Matthew Pears

Large language models (LLMs) such as ChatGPT are rapidly reshaping healthcare education and simulation-based training in non-technical skills (NTS), yet no bibliometric analysis has mapped this landscape. We searched seven open-access databases (OpenAlex, PubMed, Europe PMC, Crossref, Semantic Scholar, CORE, DOAJ) for English-language publications from January 2020 to March 2026. From 100,277 initial records, a sequential keyword funnel yielded 830 candidate papers, which were screened by 83 independent Claude Sonnet 4.6 AI agents applying pre-specified inclusion criteria (PRISMA-trAIce compliant; Cohen’s kappa = 0.86 pre-reconciliation, 1.0 post-reconciliation). The final AI-verified corpus comprised 551 papers with a compound annual growth rate of 109%, contributions from 2,398 authors across 279 journals in 58 countries, and an h-index of 41. ChatGPT dominated the model landscape (46% of papers), with open-source models virtually absent. Virtual patient chatbots were the leading simulation modality (106 papers). Among NTS domains, communication (145 papers) and decision-making (135 papers) were most studied, whereas teamwork, leadership, situational awareness, and crisis resource management were markedly underrepresented. Only 6 urology-relevant papers were identified, none examining LLM integration within boot camp training formats. The field is growing at extraordinary pace but remains concentrated in a narrow range of NTS domains and a single proprietary model. Critical gaps persist in team-based skills training, open-source model evaluation, and specialty-specific simulation. AI-assisted bibliometric screening using multiple independent agents is feasible, reliable, and scalable, offering a replicable methodology for mapping fast-evolving research fields. Author Summary: We mapped the research landscape of large language models in healthcare simulation and non-technical skills training by analysing 551 rigorously screened papers published between 2020 and 2026. Our analysis reveals a field that has exploded since the release of ChatGPT, growing at over 100% per year, but one with significant blind spots. Most research focuses on communication and clinical decision-making, while the team-based skills that prevent patient safety failures—teamwork, leadership, situational awareness, and crisis resource management—are barely studied. Almost half of all papers use a single proprietary model (ChatGPT), with open-source alternatives virtually absent. We also found that urology, despite having one of the most established simulation training programmes in surgery, has almost no research connecting large language models with simulation-based training. To conduct this analysis, we developed a novel screening approach using 83 independent AI agents, which achieved agreement with human review exceeding published benchmarks. Our open-access pipeline and dataset are freely available for other researchers to replicate or extend this work.

Virtual reality has long existed, but its wider adoption in education is recent. Studies informed by theoretical underpinned co-creation frameworks and utilization of theoretical informed evaluations are scarce in literature. Thus, this study internationally evaluated the efficacy of three virtual reality reusable e-resources (VRReRs), co-created based on the ASPIRE framework, for teaching clinical skills to university students. The study followed a mixed-methods approach, combining SUS, SUS Presence Questionnaire, TAM, and UTAUT2 with a focus group discussion. Additionally, for one VRReR, a quantitative pre/post evaluation of knowledge and comparison with lecture notes followed. Results demonstrated moderately to highly usability, effectively facilitated a strong sense of presence, confidence while using them, and willingness to continue using VRReRs in the future, while increased knowledge of the learners, highlighted their effectiveness. Although some usability issues were identified, these were considered easy to address. This work evidence, in an international context, that co-created VR resources are highly acceptable and effective, similar to other types of digital or traditional resources developed through participatory inquiry paradigm. By leveraging the benefits of VR technology, VRReRs have the potential to transform and enhance the learning experience in the field of clinical skills, ultimately advancing the digitalization of higher education.

Research into digital interventions for mental well-being promotion has grown in recent years, fuelled by the need to improve mental health prevention strategies and respond to challenges arising from the coronavirus (COVID-19) pandemic. This bibliometric analysis provides a structured overview of publication trends and themes in primary research studies reporting an array of digital interventions indexed at WoS from 2004 to 2023. Bibliometric data were collected on a sample of 1117 documents and analysed using the Biblioshiny package. Supplemental network visualisation analysis was conducted using VosViewer. The study, based on Web of Science and Scopus databases, indicates a marked increase in publications post-2020. There were seven groups of research themes clustered around “Mindfulness”, “Anxiety”, “COVID-19”, “Acceptance and Commitment Therapy”, “Depression”, “Web-based”, and “Positive Psychology”. Further, results demonstrated the growth of specific themes (e.g., mindfulness, mhealth), the defining impact of COVID-19 studies, and the importance of both randomised controlled trials and formative research. Overall, research in the field is still early in its development and is expected to continue to grow. Findings highlight the field’s dynamic response to societal and technological changes, suggesting a future trajectory that leans increasingly on digital platforms for mental health promotion and intervention. Finally, study limitations and implications for future studies are discussed.

Immersive experiential technologies find fertile grounds to grow and support healthcare education. Virtual, Augmented, or Mixed reality (VR/AR/MR) have proven to be impactful in both the educational and the affective state of the healthcare student’s increasing engagement. However, there is a lack of guidance for healthcare stakeholders on developing and integrating virtual reality resources into healthcare training. Thus, the authors applied Bardach’s Eightfold Policy Analysis Framework to critically evaluate existing protocols to determine if they are inconsistent, ineffective, or result in uncertain outcomes, following systematic pathways from concepts to decision-making. Co-creative VR resource development resulted as the preferred method. Best practices for co-creating VR Reusable e-Resources identified co-creation as an effective pathway to the prolific use of immersive media in healthcare education. Co-creation should be considered in conjunction with a training framework to enhance educational quality. Iterative cycles engaging all stakeholders enhance educational quality, while co-creation is central to the quality assurance process both for technical and topical fidelity, and tailoring resources to learners’ needs. Co-creation itself is seen as a bespoke learning modality. This paper provides the first body of evidence for co-creative VR resource development as a valid and strengthening method for healthcare immersive content development. Despite prior research supporting co-creation in immersive resource development, there were no established guidelines for best practices.