人工智能赋能护理实习生教学设计新范式

健康教育作为以患者为中心护理服务的重要工作,贯穿患者就诊、住院及出院随访的全过程。然而,受限于护理人力紧张与工作负荷增加,传统教育方式在个性化不足、执行效率低以及提升患者主动参与度等方面存在明显局限。近年来,人工智能技术特别是基于大语言模型的多智能体在自然语言交互、自主感知和推理决策等方面展现出的独特优势,为护理健康教育的智能化转型提供了新契机。文章聚焦多智能体在护理健康教育中的应用与现实挑战,并根据不同的临床应用场景和实践功能,提炼可能有助于健康教育的多智能体集合及其协同模式,旨在为未来多智能体落地护理实践提供思路。

目的：探讨人工智能结合混合式教学在肝胆外科临床教学中的应用效果。方法：选取2024年5月—2025年6月在重庆医科大学附属第二医院肝胆外科进行临床实习的90名学生，分为三组：2024年8月—11月采用传统教学模式的30名学生为对照组；2024年12月—2025年3月采用混合式教学模式的30名学生为混合式教学组；2025年3月—6月采用人工智能结合混合式教学模式的30名学生为人工智能结合混合式教学组（AI-混合组）。通过教学满意度问卷、理论知识考试、操作技能考核、临床综合思维能力评分及教学反馈，对三组教学效果进行综合评估与比较。结果：三组学生在各项教学指标中差异具有统计学意义 （P<0.05）。AI-混合组在理论成绩、技能操作、临床思维能力和教学满意度方面均显著优于对照组 and 混合式教学组，特别是在实践能力和理论掌握方面优势明显。结论：人工智能结合混合式教学模式能显著提升肝胆外科临床教学质量，增强学生的实践操作能力与临床综合素养，具有良好的推广应用价值。

Nursing education faces the dual challenges of rapidly increasing talent demand and uneven distribution of teaching resources. Traditional teaching models have obvious limitations in personalized training and practical skills development. Artificial intelligence technologies, including intelligent teaching systems, virtual simulation platforms, and natural language processing, provide innovative pathways for nursing education. Studies show that AI-assisted teaching can increase students’ average theoretical performance by 18%, shorten the time required to meet operational skill standards by 30%, and improve teaching efficiency by approximately 25%, thereby effectively supporting the construction of an integrated “theory–simulation–practice” teaching system. However, current technological applications still face problems such as insufficient accuracy in simulating complex clinical scenarios, incomplete data security mechanisms, and a decline in the quality of teacher–student interaction. In the future, efforts should focus on three major directions: constructing personalized learning pathways, integrating virtual simulation with augmented reality technologies, and developing data security mechanisms and explainable AI. These efforts will promote interdisciplinary collaboration and the establishment of full-chain intelligent support systems, ultimately achieving an organic integration of technology empowerment and the essence of education.

Against the backdrop of rapid development of medical technology and diversified patient needs, nursing education is facing innovative challenges. Traditional nursing training mainly relies on one-way knowledge transmission and mechanical operation training, which leads to insufficient clinical thinking, self-learning, and adaptability to complex situations among students. Based on the Outcome Based Education (OBE) concept, this study systematically reconstructs the nursing comprehensive skills training course and proposes a modular curriculum design framework guided by core clinical competencies, covering modules such as basic nursing operations, specialized nursing skills, and emergency treatment. Through multiple methods such as situational simulation, layered teaching, and problem-based learning (PBL), students' clinical decision-making and teamwork abilities are strengthened. A three-dimensional dynamic evaluation system including skill operation, clinical thinking, and professional ethics has been constructed, and a combination of formative evaluation and summative evaluation is adopted to track the development trajectory of students' abilities in real time.The study verified the effectiveness of the reform through empirical analysis: the experimental group's students' skill operation qualification rate increased by 23.6% compared to the traditional teaching group, the excellent rate of clinical thinking assessment increased by 18.4%, and the satisfaction rate of graduates' job competence reached 92%. Teaching feedback shows that 87.8% of students believe that practical training projects are closer to clinical practice, and 92.1% recognize the teaching value of virtual simulation platforms. Compared with traditional models, the reform curriculum has shown significant advantages in goal setting, innovative methods, and scientific evaluation, effectively shortening students' clinical adaptation period and improving the efficiency of teaching resource utilization. The study also pointed out that the current reform needs to further optimize the layered teaching strategy, strengthen interdisciplinary scenario simulation training, and establish a dynamic feedback mechanism based on big data. This study provides a replicable practical paradigm for the reform of nursing training courses, emphasizing the need for outcome oriented teaching design to closely connect with clinical needs, and promoting knowledge transfer and ability transformation through diversified teaching methods and evaluation systems. Future research will expand the sample range, explore the application of artificial intelligence and virtual reality technology in skill training, build intelligent and personalized training support systems, and promote the development of nursing education towards precision and sustainability.

This study compared scenario-based generative artificial intelligence (GenAI) patient simulation with immersive 360° virtual reality (VR) simulation in terms of perceived clinical competence, cultural awareness, AI readiness, and simulation effectiveness among nursing students. This cross-over randomised controlled study design was conducted from June 2024 to August 2024. Forty-four undergraduate nursing students from years 1–3 were randomised to receive either GenAI patient simulation (Group B) or 360° VR simulation (Group A) with a one-week washout period. Five self-reported questionnaires were used to measure clinical competency: the Clinical Competence Questionnaire (CCQ), Cultural Awareness Scale (CAS), Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS), Simulation Effectiveness Tool – Modified Questionnaire (SET-M), and a demographic questionnaire. Both interventions significantly improved clinical competence, cultural awareness, and AI readiness. When administered first, GenAI patient simulation demonstrated greater initial effects on clinical competence and AI readiness compared to the 360° VR simulation, though both groups achieved similar improvements by study completion. At T1, Group B (receiving GenAI) demonstrated significantly larger improvements in CCQ total score [47.68 (95% CI: 36.68, 58.68), p < 0.001] compared to Group A (receiving 360° VR) [24.95 (95% CI: 13.96, 35.95), p < 0.001], with significant between-group difference [16.59 (95% CI: 2.77, 30.41), p = 0.020]. At T2 (post-crossover), both groups maintained significant improvements. For MAIRS-MS (measured at baseline and following each group’s GenAI exposure), Group B showed improvement from baseline to T1 [30.18 (95% CI: 23.35, 37.01), p < 0.001] while Group A showed improvement from baseline to T2 [16.64 (95% CI: 9.80, 23.47), p < 0.001], with significant between-group difference [12.09 (95% CI: 4.43, 19.75), p = 0.003]. Both groups experienced changes in CAS scores, though between-group differences were not statistically significant. For SET-M, most participants (75%) felt debriefing contributed to their learning, and 68.2% reported increased confidence in nursing assessment skills. The findings provide preliminary evidence of its effectiveness in enhancing perceived clinical outcomes among nursing students. Both 360° VR simulation and GenAI patient simulation may serve as effective teaching tools; however, GenAI patient simulation appeared to demonstrate a greater initial effect on clinical competence and AI readiness, although both interventions proved effective across all measured domains. Not applicable.

Background: Developing engaging presimulation learning materials that provide contextualized patient information is needed to best prepare students for nursing simulation. One emerging strategy that can be used by educators to create visual images for storytelling is generative artificial intelligence (AI). Purpose: The purpose of this pilot study was to determine how the use of generative AI–created patient backstories as a presimulation strategy might affect student engagement and learning in nursing simulation. Methods: A qualitative cross-sectional survey with content analysis was completed with undergraduate nursing students following an acute care simulation. Results: Student surveys point to positive pedagogical outcomes of using AI image generation as a strategy to prepare for simulation such as decreased anxiety in simulation, increased preparatory knowledge, and increased emotional connection with the patient's story. Conclusions: Images created with generative AI hold promise for future research and transforming nursing education.

Aims This review aimed to explore the current state of generative artificial intelligence (GenAI) use in simulation-based healthcare education through a comprehensive examination of …

… Generative Artificial Intelligence (Gen AI) is increasingly being integrated into nursing simulation … about how ICU novice simulation instructors experience using Gen AI for case design. …

… simulation … nursing curricula. By highlighting both the advantages and challenges, this paper contributes to a deeper understanding of how generative AI can prepare competent nurses …

… This scoping review seeks to explore how AI is currently being integrated into simulation-… on nursing or healthcare students, simulation faculty, or simulationists engaged in simulation-…

… This scoping review identified growing momentum around generative AI's role in healthcare simulation. While early studies highlight its potential to support scalable, adaptive, and …

… High quality simulation requires a skilled educator well-versed in the simulation standards of … Generative artificial intelligence (GAI) may offer a promising avenue to support the ongoing …

Therapeutic communication is an essential nursing skill to foster nurse-patient relationships. Prelicensure nursing students experience anxiety when communicating with patients, which can impact performance. Generative artificial intelligence is a new method of simulation that offers an opportunity for nursing students to practice therapeutic communication in a safe environment. The purposes of this study were to explore: (1) the effect of generative artificial intelligence simulation on first-year baccalaureate nursing students' therapeutic communication skill; and (2) first-year baccalaureate nursing students' perceptions of using generative artificial intelligence simulation to practice therapeutic communication. Participants in the experimental group engaged in 2 virtual generative artificial intelligence simulation scenarios focused on therapeutic communication through the SimConverse platform. Findings from this study revealed nonstatistically significant higher therapeutic communication skill among students who engaged in generative AI simulation versus those who did not. Qualitative data revealed 3 themes: (1) realism, (2) practice without pressure, and (3) feedback. Given the limited, conflicting empirical findings available related to generative AI simulation and therapeutic communication among prelicensure nursing students, additional research is needed in this area. Moreover, nursing faculty need instruction on artificial intelligence to adequately train generative artificial intelligence models for appropriate use in nursing education.

The advent of artificial intelligence (AI) has prompted the introduction of novel digital technologies, including mobile learning and metaverse learning, into nursing students’ learning environments. This study used text network and topic modeling analyses to identify the research trends in generative AI in nursing education for students and patients in schools, hospitals, and community settings. Additionally, an ego network analysis using strengths, weaknesses, opportunities, and threats (SWOT) words was performed to develop a comprehensive understanding of factors that impact the integration of generative AI in nursing education. The literature was searched from five databases published until July 2024. After excluding studies whose abstracts were not available and removing duplicates, 139 articles were identified. The seven derived topics were labeled as usability in future scientific applications, application and integration of technology, simulation education, utility in image and text analysis, performance in exams, utility in assignments, and patient education. The ego network analysis focusing on the SWOT keywords revealed “healthcare”, “use”, and “risk” were common keywords. The limited emphasis on “threats”, “strengths”, and “weaknesses” compared to “opportunities” in the SWOT analysis indicated that these areas are relatively underexplored in nursing education. To integrate generative AI technology into education such as simulation training, teaching activities, and the development of personalized learning, it is necessary to identify relevant internal strengths and weaknesses of schools, hospitals, and communities that apply it, and plan practical application strategies aligned with clear institutional guidelines.

… Complex prompting and unreadiness among faculty and students are some of the reported challenges when incorporating generative artificial intelligence (GenAI) into simulation-…

… of generative artificial intelligence (AI), such as ChatGPT (Chat Generative Pre-trained Transformer), in nursing … AI can also be implemented in complex nursing simulations and decision-…

BACKGROUND Paediatric content in undergraduate nursing education is typically delivered through lectures, simulation, and clinical placements. Constraints include reduced placement availability, variable learning quality, and shortages of paediatric-qualified educators have increased reliance on simulation and virtual learning. Generative artificial intelligence (GenAI) offers scalability to support paediatric education through clinical scenarios, personalised feedback, and assessment support. AIM Identify and map existing literature on the use of GenAI in the delivery of paediatric content within undergraduate nursing programs. DESIGN This scoping review was conducted using Arksey and O'Malley's (2005) framework and reported in accordance with PRISMA-ScR guidelines. METHODS A comprehensive search of nine databases was undertaken on 8 July 2025, followed by supplementary searching in August 2025. Studies were included if they examined the use of GenAI in teaching paediatric content to undergraduate nursing students. Data was charted and synthesised narratively. RESULTS Six quantitative studies, from Asian or Middle Eastern contexts, were included. GenAI applications supported scenario-based learning, ethical reasoning, medication-safety comparisons, and assessment scoring, and were associated with improved engagement and personalised feedback. However, evidence was constrained by small, single-site designs, inconsistent GenAI reporting, reliance on self-report, and limited evaluation of competence, safety, or practice transfer. No studies included children or families' perspectives, and few addressed risks related to misinformation, developmental appropriateness, cultural safety, or bias. CONCLUSION Evidence supporting GenAI use in paediatric-focused education remains preliminary and geographically limited. While promising, applications require cautious, ethically guided implementation. Future research should prioritise multi-site, methodologically rigorous studies using paediatric-specific and safety-focused outcomes, transparent reporting, and governance that addresses privacy, bias, accuracy, and paediatric vulnerability.

Background Rapid advances in artificial intelligence (AI) offer new opportunities to address persistent challenges in healthcare professions education, particularly in oncology residency training, where rapidly evolving knowledge, complex decision-making, and limited high-fidelity practice environments hinder competency development. However, evidence from rigorously evaluated educational interventions remains limited. Methods We conducted a randomized controlled trial involving 124 breast oncology residents from three tertiary hospitals. Participants were randomly assigned to an AI-empowered intelligent teaching (AIEIT) group (n = 62) or a control group receiving conventional training (n = 62). The AIEIT model integrated a dynamic knowledge graph for personalized learning, a virtual patient–AI mentor system for adaptive skills training, a mixed-reality multidisciplinary team platform for collaborative decision-making, and a learning analytics dashboard for continuous feedback. Outcomes included knowledge acquisition, clinical reasoning, procedural competence, collaborative performance, cognitive efficiency, and longitudinal clinical outcomes. Results The AIEIT group outperformed the control group across all domains, demonstrating superior mastery of theoretical knowledge, higher procedural accuracy, and greater multidisciplinary collaboration (all P < 0.001). Cognitive workload and training time were significantly reduced, while technology adaptability and evidence-based practice utilization markedly improved. At 3-month follow-up, the AIEIT group maintained higher knowledge retention (91.2 ± 3.5% vs 76.8 ± 8.4%, P < 0.001) and better clinical outcomes, including fewer postoperative complications and higher patient satisfaction. Conclusions This study demonstrates that an AI-driven, closed-loop educational model can substantially enhance clinical competence formation in oncology residency training. By integrating data-driven personalization, human–AI collaboration, and virtual–real learning environments, the AIEIT framework offers a scalable and evidence-based approach for advancing healthcare professions education.

Cardiovascular diseases present a significant challenge in clinical practice due to their sudden onset and rapid progression. The management of these conditions necessitates cardiologists to possess strong clinical reasoning and individual competencies. The internship phase is crucial for medical students to transition from theory to practical application, with an emphasis on developing clinical thinking and skills. Despite the critical need for education on cardiovascular diseases, there is a noticeable gap in research regarding the utilization of artificial intelligence in clinical simulation teaching. This study aims to evaluate the effect and influence of AI-empowered scenario-based simulation teaching mode in the teaching of cardiovascular diseases. The study utilized a quasi-experimental research design and mixed-methods. The control group comprised 32 students using traditional teaching mode, while the experimental group included 34 students who were instructed on cardiovascular diseases using the AI-empowered scenario-based simulation teaching mode. Data collection included post-class tests, “Mini-CEX” assessments, Clinical critical thinking scale from both groups, and satisfaction surveys from experimental group. Qualitative data were gathered through semi-structured interviews. Research shows that compared with traditional teaching models, AI-empowered scenario-based simulation teaching mode significantly improve students’ performance in many aspects. The theoretical knowledge scores(P < 0.001), clinical operation skills(P = 0.0416) and clinical critical thinking abilities of students(P < 0.001) in the experimental group were significantly improved. The satisfaction survey showed that students in the experimental group were more satisfied with the teaching scene(P = 0.008), Individual participation(P = 0.006) and teaching content(P = 0.009). There is no significant difference in course discussion, group cooperation and teaching style of teachers(P > 0.05). Additionally, the qualitative data from the interviews highlighted three themes: (1) Positive new learning experience, (2) Improved clinical critical thinking skills, and (3) Valuable suggestions and concerns for further improvement. The AI-empowered scenario simulation teaching Mode plays an important role in the improvement of clinical thinking and skills of medical undergraduates. This study believes that the AI-empowered scenario simulation teaching mode is an effective and feasible teaching model, which is worthy of promotion in other courses.

In 2025, the rapid iteration of generative artificial intelligence (AI) and large language models (LLMs) has profoundly reshaped the ecosystem of medical education. This review systematically synthesizes the latest advances in AI-enabled medical education through an analysis of more than 150 core articles published in 2025 and indexed in the PubMed database. The paper first evaluates the current state of AI literacy among medical students and educators worldwide, revealing a pervasive “cognition–practice” misalignment. It then examines innovative application models of AI in curriculum integration, the development of intelligent educational tools (e.g., virtual patients and personalized tutoring systems), and AI-enhanced assessment and feedback mechanisms. Ultimately, the review examines key ethical challenges, including algorithmic bias, academic integrity, and data privacy. The findings suggest that future medical education should establish a human-centered framework of human–AI collaboration, with particular emphasis on cultivating physicians’ critical thinking and humanistic values. This review aims to provide both theoretical foundations and practical guidance for the development of a new paradigm in intelligent medical education.

This study focuses on innovative pathways for leveraging artificial intelligence (AI) technology to enhance higher education course development, with the core objective of establishing a smart course system that encompasses the entire process from course design, teaching implementation, learning support, to evaluation and feedback. Leveraging AI technologies such as knowledge graphs and large language models, a systematic smart course platform has been developed, featuring core modules including AI-assisted lesson plan design, intelligent student performance analysis, digital virtual teachers, adaptive learning pathways, and intelligent assessment feedback. Practical applications have demonstrated that the platform addresses key challenges through four pillars: ‘AI-empowered course design and planning,’ ‘innovative “teacher/student/machine” deep interaction teaching models,’ ‘adaptive learning paradigms enabling “active learning,”’ and ‘enhancing assessment methods through diversified evaluation.’ This has effectively addressed key issues such as inaccurate learning situation analysis, monotonous teaching models, insufficient teacher AI skills, and the lack of dynamic quantification in evaluations. It has significantly improved course teaching quality and student learning efficiency, providing a scalable smart course model for the digital transformation of higher education.

Artificial Intelligence is profoundly transforming innovation and development in healthcare and education. In this study, we developed an AI empowered blended learning model for disaster medicine. Leveraging the Rain Classroom platform, we established a comprehensive intelligent teaching support system covering the entire learning cycle pre class, in class, and post class. Through AI-driven enhancements, the model enables intelligent resource allocation, personalized learning paths, and high-fidelity simulation of practical training scenarios. Moreover, it addresses key challenges in traditional disaster medicine education, including fragmented knowledge delivery, insufficient practical training environments, and limited evaluation methods. Ultimately, the model enhances both the efficiency and effectiveness of disaster medicine education.

This paper describes the CPR Tutor, a real-time multimodal feedback system for cardiopulmonary resuscitation (CPR) training. The CPR Tutor detects training mistakes using recurrent neural networks. The CPR Tutor automatically recognises and assesses the quality of the chest compressions according to five CPR performance indicators. It detects training mistakes in real-time by analysing a multimodal data stream consisting of kinematic and electromyographic data. Based on this assessment, the CPR Tutor provides audio feedback to correct the most critical mistakes and improve the CPR performance. The mistake detection models of the CPR Tutor were trained using a dataset from 10 experts. Hence, we tested the validity of the CPR Tutor and the impact of its feedback functionality in a user study involving additional 10 participants. The CPR Tutor pushes forward the current state of the art of real-time multimodal tutors by providing: (1) an architecture design, (2) a methodological approach for delivering real-time feedback using multimodal data and (3) a field study on real-time feedback for CPR training. This paper details the results of a field study by quantitatively measuring the impact of the CPR Tutor feedback on the performance indicators and qualitatively analysing the participants’ questionnaire answers.

… AI has the potential to transform nursing education by providing immersive, interactive learning experiences. Nurse educators should consider integrating AI technologies while future …

This article focuses on enhancing the quality of training in nursing and midwifery specialties through the application of innovative technologies in education. The widespread integration of innovations into the education process creates expanding opportunities for the implementation of modern, sustainable, and technology-supported training methods. An innovative training system for nurses and midwives was developed and implemented over one academic year. The system incorporated educational video materials, serious games, problem-solving activities, and more. Additionally, the study explored the potential of leveraging artificial intelligence and virtual reality to enhance training effectiveness. Participants in the educational experiment were divided into an experimental group (who received additional training through innovative methods) and a control group (who underwent traditional training). Both groups underwent pre-tests and post-tests to evaluate their practical skills in injection techniques. The results demonstrated a significant improvement in the acquisition of patient care skills when modern interactive technologies were integrated into the training process. Statistical analysis confirmed the significance of the obtained results. This research provides foundational methodological guidelines for researchers, educators, and curriculum developers interested in incorporating innovative interactive technologies into healthcare education.

… This review offers the first cohesive synthesis of AI and immersive technology integration in nursing education. It provides a strategic framework for advancing educational design, …

… that allows interactive, collaborative, and immersive learning. The advancements … nursing education, and the capabilities VR and Conversational AI have in the nursing education field. …

… At the Learning level, we designed immersive experiential simulations that make it possible for learners to discover details related to the patient’s situation and practice clinical decision …

Background and Aim: Artificial intelligence (AI) is among the most promising innovations for transforming nursing education, making it more interactive, personalized, and competency-based. However, its integration also raises significant ethical and practical concerns. This scoping review aims to analyze and summarize key studies on the application of AI in university-level nursing education, focusing on its benefits, challenges, and future prospects. Methods: A scoping review was conducted using the Population, Concept, and Context (PCC) framework, targeting nursing students and educators in academic settings. A comprehensive search was carried out across the PubMed, Scopus, and Web of Science databases. Only peer-reviewed original studies published in English were included. Two researchers independently screened the studies, resolving any disagreements through team discussion. Data were synthesized narratively. Results: Of the 569 articles initially identified, 11 original studies met the inclusion criteria. The findings indicate that AI-based tools—such as virtual simulators and ChatGPT—can enhance students’ learning experiences, communication skills, and clinical preparedness. Nonetheless, several challenges were identified, including increased simulation-related anxiety, potential misuse, and ethical concerns related to data quality, privacy, and academic integrity. Conclusions: AI offers significant opportunities to enhance nursing education; however, its implementation must be approached with critical awareness and responsibility. It is essential that students develop both digital competencies and ethical sensitivity to fully leverage AI’s potential while ensuring high-quality education and responsible nursing practice.

Introduction This systematic review provides the first comprehensive synthesis of empirical studies on Artificial Intelligence (AI) integration in nursing education, offering actionable insights for nurse educators and clinical leaders. It highlights how AI transforms learning environments by enhancing personalization, feedback, and instructional efficiency. Aims To examine how AI is applied across nursing education settings and its impact on learning outcomes. Methods A systematic search of PubMed, CINAHL, IEEE Xplore, and Scopus identified peer-reviewed studies published from January 2010 to April 2025. Eligible studies focused on empirical AI applications in academic, clinical, or hybrid nursing education contexts. Studies were appraised using the Critical Appraisal Skills Programme (CASP) checklist, and findings were synthesized thematically. Results Twenty-eight studies met the inclusion criteria. AI-enhanced nursing education in four main areas: (a) personalized learning systems tailored content to individual needs, (b) simulation-based training improved decision-making in high-acuity scenarios,(c) automated assessment tools provided immediate, unbiased feedback, and (d) at the institutional level, AI supported curriculum management and predictive analytics. Common risks included technological inequities, faculty preparedness gaps, and ethical concerns around privacy and bias. Conclusion To support implementation, this study recommends: (a) integrating AI-powered simulation into emergency care training, (b) deploying adaptive platforms to support at-risk learners, and (c) using automated tools for real-time formative feedback. Diagnostic accuracy is proposed as a measurable outcome to assess impact. The next step for educators is to initiate multi-site pilot programs over 6–12 months, evaluating improvements in learning outcomes, trust, and system integration.

AIM This systematic review assesses AI's application, effectiveness and impact on nursing education, while identifying research limitations. BACKGROUND AI integration in nursing education is transforming traditional teaching and learning paradigms. DESIGN A systematic review. METHODS Following PRISMA 2020 guidelines, a search was conducted in PubMed, Web of Science, Embase, Cochrane Library and CINAHL from the inception of the databases to November 1, 2024, focusing on "Artificial Intelligence" and "nursing education." Two reviewers independently screened and assessed the literature. The quality was assessed using the Cochrane Risk of Bias 2.0 (RoB-2) tool for randomized controlled trials (RCTs), the Agency for Healthcare Research and Quality (AHRQ) tools evaluation for observational studies and the JBI Critical Appraisal Checklist for quasi-experimental studies. RESULTS Fifteen studies involving 1464 nursing students and professionals were included. The application scenarios of AI technology in nursing education are diverse and varied and it has shown significant potential in many areas of nursing education, but conflicting results have also been observed. Evaluation of literature quality showed that there were seven high-quality studies and eight medium-quality studies. Artificial intelligence was found to have a positive impact on students at three levels: learning attitude and psychological effects, learning effectiveness and comprehensive clinical nursing competencies. Key research gaps were identified, including the lack of longitudinal studies, uneven study populations and the lack of measurement instrument validity and objectivity. CONCLUSION AI positively impacts nursing education but requires further research to address gaps and ensure long-term effectiveness and privacy protection. REGISTRATION PROSPERO ID: CRD42024562849.

AIM To explore recent empirical studies on implementation of artificial intelligence in nursing education in hospital settings through the prism of the Strengths, Weaknesses, Opportunities and Threats (SWOT) model. BACKGROUND In the last decade, artificial intelligence has markedly influenced healthcare and nursing domains, particularly in improving care and educational processes for nursing staff. Despite its ongoing integration in nursing education, an understanding of its impact remained limited. DESIGN Scoping review. METHODS A systematic search using PubMed and ScienceDirect databases, following PRISMA guidelines, identified relevant studies. The main inclusion criteria were empirical studies from 2018 onwards and a focus on nursing students/registered nurses in hospital settings. The exclusion criteria were non-empirical documentation such as abstracts, editorials and opinion-related articles, as well as studies in surgical, pediatric, gynecological and mental health nursing. RESULTS In total, 15 articles were selected from a pool of 6517 documents. The aspects mentioned in the employed literature highlighted the positive impact of artificial intelligence on educational experiences, knowledge acquisition and mental safety. Challenges of the artificial intelligence implementation in the nursing education field, such as technical issues, language barriers and limited realistic experience were also identified. CONCLUSIONS The findings of the review suggest that artificial intelligence provides significant benefits for nursing education. However, continuous evaluation managing weaknesses and maximizing the educational potential of artificial intelligence in the nursing field is crucial.

The increasing integration of Artificial Intelligence (AI) and Virtual Reality (VR) in healthcare education offers innovative ways to enhance collaborative learning and improve patient safety. This narrative review examines the synergistic impact of AI-powered virtual reality (VR) simulations, such as those used in surgical training and patient communication, on knowledge acquisition, clinical skill development, and collaborative competencies among healthcare students. It also explores long-term knowledge retention, ethical considerations within virtual scenarios, and the psychological impact of high-stakes simulations on learner resilience. This review is distinguished by its exhaustive literature search, which spanned PubMed, CINAHL, Scopus, Google Scholar, and other pertinent databases, to identify studies published between 2005 and 2024. The distinct focus on AI and VR interventions in healthcare education, particularly those with outcomes related to interdisciplinary learning or patient safety, distinguishes this review. Data were thematically analyzed across domains, including adaptive learning, technical skill development, teamwork, patient safety, and ethics. The findings of this review carry significant practical implications. Five key themes emerged: adaptive learning (n = 17), immersive skill development (n = 10), teamwork enhancement (n = 10), patient safety (n = 18), and ethical considerations (n = 21). These themes underscore the potential of AI and VR in healthcare education. AI-driven adaptive systems enabled personalized VR training, enhancing engagement and knowledge retention. Real-time AI feedback during simulations improved decision-making in safe, controlled environments. Interdisciplinary team simulations enhanced communication and collaboration, which are crucial for effective clinical care. Ethical modules embedded in VR scenarios promoted moral reasoning. Several studies also reported increased learner confidence in performing clinical procedures following VR training, suggesting enhanced preparedness for practice. The integration of AI and VR holds the potential to revolutionize healthcare education, fostering personalized, immersive, and ethically informed learning. These technologies enhance technical proficiency and equip students with the complex demands of modern clinical practice. Strategic implementation can contribute to error reduction, improved patient outcomes, and a culture of safety. However, the journey is not over. Continued research is crucial for assessing the long-term outcomes and cost-effectiveness of these educational innovations, as well as for keeping pace with the rapidly evolving field of AI and VR in healthcare education.

OBJECTIVES To explore and map the evidence for virtual reality and artificial intelligence in simulation for the provision of pain education for pre and post registration nurses. DESIGN A scoping review of published and unpublished research from 2009 to 2019. DATA SOURCES Nine electronic databases and hand-searching of reference lists. REVIEW METHODS Studies were included if virtual reality or artificial intelligence interventions were used for education on pain care provision in nursing. Data were extracted and charted using an extraction tool and themes were explored using narrative analysis. RESULTS The review process resulted in the inclusion of four published studies. All studies used mixed methods and used artificial intelligence within clinical simulations as an intervention. No studies using virtual reality for pain education met the inclusion criteria. Participants of three studies were undergraduate nursing students in universities and participants in the fourth study were registered nurses within a hospital. Outcomes measured were user acceptance of the technology and feasibility in all studies. The context was hospital located and focused on acute pain episodes, with one exception being sickle cell pain. Three studies had adult patients and the other pediatric patients. The exclusion of input from a patient perspective was notable, as was a lack of interdisciplinary involvement. CONCLUSION Nurses are integral to the assessment and management of pain in many care settings requiring comprehensive communication and clinical skills. There is a paucity of research on the use of virtual reality or artificial intelligence in pain education for nurses. Current studies are preliminary in nature and/or pilot studies. Further empirical research, with robust design is required to inform nursing education, practice, and policy, thereby supporting the advancement of nursing pain education.

Technology is constantly changing and growing, and one of the areas in which it is finding ever-increasing use is the field of education. Immersive technologies and Artificial Intelligence (AI) are now a new reality in the field of education. This literature review examines the convergence of immersive technologies - such as Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) - and Artificial Intelligence (AI) in the field of education. It has revealed promising outcomes in enhancing student engagement, retention, and understanding. It explores how these technologies enhance learning experiences through engagement, personalization, and accessibility. The review identifies current trends, challenges, and opportunities, providing a comprehensive overview of existing research and possible future directions. The review synthesizes existing research to highlight the unique contributions of these technologies, their combined potential, and their impact on teaching methodologies and learning outcomes. It also addresses challenges such as costs, accessibility, and ethical considerations. The findings highlight the transformative potential of integrating immersive technologies and AI, emphasizing their role in shaping the future of education while calling for further research to maximize their benefits and mitigate limitations. This paper also identifies numerous areas for future research to explore. The objectives of this paper are: to analyze the current state of research on immersive technologies and AI in education, to identify key benefits, limitations, and challenges associated with their implementation, and to suggest future directions for research and practice.

在数字化时代，传统“灌输式”中职思政教学因忽视个性化需求、脱离实境实践，已难以适配中职生认知特点与成长诉求。本研究立足2024年“人工智能赋能创新教育生态”政策导向，聚焦生成式AI的多模态生成、情境化响应能力，先剖析“教师素养与技术应用失衡、教学目标与实践需求脱节、评价体系与个性成长错位”三大困境，再重构其“激发兴趣、深化思维、适配差异”的应用价值，最终构建“生成动态问题链、结构化支架、多元评价链”的“三阶递进”教学路径，并结合《中国特色社会主义》等课程实例验证效果。研究表明，该路径可推动中职思政教学从“离境知识传授”转向“实境素养培育”，为其数字化转型提供可操作的实践范式。

本文针对人工智能时代的护理学创新创业教育进行了探讨，构建了“护理＋X”跨界融合课程，形成了“护理+人工智能”、“护理+管理”、“护理+英语”三大课程模块。在此基础上对融合课程的课程定位、设计原则、目标等内容进行了具体的阐述，建立了“理论—实践—转化”三位一体的教学模式，并借助虚拟仿真技术、校企合作等实现“护理+X”跨界融合课程在教学过程中的落实。从目前的情况来看，这种教学模式能够有效地增强学生的跨学科意识以及创业创新意识和临床适应力，并且可以对今后护理学的人才培养起到一定的借鉴意义。

虚拟仿真技术结合了计算机技术、三维图形技术、多媒体技术等,提供多感官沉浸式体验,广泛用于多个领域。本文通过分析虚拟仿真技术在基础护理和口腔种植护理教学中的应用,总结其成效与面临的挑战。传统教学模式在培养学生自主学习和实践能力方面存在局限性,而虚拟仿真技术凭借其沉浸性和交互性,能够提高学生学习兴趣和操作技能,有效解决了传统教学中的一些不足。本文讨论了虚拟仿真技术在护理教学中遇到的技术、成本和设计等问题,并提出了相应的解决策略。

目的 探讨项目式学习在护理实习生岗前培训中对锐器伤防护技能培训的效果及其对实习期间锐器伤发生率的影响。 方法 采用便利抽样法选取2023年3月南昌理工学院医学院护理专业A、B两个班级为研究对象。采用掷硬币法将A班设为常规组, B班设为干预组。常规组接受以回顾性强化训练护理操作技能为主的常规岗前培训; 干预组在此基础上融入锐器伤防护技能的项目式学习补偿教育。采用柯氏四级培训评估模式在相应阶段自"反应、学习、行为、结果"四个递进的层面全方位评估教育效果。 结果 A班常规组和B班干预组各纳入56名护理实习生。干预组护理实习生的课程评价评分(128.67±4.39 VS 117.28±6.55)、针刺伤防护知识认知评分(109.11±4.38 VS 96.44±6.72)、安全注射行为评分(38.45±4.91 VS 32.30±5.62)、职业认同感评分(58.02±8.55 VS 51.77±15.86)、岗位胜任力评分(82.59±13.35 VS 75.61±15.09)均高于常规组, 差异均有统计学意义(均 P < 0.05)。干预组护理实习生锐器伤发生率(19.64% VS 57.14%)及平均发生频次(1.45 VS 2.13)均低于常规组; 锐器伤后例次干预率(87.50% VS 45.59%)和例次上报率(93.75% VS 32.35%)均高于常规组, 差异均有统计学意义(均 P < 0.05)。 结论 在护生岗前培训中引入项目式学习的锐器伤防护培训, 能有效提升防护技能掌握程度, 降低实习期间锐器伤发生率, 对培养护生职业防护能力具有重要实践价值。

目的 了解本科护生实习期护理职业态度的潜在类别,并分析不同潜在类别的人群特征及相关影响因素。 方法 2022年2—4月采用便利抽样法选取百色市某三级甲等医院227名本科护理专业实习生作为研究对象,采用一般资料调查问卷、护理职业态度问卷和本科实习护生临床实践能力测评量表进行调查,对其护理职业态度进行潜在剖面分析,使用无序多分类logistic回归分析护理职业态度潜在剖面分类的影响因素。 结果 百色市227名本科实习护生护理职业态度得分为（122.89±13.79）分,临床实践能力得分为（151.67±27.923）分。护理职业态度可分为护理职业态度消沉组（49.78%）、护理职业态度中立组（26.87%）和护理职业态度积极组（23.35%）3个潜在类别。临床实践能力、性别、选择护理专业原因、学业成绩、家庭成员是否有医护人员均是护理职业态度潜在类别的影响（均P<0.05）。 结论 本科护生实习期护理职业态度存在异质性,护理教育者和管理者应结合影响因素实施针对性干预,提高其护理职业态度的积极性。

目的 了解护理实习生厌恶情绪、临床归属感与职业认同的现状,并探讨临床归属感在厌恶情绪和职业认同之间的中介效应。 方法 采用便利抽样方法,于2023年12月—2024年2月选取广西壮族自治区3所高等院校的282名护理专业实习生作为研究对象,采用一般资料调查表、中文版厌恶情绪量表、临床归属感量表、职业认同量表进行调查,并对数据进行分析。 结果 282名护理实习生厌恶情绪为（46.02±10.82）分,临床归属感为（90.00±16.40）分,职业认同为（86.06±15.06）分。护理实习生厌恶情绪与临床归属感呈负相关（ r =-0.455, P <0.01）,与职业认同呈负相关（ r =-0.441, P <0.01）,临床归属感与职业认同呈正相关（ r =0.531, P <0.01）,临床归属感在厌恶情绪与职业认同之间起部分中介作用,中介效应占总效应的43.07%,中介效应的95% CI 为-0.328~-0.160。 结论 护理教育者和管理者应对护理实习生厌恶情绪进行干预,加强培养临床归属感,进而提升其职业认同感,推动护理行业发展。

目的 了解三级甲等医院实习护生患者安全态度和职业素养、临床学习环境现状及两者间的关系,为提升实习护生患者安全意识和职业素养提供科学建议。 方法 2023年5—7月,采用中文版实习学生患者安全态度和职业素养问卷、临床学习环境评估量表对重庆市、四川省、贵州省和云南省5家三级甲等医院的402名实习护生进行调查,并对数据进行分析。 结果 重庆市、四川省、贵州省和云南省5家三级甲等医院的402名实习护生患者安全态度和职业素养得分为（135.81±18.92）分,临床学习环境总分为（162.84±28.28）分;不同年龄、培养层次、实习时长的护生患者安全态度得分比较,差异均有统计学意义（均 P <0.05）,参加过患者安全培训的护生安全态度和职业素养各维度得分均显著高于未参加培训者（ P <0.05）;临床学习环境与患者安全态度和职业素养各维度均呈显著正相关（ r =0.219~0.800,均 P< 0.05）;是否参加过患者安全培训、督导关系和科室总带教角色均是患者安全态度和职业素养的重要影响因素（ β =0.201~0.302,均 P <0.05）。 结论 实习护生患者安全态度和职业素养处于较高水平,患者安全教育、良好的师生关系,以及科学的教学组织有助于实习护生患者安全意识的建立和职业素养提升。

目的 了解实习护生的患者安全态度和职业素养现状并分析其影响因素。 方法 2021年10月，选取南京市某三级甲等医院的303名实习护生作为调查对象，采用实习护生患者安全态度和职业素养量表、临床学习环境评价量表、领悟社会支持量表进行调查，并对数据进行分析。 结果 实习护生的患者安全态度和职业素养总分为（129.04±18.64）分，临床学习环境得分为（176.40±23.47）分，领悟社会支持得分为（66.50±10.67）分。不同性别、实习时间、是否发生护理差错、是否参加患者安全培训、对护理专业喜爱程度、临床实习满意度的实习护生患者安全态度和职业素养比较，差异均有统计意义（均 P <0.05）。患者安全态度和职业素养与临床学习环境、领悟社会支持均呈显著正相关（ r =0.547、0.402，均 P <0.01），临床学习环境与领悟社会支持呈显著正相关（ r =0.410， P <0.01）。临床学习环境、领悟社会支持、临床实习满意度均是实习护生的患者安全态度和职业素养的主要影响因素，共解释实习护生的患者安全态度和职业素养总变异量的34.5%。 结论 实习护生的患者安全态度和职业素养处于较高水平，但仍需进一步提升。学校及护理教育者可通过制定患者安全培训课程、改进带教老师教学方式，给予鼓励和提供社会支持等，提升护生患者安全态度 and 职业素养水平。

Abstract Background As generative artificial intelligence (GenAI) tools continue advancing, rigorous evaluations are needed to understand their capabilities relative to experienced clinicians and nurses. The aim of this study was to objectively compare the diagnostic accuracy and response formats of ICU nurses versus various GenAI models, with a qualitative interpretation of the quantitative results. Methods This formative study utilized four written clinical scenarios representative of real ICU patient cases to simulate diagnostic challenges. The scenarios were developed by expert nurses and underwent validation against current literature. Seventy‐four ICU nurses participated in a simulation‐based assessment involving four written clinical scenarios. Simultaneously, we asked ChatGPT‐4 and Claude‐2.0 to provide initial assessments and treatment recommendations for the same scenarios. The responses from ChatGPT‐4 and Claude‐2.0 were then scored by certified ICU nurses for accuracy, completeness and response. Results Nurses consistently achieved higher diagnostic accuracy than AI across open‐ended scenarios, though certain models matched or exceeded human performance on standardized cases. Reaction times also diverged substantially. Qualitative response format differences emerged such as concision versus verbosity. Variations in GenAI models system performance across cases highlighted generalizability challenges. Conclusions While GenAI demonstrated valuable skills, experienced nurses outperformed in open‐ended domains requiring holistic judgement. Continued development to strengthen generalized decision‐making abilities is warranted before autonomous clinical integration. Response format interfaces should consider leveraging distinct strengths. Rigorous mixed methods research involving diverse stakeholders can help iteratively inform safe, beneficial human‐GenAI partnerships centred on experience‐guided care augmentation. Relevance to Clinical Practice This mixed‐methods simulation study provides formative insights into optimizing collaborative models of GenAI and nursing knowledge to support patient assessment and decision‐making in intensive care. The findings can help guide development of explainable GenAI decision support tailored for critical care environments. Patient or Public Contribution Patients or public were not involved in the design and implementation of the study or the analysis and interpretation of the data.

INTRODUCTION Generative artificial intelligence (AI) is revolutionizing healthcare, necessitating corresponding advancements in nursing education to ensure that future nurses are equipped for a technologically driven environment. This article explores the imperative integration of generative AI literacy in nursing education. IMPLICATIONS FOR NURSE EDUCATORS The article delves into the practical challenges and opportunities presented by generative AI in nursing. It underscores the need for educators to adapt curricula and teaching methods to effectively incorporate generative AI learning, ensuring students are proficient in generative AI technologies and aware of their ethical implications. GENERATIVE AI LITERACY Defined as a core educational requirement, this section highlights the skills and knowledge that nurse educators must impart. It encompasses the ability to critically assess AI-generated content, understand the underlying technologies, and responsibly apply this knowledge in clinical settings. CONCLUSION The article concludes by emphasizing the urgency of integrating generative AI literacy into nursing education. It advocates for a proactive approach to curriculum development and calls for global collaboration and standardization in AI education to address the diverse and evolving needs of healthcare.

AIM The aim of this integrative review is to critically appraise and synthesise empirical evidence on the clinical applications, outcomes, and implications of generative artificial intelligence in nursing practice. DESIGN Integrative review following Whittemore and Knafl's five-stage framework. METHODS Systematic searches were performed for peer-reviewed articles and book chapters published between 1 January 2018 and 30 June 2025. Two reviewers independently screened titles/abstracts and full texts against predefined inclusion/exclusion criteria focused on generative artificial intelligence tools embedded in nursing clinical workflow (excluding nursing education-only applications). Data were extracted into a standardised matrix and appraised for quality using design-appropriate checklists. Guided by Whittemore and Knafl's integrative review framework, a constant comparative analysis was applied to derive the main themes and subthemes. DATA SOURCES CINAHL, MEDLINE, and Embase. RESULTS Included literature was a representative mix of single-group quality improvement pilots, mixed-method usability and feasibility studies, randomised controlled trials, qualitative descriptive and phenomenological studies, as well as preliminary and proof-of-concept observational research. Four overarching themes emerged: (1) Workflow Integration and Efficiency, (2) AI-Augmented Clinical Reasoning, (3) Patient-Facing Communication and Education, and (4) Role Boundaries, Ethics and Trust. CONCLUSION Generative artificial intelligence holds promise for enhancing nursing efficiency, supporting clinical decision making, and extending patient communication. However, consistent human validation, ethical boundary setting, and more rigorous, longitudinal outcome and equity evaluations are essential before widespread clinical adoption. IMPLICATIONS FOR THE PROFESSION AND PATIENT CARE Although generative artificial intelligence could reduce nurses' documentation workload and routine decision-making burden, these gains cannot be assumed. Safe and effective integration will require rigorous nurse training, robust governance, transparent labelling of AI-generated content, and ongoing evaluation of both clinical outcomes and equity impacts. Without these safeguards, generative artificial intelligence risks introducing new errors and undermining patient safety and trust. REPORTING METHOD PRISMA 2020.

… AI has the potential to transform medicine, but only if clinicians are prepared and trained to … , we can train a generation of doctors who are not just AI-aware but AI-empowered. In this …

Abstract In the first decade of this century, physicians maintained considerable professional autonomy, enabling discretionary evaluation and implementation of new technologies according to individual practice requirements. The past decade, however, has witnessed significant restructuring of medical practice patterns in the United States, with most physicians transitioning to employed status. Concurrently, technological advances and other incentives drove the implementation of electronic systems into the clinic, which these physicians were compelled to integrate. Health care practitioners have now been introduced to applications based on large language models, largely driven by artificial intelligence (AI) developers as well as established electronic health record vendors eager to incorporate these innovations. Although generative AI assistance promises enhanced clinical efficiency and diagnostic precision, its rapid advancement may potentially redefine clinical provider roles and transform workflows, as it has already altered expectations of physician productivity, as well as introduced unprecedented liability considerations. Recognition of the input of physicians and other clinical stakeholders in this nascent stage of AI integration is essential. This requires a more comprehensive understanding of AI as a sophisticated clinical tool. Accordingly, we advocate for its systematic incorporation into standard medical curricula.

BACKGROUND Artificial Intelligence (AI)-empowered health coaching (HC) has the potential to enhance HC effectiveness by providing real-time, evidence-based support. However, integrating AI into live HC sessions presents challenges, particularly in retrieval accuracy, usability, and engagement. This study evaluates the feasibility of an AI-empowered HC intervention by examining human-AI interaction within a pilot randomized controlled trial. METHODS A process evaluation was conducted using a mixed-methods approach, combining focus group discussions and post-trial quantitative assessments. We explored (i) health coaches' receptivity to AI-empowered HC before the trial, (ii) their engagement and acceptance of the AI-powered Question/Answer (Q/A) system during the trial, and (iii) their recommendations for improvements. RESULTS Health coaches expressed positive attitudes toward the AI-empowered HC model, particularly appreciating its ability to provide factual, evidence-based responses. However, engagement was hindered by challenges such as irrelevant or insufficiently detailed answers, which sometimes disrupted the HC flow. Specific recommendations for improvement included enhanced retrieval accuracy, expanded answer options, a full session history, session summaries, and a more interactive user interface. CONCLUSIONS While AI-empowered HC holds promise, current limitations in extractive Q/A accuracy must be addressed to improve usability and integration within HC workflows. Future work should focus on refining AI retrieval mechanisms, incorporating personalization features, and expanding its adaptability to diverse HC settings. These findings will inform the development of more user-centered AI-empowered HC model that effectively support human health coaches while maintaining the integrity of client interactions.

Abstract The technological advancements are invariably re-shaping the economy, and the emergence of Artificial Intelligence as the panacea is in the health sector. This thesis contemplates AI's fundamental function in avoiding healthcare system revolution including such processes as diagnosis, treatment, personalized medicine, and administrative functions among many others. AI algorithms, which include machine learning and deep learning techniques, have been shown impressive results in diagnosing and predicting the onset of diseases. Furthermore, the AI-based decision support systems can play the role of supporting clinical decision making since real-time insights as well as big data are easy to use by these systems, ultimately leading to improved treatment strategy with quality patient outcomes. This coupled with the development of an AI in precision medicine has also led to the development of personalized interventions to fit the genetic, environmental, and lifestyle factors of an individual. The establishment of such a system has started a personalized care era. Moreover, AI-equipped tools help in the interpretation of medical images and genetic data, which in turn improves the process of locating biomarkers or finding therapeutic targets for complex diseases. AI-based systems have facilitated not only medical procedures but also, they have improved the efficiency of administrative stuffs such as appointment making, billing and electronic health record maintenance. This always results in better operational efficiencies and cost saving in healthcare institutions as a result. Furthermore, AI-enabled chatbots and virtual assistance have been an instrumental factor in boosting patient engagement and granting patient access to healthcare services, particularly in distal or disenfranchised areas. Nevertheless, AI finds its usage in healthcare has its flip side the challenges and ethical concerns though. It has addressed topics including data privacy, algorithm biases, and also raised attention on the need for regulatory body. It includes the effects of AI on healthcare workforce as well highlighting the need for upskilling and reskilling of workers required for complete utilization of AI potential.

Summary Precision management of chronic diseases is crucial for improving patient quality of life and alleviating global health burdens. Advancements at the intersection of medicine and engineering, particularly through artificial intelligence (AI), have driven significant progress in precision care. From the perspective of the full life span management of chronic diseases, we focus on medicine-engineering crossover for monitoring chronic diseases, developing and implementing precision care plans, and evaluating care outcomes. Through an in-depth discussion, we address key issues such as AI’s potential to enable precision care and the challenges associated with its implementation, including data accuracy, privacy concerns, and clinical adoption. Emphasizing the importance of nurses embracing new technologies and interdisciplinary collaboration, this paper highlights how technological innovation can improve chronic disease management, particularly by enhancing care efficiency and personalizing health interventions. We aim to support the development of integrated healthcare solutions that improve patient outcomes in chronic disease management.

Introduction Artificial intelligence (AI) technologies are increasingly applied to empower clinical decision support systems (CDSS), providing patient-specific recommendations to improve clinical work. Equally important to technical advancement is human, social, and contextual factors that impact the successful implementation and user adoption of AI-empowered CDSS (AI-CDSS). With the growing interest in human-centered design and evaluation of such tools, it is critical to synthesize the knowledge and experiences reported in prior work and shed light on future work. Methods Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted a systematic review to gain an in-depth understanding of how AI-empowered CDSS was used, designed, and evaluated, and how clinician users perceived such systems. We performed literature search in five databases for articles published between the years 2011 and 2022. A total of 19874 articles were retrieved and screened, with 20 articles included for in-depth analysis. Results The reviewed studies assessed different aspects of AI-CDSS, including effectiveness (e.g., improved patient evaluation and work efficiency), user needs (e.g., informational and technological needs), user experience (e.g., satisfaction, trust, usability, workload, and understandability), and other dimensions (e.g., the impact of AI-CDSS on workflow and patient-provider relationship). Despite the promising nature of AI-CDSS, our findings highlighted six major challenges of implementing such systems, including technical limitation, workflow misalignment, attitudinal barriers, informational barriers, usability issues, and environmental barriers. These sociotechnical challenges prevent the effective use of AI-based CDSS interventions in clinical settings. Discussion Our study highlights the paucity of studies examining the user needs, perceptions, and experiences of AI-CDSS. Based on the findings, we discuss design implications and future research directions.

… clinical workflows and decision making, but deployment remains uneven. In UK clinical practice, the tool most clinicians … , without institutional guidance or training. Seamless integration …

Traditional Medicine (TM) is the oldest healthcare form and has been increasingly adopted as the primary or complementary medical therapy in the world. However, TM's practical development remains highly challenging. While artificial intelligence (AI) has become powerful in advancing modern medicine, limited attention has been paid to its potential and usage in TM. This study addresses this gap through a probe-based interview study with 16 TM clinicians, examining their experiences, perceptions, and expectations of AI-empowered clinical support systems. Our findings reveal that despite numerous AI-CDS systems, their practical usage in TM settings was still limited. We identify a series of practical challenges when integrating AI-CDS into TM clinical scenarios, largely due to TM's unique features and the significant data work challenges these features present. We end by critically discussing the potential issues that may arise when integrating AI into practical TM scenarios, and proposing a series of practical recommendations for future studies.

The paper investigates the challenges encountered in the implementation artificial intelligence (AI) in rural healthcare in China, with specific focus on the viewpoint of rural doctors. Through a mixed-methods approach combining telephone interviews and questionnaire surveys targeting rural medical practitioners, the study reveals three key dimensions of difficulty: cognitive disparities causing needs mismatch and insufficient guidance, the lack of institutional support leading to an absence of standardized and sustainable AI practices, and infrastructural constraints impeding AI integration. Based on empirical findings, the study offers practical recommendations for enhancing the deployment of AI in rural healthcare systems.

… during the medical examination and … Learning (DL) techniques and WiFi tools to monitor and verify the patient’s position continuously; the second integrates Reinforcement Learning (RL…

… Both approaches rely on human expertise, but the one that involves training artificial … PROs in clinical studies. We plan now to identify PROMs/PREMs in any field of medical research (…

Background Integrated Chinese-Western medicine (ICWM) is a distinctive medical system that plays an important role in healthcare and has received increasing attention in recent years. To facilitate the dissemination of evidence in ICWM, we developed an Artificial Intelligence (AI)-empowered Clinical Evidence for Integrated Chinese-Western Medicine (ACE-iMed) platform. Methods A multidisciplinary working group was established, including individuals with professional backgrounds in evidence-based medicine methodology, Chinese medicine (CM), Western medicine (WM), and ICWM clinical practice and research, and computer science. Through multiple rounds of discussions, the working group defined the framework and methodology of the platform, and then applied the platform to summarize evidence for eight diseases. Results The ACE-iMed platform (website: www.aceimed.org) contains two interfaces. The first enables the developers to store and screen the literature, perform methodological quality assessments, and generate evidence summaries. The AI-empowered workflows showed good consistency and stability across multiple stages, including literature screening and assessment of risk of bias/methodological quality, and effectively support summarizing evidence for eight diseases. The second interface, intended for end users, provides synchronized access to the included literature and the generated summaries, enabling quick access to clinical question-oriented evidence resources. Conclusion This study introduces an AI-empowered, clinical question-oriented ICWM evidence platform. Application across eight diseases demonstrated the platform’s feasibility and practical utility. The platform not only supports the developers in summarizing evidence but also provides end users with a potential pathway to access evidence and its summaries.

… machine learning algorithms to analyze and interpret complex traditional medical data. These models can provide disease diagnoses, treatment plans, and personalized medical advice …

… framework, which we named ‘clinical artificial-intelligence operations’ (ClinAIOps), for effectively operationalizing AI in clinical care when multiple feedback loops are involved. We lay …

Diagnostic errors in health care pose significant risks to patient safety and are disturbingly common. In the emergency department (ED), the chaotic and high‐pressure environment increases the likelihood of these errors, as emergency clinicians must make rapid decisions with limited information, often under cognitive overload. Artificial intelligence (AI) offers promising solutions to improve diagnostic errors in three key areas: information gathering, clinical decision support (CDS), and feedback through quality improvement. AI can streamline the information‐gathering process by automating data retrieval, reducing cognitive load, and providing clinicians with essential patient details quickly. AI‐driven CDS systems enhance diagnostic decision making by offering real‐time insights, reducing cognitive biases, and prioritizing differential diagnoses. Furthermore, AI‐powered feedback loops can facilitate continuous learning and refinement of diagnostic processes by providing targeted education and outcome feedback to clinicians. By integrating AI into these areas, the potential for reducing diagnostic errors and improving patient safety in the ED is substantial. However, successfully implementing AI in the ED is challenging and complex. Developing, validating, and implementing AI as a safe, human‐centered ED tool requires thoughtful design and meticulous attention to ethical and practical considerations. Clinicians and patients must be integrated as key stakeholders across these processes. Ultimately, AI should be seen as a tool that assists clinicians by supporting better, faster decisions and thus enhances patient outcomes.

Background Digital healthcare's advance has underscored an urgent requirement for solid medical record quality control, critical for data integrity, surpassing manual methods’ inadequacies. Objective The goal was to develop an AI system to manage medical record quality control comprehensively, using advanced AI like reinforcement learning and NLP to boost management's precision and efficiency. Methods This AI system uses a closed-loop framework for real-time record review using natural language processing techniques and reinforcement learning, synchronized with the hospital information system. It features a data layer for monitoring, a service layer for AI analysis, and a presentation layer for user engagement. Its impact was evaluated by comparing quality metrics pre- and post-deployment. Results With the AI system, quality control became fully operational, with review times per record plummeting from 4200 s to 2 s. The share of Grade A records rose from 89.43% to 99.21%, and the system markedly minimized formal and substantive record errors, enhancing completeness and accuracy. The implementation of the artificial intelligence-based medical record quality control system optimizes the quality control process, dynamically regulates the diagnostic behavior of medical staff, and promotes the standardization and normalization of clinical medical record writing. Conclusions The AI-driven system significantly upgraded the management of medical records in terms of efficiency and accuracy. It provides a scalable approach for hospitals to refine quality control, propelling healthcare towards heightened intelligence and automation, and foreshadowing AI's pivotal role in future healthcare quality management.

There is a growing recognition of the need for clinical trials to safely and effectively deploy artificial intelligence (AI) in clinical settings. We introduce dynamic deployment as a framework for AI clinical trials tailored for the dynamic nature of large language models, making possible complex medical AI systems which continuously learn and adapt in situ from new data and interactions with users while enabling continuous real-time monitoring and clinical validation.

In modern healthcare, treatment plans are largely static and based on episodic clinical evaluations, limiting their responsiveness to real-time changes in patient health. This paper proposes a dynamic, closed-loop system that integrates physiological and behavioral data from smartwatches—such as heart rate variability (HRV), oxygen saturation, activity levels, and sleep quality—into hospital dashboards via secure APIs and interoperability standards like FHIR. The system employs lightweight, interpretable machine learning models to detect anomalies and long-term trends in patient health. Upon detection, the system generates automated recommendations for clinicians to adjust treatment components, including medication regimens, physiotherapy protocols, and lifestyle interventions. Once approved, these suggestions are communicated to patients via mHealth interfaces, creating a bi-directional feedback loop. Designed for use in chronic disease management, elderly care, and post-operative recovery, this framework aims to improve clinical outcomes, enhance patient compliance, and reduce healthcare burden. A prototype was developed and tested using synthetic data, with preliminary results demonstrating feasibility, responsiveness, and clinical utility. This study lays the foundation for next-generation precision care systems that evolve continuously with patient needs.

Integrating artificial intelligence and new diagnostic platforms into routine clinical microbiology laboratory procedures has grown increasingly intriguing, holding promises of reducing turnaround time and cost and maximizing efficiency. At least one billion people are suffering from fungal infections, leading to over 1.6 million mortality every year. Despite the increasing demand for fungal diagnosis, current approaches suffer from manual bias, long cultivation time (from days to months), and low sensitivity (only 50% produce positive fungal cultures). Delayed and inaccurate treatments consequently lead to higher hospital costs, mobility and mortality rates. Here, we developed single-cell Raman spectroscopy and artificial intelligence to achieve rapid identification of infectious fungi. The classification between fungi and bacteria infections was initially achieved with 100% sensitivity and specificity using single-cell Raman spectra (SCRS). Then, we constructed a Raman dataset from clinical fungal isolates obtained from 94 patients, consisting of 115,129 SCRS. By training a classification model with an optimized clinical feedback loop, just 5 cells per patient (acquisition time 2 s per cell) made the most accurate classification. This protocol has achieved 100% accuracies for fungal identification at the species level. This protocol was transformed to assessing clinical samples of urinary tract infection, obtaining the correct diagnosis from raw sample-to-result within 1 h.

… In addition, we highlight the potential of artificial intelligence enhancement of CLS control … loop systems The control algorithm processes the sensor inputs to calculate, in a feedback loop…

Artificial intelligence chatbots have achieved unprecedented adoption, with millions now using these systems for emotional support and companionship in contexts of widespread social isolation and capacity-constrained mental health services. While some users report psychological benefits, concerning edge cases are emerging, including reports of suicide, violence, and delusional thinking linked to emotional relationships with chatbots. To understand these risks we need to consider the interaction between human cognitive-emotional biases and chatbot behavioural tendencies, the latter including companionship-reinforcing behaviours such as sycophancy, role-play and anthropomimesis. Individuals with preexisting mental health conditions may face increased risks of chatbot-induced changes in beliefs and behaviour, particularly where these conditions manifest in altered belief-updating, reality-testing, and social isolation. To address this emerging public health concern, we need coordinated action across clinical practice, AI development, and regulatory frameworks.

In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data—from patient records to imaging—graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters or minimal to no re-training. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pre-training, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way to clinically meaningful predictions.

Prognostic models developed for use in the intensive care unit (ICU) can inform treatment decisions and improve patient care. However, despite extensive research, few models have contributed to improved patient-centred outcomes. A major limitation is that the influence of treatment interventions on patient outcomes during model development and validation is often overlooked. Upon implementation, prognostic models can affect clinical interventions, creating feedback loops that alter the relationship between predictors and observed patient outcomes. This alteration caused by model-mediated intervention is known as model drift. Positive feedback loops reinforce initial prognoses, leading to self-fulfilling prophecies, whereas negative feedback loops obscure the efficacy of successful interventions by rendering them as apparent model inaccuracies. To mitigate these issues, prognostic models for use in ICUs should account for treatment effects and the causal relationships among predictions, interventions, and outcomes. Thus, collaboration among data scientists, epidemiologists, clinical researchers, and implementation scientists is required to ensure that prognostic models enhance patient care without causing inadvertent harm.

BACKGROUND The image segmentation of skull CT is the cornerstone for the computer-assisted craniomaxillofacial surgery in multiple aspects. This study aims to introduce an AI-enabled automatic segmentation and propose its prospect in facilitating the computer-assisted surgery. METHODS Three patients enrolled in a clinical trial of computer-assisted craniomaxillofacial surgery were randomly selected for this study. The preoperative helical CT scans of the head and neck region were subjected to the AI-enabled automatic segmentation in Mimics Viewer. The performance of AI segmentation was evaluated based on the requirements of computer-assisted surgery. RESULTS All three patients were successfully segmented by the AI-enabled automatic segmentation. The performance of AI segmentation was excellent regarding key anatomical structures. The overall quality of bone surface was satisfying. The median DICE coefficient was 92.4% for the maxilla, and 94.9% for the mandible, which fulfilled the requirements of computer-assisted craniomaxillofacial surgery. CONCLUSIONS The AI-enabled automatic segmentation could facilitate the preoperative virtual planning and postoperative outcome verification, which formed a feedback loop to enhance the current workflow of computer-assisted surgery. More studies are warranted to confirm the robustness of AI segmentation with more cases.

Background Optimization of closed-loop automated insulin delivery for patients with type 1 diabetes is still necessary. The aim of this study was to evaluate whether adding 25 mg/day to closed-loop automated insulin delivery would improve glycemic control and how safe this combined therapy would be. Methods We performed a 2 · 2 factorial randomized, placebo-controlled, crossover two-center trial in adults, comparing 4 weeks of closed-loop with sensor-augmented pump

BACKGROUND The integration of artificial intelligence in healthcare has transformed clinical practice and research methodologies. However, concerns regarding algorithmic accountability, interpretability, and safety have necessitated human oversight in AI systems. Human in the loop artificial intelligence represents a collaborative paradigm where human expertise and machine intelligence converge to enhance decision making while maintaining ethical standards and clinical safety. AIM This review synthesizes current evidence on human in the loop AI in healthcare delivery and research, examining implementation frameworks, clinical outcomes, comparative advantages over fully automated and clinician-only approaches, and challenges. METHOD A comprehensive narrative review was conducted using PubMed, Scopus, Web of Science, and IEEE Xplore databases covering studies from 2018 to 2025. Data were thematically synthesized to identify patterns, frameworks, and outcomes. This narrative approach enables comprehensive conceptual synthesis across diverse HITL-AI applications and contexts. RESULTS Human in the loop AI demonstrates significant applications across diagnostic imaging, clinical decision support, patient monitoring, drug discovery, and research data analysis. Evidence indicates improved diagnostic accuracy, reduced medical errors, enhanced patient safety, and increased clinician trust compared to both automated AI and traditional approaches. Implementation requires EHR interoperability, clear liability frameworks, adaptive training protocols, and quantum-safe cryptographic security. Challenges include workflow integration, regulatory gaps for adaptive systems, and sustainability concerns. CONCLUSION This review advances the field by synthesizing cross-domain implementation patterns, mapping collaboration models to risk-stratified contexts, identifying regulatory gaps for adaptive systems, and proposing future directions including post-quantum cryptographic integration, AI-driven adaptive architectures, and multi-center scalability frameworks for optimizing human-machine collaboration in healthcare.

Artificial intelligence (AI) is transforming dentomaxillofacial radiology education by enabling adaptive, personalized, and data-driven learning experiences. This review critically examines the pedagogical potential of AI within dental curricula, focusing on its ability to enhance student engagement, improve diagnostic competencies, and streamline clinical decision-making processes. Key innovations include real-time feedback systems, AI-guided simulations, automated assessments, and clinical decision support tools. Through these resources, AI transforms static learning into dynamic, interactive, and competency-based education. Additionally, this review discusses the integration of AI into formative assessment frameworks, such as OSCEs and mini-CEX, and its impact on student confidence, performance tracking, and educational scalability. Although primarily narrative in structure, this review synthesizes the current literature on dentomaxillofacial radiology education, supported by selected insights from medical radiology, to provide a comprehensive and up-to-date perspective on the educational applications of AI. Challenges (including ethical implications and other practical considerations) are addressed, alongside future directions for research and curriculum development. Overall, AI has the potential to significantly enhance radiology education by fostering clinically competent, ethically grounded, and technologically literate dental professionals.

Explainable Artificial Intelligence (XAI) within mental health diagnosis has emerged as a groundbreaking approach to fulfill transparency, trust and interpretability in AI-based health care systems. The present review incorporates the recent advances in applying XAI to detection, diagnosis, and management of mental health through diverse methodologies, such as linguistic analysis and social media mining and wearable biosensors and deep learning models. The studies pinpoint the importance of XAI in the interpretation of opaque AI judgments, the establishment of trust by clinicians, and ethical application in sensitive mental health settings. Most strikingly, the applications can be found in the areas of depression and psychotic disorder prediction, autism spectrum disorder assessment, and suicide risk assessment. Multimodal data fusion, logic-based neural networks, personalization and clinical usability Multimodal data fusion, logic-based neural networks, and human-centered interfaces are the emerging trends. Issues of data quality, model generalizability and understanding of the model by the users still remain to be solved by interdisciplinary efforts. The review emphasizes the importance of XAI in improving the diagnostic accuracy of AI as well as responsible AI usage in psychiatry. With explainability and deep AI growing in popularity as the mental health issues gain importance as a matter of public health, there is an opportunity to explore what explainability can bring to accessible and effective solutions to mental healthcare.

Background Errors in reasoning are a common cause of diagnostic error. However, it is difficult to improve performance partly because providers receive little feedback on diagnostic performance. Examining means of providing consistent feedback and enabling continuous improvement may provide novel insights for diagnostic performance. Methods We developed a model for improving diagnostic performance through feedback using a six-step qualitative research process, including a review of existing models from within and outside of medicine, a survey, semistructured interviews with individuals working in and outside of medicine, the development of the new model, an interdisciplinary consensus meeting, and a refinement of the model. Results We applied theory and knowledge from other fields to help us conceptualise learning and comparison and translate that knowledge into an applied diagnostic context. This helped us develop a model, the Diagnosis Learning Cycle, which illustrates the need for clinicians to be given feedback about both their confidence and reasoning in a diagnosis and to be able to seamlessly compare diagnostic hypotheses and outcomes. This information would be stored in a repository to allow accessibility. Such a process would standardise diagnostic feedback and help providers learn from their practice and improve diagnostic performance. This model adds to existing models in diagnosis by including a detailed picture of diagnostic reasoning and the elements required to improve outcomes and calibration. Conclusion A consistent, standard programme of feedback that includes representations of clinicians’ confidence and reasoning is a common element in non-medical fields that could be applied to medicine. Adapting this approach to diagnosis in healthcare is a promising next step. This information must be stored reliably and accessed consistently. The next steps include testing the Diagnosis Learning Cycle in clinical settings.

Intelligence amplification exploits the opportunities of artificial intelligence, which includes data analytic techniques and codified knowledge for increasing the intelligence of human decision makers. Intelligence amplification does not replace human decision makers but may help especially professionals in making complex decisions by well-designed human-AI system learning interactions (i.e., triple loop learning). To understand the adoption challenges of intelligence amplification systems, we analyse the adoption of clinical decision support systems (CDSS) as an organizational learning process by the case of a CDSS implementation for deciding on administering antibiotics to prematurely born babies. We identify user-oriented single and double loop learning processes, triple loop learning, and institutional deutero learning processes as organizational learning processes that must be realized for effective intelligence amplification adoption. We summarize these insights in a system dynamic model—containing knowledge stocks and their transformation processes—by which we analytically structure insights from the diverse studies of CDSS and intelligence amplification adoption and by which intelligence amplification projects are given an analytic theory for their design and management. From our case study, we find multiple challenges of deutero learning that influence the effectiveness of IA implementation learning as transforming tacit knowledge into explicit knowledge and explicit knowledge back to tacit knowledge. In a discussion of implications, we generate further research directions and discuss the generalization of our case findings to different organizations.

The integration of artificial intelligence (AI) in healthcare delivery represents a transformative opportunity to enhance the lives of people living with disabilities. AI-driven technologies, such as assistive devices, conversational agents, and rehabilitation tools, can mitigate health disparities, improve diagnostic accuracy, and facilitate effective communication with healthcare providers, fostering more equitable healthcare environments. This commentary explores these applications while addressing the ethical challenges and limitations associated with AI deployment. Specific challenges, such as algorithmic bias, privacy risks with patient data, and the complexity of designing inclusive technologies, are discussed to provide a balanced perspective. For example, biased diagnostic tools may lead to inequitable care, and privacy breaches can compromise sensitive data. Key areas of focus include personalised care through AI-powered systems, the design of inclusive AI technologies incorporating continuous feedback loops and partnerships with advocacy groups, and the development of AI-enabled robotics for physical assistance. This commentary paper emphasises the importance of addressing these limitations alongside advancing ethical AI practices and ensuring continuous user involvement to meet the diverse needs of people living with disabilities, ultimately promoting greater independence and participation in society. Consequently, while AI holds transformative potential in advancing equitable and inclusive healthcare for people with disabilities, addressing ethical challenges, overcoming limitations, and fostering user-centred design are essential to fully realise its benefits and ensure these innovations promote autonomy, accessibility, and well-being.

Background There is a lack of evidence in the literature regarding the learning outcomes of immersive technologies as educational tools for teaching university-level health care students. Objective The aim of this review is to assess the learning outcomes of immersive technologies compared with traditional learning modalities with regard to knowledge and the participants’ learning experience in medical, midwifery, and nursing preclinical university education. Methods A systematic review was conducted according to the Cochrane Collaboration guidelines. Randomized controlled trials comparing traditional learning methods with virtual, augmented, or mixed reality for the education of medicine, nursing, or midwifery students were evaluated. The identified studies were screened by 2 authors independently. Disagreements were discussed with a third reviewer. The quality of evidence was assessed using the Medical Education Research Study Quality Instrument (MERSQI). The review protocol was registered with PROSPERO (International Prospective Register of Systematic Reviews) in April 2020. Results Of 15,627 studies, 29 (0.19%) randomized controlled trials (N=2722 students) were included and evaluated using the MERSQI tool. Knowledge gain was found to be equal when immersive technologies were compared with traditional learning modalities; however, the learning experience increased with immersive technologies. The mean MERSQI score was 12.64 (SD 1.6), the median was 12.50, and the mode was 13.50. Immersive technology was predominantly used to teach clinical skills (15/29, 52%), and virtual reality (22/29, 76%) was the most commonly used form of immersive technology. Knowledge was the primary outcome in 97% (28/29) of studies. Approximately 66% (19/29) of studies used validated instruments and scales to assess secondary learning outcomes, including satisfaction, self-efficacy, engagement, and perceptions of the learning experience. Of the 29 studies, 19 (66%) included medical students (1706/2722, 62.67%), 8 (28%) included nursing students (727/2722, 26.71%), and 2 (7%) included both medical and nursing students (289/2722, 10.62%). There were no studies involving midwifery students. The studies were based on the following disciplines: anatomy, basic clinical skills and history-taking skills, neurology, respiratory medicine, acute medicine, dermatology, communication skills, internal medicine, and emergency medicine. Conclusions Virtual, augmented, and mixed reality play an important role in the education of preclinical medical and nursing university students. When compared with traditional educational modalities, the learning gain is equal with immersive technologies. Learning outcomes such as student satisfaction, self-efficacy, and engagement all increase with the use of immersive technology, suggesting that it is an optimal tool for education.

Background The adoption of immersive technology in simulation-based nursing education has grown significantly, offering a solution to resource limitations and enabling safe access to clinical environments. Despite its advantages, there are still diverse reports regarding the effectiveness of immersive technology. It is crucial to verify the effectiveness of immersive technology in nursing education to inform future educational programs. Objective This systematic review aimed to identify the contents of immersive technology–based education for undergraduate nursing students and evaluate the effectiveness of immersive technology compared to traditional teaching methods. Methods A literature search was performed using 4 databases: PubMed, CINAHL, Embase, and Web of Science; the latest search was completed on January 19, 2023. The inclusion criteria were as follows: participants were undergraduate nursing students; studies were published in Korean or English; designs included randomized controlled trials (RCTs) or nonrandomized studies; and interventions involved virtual reality (VR), augmented reality (AR), mixed reality, or extended reality. Quality assessment was conducted using Cochrane Risk-of-Bias Tool version 2 for RCTs and the Risk-of-Bias Assessment Tool for Nonrandomized Studies. The main outcomes of the included studies were classified according to the New World Kirkpatrick Model (NWKM), ranging from level 1 (reaction) to level 4 (results). Meta-analysis was conducted using RevMan 5.4 software, and subgroup analysis was conducted due to heterogeneity of the results of the meta-analysis. The Grading of Recommendations, Assessment, Development, and Evaluation approach was adopted for assessing certainty and synthesizing results of the relevant literature. Results A total of 23 studies were included, with participant numbers ranging from 33 to 289. Of these, 19 (82.6%) studies adopted VR to simulate various nursing scenarios, including disaster training, resuscitation, health assessments, and home health care; 4 (17.4%) studies used AR technologies; and 15 (65.2%) studies involved virtual patients in their scenarios. Based on the NWKM, the main outcome variables were classified as level 1 (usability and satisfaction), level 2 (knowledge, motivation, confidence, performance, attitude, and self-efficacy), and level 3 (clinical reasoning); level 4 outcomes were not found in the selected studies. Results of the subgroup analysis showed that immersive technology–based nursing education is more effective than traditional education in knowledge attainment (standard mean difference [SMD]=0.59, 95% CI 0.28-0.90, P<.001, I2=49%). Additionally, there were significant difference differences between the experimental and control group in confidence (SMD=0.70, 95% CI 0.05-1.35, P=.03, I2=82%) and self-efficacy (SMD=0.86, 95% CI 0.42-1.30, P<.001, I2=63%). Conclusions These findings support the effectiveness of immersive technology–based education for undergraduate nursing students, despite heterogeneity in methods and interventions. We suggest that long-term cohort studies be conducted to evaluate the effects of immersive technology–based nursing education on NWKM level 4.

… IVR simulation can be integrated into nursing courses following the Healthcare Simulation … of clinical education is achieved. To fully realize the benefits IVR in nursing education and …

BACKGROUND As psychiatric nursing education becomes increasingly important, there is a growing need for simulations that reflect real clinical scenarios. This study explores the effectiveness of immersive virtual reality in psychiatric nursing education for both nursing students and nurses. METHODS A comprehensive literature search was conducted in 11 databases (PubMed, Embase, CENTRAL, Web of Science, CINAHL, MEDLINE, PsycINFO, RISS, KISS, KoreaMED, and DBpia) using a search strategy based on PRISMA. RESULTS Out of 3111 studies extracted, 7 were included in the systematic review. The findings indicate that immersive virtual reality simulations in psychiatric nursing education may be beneficial in enhancing communication skills, empathy, cognitive engagement, and motivation for learning. Cognitive outcomes included increased presence and attention, but improvements in knowledge acquisition were mixed. Affective outcomes showed positive effects on empathy, reduced bias toward mental illness, and improved cultural competence. CONCLUSION This study highlights that immersive virtual reality simulation in psychiatric nursing education offers high educational effectiveness and realism, making it a promising alternative to traditional teaching methods.