Explore the vast range of titles available.

Building on the assertion that nearly every clinician will eventually use artificial intelligence (AI), this study provides a triangulated qualitative analysis of the requirements, challenges, and prospects for integrating AI into routine health care practice. This skills gap contributes to cautious and uneven adoption across clinical settings. Despite advancements, many health care professionals report a self-perceived lack of proficiency in comprehending, critically evaluating, and ethically deploying AI tools, which contributes to cautious adoption in clinical settings. While addressing key research questions, the study investigates the necessary prerequisites, barriers, and opportunities for AI adoption and specific training priorities that medical staff require. The study is uniquely focused on the health care workforce, moving beyond the predominant emphasis in the literature on medical students. Situated in Flanders, Belgium, a recognized innovation leader but with moderate lifelong learning participation, this research combines 15 semistructured expert interviews, a regional survey of 134 health care professionals, and 3 co-interpretive focus groups with 39 stakeholders, all conducted in 2024. The results expose small generational and mainly occupational divides. For instance, 85.07% (114/134) of survey respondents expressed interest in introductory AI courses tailored to health care, while 80% (107/134) of them sought practical, job-relevant AI skills. However, only 13.8% (19/134) of clinicians felt that their training adequately prepared them for AI integration. Notably, younger professionals (<30 years of age) were most eager to engage with AI but also expressed greater concern about job displacement, while older professionals (>50 years of age) prioritized reducing administrative burden. Physicians and dentists reported higher self-assessed AI knowledge, whereas nurses and physiotherapists showed the lowest familiarity. The survey also revealed differences in preferred learning formats, with doctors favoring flexible, asynchronous learning and nurses emphasizing the need for accredited, employer-supported training during work hours. Ethics, though emphasized in academic literature, ranked low in training interest among most practitioners, except for younger and palliative care professionals. Focus group participants confirmed the need for clear regulatory guidance and access to accredited, practically oriented training. A significant insight was that nurses often lacked institutional support and funding for training, despite their pivotal role in AI-enabled workflows. Taken together, these findings indicate that a one-size-fits-all approach to AI education in health care is unlikely to be effective. By triangulating insights across research stages, this study highlights the need for occupation-specific, accessible, and accredited AI training programs that bridge gaps in digital literacy and align with practical clinical priorities. The qualitative insights obtained can inform policy and training priorities in light of the European Union (EU) AI literacy mandates, while highlighting persistent gaps in workforce preparation.

European health care systems face mounting pressures from an aging population, workforce shortages, and decentralization, challenging the delivery of accessible, high-quality care. eHealth solutions are widely promoted to enhance efficiency and improve the quality of care. Despite a strong policy report, anticipated benefits remain unrealized, as implementation processes often encounter barriers and high failure rates. Research shows that drivers and barriers are dynamic and shaped by actor interactions. Some studies suggest that certain actors, often acting as bricoleurs, play a critical role in overcoming these barriers through adaptive and improvised practices. However, little is known about how these actors enact roles, what features enable bricolage, and how structural conditions influence these practices. The aim of this study is twofold. First, it investigates the roles and features of actors involved in innovation processes, with a particular emphasis on the application of bricolage to overcome barriers and the influence of structural factors on these processes. Second, it aims to contribute both theoretical and empirical insights to deepen the understanding of barrier dynamics within innovation processes. We conducted a multiple-case study comprising 10 semistructured interviews, 11 focus groups with health care professionals, managers, trainers, and policymakers, participant observations of training sessions, and document analysis. An iterative process integrated the dramaturgical approach with the concept of bricolage, guiding the reflexive thematic analyses. Roles were enacted based on available information, context, and assigned functions. Service specialists (eg, superusers) and mediators (eg, unit or project managers) gained backstage insights through shadowing staff, evaluations, and support activities. When mandated and equipped with contextual and technical knowledge, these actors became bricoleurs, addressing unforeseen challenges by creatively mobilizing resources and thereby transforming barriers into promoters. Effective bricolage required proximity to the implementation site, dedicated involvement, and experiential knowledge of health care and technical domains. Key drivers included colocation, supportive management, stable teams, superusers, tailored training, follow-up activities, and informal evaluations. Barriers such as organizational silos, leadership shifts, staffing shortages, high turnover, geographic dispersion, and technology perceived as challenging or surveillance-oriented constrained bricolage and hindered implementation. Actors may become bricoleurs when their assigned roles, contextual knowledge, and backstage access enable them to improvise in response to unforeseen challenges. Through a dramaturgical lens, bricolage is an adaptive performance that sustains frontstage care delivery. Bricoleurs combine proximity, experiential knowledge, and dual expertise to transform barriers into drivers by adjusting the innovation process and fostering interaction. These practices illustrate the mutual shaping of structure and agency: enabling conditions expand the space for bricolage, while barriers narrow it. Understanding this dynamic is essential for advancing theory on innovation processes and for designing implementation strategies that leverage bricolage as a mechanism for transforming barriers into drivers of innovation.

Health Evidence provides access to quality appraisals for >10,000 evidence syntheses on the effectiveness and cost-effectiveness of public health and health promotion interventions. Maintaining Health Evidence has become increasingly resource-intensive due to the exponential growth of published literature. Innovative screening methods using artificial intelligence (AI) can potentially improve efficiency. The objectives of this project are to: (1) assess the ability of AI-assisted screening to correctly predict nonrelevant references at the title and abstract level and investigate the consistency of this performance over time, and (2) evaluate the impact of AI-assisted screening on the overall monthly manual screening set. Training and testing were conducted using the DistillerSR AI Preview & Rank feature. A set of manually screened references (n=43,273) was uploaded and used to train the AI feature and assign probability scores to each reference to predict relevance. A minimum threshold was established where the AI feature correctly identified all manually screened relevant references. The AI feature was tested on a separate set of references (n=72,686) from the May 2019 to April 2020 monthly searches. The testing set was used to determine an optimal threshold that ensured >99% of relevant references would continue to be added to Health Evidence. The performance of AI-assisted screening at the title and abstract screening level was evaluated using recall, specificity, precision, negative predictive value, and the number of references removed by AI. The number and percentage of references removed by AI-assisted screening and the change in monthly manual screening time were estimated using an implementation reference set (n=272,253) from November 2020 to 2023. The minimum threshold in the training set of references was 0.068, which correctly removed 37% (n=16,122) of nonrelevant references. Analysis of the testing set identified an optimal threshold of 0.17, which removed 51,706 (71.14%) references using AI-assisted screening. A slight decrease in recall between the 0.068 minimum threshold (99.68%) and the 0.17 optimal threshold (94.84%) was noted, resulting in four missed references included via manual screening at the full-text level. This was accompanied by an increase in specificity from 35.95% to 71.70%, doubling the proportion of references AI-assisted screening correctly predicted as not relevant. Over 3 years of implementation, the number of references requiring manual screening was reduced by 70%, reducing the time spent manually screening by an estimated 382 hours. Given the magnitude of newly published peer-reviewed evidence, the curation of evidence supports decision makers in making informed decisions. AI-assisted screening can be an important tool to supplement manual screening and reduce the number of references that require manual screening, ensuring that the continued availability of curated high-quality synthesis evidence in public health is possible.

Human factors (HF), or ergonomics, which explores the interaction between humans and systems, has been used to support design in safety-critical industries such as aviation, transportation, nuclear power, and manufacturing. HF methods have the potential to support the safe design of health IT; however, the evaluation of HF methods to determine their effectiveness and feasibility in this context has been limited. The aim of this study was to identify criteria for evaluating HF methods when applied to real-world projects and to use these to propose a framework for method evaluation. The study design was qualitative and descriptive and involved semistructured interviews with HF experts working across health and nonhealth industries in academic and/or practitioner roles. HF experts held a relevant degree (eg, ergonomics and HF engineering) and were actively using their HF expertise. Results were thematically analyzed. A total of 21 participants took part, and interviews lasted, on average, 52 (range 39-103) minutes. Participants mentioned that they did not routinely evaluate methods; however, when asked how they would evaluate methods, they outlined a range of criteria to support method evaluation. Overall, 5 criteria and 28 subcriteria were identified. High-level criteria included effectiveness, efficiency, ease of use and acceptability, and impact on the solution. Results from this study were used to propose a framework for evaluating HF methods used in real-world health IT projects. The framework should provide organizations with valuable information on how to optimize the application and outcomes of HF methods and build HF capability within organizations, particularly where this capability may be lacking.

Formative evaluation is widely used in implementation science to anticipate barriers and facilitators prior to the deployment of health technologies, typically relying on stakeholders' reported beliefs collected before real-world exposure. This approach has proven informative for many digital health tools; however, its application to immersive and embodied technologies such as extended reality (XR) warrants closer scrutiny. Most XR interventions in health care are delivered through head-mounted displays, which depend on spatial perception and sensorimotor engagement. Several implementation-relevant properties, including comfort, perceived intrusiveness, safety, and workflow disruption, often become apparent only through direct interaction. At the same time, large segments of the health care workforce remain XR-naive, such that preuse judgments are frequently shaped by anticipation rather than experience. Drawing on concepts from implementation science, grounded cognition, and human-computer interaction, this Viewpoint examines a plausible interpretive problem in XR adoption and argues that perception-based formative evaluation, when applied through frameworks developed for screen-based technologies, may misclassify barriers and facilitators. Rather than questioning formative evaluation as a methodological approach, we identify a boundary condition for its interpretability in experience-dependent technologies and propose a pragmatic refinement: incorporating brief experiential familiarization before eliciting stakeholder perceptions to strengthen early-stage assessment and improve alignment with real-world implementation decisions.

Symptom checkers are apps and websites that assist medical laypeople in diagnosing their symptoms and determining which course of action to take. When evaluating these tools, previous studies primarily used an approach introduced a decade ago that lacked any type of quality control. Numerous studies have criticized this approach, and several empirical studies have sought to improve specific aspects of evaluations. However, even after a decade, a high-quality methodological framework for standardizing the evaluation of symptom checkers is still lacking. This paper synthesizes empirical studies to outline the Symptom Checker Accuracy Reporting Framework (SCARF) and a corresponding checklist for standardizing evaluations based on representative case selection, an externally and internally valid evaluation design, and metrics that increase cross-study comparability. This approach is supported by several open access resources to facilitate implementation. Ultimately, it should enhance the quality and comparability of future evaluations of online and artificial intelligence (AI)–based symptom checkers, diagnostic decision support systems, and large language models to enable meta-analyses and help stakeholders make more informed decisions.

Electronic health records (EHRs) play an essential role in modern health care, enabling data sharing and improving patient safety; however, even though vendors must adhere to International Organization for Standardization-related usability standards for EHR certification, persistent usability issues continue to undermine efficiency, contribute to clinician burden, and increase the risk of preventable errors. This scoping review synthesizes existing research on EHR adoption and usability, emphasizing theoretical models, measurement approaches, factors, and analytic methods used to assess or predict usability. We identify gaps and opportunities for integrating predictive analytics and artificial intelligence (AI) to advance research and improve the usability of EHRs. Following Joanna Briggs Institute and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we systematically searched MEDLINE, Web of Science, IEEE Xplore, and Scopus library databases for studies published between January 1, 2009, and April 9, 2025. Inclusion criteria focused on empirical research using predictive methods or models related to EHR usability. Data were charted and synthesized thematically. Of the 2323 screened papers, 47 studies met inclusion criteria. Most research examined or predicted EHR adoption (not usability) using dominant frameworks, such as the technology acceptance model, unified theory of acceptance and use of technology, and the information system success model, which comprised usability. Factors related to usability-particularly perceived usefulness, perceived ease of use, effort expectancy, and facilitating conditions via the EHR adoption models-appeared frequently. Regression-based methods and structural equation modeling were the most common analytic techniques. No studies applied predictive modeling or AI to predict EHR usability. The focus of this study on the prediction of EHR usability and adoption for the past 15 years is distinctive in the literature. It extends prior usability reviews (mostly focusing on adoption, not prediction of usability). Predictive modeling for EHR usability remains underdeveloped throughout 2009 to 2025. Dominant frameworks in the EHR literature continue to prioritize predicting adoption over operational usability. These models rely heavily on self-reported, cross-sectional measures captured at a single postimplementation time point, embedding systematic bias and obscuring longitudinal usability dynamics. Despite the application of increasingly sophisticated predictive techniques-primarily variants of regression and structural equation modeling-usability has remained analytically subordinate to adoption and acceptance constructs for more than 15 years. As a result, widely used models, such as the technology acceptance model and unified theory of acceptance and use of technology, position usability merely as an antecedent to intention or use, rather than as an independent, system-level property that can be empirically measured, modeled, and predicted. Therefore, there is substantial opportunity to integrate predictive analytics, AI, and longitudinal usability measures to build dynamic models.

Near miss events can reveal system problems before patients are harmed, but current reviews are inconsistent and often rely on simple counts that are distorted by patient volume and reporting culture. Consequently, leaders cannot tell whether a rise in reports means that safety is getting worse or that staff are reporting more, and current systems are not strong enough to clearly separate real safety risks from random variation. This study developed a 3-level near miss framework (NM³), a conceptual framework that converts descriptive near miss data into decision-grade intelligence through a structured, evidence-based process, including baseline measurement and advanced interpretation and governance. NM³ was developed to provide decision-grade analytics for acute inpatient hospital settings. The framework was designed as a maturity model, progressing from baseline measurement to advanced interpretation. It integrates standardized definitions, rate calculations, statistical process control, severity weighting, and learning metrics. Level 1 establishes an organizational baseline through near miss rates per 1000 patient-days and near miss-to-harm ratios monitored with control charts. Level 2 introduces domain-specific denominators and unit-level charts to detect local variation. Level 3 applies severity weighting to generate a Near Miss Index; incorporates learning yields at 90 and 180 days; and triangulates near miss trends with harm events, exposure, reporting volume, and culture measures. A synthetic example demonstrates how the framework converts raw reports into stable rates, weighted indices, and learning metrics. NM³ provides a structured pathway for organizations to strengthen near miss analytics. By progressing through maturity levels, leaders can improve the interpretation of safety signals, prioritize high-consequence risks, and integrate near miss reporting into governance.

Tailoring is an important strategy to improve uptake and efficacy of medical information and guidance provided through eHealth interventions. Given the rapid expansion of eHealth, understanding the design rationale of such tailored interventions is vital for further development of and research into eHealth interventions aimed at improving health and healthy behavior. This systematic review examines the use of health literacy concepts through tailoring strategies in digital health interventions (eHealth) aimed at improving health and how these elements inform the overall design rationale. A systematic search of PubMed, PsycINFO, Web of Science, and ACM databases yielded 31 eligible randomized trials that focused on adult health improvement through eHealth interventions. Eligible studies compared tailored versus nontailored eHealth interventions for adults, excluding non-English papers and those addressing solely readability or targeting populations with accessibility barriers. Data extraction focused on study characteristics, health literacy components, tailoring methods, and design rationales, with study quality evaluated using Quality Assessment for Diverse Studies (QuADS) by independent reviewers. Most interventions applied both cognitive and social health literacy concepts and predominantly used content matching as a tailoring strategy. Of all studies using content matching, most used one or more supporting theories as well as end-user data to inform the content matching. While choices for individual intervention components were mostly explicated, detailed descriptions of the design process were scarce, with only a few studies articulating an underlying narrative that integrated the most important chosen components. While tailored eHealth interventions demonstrate promise in enhancing health literacy and the trial design of the interventions overall was of good quality, inconsistent documentation of design rationales impedes replicability and broader application of the used eHealth concepts. This calls for more detailed reporting on the design choices of the intervention in efficacy studies, so that reported outcomes can be easier connected to choices made in the design of the eHealth intervention.

Providing tailored information is an essential part of health care. However, physicians often lack time for detailed education during the consultation. An additional, tailored digital health information service (DHIS) could help physicians meet their patients' information needs regardless of time and place and extend physician-patient communication to the digital realm. This study aimed to examine physicians' intentions to provide a DHIS to their patients and identify facilitating factors and barriers, guided by the extended unified theory of acceptance and use of technology. A cross-sectional online survey with German physicians from various specialties was conducted in March 2022. The sample (N=364) ranged in age from 33 to 75 years (mean 53.92, SD 8.12), and the majority were male participants (31.9% [n=116] female participants). A blockwise multiple linear regression analysis was conducted to identify facilitating factors and barriers of physicians' intentions to provide a DHIS. Overall, 54.1% (n=197) of the surveyed physicians were (rather) willing to provide a tailored DHIS, 23.9% (n=87) were undecided, and 22% (n=80) were (rather) not willing to provide such a service to their patients. The overall model of a blockwise multiple linear regression analysis explained 56.8% of the variance of physicians' intentions. Perceived usefulness for job performance and patient outcomes as well as personal innovativeness was positively associated with physicians' intentions to provide a DHIS to their patients. Ease of use, social influence, facilitating conditions, price value, and habit were not associated with their intentions. The perspective of the majority of surveyed physicians suggests that a tailored DHIS seems to be a promising way to provide additional health information and thus enhance face-to-face physician-patient communication. Efforts supporting the implementation of DHIS should address job performance and patient outcomes in particular. Further, physicians with a more positive attitude could serve as multipliers to increase the adoption of DHIS.