DIGITAL HEALTH

BackgroundAnticipatory injectable medications for symptom control are a key end-of-life care intervention. However, ensuring their safe and timely use in the community is a global challenge. The needs and priorities of stakeholders involved in processes for prescribing and administering these medications remain underexplored. We must understand these perspectives to design inclusive and adaptive systems. AimTo identify the needs and priorities of key stakeholders involved in community-based systems for using anticipatory injectable medications. DesignWe adopted a qualitative exploratory design, using an online survey between September and October 2024. Participants provided anonymised demographic information and completed up to four prompts capturing their stakeholder role, needs and priorities. Data were analysed using a combined inductive-deductive framework to produce synthesised shortlists of priorities and needs. Setting/participantsUK-based professional and public participants were recruited through social media, professional networks, charities, and public engagement events. ResultsIn total, 439 participants contributed 729 responses across various stakeholder groups. Findings revealed substantial diversity in stakeholder needs and priorities, both within and between groups. However, most stakeholder groups prioritised timely care, minimising of suffering, and wanted nationally consistent guidance for using injectable medications. Broader societal influences also shaped responses. ConclusionsOur findings highlight wide diversity in priorities and needs between stakeholders for using anticipatory injectable medications in the community. We propose that inclusive system design should include comprehensive assessment of key stakeholders needs and priorities, with the aim of providing better care. Our study demonstrates that stakeholder needs assessment offers a valuable framework to achieve this. What is already known about the topic?O_LIAnticipatory injectable medications are a widely used intervention in several countries to support timely end-of-life symptom control at home. C_LIO_LIThere are ongoing challenges with delays, inconsistent access, and variations in prescribing and governance across regions, indicating that system design influences both timeliness and safety. C_LIO_LIExisting research has primarily focused on the needs of individual professional groups, and no prior work has mapped the differing needs of all stakeholders involved in these systems. C_LI What this paper adds?O_LIOur study demonstrates that stakeholder groups have diverse needs but most share some core priorities -timely care, national consistency in practice guidance, and minimising suffering. C_LIO_LIWider societal factors and concerns shape stakeholder expectations of end-of-life medication systems. C_LIO_LIOur approach to stakeholder needs assessment reveals system requirements that consensus-based or single-perspective approaches often overlook. C_LI Implications for practice, theory, or policyO_LISystem improvements should be tailored to the specific needs of key stakeholder groups rather than assuming uniform priorities. C_LIO_LIStrong cross-stakeholder support exists for national, practical guidance on anticipatory prescribing, equipment, training, and governance. C_LIO_LIStakeholder needs assessment offers a useful method for designing safer, more responsive end-of-life medication systems. C_LI

BackgroundThe prevalence of diabetes in low- and middle-income countries is rising, and the most important treatment is maintaining a healthy lifestyle. Good diabetes self-care management is associated with better outcomes, but barriers to adhering to its management are knowledge deficits and a lack of social support. Traditionally, diabetes self-care management education and support are conducted by health care workers (HCWs), but limited access to HCWs restricts this activity. Digital health interventions can help overcome some barriers. ObjectiveTo describe type 2 diabetic patients perception of using WhatsApp for diabetes education, as well as the barriers and enablers they experienced in their usage, in the Tigray region of Ethiopia. MethodThis study is a collaboration between researchers from Norway and a researcher from Ethiopia. A qualitative explorative and descriptive approach was adopted. The co-researcher in Ethiopia recruited the participants, and research assistants conducted 17 interviews with a semi-structured interview guide based on the technology acceptance model. The interviews were conducted in Tigrinya, transcribed and translated to English, and de-identified before analysis. The data were analysed using NVIVO 14 with reflexive thematic analysis. ResultsFrom the data, the following four themes were developed: experienced enhanced self-care, digital access to HCWs, digital support, and barriers and enablers. The participants perceived WhatsApp as highly useful. The participants said that they gained new knowledge and experienced social support and increased access to HCWs when using WhatsApp. ConclusionWhatsApp was perceived as easy to use, but some barriers were reported. This study indicates that WhatsApp may contribute to enhancing access to diabetes self-care management education and support.

Digital therapeutics (DTx) are patient-facing apps designed to support individuals in their daily lives. Therefore, they have the potential to revolutionize healthcare by empowering and engaging patients to become active players in their own care. Despite the increasing adoption of DTx in national healthcare systems, research on their design remains limited. The present study introduces "DiGATax", a taxonomy designed to categorize and analyze DTx, including perspectives on content, intervention delivery logic and technology, as well as the patients interface, consolidating and expanding upon prior taxonomic work. Based on n = 44 applications retrieved from the German DiGA directory that demonstrated positive health outcomes, the taxonomy is supported by empirical evidence. Additionally, the study contributes by presenting an archetype framework of DTx derived from a taxonomy-based cluster analysis. Further analyses offer insights into specific combinations of DTx characteristics across archetypes, the user interface as a key factor in their acceptance, and potential links between DTx design and health-related and user engagement outcomes. By offering new insights into DTx design, this study contributes towards more organized research and reporting, ultimately paving the way for the development of effective solutions. It also marks a further step towards Meta-DTx, which aim to align patient care for multimorbid patients under one umbrella.

This paper describes eHEALS.com.br, a web-based platform that automates the administration of the Brazilian eHealth Literacy Scale (eHEALS-Br). The system collects responses online, scores users in real time, and provides personalized feedback based on five levels of digital health literacy. A systematic literature review was conducted to map existing instruments and identify gaps related to automation, temporal control, and inclusion. The platform architecture combines a React and TypeScript frontend with a Node.js and MongoDB backend, deployed on a secure virtual private server. In a pilot study with 12 participants, the automated eHEALS-Br scale demon-strated excellent internal consistency (Cronbachs alpha = 0.929), and additional questionnaire dimensions also showed good reliability. The results demonstrate the feasibility of automating eHEALS-Br, supporting both population studies and individualized clinical use, and reinforcing the potential of digital health tools for monitoring and improving health literacy in Brazil.

BackgroundIndividuals with severe mobility impairments (SMI) often experience significant psychological distress and chronic pain. Virtual walking (VW) presents an innovative rehabilitation approach to improve mood and alleviate pain. This study aimed to develop a home-based VW system with integrated mood and symptom tracking and to report on its feasibility and usability in a user study with individuals with SMI. MethodsA multidisciplinary, iterative frame-work guided the systems development. Following initial contextual research and design iterations, a user study was conducted with 11 participants with SMI. A repeated measures pre-post design was employed. Feasibility and usability were primarily assessed through post-study qualitative interviews, analyzed via content analysis. Changes in mood and symptoms were measured immediately before and after each session. Momentary mood was captured using an in-virtual reality (in-VR) two-dimensional (2D) affect grid, while embedded single-item state ratings were used to track anxiety, depressed mood, and pain. Daily mood changes and symptom trajectories were analyzed using logistic regression and generalized estimating equations (GEE), respectively. ResultsContextual research guided the system design towards enhancing accessibility, ergonomics, and therapeutic engagement. The final VW system featured three core modules: locomotion, multi-sensory feedback, and mood/symptom tracking. Qualitative analysis of the user study revealed high acceptance for the VW system, alongside challenges related to content variety and hardware ergonomics. Each intervention session was significantly associated with an immediate positive mood shift (odds ratio (OR) = 1.83), as measured by the affect grid. Furthermore, GEE models revealed a significant reduction in self-reported depression and anxiety symptoms over the intervention period (all P < 0.01). ConclusionsThis study confirms the feasibility and acceptability of the novel VW system for home-based use by individuals with SMI. The preliminary evidence suggests the system has high potential as a tool for improving mood and alleviating psychological distress. Future large-scale randomized controlled trials are warranted to establish its clinical efficacy. Trial registration numberNCT07073144-07/17/2025.

Technological innovations such as eHealth are vital for improving healthcare accessibility, quality, and sustainability. While most research addresses adoption at the individual or team level, less is known about organisational factors enabling sustainable transformation. Organisational readiness is a key determinant of success. The Organizational eHealth Readiness (OeHR) model, developed in Polish primary care, assesses five dimensions: Strategy, Competence, Culture, Structure, and Technology, but its applicability in Dutch health care remains unclear. This mixed-methods study evaluated the OeHR model in Dutch hospitals. A validated 32-item questionnaire, translated into Dutch, was completed by managers and implementation specialists of 15 top-clinical hospitals (n=22). Descriptive statistics, regression analyses, and Principal Component Analysis provided insight into how the five dimensions jointly reflect organisational readiness for eHealth. Three focus groups (n=14) in two hospitals explored construct interpretation, missing dimensions, and model usability. Qualitative data were analysed using deductive coding on OeHR dimensions and emergent themes to refine the questionnaire. Quantitative analyses identified organisational culture as the only significant predictor of subjective eHealth readiness, while other dimensions showed no independent effect. Open responses and focus groups confirmed the centrality of culture and suggested refinements to all components, including clearer definitions, structural flexibility, and attention to external factors. Overall, the OeHR model was valued for strategic guidance but required contextualisation for practical use. This study showed that the OeHR model provides a valuable framework for assessing eHealth readiness in Dutch hospitals, with cultural readiness emerging as the most influential yet conceptually ambiguous dimension. Strategy, competence, structural and technological readiness mainly act as contextual enablers rather than direct predictors. The findings highlight the need to refine definitions, reduce overlap, and explore additional layers such as personal, operational, and societal readiness. Strengthening conceptual clarity and developing context-sensitive tools could enhance applicability and guide hospitals in translating readiness into digital transformation. Author summaryeHealth, such as home monitoring and online consultations with healthcare providers, is becoming increasingly important. Hospitals want to implement eHealth effectively, but this is only possible if the organisation is ready for it. The Organisational eHealth Readiness model helps to assess how "eHealth-ready" an organisation is. This model looks at five components: strategy, competencies, culture, structure and technology. In our research, we examined whether this model is also suitable for Dutch hospitals and which factors were still missing. We did this using a questionnaire among professionals and three focus groups, all involved in the implementation of eHealth. This showed that all components of the model are important, but that the culture of the organisation plays a central role. If employees are open to change and innovation, this acts as a driving force for eHealth. The other components, such as technology and strategy, appear to be primarily preconditions: necessary, but not sufficient to enable real change. Participants found the model useful, but felt that some factors were missing, such as leadership, collaboration, flexibility and the influence of legislation and regulations. They also mentioned that the organisation must have the capacity to cope with change effectively. Adapting the model to include these points could better support hospitals in healthcare transformation in the future.

In this paper, we present conversational longitudinal ecological assessment (CLEA), a novel conversational AI-enabled method for collecting ecologically valid, temporally sensitive qualitative health data via mobile instant messaging. We report findings from an exploratory deployment of an instantiation of CLEA within a 12-week community-based weight management programme, delivered by a charity partner in an area of deprivation. Using WhatsApp, we deployed our CLEA chat-agent to conduct twice-weekly conversational data collection sessions with participants, to elicit data about their experience of the programme and associated behaviour change. This was followed by in-person semi-structured interviews (N = 9) to examine user experiences and perceptions of interacting with the chat-agent. Participants reported that WhatsApps familiarity supported accessibility and sustained engagement, while the conversational format encouraged reflection directed towards the research focus. Responding to chat-agent prompts required cognitive effort, leading some participants to defer engagement until they had adequate time and mental space; however, this reflective demand was largely experienced as beneficial within the programme context. The AIs quasi-human interactional qualities fostered a sense of support while reducing social judgement, enabling more candid disclosure. Together, these findings demonstrate initial feasibility and acceptability of CLEA for longitudinal qualitative data collection in an underserved population, and illustrate its capacity to elicit meaningful, contextually grounded insights consistently over time, that can be used in the formative stage of digital health intervention development. The study highlights both the opportunities and trade-offs of conversational AI for qualitative data collection, including design implications for health researchers looking to implement or extend the method. Finally, we position CLEA in relation to other longitudinal methods of health data elicitation. Author summaryDeveloping effective interventions for health behaviours such as healthy eating and physical activity requires methods that can capture the complex, individual factors shaping peoples everyday experiences, including stress and motivation. Because such factors often fluctuate over time, longitudinal approaches are needed to understand how experiences and behaviours unfold in real-world contexts. For such methods to be effective, they must also be acceptable, engaging, and accessible--particularly for underserved or disadvantaged populations who are disproportionately affected by health-related conditions such as obesity. In this study, we introduce conversational longitudinal ecological assessment (CLEA), a digital health method that uses conversational AI technology to collect ecologically valid qualitative data over time through an accessible communication platform. We demonstrate the feasibility, acceptability, and utility of CLEA through a real-world deployment investigating an underserved groups experience of a community-based weight management programme. To support other health researchers, we position CLEA in relation to existing longitudinal methods and highlight the key design considerations that shape engagement, data quality, and participant experience.

Eye tracking is recognized as a gold standard for measuring visual attention and cognitive engagement. In this study, it offers a useful lens for understanding how primary care providers balance patient communication with navigation of electronic health records (EHRs). We used wearable eye tracking to collect visual information processing behavior and conducted a retrospective think-aloud protocol to examine how primary care clinicians processed suiciderelated information (CAT-MH(R)) embedded in the EHR during simulated visits. Eye-movement data showed substantial visual attention directed toward the EHR, indicating added information-processing demands during communication. Retrospective think-aloud data supported the analysis of eye movement data by revealing that clinicians searched multiple record sections to verify risk indicators and often postponed suicide-related discussions until confirming relevant results. These findings illustrate how EHR-embedded screening tools shape clinical attention and encounter flow.

ImportanceClinician adoption and adaptation of new tools evolve over time. Prior studies of ambient Artificial intelligence (AI) scribes have primarily relied on single time-point measurements (e.g., pre-post), potentially obfuscating their true impact on outcomes. ObjectiveTo investigate longitudinal effects of an AI scribe tool on patient encounter-level outcomes. DesignCase series across 48 weeks (24 pre, 24 post) per clinician. SettingPrimary care clinical encounters occurring between 01/05/24 and 10/31/25. ParticipantsPrimary care clinicians (attending physicians and advanced practice providers). ExposureAmbient AI scribe introduction to clinical workflow, indexed to study day zero, per clinician. Main outcomes and measuresEncounter-level measurements of documentation time (note writing time, time outside of scheduled hours (TOSH), pajama time), note writing patterns (note length, note closure <24h) and clinicians billed work Relative Value Units (wRVU) with a focus on changes from pre-period outcomes at Day 0 and 150. Results220 primary care clinicians (Mean age=43.7, 70.9% females; 56.4% physicians) from 36 clinics, conducting 314,845 patient encounters were included. All outcomes evolved from day zero to day 150 and are compared back to pre-period levels. There was evidence of an immediate 7% decrease on average in note writing time at day zero (Incidence Rate Ratio, IRR 0.93, 95%CI [0.89, 0.96]), intensifying to a 15% decrease by day 150 (IRR 0.85, 95%CI [0.83, 0.87]). There was no evidence of a change in pajama time or TOSH at day zero; however, at day 150, there was evidence of a 18% decrease in pajama time (0.82, 95%CI [0.73, 0.91]) and a 13% decrease in TOSH (0.87, 95%CI [0.77, 0.99]). At day zero, there was evidence of a 5% increase (1.05, 95%CI [1.00, 1.10]) in note length and 31% increase in note closures (1.31, 95%CI [1.13, 1.53]), with both slowly attenuating to pre-period levels by day 150. Although there was no evidence of changes in wRVU at day zero, there was a 2% increase total wRVU at day 150 (1.02, 95%CI [1.01, 1.03]). Conclusions and relevanceLongitudinal changes were gradual, but persistent, underscoring the gradual adaptation of AI scribes, as clinicians situated these tools within their workflows. Key PointsO_ST_ABSQuestionC_ST_ABSHow do the patterns of use of an ambient Artificial Intelligence (AI) scribe evolve over time? FindingsIn this longitudinal, quasi-experimental study on clinician use of an ambient AI scribe, documentation time, note writing patterns and financial productivity evolved over a 150-day period. Compared to the pre-period, note writing time savings increased from 7% (day zero) to 15% (day 150); changes in all other considered outcomes including time outside of scheduled hours, pajama time, note length, note closure <24h, billed work Relative Value Units evolved over the 150-day period. MeaningClinician use of ambient AI scribes showed persistent changes in patterns of use over a 150-day period, highlighting a gradual adaptation process and the need for longitudinal assessment.

Objective: Evaluating and monitoring patients with cervical spondylotic myelopathy (CSM) remains a challenge due to limited tools for assessing objective neurological disability longitudinally and in the home environment. Given their prevalence and low cost, mobile health (mHealth), and specifically smartphone technologies offer a promising approach to fill this gap. This study explored stakeholder perspectives on the role of mHealth in CSM monitoring to inform development of a smartphone-based assessment application. Methods: We conducted semi-structured interviews with 15 patients with CSM and 14 healthcare providers (spine surgeons, physical therapists, and occupational therapists). Interviews explored current assessment practices, perceived limitations, and attitudes toward mHealth integration. Data were analyzed using thematic analysis. Results: Two major themes emerged from provider interviews: (1) diagnosing and monitoring CSM is challenging due to limitations in current tools, and (2) mHealth presents significant opportunities but requires thoughtful integration. Providers described current methods and technologies, clinical signs and symptoms, and challenges evaluating patients. Current tools were viewed as inadequate for precision medicine, with inter-rater variability and inability to capture real-world function. Within the second theme, providers identified ways mHealth could improve care, challenges for integration, and practical implementation considerations. Patients expressed strong interest in objective, longitudinal monitoring of gait, dexterity, and daily function. Conclusions: Stakeholders recognized substantial potential for mHealth to address unmet needs in CSM assessment. Successful implementation will require intuitive design, electronic medical record integration, and attention to accessibility. These findings provide a foundation for user-centered development of digital health tools in CSM care.

BackgroundDigital health technologies, including artificial intelligence (AI)-powered tools and virtual reality (VR) interventions, are increasingly being deployed to support caregivers of patients with chronic conditions. However, the factors influencing caregiver acceptance of these technologies remain poorly understood. ObjectiveThis study aimed to develop and validate a structural equation model (SEM) to examine the determinants of digital health technology acceptance among caregivers of patients with end-stage kidney disease (ESKD). MethodsA cross-sectional survey was conducted among 342 caregivers recruited from nephrology clinics across three tertiary hospitals in Singapore. The survey instrument measured perceived usefulness, perceived ease of use, social influence, facilitating conditions, caregiver burden, technology anxiety, and behavioral intention to use digital health tools. Confirmatory factor analysis (CFA) and structural equation modeling were performed using maximum likelihood estimation. ResultsThe final SEM demonstrated good model fit (CFI = 0.952, TLI = 0.943, RMSEA = 0.048, SRMR = 0.041). Perceived usefulness ({beta} = 0.42, p < 0.001), perceived ease of use ({beta} = 0.31, p < 0.001), and social influence ({beta} = 0.28, p < 0.001) were significant positive predictors of behavioral intention. Caregiver burden had an indirect effect on intention mediated through technology anxiety ({beta} = -0.18, p = 0.003). The model explained 64% of the variance in behavioral intention to adopt digital health technologies. ConclusionsThis study provides a validated framework for understanding caregiver acceptance of digital health technologies. Interventions targeting perceived usefulness and addressing technology anxiety among burdened caregivers may enhance adoption rates. These findings have implications for the design and implementation of AI-powered and VR-based caregiver support systems.

BackgroundTyping in the electronic health record (EHR) takes up healthcare providers time and cognitive space and constitutes a substantial administrative burden contributing to high burnout rates in healthcare. Ambient digital scribes may improve this problem. ObjectiveTo investigate the effect of the use of Autoscriber, an ambient digital scribe, on healthcare providers administrative workload and the quality of medical notes in the EHR. MethodsA study period of 26 weeks was randomized into weeks when healthcare providers were allowed to use Autoscriber (intervention weeks) and weeks when they were not (control weeks) in a 2:1 ratio. Workload was assessed by comparing the number of characters typed in the medical note during control weeks with the number of modifications that were made to the summary produced by Autoscriber during intervention weeks. Quality of the medical note was measured by having a large language model (LLM) count the number of hallucinations, incorrect negations, context conflation errors, speculations, other inaccuracies, omissions, succinctness errors, organization errors and terminology errors per medical note. ResultsBetween 1 November 2024 and 30 April 2025, 35 healthcare providers from 14 different specialties recorded 387 consultations in intervention weeks, and 142 in control weeks. The median number of characters typed per medical note was 1079 in control weeks and the median number of modifications necessary to produce the medical note was 351 in intervention weeks, compatible with a lower workload. All types of errors occurred significantly less frequently in notes made with the support of Autoscriber than in those without, except for speculations, where the difference did not reach statistical significance. ConclusionsThe use of Autoscriber resulted in a lower workload and a higher quality of the medical note.

BackgroundPalliative care improves quality of life and reduces healthcare utilization for people with heart failure, yet referrals remain inconsistent and delayed. Clinical decision support (CDS) offers a promising strategy to facilitate timely palliative care, but no CDS tool currently exists to specifically support palliative care decision-making in this population. MethodsGuided by the User-Centered Framework for Implementation of Technology (UFIT), we conducted a qualitative descriptive study of focus groups and interviews with referring (i.e., hospitalists, cardiologists) and palliative care clinicians across two hospitals in an academic health system. Using rapid qualitative and content analysis, we identified needs, contextual factors, and design requirements to inform CDS tool development for timely palliative care. ResultsClinicians (n=25) identified pain points in the current workflow, clinicians goals and expectations for earlier referral, and barriers to timely palliative care, such as timing uncertainty. Informational needs included prognostic and clinical data. Context reflected clinicians prior experiences with CDS tools, where they reported few options specific to palliative care and disliked interruptive "pop-up" alerts not tailored to clinical contexts or workflow. CDS requirements included incorporation of objective markers of clinical deterioration, tailored recommendations and workflow integration based on clinical acuity and palliative needs, and a clear, visually appealing design. ConclusionsClinicians identified critical information for a CDS tool to promote timely palliative care for patients with heart failure. These findings directly inform the design, workflow, implementation strategies, and future pilot testing of our palliative care CDS tool and subsequent clinical trial. Clinical Perspective1) What is new?O_LIThis study is the first to apply the UFIT framework to guide the development of a CDS tool to promote timely palliative care among patients with heart failure. C_LIO_LIThis work advances palliative care innovation by showing how a CDS tool can address barriers through integration of clinical and contextual insights. C_LI 2) What are the clinical implications?O_LIThis qualitative study informs the development of a clinical decision support tool to promote guideline-concordant palliative care in heart failure. C_LIO_LIFindings underscore that successful implementation of CDS tools depends on the tools alignment with established clinical workflows to enhance usability, support clinician adoption, and minimize workflow disruption. C_LI

PurposeVisual function testing in retinal prosthesis users relies on repetitive psychophysical tasks that are cognitively demanding and fatiguing. Gamification may increase engagement, but its effects on perceptual performance in implanted users remain unclear. MethodsThree Argus II users completed circle localization and motion direction discrimination in clinical and gamified versions. Visual stimuli, trial structure, and response requirements were matched within each participant; gamified versions added scoring, background music, and affectively framed end-of-trial auditory feedback. Difficulty and response format were calibrated to individual abilities (8AFC for two participants; 4AFC restricted to cardinal directions for one participant). ResultsGamification improved accuracy and reduced angular error in localization but did not improve motion discrimination. Effects were task-dependent and varied across participants, with reduced precision in the gamified motion task for one user. Participants preferred gamified localization and reported higher enjoyment and sustained attention; responses to gamified motion were mixed. ConclusionsGamification can influence measured performance and user experience in prosthetic vision testing, but benefits are not universal and depend on task demands and cognitive load, indicating that engagement can affect outcomes in tests often treated as objective. Translational relevancePersonalized, engagement-aware gamified tools with adaptive difficulty may improve the usability and scalability of prosthetic vision assessment and rehabilitation, including at-home training.

Artificial intelligence (AI) is increasingly integrated into healthcare delivery, yet patient acceptance in resource constrained settings remains incompletely characterized. This study assessed attitudes toward AI supported care among patients attending hospitals in three Jordanian governorates (Amman, Balqa, Irbid) and examined demographic and digital literacy correlates of acceptance. In a cross sectional survey (n = 500 complete questionnaires), participants rated exposure to AI in healthcare and five attitudinal domains, namely perceived usefulness or performance expectancy, trust and transparency, privacy and perceived risks, empathy and human interaction, and readiness or behavioral intention, using 25 items on 5 point Likert scales. Patients expressed conditional optimism: empathy and human interaction was most strongly endorsed (M = 4.33, SD = 0.58), alongside relatively high perceived usefulness (M = 3.97, SD = 0.68), while trust and transparency (M = 3.57, SD = 0.74) and readiness (M = 3.66, SD = 0.90) were moderate to high; privacy and risk concerns were moderate (M = 3.51, SD = 0.77) and self reported exposure was lowest (M = 2.57, SD = 1.07). The highest agreement item indicated preference for AI to work alongside physicians rather than be relied on alone (M = 4.47, SD = 0.81). Trust and transparency and perceived usefulness were positively associated with readiness (r = 0.48 and r = 0.44, respectively; p <.001), while privacy and perceived risks were negatively correlated with trust and usefulness. In multivariable regression adjusting for gender, age group, education, prior AI health app or device use, and self rated digital skill, lower educational attainment (less than high school and high school) predicted reduced readiness, whereas higher digital skill predicted increased readiness (R2 = 0.101). These findings suggest that implementation strategies in Jordan should emphasize human involvement alongside AI, transparent communication and governance, and interventions that build digital confidence and reduce readiness gaps linked to education. Author summaryAI is increasingly used in healthcare, for example to support diagnosis, triage, and treatment decisions. Whether these tools are accepted by patients depends not only on how well they work, but also on whether patients trust them, understand how they are used, and feel their privacy is protected. Evidence on patient views in middle income and resource constrained settings is still limited. We surveyed 500 patients attending hospitals in three Jordanian governorates to understand how they view AI supported care. Patients generally expected AI to be useful, but they strongly preferred that clinicians remain actively involved and that AI supports rather than replaces physicians. Trust and perceived usefulness were closely linked to willingness to accept AI enabled care, while privacy concerns were present and shaped trust. Readiness to accept AI was lower among participants with lower educational attainment and higher among those with greater self rated digital skill. These findings suggest that successful implementation in Jordan should prioritize transparent communication, strong privacy safeguards, and human centered workflows, while also strengthening digital confidence to avoid widening gaps in acceptance.

BackgroundEHR documentation and chart review contribute to clinician workload and burnout. To alleviate pre-charting burden, Epic has released a new generative AI chart summarizer tool, which has become widely adopted; however, its impact has not been examined in randomized trials. ObjectiveTo evaluate whether access to an Epic generative AI chart summarization tool reduces cognitive task load among ambulatory providers compared with usual care. MethodsTwo-arm, parallel-group randomized controlled trial among ambulatory clinicians across multiple specialties. Clinicians will be randomized 1:1 to tool access versus usual care for 90 days. The primary outcome is change in a 4-item physician task load (PTL) adapted for the pre-charting task. Exploratory outcomes include EHR-derived time metrics (Caboodle and Signal), professional fulfillment/burnout (PFI), usability (SUS), clinician satisfaction, aggregated patient experience item from CG-CAHPS, and reported safety related metrics. Ethics and DisseminationAnalyses will use clinician-level survey responses and aggregated EHR metrics; no patient-level protected health information will be included in the analytic dataset. Results will be disseminated via preprint and peer-reviewed publication. Article summary - Strengths and limitations of this studyO_LIThis study is a 3-month pragmatic randomized controlled trial evaluating a native EHR-embedded generative AI tool that summarizes prior clinical notes for ambulatory encounters. C_LIO_LIThe primary outcome uses a validated cognitive task load instrument adapted specifically for pre-charting activities. C_LIO_LIExploratory outcomes include objective EHR-derived time metrics, validated psychometric measures of burnout and professional fulfillment, and clinician-reported survey measures assessing perceived usefulness of the tool. C_LIO_LIThe trial is single-centered, which may limit generalizabilty, and the intervention is optional-use and unblinded, which may attenuate observed effects and introduce performance bias. C_LI

BackgroundGenerative artificial intelligence (GenAI) in healthcare may reduce administrative burden and enhance quality of care. Large language models (LLMs) can generate draft responses to patient messages using electronic health record (EHR) data. This could mitigate increased workload related to high message volumes. While effectiveness and feasibility of these GenAI tools have been studied in the United States, evidence from non-English contexts is scarce, particularly regarding user experience. ObjectiveThis study evaluated the effectiveness, feasibility and barriers and facilitators of implementing Epics Augmented Response Technology (Art) GenAI tool (Epic Systems Corporation, Verona, WI, USA) in a Dutch academic healthcare setting among a broad range of end users. It explored healthcare professionals (HCP) usage metrics, expectations, and early user experiences. MethodsWe conducted a hybrid type 1 effectiveness-implementation design. HCPs of four clinical departments (dermatology, medical oncology, otorhinolaryngology, and pulmonology) participated in a six-month study. Effectiveness of Art was assessed using efficiency indicators from Epic (including all InBasket users in the hospital) and survey scales measuring well-being and clinical efficiency at three time points: PRE, POST-1 (1 month), and POST-2 (4 months). Feasibility of Art was evaluated through adoption indicators from Epic and survey scales on use and usability. Barriers and facilitators of Art implementation were collected through the survey and thematized using the NASSS framework (Nonadoption, Abandonment, Scale-up, Spread and Sustainability). Results237 unique HCPs generated a total of 8,410 drafts. Review and drafting times were similar for users with and without Art, indicating minimal differences. Perceived clinical efficiency declined significantly from PRE to POST-2, while well-being remained unchanged. Adoption was initially high but decreased over time, averaging 16.7% across departments. Usability and intention-to-use scores also declined significantly. Oualitative findings highlighted time savings, well-structured drafts, and patient-centered language as facilitators. Reported barriers included limited impact on time, low practical utility, content inaccuracies, and style misalignment. ConclusionsThis evaluation of a GenAI tool for patient-provider communication in a non-English academic hospital revealed mixed perceptions of effectiveness and feasibility. High initial expectations contrasted with limited perceived impact on time-savings, well-being and clinical efficiency, alongside declining adoption and usability. Barriers and facilitators revealed contrasting views. These findings underscore the need for a workflow for the handling of user feedback, guidance on clinical responsibilities, along with clear communication about the tools purpose and limitations to manage expectations. Additionally, establishing consensus on a set of quality indicators and their thresholds that indicate when a GenAI tool is sufficiently robust will be critical for responsible scaling of GenAI in clinical practice.

Large language models (LLMs) are increasingly used for qualitative thematic analysis, yet evidence on their performance in analysing focus-group data, where polyvocality and context complicate coding, remains limited. Given the increasing role of such models in thematic analysis, there is a need for methodological frameworks that enable systematic, metric-based comparisons between human and model-based analyses. We conducted a blinded mixed-methods comparison of two general-purpose LLMs (ChatGPT-5 and Claude 4 Sonnet), an LLM-based qualitative coding application (QualiGPT), and blinded human analysts on an in-person focus-group transcript informing an AI-enabled digital health proposal. We evaluated deductive coding using a 10-code, 6-theme codebook against an expert consensus adjudication; inductive coding with a structured Likert-scale comparison to a reference-standard set of inductive themes generated by expert consensus; and manual quote verification of LLM segments to define LLM hallucination (evidence absent or non-supportive) and error rate (including partial matches and speaker-coded segments). During deductive coding against an expert consensus adjudication, large language models (LLMs) yielded a mean agreement of 93.5% (95% CI 92.5-94.5) with {kappa} = 0.34 (95% CI 0.26-0.40); blinded human coders achieved 92.7% (95% CI 91.6-93.9) agreement with {kappa} = 0.34 (95% CI 0.26-0.41). Mean Gwets AC1 was 0.92 (95% CI 0.90-0.93) for the blinded human analysis, and 0.93 (95% CI 0.92-0.94) for the LLM-assisted deductive analysis, reflecting high agreement despite the low overall code prevalence (7.8%, SD = 3.2%). Only one model achieved non-inferiority in inductive analysis of the transcript (p = 0.043). The strict hallucination rate in inductive analysis was 1.2% (SD = 2.1%). LLMs were non-inferior to human analysts for deductive coding of the focus-group data, with variable performance in inductive analysis. Low hallucination but significant comprehensive error rates indicate that LLMs can augment qualitative analysis but require human verification. Author summaryQualitative research plays an important role in digital health, assisting in the implementation of healthcare technologies and innovations. However, analysing qualitative data in the form of focus groups is time-consuming and requires human expertise. Large Language Models (LLMs) are being increasingly used in qualitative research analysis, although evidence on their performance in analysing focus group data is limited. We compared the performance of LLMs to blinded human analysts in analysing a focus group transcript on AI implementations in healthcare. We used both qualitative and quantitative metrics to evaluate the performance of LLMs in thematic analysis. We found that the LLMs performed similarly to humans when applying pre-defined codes (deductive analysis), with a low rate of hallucination. However, in open-ended theme generation (inductive analysis) their performance was more variable, particularly in areas requiring interpretation of tone, nuance, or conversational context. These findings suggest that LLMs can be used to support interpretation of qualitative data, rather than replace human analysts. We provide a reproducible framework in analysing the performance of LLMs in qualitative analysis.

BackgroundShort-video platforms have become increasingly important sources of health information for the general public. However, the informational quality and dissemination patterns of content related to specific therapeutic modalities, such as enhanced external counterpulsation (EECP), remain insufficiently characterized. This study aimed to evaluate the informational quality of EECP-related videos on a short-video platform and to examine the relationship between content quality and user engagement. MethodsA cross-sectional content analysis was conducted on EECP-related short videos identified through keyword-based searches. Informational quality was independently assessed using four validated instruments: the Global Quality Scale (GQS), the Journal of the American Medical Association (JAMA) benchmark criteria, the modified DISCERN instrument (mDISCERN), and the Video Information and Quality Index (VIQI). Video characteristics and user engagement metrics were extracted and analyzed. ResultsOverall, EECP-related videos demonstrated low-to-moderate informational quality across all assessment tools. Longer video duration was consistently associated with higher informational quality scores. In contrast, user engagement metrics, including the number of likes and comments, showed weak or negative associations with informational quality. Compared with videos addressing other coronary heart disease treatments, EECP-related videos were less frequently represented and received lower overall engagement. ConclusionsEECP-related content on short-video platforms is characterized by limited visibility and modest informational quality, with a notable misalignment between user engagement and informational value. These findings suggest that clinically relevant but complex therapies such as EECP may be structurally disadvantaged in short-video health communication environments.

BackgroundTinnitus affects a substantial proportion of the global population and can severely disrupt sleep, mood, and daily functioning, yet the quality of mobile health apps designed for tinnitus management remains highly variable. Traditional evaluation methods, including clinical trials, expert rating scales, and small-scale surveys, rarely capture large-scale, feature-level feedback from real-world users, leaving a gap in understanding which app characteristics drive sustained engagement and satisfaction. MethodsThis study analysed 342,520 English-language reviews from 84 tinnitus-related apps on iOS and Android collected between 2015 and 2025. A pipeline first applied VADER-based preprocessing and sentiment assignment, then trained a graph neural network aspect-based sentiment analysis (GNN-ABSA) model operating on sentence-level dependency graphs to infer feature-level sentiment for domains such as sound therapy, sleep support, pricing, advertisements, stability, and user interface. ResultsThe GNN-ABSA model achieved an accuracy of 84.4% and a macro F1 score of 0.829 on unseen aspect-level test data, indicating stable performance across sentiment classes. Therapeutic features like sound masking and sleep support were associated with predominantly positive sentiment, whereas pricing, advertisements, background playback, and technical stability attracted more neutral or negative feedback over the ten-year period. ConclusionsLarge-scale, graph-based feature-level sentiment analysis provides a user-cantered perspective that complements clinical trials and expert app quality ratings, offering actionable guidance for developers seeking to prioritize design improvements, supporting clinicians in recommending suitable apps to patients, and informing the design of more explainable and user-driven digital health tools. Trial RegistrationNot applicable. This study analysed publicly available app store reviews and did not involve human participants.