lee, Chul-Woo Jung, Ho-Geol Ryu, Hyung-Chul Lee","doi":"10.1177/20552076261479434","DOIUrl":"https://doi.org/10.1177/20552076261479434","url":null,"abstract":"<p><strong>Background: </strong>Cardiac output (CO) is essential for systemic oxygen delivery, but gold-standard measurement using pulmonary artery catheter thermodilution remains invasive. Arterial pressure-based cardiac output (APCO) devices are widely used but still require arterial catheterization. We developed and validated a deep learning (DL) model that simultaneously estimates stroke volume (SV), systolic blood pressure (SBP), and diastolic blood pressure (DBP) using electrocardiogram (ECG) and photoplethysmogram (PPG).</p><p><strong>Methods: </strong>We retrospectively analyzed 881 surgical cases at Seoul National University Hospital (Aug 2016 - Dec 2020) with simultaneous ECG, PPG, arterial blood pressure waveform (ABP), SV measured by the APCO devices, and demographics. After signal-quality rules and arterial-line plausibility filters, 20-s ECG/PPG segments were paired SV to form samples. A DL model using ECG, PPG, the first and second derivatives of PPG, demographic variables, and ECG-derived features simultaneously estimated SV, SBP, and DBP. Model performance was evaluated in a temporal hold-out cohort using error metrics, Bland-Altman analysis, and 10-min interval trend analysis. SBP and DBP performance was assessed against ISO 81060-3:2022 criteria.</p><p><strong>Results: </strong>The test set comprised 128 cases (31,637 segments). Our DL model achieved a mean absolute error of 10.761 mL/beat and percentage limits of agreement ranging from -26.905% to 29.563%. SBP and DBP showed mean errors of 0.661 and 1.439 mmHg, with standard deviations of 9.716 and 6.684 mmHg, respectively, meeting the ISO 81060-3:2022 criteria.</p><p><strong>Conclusion: </strong>A DL model using ECG/PPG and demographics can estimate SV with clinically useful performance while simultaneously predicting SBP/DBP, potentially expanding continuous hemodynamic monitoring to non-arterial-line cases.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261479434"},"PeriodicalIF":3.9,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487053/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dietary micronutrients, whole food patterns, and restless legs syndrome in coronary heart disease: A dual dietary profiling machine learning analysis using NHANES data.","authors":"Haoyang Hu, Shanshan Kong, Zekai Yu, Jingxi Wu, Fei Yang","doi":"10.1177/20552076261480878","DOIUrl":"https://doi.org/10.1177/20552076261480878","url":null,"abstract":"<p><strong>Background: </strong>The relationships between dietary patterns and restless legs syndrome (RLS) risk in patients with coronary heart disease (CHD) are poorly understood. This study aimed to identify dietary factors associated with RLS risk in this specific population.</p><p><strong>Methods: </strong>We analyzed NHANES data (2005-2018) using two complementary dietary representations: micronutrient profiles and food-group profiles derived from the MyPyramid Equivalents Database linked to NHANES dietary recalls. Six machine-learning models were developed using Boruta for feature selection and SMOTE to address class imbalance. Model robustness was further evaluated through temporal validation, and SHAP and LIME were used for model interpretation.</p><p><strong>Results: </strong>Random forest demonstrated the highest predictive performance in both micronutrient and food-group models. SHAP analysis indicated that Lycopene, Caffeine, Alpha-carotene, Vitamin C, Food folate, and Magnesium showed contributions toward lower predicted RLS probability, whereas Calcium, Moisture, and Vitamin B1 showed contributions toward higher predicted RLS probability. These model-derived directions represent associations rather than causal effects. In the food-group model, total red and orange vegetables, total vegetables, and white potatoes were inversely associated with RLS. Conversely, Milk, Meat, and Added Sugars were positively associated with predicted RLS probability.</p><p><strong>Conclusion: </strong>Random forest models effectively identify dietary risk factors for RLS in CHD patients. Nutrient-dense dietary patterns, particularly those characterized by higher consumption of specific vegetables and antioxidant-related nutrients, were associated with lower predicted RLS probability, whereas higher consumption of milk, meat, and added sugars was associated with higher predicted RLS probability. These findings suggest that dietary patterns characterized by specific nutrient and food-group profiles may be associated with RLS risk among CHD patients and warrant further investigation in independent prospective studies.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261480878"},"PeriodicalIF":3.9,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487140/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a pragmatic multidisciplinary protocol to validate a contactless fall detection system for older adults in long-term care facilities.","authors":"Chang-Chun Chen, Alisha H Johnson, Marjorie Skubic, Shu-Fen Wung","doi":"10.1177/20552076261478219","DOIUrl":"https://doi.org/10.1177/20552076261478219","url":null,"abstract":"<p><strong>Background: </strong>Falls among residents of long-term care facilities are associated with substantial morbidity, mortality, and healthcare utilization. Despite the availability of numerous fall detection technologies, practical protocols for evaluating performance in real-world care environments remain limited.</p><p><strong>Objective: </strong>To develop a pragmatic and replicable protocol for validating contactless fall detection systems in long-term care environments.</p><p><strong>Methods: </strong>This article presents a protocol that combines structured testing by trained stunt actors, continuous real-world monitoring, and predefined procedures for event verification and classification to evaluate system performance across fall and non-fall events relevant to older adults.</p><p><strong>Protocol description: </strong>The protocol consists of three phases: pre-implementation assessment, system implementation and training, and system verification. It incorporates site assessment, sensor deployment, scripted testing, continuous monitoring, event verification, and predefined analytical procedures under real-world conditions.</p><p><strong>Conclusion: </strong>This protocol provides an approach for evaluating contactless fall detection systems in long-term care environments. Future studies are needed to apply the protocol across different sensor platforms and care settings to evaluate reproducibility, generalizability, and operational feasibility.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261478219"},"PeriodicalIF":3.9,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487066/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A non-fungible token (NFT)-Based framework for antenatal care in resource-constrained settings.","authors":"Khulekani Sibanda, Patrick Ndayizigamiye, Hossana Twinomurinzi","doi":"10.1177/20552076261478842","DOIUrl":"https://doi.org/10.1177/20552076261478842","url":null,"abstract":"<p><strong>Background: </strong>In many low-resource settings, maternal health records are paper-based, fragmented, and predominantly controlled by institutions. These conditions limit patient agency, disrupt continuity of care, and constrain the efficiency of service delivery.</p><p><strong>Objective: </strong>This study examines the potential of blockchain technology, specifically non-fungible tokens (NFTs), to support a patient-centred approach to antenatal and postnatal record management.</p><p><strong>Methods: </strong>Drawing on Actor-Network Theory (ANT), we conducted a qualitative case study involving eight semi-structured stakeholder interviews at primary healthcare facilities in Zimbabwe. The themes that emerged from the qualitative enquiry were triangulated with observational data and findings from a previously conducted and published systematic literature review by the authors. This multi-method design enabled the exploration of both technical and socio-organisational factors shaping maternal record practices.</p><p><strong>Results: </strong>The study identified persistent challenges, including record duplication, limited interoperability, weak referral mechanisms, and inadequate processes for patient consent and data control. To address these gaps, an NFT-based conceptual architectural framework is proposed that tokenises record ownership and consent for data sharing. This framework has the potential to enable patients to exercise greater agency by controlling access to their data while allowing providers to be granted secure, time-bound permissions tailored to their clinical needs. NFTs also have the potential to reconfigure socio-technical networks by aligning stakeholder interests, strengthening patient agency, and supporting sustainable mobilisation across the health system.</p><p><strong>Conclusions: </strong>The proposed architectural framework is intended to position women as active participants in their maternal care pathways and to strengthen continuity across encounters. By embedding ownership and consent into digital records, blockchain-enabled management offers a potential pathway to more secure, equitable, and patient-centred maternal health systems in low-resource contexts. Empirical validation through pilot implementation and stakeholder co-design is essential before deployment.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261478842"},"PeriodicalIF":3.9,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487137/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ability meets motivation: A TAM-Integrated approach using informatics competency and self-efficacy to explain variance in AI clinical system adoption: Cross-sectional study.","authors":"Nader Alnomasy, Sudharani Banappagoudar, Habib Alrashedi, Sharifah Alsayed, Razan Alsayed, Ebtsam Abou Hashish","doi":"10.1177/20552076261479419","DOIUrl":"https://doi.org/10.1177/20552076261479419","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI)-enabled clinical systems are integrated into nursing education and healthcare, yet nursing students remain inadequately prepared to use them. Although the Technology Acceptance Model (TAM) has been applied to explain technology adoption, limited evidence has examined informatics competency & digital self-efficacy as antecedents influencing AI adoption through separate acceptance pathways.</p><p><strong>Objective: </strong>To develop and validate an extended Technology Acceptance-Competency Structural Model (TAC-SM) by examining the direct & indirect effects of informatics competency & digital self-efficacy on undergraduate nursing students' behavioral intention to adopt AI-enabled clinical systems through perceived ease of use and perceived usefulness.</p><p><strong>Methods: </strong>A cross-sectional study included undergraduate nursing students at the College of Nursing, University of Ha'il, Saudi Arabia. Of 426 questionnaires received, 10 were excluded after screening, yielding a final sample of 416. Participants completed the Competency in Nursing Informatics & Computer Applications Scale, Digital Task Self-Efficacy Scale, and adapted TAM measures. Confirmatory factor analysis, structural equation modelling, and bootstrapped mediation analyses with 5,000 resamples were performed.</p><p><strong>Results: </strong>The TAC-SM demonstrated satisfactory model fit (χ²/df = 2.11, CFI = 0.94, TLI = 0.93, RMSEA = 0.062, SRMR = 0.041). Informatics competency was positively associated with perceived ease of use (β = 0.42, p < .001), whereas digital self-efficacy was positively associated with perceived usefulness (β = 0.47, p < .001). Perceived usefulness (β = 0.55, p < .001) and perceived ease of use (β = 0.21, p < .01) were directly associated with behavioral intention. Informatics competency and digital self-efficacy demonstrated significant indirect associations with behavioral intention through the proposed TAM pathways, with the strongest indirect pathway observed for digital self-efficacy → perceived usefulness → behavioral intention (β = 0.259, p < .001). Students with prior informatics training reported higher scores across the study constructs.</p><p><strong>Conclusion: </strong>The TAC-SM demonstrates that technical competence & motivational confidence influence AI adoption through distinct but complementary pathways. Integrating informatics competency & digital self-efficacy into nursing curricula may strengthen students' readiness to adopt AI-enabled clinical systems.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261479419"},"PeriodicalIF":3.9,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487126/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148801360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}