{ "version": "https://jsonfeed.org/version/1", "title": "Digital Health Evidence (most recently added)", "home_page_url": "http://www.digitalhealthevidence.net/", "feed_url": "http://www.digitalhealthevidence.net/feed/added/json", "description": "The most recently added Digital Health evidence", "icon": "http://www.digitalhealthevidence/logo_horizontal_small.png", "author": { "name": "James BonTempo", "url": "https://www.linkedin.com/in/jamesbontempo/" }, "items": [ { "id": "http://doi.org/10.2147/JMDH.S605694", "content_html": "Suboptimal glycemic control remains a major challenge among adults with type 2 diabetes (T2D). Illness perceptions may influence diabetes self-management behaviors and glycemic control. To evaluate the effects of a nurse-led diabetes perception intervention delivered via a mobile messaging platform (LINE) on glycemic control, illness perceptions, and patient satisfaction among adults with T2D and poorly controlled glucose. A randomized controlled trial was conducted among 102 adults aged 30-59 years with T2D and poorly controlled glucose [HbA1c 7.5-9.0% or FPG ≥130 mg/dL]. Participants were randomly assigned to either a nurse-led diabetes perception intervention delivered via LINE plus standard care (n = 51) or standard care alone (n = 51). HbA1c, FPG, and patient satisfaction were assessed at baseline and week 13, and illness perceptions at baseline, week 6, and week 13. Data were analyzed using analysis of covariance and repeated-measures analysis of variance. Baseline characteristics were comparable between groups. At week 13, after adjustment for baseline values, the intervention group demonstrated significantly lower HbA1c (7.26% vs 7.91%; mean difference = -0.65%, 95% CI: -1.14 to -0.17; p = 0.008), FPG (123.12 vs 164.36 mg/dL; mean difference = -41.24 mg/dL, 95% CI: -57.37 to -25.11; p <0.001), and illness perception scores (31.90 vs 38.39; mean difference = -6.49, 95% CI: -9.58 to -3.40; p <0.001), together with higher patient satisfaction scores (63.90 vs 58.63; mean difference = 5.27, 95% CI: 2.38 to 8.17; p <0.001), compared with the control group. The nurse-led diabetes perception intervention delivered via LINE significantly improved glycemic control, illness perceptions, and patient satisfaction among adults with T2D and poorly controlled glucose. These findings support the potential integration of this accessible and feasible nursing intervention into diabetes self-management support in clinical practice. ", "url": "http://doi.org/10.2147/JMDH.S605694", "title": "Effects of a Nurse-Led Diabetes Perception Intervention Delivered via a Mobile Messaging Platform (LINE) on Glycemic Control and Patient Outcomes Among Adults with Diabetes and Poorly Controlled Glucose: A Randomized Controlled Trial.", "summary": "Effects of a Nurse-Led Diabetes Perception Intervention Delivered via a Mobile Messaging Platform (LINE) on Glycemic Control and Patient Outcomes Among Adults with Diabetes and Poorly Controlled Glucose: A Randomized Controlled Trial. - Journal of multidisciplinary healthcare", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Jantaramanee, V; Sriyuktasuth, A; Kesornsri, S; Satitvipawee, P; Niramitmahapanya, S", "url": "https://orcid.org/0000-0001-8427-7370" } }, { "id": "http://doi.org/10.2147/JHL.S622179", "content_html": "Ambient artificial intelligence (AI) scribes are increasingly being adopted to address the clinical documentation burden associated with electronic health records (EHRs), which contributes to physician burnout, after-hours work, and reduced patient-clinician interaction. These systems capture clinician-patient conversations and use speech recognition and natural language processing (NLP) to generate draft clinical notes. Newer platforms are evolving into AI clinical copilots with additional functions such as pre-charting, clinical prompting, and safety checks. This article presents a structured, evidence-informed narrative synthesis and leadership analysis of ambient AI scribe implementation in hospital settings. Using Leavitt's Diamond model of organizational change, we examine the interdependent roles of Structure, Technology, People, and Process/Task in shaping successful adoption. Early evidence suggests meaningful reductions in documentation time, increased same-day note completion, and improvements in clinician-reported workload and engagement. However, certain risks and uncertainties remain, including transcription errors, hallucinated or omitted clinical content, variable performance across specialties, accents, and care settings, unresolved medico-legal liability, privacy/data-use concerns, uneven clinician adoption, and unclear short-term financial return on investment (ROI). We argue that the successful implementation of ambient AI scribes depends less on technical capability alone and more on prudent healthcare leadership and multidisciplinary governance. It also requires robust consent and data-protection frameworks, workflow redesign, clinician training, and ongoing monitoring of quality, safety, and well-being outcomes. Our principal contribution is a structured, domain-by-domain implementation framework that translates these requirements into concrete leadership questions, recommendations, accountable owners, and metrics for hospital leaders adopting ambient AI scribes. While ambient AI scribes promise to reduce administrative burden and restore time for patient-centered care, their potential will only be realized through strategically governed adoption aligned with an organization's culture and broader health-system priorities. ", "url": "http://doi.org/10.2147/JHL.S622179", "title": "Implementation of Ambient AI Scribes in Hospitals: Lessons for Healthcare Leadership, Governance, and Change Management.", "summary": "Implementation of Ambient AI Scribes in Hospitals: Lessons for Healthcare Leadership, Governance, and Change Management. - Journal of healthcare leadership", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Zhou, KX; Ng, QX; Tan, HK; Er, EYW; Wu, DT; Nguyen, TT; Gigliotti, J; Siqueira, WL; Makhoul, N", "url": "https://orcid.org/0000-0003-0332-9947" } }, { "id": "http://doi.org/10.1136/bmjoq-2025-004129", "content_html": "Teledermatology is increasingly used to triage urgent suspected skin cancer referrals. A direct-to-surgery pathway allows selected patients to proceed directly to biopsy or excision without a preliminary face-to-face consultation. This study evaluated the safety, efficiency and diagnostic performance of a direct-to-surgery teledermatology pathway within a large National Health Service (NHS) skin cancer service. A service evaluation was conducted at the University Hospitals of North Midlands. All teledermatology referrals received between February 2022 and July 2024 were reviewed. Demographics, pathway intervals, surgical outcomes, cancellations, histopathology and complications were extracted from electronic records. The primary outcome was compliance with the 28-day Faster Diagnosis Standard. Secondary outcomes included compliance with the 62-day referral-to-treatment target, surgical complications, cancellation rates and diagnostic concordance between teledermatology assessment and histopathology. Of 18 587 teledermatology referrals, 5120 were triaged to the direct-to-surgery pathway. Following exclusion of 20 miscoded entries and 1 duplicate record, 5099 patients were included. A total of 4830 patients underwent surgery and 4825 had definitive histopathological diagnoses. The median time from referral to histology reporting was 46 days. Compliance with the 28-day Faster Diagnosis Standard was 99.86% (5092/5099), substantially exceeding the national target of 75%. Among patients diagnosed with melanoma or squamous cell carcinoma, 75.5% (440/583) commenced treatment within the 62-day referral-to-treatment target. Histopathology identified malignant pathology in 35.5% of lesions and premalignant pathology in a further 15.5%. Among lesions with both a recorded teledermatology diagnosis and definitive histology, overall concordance was 41.5% (1113/2679) with fair agreement (Cohen's κ=0.34). The overall complication rate was 1.3%. This large single-centre evaluation demonstrates that a direct-to-surgery teledermatology pathway can safely support high-volume skin cancer surgery while achieving excellent compliance with the Faster Diagnosis Standard. Low complication rates and efficient progression through the diagnostic pathway support the use of teledermatology as an effective risk-stratification tool within contemporary skin cancer services. ", "url": "http://doi.org/10.1136/bmjoq-2025-004129", "title": "From screen to scalpel: safety, efficiency and diagnostic performance of a direct-to-surgery teledermatology pathway.", "summary": "From screen to scalpel: safety, efficiency and diagnostic performance of a direct-to-surgery teledermatology pathway. - BMJ open quality", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Nour, S; Sullivan-McHale, J; Tzatzidou, A; Yap, YT; Nguyen, LTT; Ramamurthy, V; Paul, M; Bisarya, K", "url": "https://orcid.org/0000-0002-8748-695X" } }, { "id": "http://doi.org/10.1136/bmjopen-2026-119389", "content_html": "Type 2 diabetes mellitus (T2DM) affects hundreds of millions of people worldwide. Self-management education is a cornerstone of diabetes care. Digital technology-based interventions have demonstrated short-term benefits; however, their medium-term to long-term effects remain unclear. We will systematically search seven databases (PubMed, Embase, the Cochrane Library, the China National Knowledge Infrastructure [CNKI], the China Biomedical Literature Database [CBM], Wanfang and the China Science Journal Database [VIP]) and three clinical trial registries (ClinicalTrials.gov, Chinese Clinical Trial Registry [ChiCTR] and WHO International Clinical Trials Registry Platform [ICTRP]) from inception to March 2026. We will include randomised controlled trials that provide diabetes self-management education via digital technologies, such as mobile applications, websites, text messaging, remote monitoring or computer programmes. Interventions may be fully digital or hybrid, provided that digital technology is the core delivery method. Eligible studies will involve adults with T2DM or studies in which at least 80% of the participants have T2DM, with a minimum follow-up of 12 months. Primary outcomes will be mortality, diabetes-related complications, hospitalisations, severe hypoglycaemia, quality of life and glycated haemoglobin. Secondary outcomes include fasting plasma glucose, lipids, blood pressure, anthropometric measures and patient-reported outcomes such as self-management behaviours and diabetes distress. Two reviewers will independently screen studies, extract data and assess the risk of bias using the Cochrane Risk of Bias 2 (RoB 2) tool. Where data are sufficient and studies are adequately comparable in terms of participants, interventions, comparators, outcomes and study design, we will perform meta-analyses using Cochrane Review Manager (RevMan) V.5.3 and Stata V.19.0. Heterogeneity will be explored through subgroup analyses and meta-regression. The certainty of evidence will be assessed using the Grading of Recommendations Assessment, Development and Evaluation approach. As this study will synthesise the published data, ethical approval is not required. CRD420251135023. ", "url": "http://doi.org/10.1136/bmjopen-2026-119389", "title": "Medium-term to long-term effect of digital self-management interventions for type 2 diabetes mellitus: protocol of a systematic review.", "summary": "Medium-term to long-term effect of digital self-management interventions for type 2 diabetes mellitus: protocol of a systematic review. - BMJ open", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Zhao, D; Tang, P; Chen, Y; Yang, J", "url": "https://orcid.org/0009-0008-6120-5786" } }, { "id": "http://doi.org/10.1016/j.neunet.2026.109602", "content_html": "Video-based intelligent applications such as autonomous driving, video understanding, and telemedicine rely heavily on the availability of robust and transferable semantic representations. In practical systems, however, video signals transmitted over wireless links are often exposed to severe and unpredictable distortions caused by bandwidth limitations, time-varying noise, and transmission impairments. Under such conditions, high reconstruction quality does not necessarily guarantee the preservation of semantic structures that support downstream reasoning, leading to degraded temporal coherence and poor generalization to unseen tasks. Existing learning-based video transmission and compression methods predominantly optimize pixel-level reconstruction fidelity, while the preservation of general, task-agnostic semantic representations remains insufficiently explored. To address this challenge, we propose a novel end-to-end deep joint source-channel coding (DeepJSCC) framework for video semantic transmission, which explicitly perserves general semantic information for diverse downstream video tasks over wireless channels. Our framework firstly employs a Video-level Semantic Alignment Module (VSAM) to reduce semantic distance between original and reconstructed videos by video-level contrastive learning objectives. Additionally, we propose the Temporal Consistency Learning Module (TCLM) to enhance temporal coherence by predicting future-frame semantic embeddings, enabling more stable temporal dynamics in reconstructed videos. The experiments demonstrate that the proposed framework achieves reconstruction quality comparable to existing DeepJSCC-based and traditional transmission schemes, while delivering consistent performance gains across multiple video downstream tasks without any task-specific fine-tuning. ", "url": "http://doi.org/10.1016/j.neunet.2026.109602", "title": "DeepJSCC for video semantic communication with general semantic preservation.", "summary": "DeepJSCC for video semantic communication with general semantic preservation. - Neural networks : the official journal of the International Neural Network Society", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Li, J; Chen, X; Deng, X", "url": "http://csu.edu.cn" } }, { "id": "http://doi.org/10.1016/j.ejrad.2026.113224", "content_html": "The rapid expansion of medical imaging, increasing demand for rapid reporting, workforce shortages, and advances in digital health infrastructure have facilitated the widespread adoption of teleradiology and outsourced radiology services. These models may improve access, turnaround time, and subspecialty coverage, particularly in regions with limited radiological resources. However, outsourcing also introduces challenges related to quality assurance, radiologist accountability, workload transparency, reporting standardization, appropriateness of imaging, duplicate examinations, and continuity of care. Türkiye has developed a national teleradiology infrastructure that enables remote access to imaging examinations, reporting, teleconsultation, and quality assessment. The Turkish Society of Radiology (TSR) has established guidelines stating that teleradiology should meet the same quality criteria as onsite radiology and should be supported by written quality-control, quality-improvement, and patient-safety plans [2]. This perspective proposes a national quality framework for outsourced and teleradiology services based on five principles: radiologist-level traceability, standardized quality assurance, appropriateness-based imaging, prevention of duplicate examinations, and transparent measurement of patient- and system-level outcomes. Outsourcing itself should not be regarded as inherently detrimental; rather, outsourcing without measurable quality assurance and accountability represents the greater risk. Importantly, this framework is a normative proposal rather than a validated quality-improvement intervention. Components already supported by professional-society guidance are distinguished from proposed national integration and measurement elements, and the framework requires prospective evaluation before any effectiveness claim can be made. ", "url": "http://doi.org/10.1016/j.ejrad.2026.113224", "title": "Who reads the scan? quality, accountability, and appropriateness in the era of outsourced radiology: a perspective from Türkiye.", "summary": "Who reads the scan? quality, accountability, and appropriateness in the era of outsourced radiology: a perspective from Türkiye. - European journal of radiology", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Altunbulak, HI", "url": "http://gmail.com" } }, { "id": "http://doi.org/10.1016/j.jgo.2026.104121", "content_html": "As the number of older cancer survivors (OCS) grows in number, telehealth can enhance their healthcare access, yet uneven digital engagement may exacerbate existing gaps in survivorship care. We aimed to describe digital technology and telehealth use among OCS and assess how sociodemographic and psychosocial factors are related to digital health and telehealth use. We analyzed the Health Information National Trends Survey 7 (HINTS 7; March-September 2024) respondents aged ≥60 years (N = 691; analytic N = 638). Survey-weighted logistic regression models with multiple imputation were used to evaluate relationships between sociodemographic and psychosocial factors and digital engagement and telehealth use. Digital engagement was common but variable among OCS. Most reported frequent internet use (81.5%; n = 571) and smartphone use (78.9%; n = 545), while fewer used tablets (41.2%; n = 285) or participated in telehealth visits in the past year (33.1%; n = 229). However, 63.7% (n = 440) expressed willingness to use telehealth in the future if it were offered. Compared with ≥$100 k, income $50 k-$99 k and < $50 k were associated with lower odds of broadband access (aOR 0.28; 95%CI: 0.11-0.75 and aOR 0.38; 95%CI: 0.17-0.86), and viewing test results online (aOR 0.20; 95%CI: 0.08-0.51 and aOR 0.14; 95% CI: 0.05-0.38). Lower education was associated with reduced desktop/laptop use (aOR 0.30; 95%CI: 0.11-0.79 and aOR 0.24; 95%CI: 0.08-0.71) and provider messaging (aOR 0.34; 95%CI: 0.18-0.64). Black OCS had lower odds of broadband access (aOR 0.43; 95%CI: 0.20-0.95) but higher odds of cellular internet use (aOR 2.70; 95%CI: 1.21-6.05). Depression/anxiety was associated with lower odds of viewing test results (aOR 0.40; 95%CI: 0.19-0.84) but higher odds of technology frustration (aOR 4.44; 95%CI: 1.79-11.03). Female participants had higher odds of willingness to use telehealth (aOR 2.15; 95% CI: 1.19-3.90). Digital engagement among OCS is widespread but uneven, with persistent gaps by income, race, and education. Addressing gaps in access, connectivity, and digital literacy will be essential to ensure improved telehealth-enabled survivorship care. ", "url": "http://doi.org/10.1016/j.jgo.2026.104121", "title": "Connected care in a digital world: Engagement and telehealth use in older cancer survivors.", "summary": "Connected care in a digital world: Engagement and telehealth use in older cancer survivors. - Journal of geriatric oncology", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Odera, JO; Osazuwa-Peters, N; Ramos, K", "url": "http://duke.edu" } }, { "id": "http://doi.org/10.1016/j.ijmedinf.2026.106701", "content_html": "To examine the characteristics, implementation strategies, and reported impacts of Human-in-the-Loop (HITL) processes across the lifecycle of AI-enabled Clinical Decision Support Systems (CDSS), and to propose a reporting checklist for HITL in clinical AI research. HITL is a conceptual and technical approach that integrates human expertise into AI systems, widely recognised for its potential to improve transparency, safety, and contextual relevance in clinical settings. While AI-CDSS tools are increasingly embedded in healthcare, HITL practices remain poorly defined and unevenly implemented. This review aimed to systematically map how HITL is conceptualised and deployed across the lifecycle of AI-CDSS. A comprehensive search was conducted across MEDLINE, Embase, Web of Science, PsycINFO, Google Scholar, and Scopus in August 2024, followed by a manual identification phase concluding in mid-2025. We included primary studies involving healthcare professionals interacting with AI-enabled CDSS in any clinical setting, where HITL processes were described at any stage of the model lifecycle (development, review, oversight, or maintenance). Studies were excluded if they lacked real-world clinical relevance or did not involve clinician interaction with AI systems. Study selection and data extraction were performed by two independent reviewers using Covidence. Extracted data were mapped to four idealised phases of the AI-CDSS lifecycle. Twelve studies met the inclusion criteria. All included clinician involvement during development-primarily through expert annotation and rule-based model design. Fewer studies reported HITL processes during review (n = 11), oversight (n = 0), or maintenance (n = 2) phases. HITL was frequently limited to static or retrospective contributions, with few examples of iterative or real-time engagement. Most studies involved small-scale datasets and a limited number of annotators. Conceptual ambiguity and inconsistent terminology further limited clarity in how HITL was defined or justified. HITL utilisation and reporting predominantly focused on early-stage model development, with limited attention to oversight or iterative refinement. The small scale and narrow scope of clinician involvement may constrain generalisability and impact. To address these gaps, we propose a pragmatic HITL reporting checklist structured around six domains of the AI-CDSS life cycle. Adoption of standardised HITL reporting can support the governance, regulatory compliance, and safe translation of clinical AI systems into routine care. ", "url": "http://doi.org/10.1016/j.ijmedinf.2026.106701", "title": "Human in the loop in AI-enabled clinical decision support: a systematic scoping review and reporting checklist for lifecycle governance.", "summary": "Human in the loop in AI-enabled clinical decision support: a systematic scoping review and reporting checklist for lifecycle governance. - International journal of medical informatics", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Bakker, M; Van Garderen, A; Paget, T; Zhao, L; Naicker, L; Radhakrishnan, A; Bidargarddi, N", "url": "http://sa.gov.au" } }, { "id": "http://doi.org/10.1080/01652176.2026.2720640", "content_html": "Magnetic resonance imaging (MRI) systems continue to grow in number in veterinary and human medicine with higher field strength magnets increasingly available; however, the associated high costs have created healthcare inequities. This technical feasibility study aimed to evaluate a low-cost, portable, and permanent magnet-based 0.05 T low-field system (LF), originally designed for human neuroimaging, for assessing the canine brain. By using 23 canine cadavers, a scanning protocol was developed, consisting of transverse T1-weighted (T1w) and T2-weighted (T2w) sequences, and compared to a 1.5 T (HF) protocol for the visibility of 22 anatomical features. For the purpose of hydrocephalus evaluation, the LF system showed non-inferior detection of the lateral ventricles (LV) and mesencephalic aqueduct on T2w sequences with >90% conditional probability for detecting these features on the LF, given they were present on the HF. For T1w sequences, the LF system had inconclusive non-inferiority for detection of LV with 76.6% conditional probability. In summary, a canine brain scanning protocol was successfully developed for a 0.05 T MRI with preliminary evaluation suggestive that this device can aid with the detection of hydrocephalus. Future in vivo studies are required to evaluate the device's true clinical application. ", "url": "http://doi.org/10.1080/01652176.2026.2720640", "title": "Evaluation of a 0.05 T low-field MRI system for canine brain imaging via comparison with images acquired at 1.5 T field strength: a pilot cadaver study.", "summary": "Evaluation of a 0.05 T low-field MRI system for canine brain imaging via comparison with images acquired at 1.5 T field strength: a pilot cadaver study. - The veterinary quarterly", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Burgers, EM; Miles, S; Veraa, S; O'Reilly, T; van den Broek, R; Najac, C; Lena, B; Webb, A", "url": "http://unknown.com" } }, { "id": "http://doi.org/10.3791/71452", "content_html": "Diabetic foot ulcers (DFUs) remain a major cause of infection, hospitalization, impaired quality of life, and non-traumatic lower-limb amputation among people with diabetes. Effective management requires coordinated prevention, structured foot-risk assessment, pressure offloading, wound care, infection surveillance, patient education, and multidisciplinary follow-up. This narrative review examines the nurse-led and nurse-supported components of contemporary DFU care. Nurses contribute through routine foot and wound assessment, reinforcement of preventive behaviors and treatment adherence, support for offloading, monitoring after debridement and advanced wound therapies, and early recognition of infection, ischemia, osteomyelitis, or clinical deterioration. Patient and caregiver education should be practical, individualized, and reinforced over time. Current evidence most consistently supports improvements in foot-care knowledge, self-management behavior, and healthcare-provider competence, whereas effects on ulcer recurrence, hospitalization, and amputation remain less certain. Digital technologies, including telemedicine, wearable sensors, mobile health platforms, and artificial intelligence-based wound assessment, may improve access to monitoring, communication, and early risk detection. However, their evidence base and clinical readiness vary, and improved monitoring does not necessarily translate into better healing or fewer amputations. Their usefulness depends on patient training, data quality, governance, timely professional review, and integration with safe referral pathways. Digital tools should therefore support, rather than replace, direct clinical assessment and multidisciplinary decision-making. Overall, nursing practice is essential for translating evidence-based DFU management into continuous, coordinated, and patient-centered care. ", "url": "http://doi.org/10.3791/71452", "title": "Nursing Roles in Diabetic Foot Ulcer Prevention, Wound Management, and Digital Monitoring.", "summary": "Nursing Roles in Diabetic Foot Ulcer Prevention, Wound Management, and Digital Monitoring. - Journal of visualized experiments : JoVE", "date_modified": "2026-09-13T00:00:00.000Z", "author": { "name": "Ding, D; Hamoud Alhaskawi, A; Shen, J; Yang, M; Liu, Y; He, L; Alhaskawi, A; Zou, X; Zhou, W; Li, J; Lu, H", "url": "http://unknown.com" } } ] }