Nurse Education in Practice最新文献_第2页

Hearing the deaf nursing student: Navigating inclusive nurse education in ableist learning environments 聋人护理学生的听力：在残疾学习环境中导航全纳护理教育

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-10 DOI: 10.1016/j.nepr.2026.104719

Rachel Birch , Christopher Seymour , Samuel Beckett , Gayatri Nambiar-Greenwood

Aim

This aim of this discussion paper is to explore and reflect those biases and limiting discriminatory practices of those of us entrusted to support the educational journey of a deaf Mental Health student nurse, through his lens, to reconsider and re-examine what it means to be genuinely inclusive.

Background

Adopting an ethos of social justice, this discussion connects the narrative of this student to those who supported him through his 3-year degree learning experience in university and clinical placements. Our reflections as educators are based on deconstructing and connecting concepts around ableist, stigmatizing discrimination alongside the student narrative.

Design

A critical discussion paper.

Methods

Adopting the principles of a qualitative case study approach as a reflective evaluation to interrogate our pre-judgments, thought processes and habitual responses, to understand our complex roles in relation to enabling successful student journeys.

Results

The inclusion of a deaf student in a ‘hearing’ cohort required pre-planning and great thought, for it to be truly inclusive. Although practical solutions to the physicality of communication was resolvable, the greater challenge and constant advocative negotiations from his Personal Tutor came from pre-conceived ideas and attitudes more in adult placement settings, whose apprehensions of this students’ learning fixated around safety, responding to emergency bells and fast communication.

Conclusions

The approach to a person with disabilities needs to begin with the assumption that everyone has a right to contribute to and benefit from higher education and an equal chance to be what they perceive as their contribution to society.

目的本讨论文件的目的是通过他的镜头，探索和反映我们这些受托支持聋人心理健康学生护士的教育旅程的人的偏见和限制歧视性做法，重新考虑和重新审视真正包容的意义。采用社会正义的精神，这个讨论将这个学生的叙述与那些通过他在大学和临床实习的3年学位学习经历支持他的人联系起来。作为教育工作者，我们的反思是基于解构和联系围绕残疾主义者的概念，将歧视与学生的叙述联系起来。设计一篇重要的讨论论文。方法采用定性案例研究方法的原则作为反思性评估，询问我们的预判断、思维过程和习惯性反应，以了解我们在成功的学生旅程中所扮演的复杂角色。结果将失聪学生纳入“听力正常”的群体需要事先计划和深思熟虑，才能真正做到包容。虽然物理沟通的实际解决方案是可以解决的，但他的私人导师更大的挑战和不断的倡导谈判更多地来自于成人安置环境中先入为主的想法和态度，他们对学生学习的理解围绕着安全，应对紧急铃声和快速沟通。对待残疾人的方式需要从这样一个假设开始：每个人都有权利为高等教育做出贡献并从中受益，并且有平等的机会成为他们认为对社会的贡献。

{"title":"Hearing the deaf nursing student: Navigating inclusive nurse education in ableist learning environments","authors":"Rachel Birch , Christopher Seymour , Samuel Beckett , Gayatri Nambiar-Greenwood","doi":"10.1016/j.nepr.2026.104719","DOIUrl":"10.1016/j.nepr.2026.104719","url":null,"abstract":"<div><h3>Aim</h3><div>This aim of this discussion paper is to explore and reflect those biases and limiting discriminatory practices of those of us entrusted to support the educational journey of a deaf Mental Health student nurse, through his lens, to reconsider and re-examine what it means to be genuinely inclusive.</div></div><div><h3>Background</h3><div>Adopting an ethos of social justice, this discussion connects the narrative of this student to those who supported him through his 3-year degree learning experience in university and clinical placements. Our reflections as educators are based on deconstructing and connecting concepts around ableist, stigmatizing discrimination alongside the student narrative.</div></div><div><h3>Design</h3><div>A critical discussion paper.</div></div><div><h3>Methods</h3><div>Adopting the principles of a qualitative case study approach as a reflective evaluation to interrogate our pre-judgments, thought processes and habitual responses, to understand our complex roles in relation to enabling successful student journeys.</div></div><div><h3>Results</h3><div>The inclusion of a deaf student in a ‘hearing’ cohort required pre-planning and great thought, for it to be truly inclusive. Although practical solutions to the physicality of communication was resolvable, the greater challenge and constant advocative negotiations from his Personal Tutor came from pre-conceived ideas and attitudes more in adult placement settings, whose apprehensions of this students’ learning fixated around safety, responding to emergency bells and fast communication.</div></div><div><h3>Conclusions</h3><div>The approach to a person with disabilities needs to begin with the assumption that everyone has a right to contribute to and benefit from higher education and an equal chance to be what they perceive as their contribution to society.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104719"},"PeriodicalIF":4.0,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Operationalizing joy in nursing education: Simulation and interprofessional learning as catalysts for resilience and renewal 在护理教育中实施快乐：模拟和跨专业学习作为恢复力和更新的催化剂

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-09 DOI: 10.1016/j.nepr.2026.104718

Mohammed Al-Hassan

Aim

To propose a conceptual framework that repositions joy as a pedagogical imperative in nursing education and demonstrates how Simulation-Based Learning (SBL) and Interprofessional Education (IPE) can serve as catalysts for cultivating resilience, connection and renewal.

Background

Burnout, moral distress and disengagement among students and educators have revealed the emotional fragility of current educational systems. The Institute for Healthcare Improvement’s Framework for Joy in Work and Bernard’s values alignment theory suggest that joy is not an emotional byproduct but a strategic condition for engagement and well-being.

Design

This paper presents a conceptual synthesis integrating insights from positive psychology, learning science and organizational theory to advance The Joyful Learning Cycle (JLC), a new model for embedding joy as a design principle in nursing education.

Methods

The JLC model was developed through theoretical integration of existing frameworks and reflective analysis of SBL and IPE pedagogies. The five interrelated phases, Inquiry, Connection, Reflection, Celebration and Renewal, operationalize joy as a regenerative, teachable process.

Results

SBL and IPE are identified as high-impact educational modalities that naturally support the cultivation of joy through psychological safety, collective efficacy and shared purpose. The JLC demonstrates how joy can be intentionally designed, measured and sustained within faculty development and curriculum design.

Conclusions

Joy is a pedagogical vital sign, an indicator of learning health and educator well-being. Embedding joy alongside competence as a core metric can transform nursing education into a system that not only trains skilled professionals but sustains the humanity of those who teach and learn.

目的提出一个概念框架，将快乐重新定位为护理教育的教学要求，并展示基于模拟的学习（SBL）和跨专业教育（IPE）如何成为培养弹性、联系和更新的催化剂。学生和教育工作者的职业倦怠、道德困境和脱离参与揭示了当前教育系统在情感上的脆弱性。医疗保健改进研究所的工作乐趣框架和伯纳德的价值观一致性理论表明，快乐不是情感的副产品，而是参与和幸福的战略条件。本文综合了积极心理学、学习科学和组织理论的见解，提出了一个概念综合，以推进快乐学习周期（JLC），这是一个将快乐作为护理教育设计原则的新模型。方法通过对现有框架的理论整合，以及对SBL和IPE教学法的反思分析，构建JLC模型。五个相互关联的阶段，探究，连接，反思，庆祝和更新，将快乐作为一个再生的，可教的过程进行操作。结果ssbl和IPE被认为是高影响力的教育模式，通过心理安全、集体效能和共同目标自然地支持快乐的培养。JLC展示了如何在教师发展和课程设计中有意地设计、衡量和维持快乐。结论快乐是教学生命体征，是学习健康和教育者幸福感的指标。将快乐与能力一起作为核心衡量标准，可以将护理教育转变为一个不仅培养熟练的专业人员，而且保持教与学人员人性的体系。

{"title":"Operationalizing joy in nursing education: Simulation and interprofessional learning as catalysts for resilience and renewal","authors":"Mohammed Al-Hassan","doi":"10.1016/j.nepr.2026.104718","DOIUrl":"10.1016/j.nepr.2026.104718","url":null,"abstract":"<div><h3>Aim</h3><div>To propose a conceptual framework that repositions joy as a pedagogical imperative in nursing education and demonstrates how Simulation-Based Learning (SBL) and Interprofessional Education (IPE) can serve as catalysts for cultivating resilience, connection and renewal.</div></div><div><h3>Background</h3><div>Burnout, moral distress and disengagement among students and educators have revealed the emotional fragility of current educational systems. The Institute for Healthcare Improvement’s Framework for Joy in Work and Bernard’s values alignment theory suggest that joy is not an emotional byproduct but a strategic condition for engagement and well-being.</div></div><div><h3>Design</h3><div>This paper presents a conceptual synthesis integrating insights from positive psychology, learning science and organizational theory to advance The Joyful Learning Cycle (JLC), a new model for embedding joy as a design principle in nursing education.</div></div><div><h3>Methods</h3><div>The JLC model was developed through theoretical integration of existing frameworks and reflective analysis of SBL and IPE pedagogies. The five interrelated phases, Inquiry, Connection, Reflection, Celebration and Renewal, operationalize joy as a regenerative, teachable process.</div></div><div><h3>Results</h3><div>SBL and IPE are identified as high-impact educational modalities that naturally support the cultivation of joy through psychological safety, collective efficacy and shared purpose. The JLC demonstrates how joy can be intentionally designed, measured and sustained within faculty development and curriculum design.</div></div><div><h3>Conclusions</h3><div>Joy is a pedagogical vital sign, an indicator of learning health and educator well-being. Embedding joy alongside competence as a core metric can transform nursing education into a system that not only trains skilled professionals but sustains the humanity of those who teach and learn.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104718"},"PeriodicalIF":4.0,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A large language model-powered reflective AI agent for evidence-based nursing education: Design and evaluation 基于循证护理教育的大型语言模型驱动的反思性人工智能代理：设计和评估

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-09 DOI: 10.1016/j.nepr.2026.104710

Shuqi Yang , Manfei Shi , Yuhang Qian , Tiantian Hu , Zongan Huang , Shuai Wang , Zheng Zhu

Aim

To develop and evaluate the Evidence-Based Nursing Expert (EBN-Expert), a domain-specific intelligent agent designed to support reflective learning in evidence-based nursing education.

Background

Evidence-based practice (EBP) is a core competency in nursing education yet remains challenging for students to master due to its emphasis on critical thinking and decision-making. Traditional teaching methods often fall short in fostering these higher-order skills. While large language models (LLMs) are increasingly used in education, general-purpose systems offer limited support for the specific demands of EBP.

Design

A comparative evaluation study using standardized exam questions aligned with a widely used evidence-based nursing curriculum.

Methods

The EBN-Expert was constructed with content from the textbook Evidence-Based Nursing and designed around a closed-loop workflow incorporating Retrieval, Reflection and Decision-making modules. The system was evaluated using 124 standardized test items and compared with three leading general-purpose LLMs: ChatGPT-o1, DeepSeek-R1 and Kimi.

Results

The EBN-Expert significantly outperformed three general-purpose models (P < 0.001), achieving the highest overall score (1035.00 ± 17.32). It led in most of the 12 textbook chapters, especially in those requiring methodological or interpretive reasoning. It maintained perfect accuracy in true/false questions and excelled in multiple-choice formats. A mixed effects model further confirmed its superior accuracy and response consistency, especially at intermediate difficulty levels (Level 2 and Level 4).

Conclusion

The EBN-Expert illustrates the promise of domain-specific generative AI tools in nursing education. Its alignment with curriculum structure, high accuracy and reflective reasoning capabilities position it as a scalable and trustworthy approach for advancing EBP training.

目的开发和评估循证护理专家（EBN-Expert），这是一个特定领域的智能代理，旨在支持循证护理教育中的反思性学习。基于证据的实践（EBP）是护理教育的核心能力，但由于其强调批判性思维和决策，对学生来说仍然具有挑战性。传统的教学方法在培养这些高级技能方面往往不足。虽然大型语言模型（llm）越来越多地用于教育，但通用系统对EBP的特定需求提供有限的支持。设计一项比较评估研究，采用与广泛使用的循证护理课程相一致的标准化考试问题。方法采用循证护理教材内容构建EBN-Expert，并以检索、反思、决策模块为闭环工作流进行设计。该系统使用124个标准化测试项目进行评估，并与三种领先的通用llm （chatgpt - 01、DeepSeek-R1和Kimi）进行了比较。结果EBN-Expert显著优于3种通用模型（P <； 0.001），获得最高的综合得分（1035.00 ± 17.32）。它在12个教科书章节中的大部分章节中占据主导地位，尤其是那些需要方法论或解释性推理的章节。它在真假问题中保持了完美的准确性，在多项选择题中表现出色。混合效应模型进一步证实了其较好的准确率和反应一致性，特别是在中等难度水平（Level 2和Level 4）。ebn专家展示了特定领域的生成人工智能工具在护理教育中的前景。它与课程结构、高精度和反思推理能力相一致，使其成为推进EBP培训的可扩展和值得信赖的方法。

{"title":"A large language model-powered reflective AI agent for evidence-based nursing education: Design and evaluation","authors":"Shuqi Yang , Manfei Shi , Yuhang Qian , Tiantian Hu , Zongan Huang , Shuai Wang , Zheng Zhu","doi":"10.1016/j.nepr.2026.104710","DOIUrl":"10.1016/j.nepr.2026.104710","url":null,"abstract":"<div><h3>Aim</h3><div>To develop and evaluate the <em>Evidence-Based Nursing Expert (EBN-Expert),</em> a domain-specific intelligent agent designed to support reflective learning in evidence-based nursing education.</div></div><div><h3>Background</h3><div>Evidence-based practice (EBP) is a core competency in nursing education yet remains challenging for students to master due to its emphasis on critical thinking and decision-making. Traditional teaching methods often fall short in fostering these higher-order skills. While large language models (LLMs) are increasingly used in education, general-purpose systems offer limited support for the specific demands of EBP.</div></div><div><h3>Design</h3><div>A comparative evaluation study using standardized exam questions aligned with a widely used evidence-based nursing curriculum.</div></div><div><h3>Methods</h3><div>The <em>EBN-Expert</em> was constructed with content from the textbook <em>Evidence-Based Nursing</em> and designed around a closed-loop workflow incorporating Retrieval, Reflection and Decision-making modules. The system was evaluated using 124 standardized test items and compared with three leading general-purpose LLMs: ChatGPT-o1, DeepSeek-R1 and Kimi.</div></div><div><h3>Results</h3><div>The <em>EBN-Expert</em> significantly outperformed three general-purpose models (<em>P</em> < 0.001), achieving the highest overall score (1035.00 ± 17.32). It led in most of the 12 textbook chapters, especially in those requiring methodological or interpretive reasoning. It maintained perfect accuracy in true/false questions and excelled in multiple-choice formats. A mixed effects model further confirmed its superior accuracy and response consistency, especially at intermediate difficulty levels (Level 2 and Level 4).</div></div><div><h3>Conclusion</h3><div>The <em>EBN-Expert</em> illustrates the promise of domain-specific generative AI tools in nursing education. Its alignment with curriculum structure, high accuracy and reflective reasoning capabilities position it as a scalable and trustworthy approach for advancing EBP training.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104710"},"PeriodicalIF":4.0,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to "Voices from the ICU: Nursing students' experiences of family involvement in patient care" [Nurse Educ. Pract. 90 (2026), 104625]. “来自ICU的声音：护理学生的家庭参与病人护理的经验”的更正[护士教育]。实践，90(2026),104625]。

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-08 DOI: 10.1016/j.nepr.2026.104708

Deema Mahasneh, Noordeen Shoqirat, Charleen Singh, Tuba Sengul, Zyrene Marsh, Joanne Jody Minnick

引用次数: 0

End-of-life care preparedness program for senior nursing students in Türkiye: Effects on attitudes and self-efficacy in a randomized controlled trial <s:1>基耶大学护生临终关怀准备计划：对态度和自我效能感的随机对照试验

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-08 DOI: 10.1016/j.nepr.2026.104717

Sinem Öcalan , Aylin Bilgin , Hilal Altundal Duru , Mustafa Sabri Kovancı

Aim

To evaluate the effectiveness of an online End-of-Life Care Preparedness Program on senior nursing students’ attitudes toward caring for dying patients and their self-efficacy in end-of-life care.

Background

Senior nursing students often experience fear and uncertainty when facing death due to insufficient preparation and limited clinical exposure, which may hinder the provision of quality end-of-life care. Structured, culturally adapted educational interventions are therefore needed to enhance readiness and competence.

Design

Randomized controlled trial with pre-test, post-test and one-month follow-up assessments.

Methods

Sixty senior nursing students from two universities were randomized to either an intervention group receiving the End-of-Life Care Preparedness Program (four weekly 90-minute online sessions via Microsoft Teams) or a control group continuing routine education. Data were collected between April and June 2025 (pre-test in April, post-test in May, follow-up in June). Outcomes were measured using the Frommelt Attitudes Toward Care of the Dying Scale (FATCOD) and the End-of-Life and Postmortem Self-Efficacy Scale (ELPSES). Data were analyzed using repeated-measures GLM with Bonferroni-adjusted comparisons.

Results

The intervention group showed a significant increase in attitudes and self-efficacy from pre-test to post-test, sustained at one-month follow-up (p < 00.001). The control group demonstrated a decline. Time × group interactions were significant for attitudes (F = 31.854, p < 00.001, ηp² =.359) and self-efficacy (F = 14.224, p < 00.001, ηp² =.200).

Conclusion

The program significantly improved students’ attitudes and self-efficacy with sustained effects, underscoring the need to integrate culturally sensitive, digitally delivered death education into nursing curricula.

目的评价在线临终关怀预备课程对高年级护生临终关怀态度及临终关怀自我效能感的影响。背景：由于准备不足和临床接触有限，高年级护理学生在面对死亡时经常感到恐惧和不确定，这可能会阻碍提供高质量的临终关怀。因此，需要有结构的、适应文化的教育干预措施来提高准备和能力。设计随机对照试验，包括测试前、测试后和1个月随访评估。方法60名来自两所大学的护理系高年级学生随机分为干预组和对照组，实验组接受临终关怀准备计划（每周4次，每次90分钟，通过Microsoft Teams进行在线培训）。数据收集时间为2025年4月至6月（4月前测，5月后测，6月随访）。结果采用Frommelt临终关怀态度量表（FATCOD）和临终和死后自我效能量表（elpse）进行测量。数据分析采用重复测量GLM和bonferroni调整比较。结果干预组的态度和自我效能感从测试前到测试后显著提高，并持续1个月（p <； 00.001）。对照组表现出衰退。时间× 组交互作用对态度（F = 31.854, p & 00.001,ηp²= 0.359）和自我效能（F = 14.224, p <； 00.001,ηp²= 0.200）有显著影响。结论该项目显著改善了学生的态度和自我效能感，且效果持续，强调了将文化敏感的数字化死亡教育纳入护理课程的必要性。

{"title":"End-of-life care preparedness program for senior nursing students in Türkiye: Effects on attitudes and self-efficacy in a randomized controlled trial","authors":"Sinem Öcalan , Aylin Bilgin , Hilal Altundal Duru , Mustafa Sabri Kovancı","doi":"10.1016/j.nepr.2026.104717","DOIUrl":"10.1016/j.nepr.2026.104717","url":null,"abstract":"<div><h3>Aim</h3><div>To evaluate the effectiveness of an online End-of-Life Care Preparedness Program on senior nursing students’ attitudes toward caring for dying patients and their self-efficacy in end-of-life care.</div></div><div><h3>Background</h3><div>Senior nursing students often experience fear and uncertainty when facing death due to insufficient preparation and limited clinical exposure, which may hinder the provision of quality end-of-life care. Structured, culturally adapted educational interventions are therefore needed to enhance readiness and competence.</div></div><div><h3>Design</h3><div>Randomized controlled trial with pre-test, post-test and one-month follow-up assessments.</div></div><div><h3>Methods</h3><div>Sixty senior nursing students from two universities were randomized to either an intervention group receiving the End-of-Life Care Preparedness Program (four weekly 90-minute online sessions via Microsoft Teams) or a control group continuing routine education. Data were collected between April and June 2025 (pre-test in April, post-test in May, follow-up in June). Outcomes were measured using the Frommelt Attitudes Toward Care of the Dying Scale (FATCOD) and the End-of-Life and Postmortem Self-Efficacy Scale (ELPSES). Data were analyzed using repeated-measures GLM with Bonferroni-adjusted comparisons.</div></div><div><h3>Results</h3><div>The intervention group showed a significant increase in attitudes and self-efficacy from pre-test to post-test, sustained at one-month follow-up (p < 00.001). The control group demonstrated a decline. Time × group interactions were significant for attitudes (F = 31.854, p < 00.001, ηp² =.359) and self-efficacy (F = 14.224, p < 00.001, ηp² =.200).</div></div><div><h3>Conclusion</h3><div>The program significantly improved students’ attitudes and self-efficacy with sustained effects, underscoring the need to integrate culturally sensitive, digitally delivered death education into nursing curricula.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104717"},"PeriodicalIF":4.0,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interpreting free-text cardiac catheterisation reports: A machine learning approach informed by focused ethnography 解读自由文本心导管检查报告：一种由重点人种学提供信息的机器学习方法

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-08 DOI: 10.1016/j.nepr.2026.104715

Lu-Yen Anny Chen , En-Hau Yeh , Phone Lin , Mu-Yang Hsieh , Cheng-Pei Lin , Zih-Yong Liao

Aim

To examine how focused ethnographic insights can inform the development of a machine learning pipeline to improve the extraction of clinically relevant information from percutaneous coronary intervention (PCI) documentation and support nursing education and practice.

Background

Cardiac catheterisation procedures produce detailed documentation, often embedded in free-text fields in electronic health records. For nurses delivering post-procedural care, extracting this information is time-consuming and prone to error. While machine learning (ML) offers automation potential, many models struggle to handle contextual and structural inconsistencies in real-world documentation.

Design

A qualitative-informed machine learning study using focused ethnography and rule-based model development.

Methods

The study was conducted at a tertiary medical centre in Taiwan and included 200 h of non-participant ethnographic observation to explore documentation practices in PCI reporting. Ethnographic data were thematically analysed to identify structural patterns, linguistic variability and workflow behaviours. These insights informed the iterative development of a rule-based ML pipeline, which was tested on 4128 de-identified PCI reports to evaluate extraction accuracy.

Results

Three key patterns were identified: structured use of templates, formatting inconsistencies and free-form narrative variability. These informed the application of four extraction strategies: (1) rule-based and ontology-driven methods; (2) statistical topic modelling; (3) deep learning models and (4) large language models. A rule-based approach was selected for its adaptability and interpretability. Extraction accuracy exceeded 99 % in structured fields and approximately 50 % in narrative-rich sections.

Conclusion

Combining ethnography with machine learning enhances automated clinical documentation interpretation and supports AI-informed nursing education through improved digital literacy and contextual awareness.

目的研究集中的人种学见解如何为机器学习管道的发展提供信息，以改进从经皮冠状动脉介入治疗（PCI）文件中提取临床相关信息，并支持护理教育和实践。心导管手术产生详细的文档，通常嵌入在电子健康记录的自由文本字段中。对于提供术后护理的护士来说，提取这些信息既耗时又容易出错。虽然机器学习（ML）提供了自动化潜力，但许多模型难以处理现实世界文档中的上下文和结构不一致。设计一个定性的机器学习研究，使用集中的人种学和基于规则的模型开发。方法本研究在台湾某三级医疗中心进行，包括200 h的非参与性人种学观察，以探讨PCI报告的文献实践。对人种学数据进行了主题分析，以确定结构模式、语言可变性和工作流程行为。这些见解为基于规则的ML管道的迭代开发提供了信息，该管道在4128份去识别的PCI报告上进行了测试，以评估提取的准确性。结果确定了三个关键模式：模板的结构化使用、格式的不一致性和自由形式的叙述可变性。这为四种提取策略的应用提供了依据：(1)基于规则和本体驱动的方法；(2)统计主题建模；(3)深度学习模型和(4)大型语言模型。基于规则的方法具有适应性和可解释性。在结构化领域的提取精度超过99% %，在富含叙述的领域的提取精度约为50% %。结论：将民族志与机器学习相结合，可以增强临床文献的自动化解释，并通过提高数字素养和上下文意识来支持人工智能护理教育。

{"title":"Interpreting free-text cardiac catheterisation reports: A machine learning approach informed by focused ethnography","authors":"Lu-Yen Anny Chen , En-Hau Yeh , Phone Lin , Mu-Yang Hsieh , Cheng-Pei Lin , Zih-Yong Liao","doi":"10.1016/j.nepr.2026.104715","DOIUrl":"10.1016/j.nepr.2026.104715","url":null,"abstract":"<div><h3>Aim</h3><div>To examine how focused ethnographic insights can inform the development of a machine learning pipeline to improve the extraction of clinically relevant information from percutaneous coronary intervention (PCI) documentation and support nursing education and practice.</div></div><div><h3>Background</h3><div>Cardiac catheterisation procedures produce detailed documentation, often embedded in free-text fields in electronic health records. For nurses delivering post-procedural care, extracting this information is time-consuming and prone to error. While machine learning (ML) offers automation potential, many models struggle to handle contextual and structural inconsistencies in real-world documentation.</div></div><div><h3>Design</h3><div>A qualitative-informed machine learning study using focused ethnography and rule-based model development.</div></div><div><h3>Methods</h3><div>The study was conducted at a tertiary medical centre in Taiwan and included 200 h of non-participant ethnographic observation to explore documentation practices in PCI reporting. Ethnographic data were thematically analysed to identify structural patterns, linguistic variability and workflow behaviours. These insights informed the iterative development of a rule-based ML pipeline, which was tested on 4128 de-identified PCI reports to evaluate extraction accuracy.</div></div><div><h3>Results</h3><div>Three key patterns were identified: structured use of templates, formatting inconsistencies and free-form narrative variability. These informed the application of four extraction strategies: (1) rule-based and ontology-driven methods; (2) statistical topic modelling; (3) deep learning models and (4) large language models. A rule-based approach was selected for its adaptability and interpretability. Extraction accuracy exceeded 99 % in structured fields and approximately 50 % in narrative-rich sections.</div></div><div><h3>Conclusion</h3><div>Combining ethnography with machine learning enhances automated clinical documentation interpretation and supports AI-informed nursing education through improved digital literacy and contextual awareness.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104715"},"PeriodicalIF":4.0,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging AI simulations for enhancing cultural responsiveness and interprofessional collaboration in health professions education 利用人工智能模拟增强卫生专业教育中的文化响应能力和跨专业协作

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-06 DOI: 10.1016/j.nepr.2026.104711

Zahra Aziz , Amna C. Mazeh , Dragan Ilic , Melissa Ciardulli , Safae Nour El Hadi , Alberto Camuccio , Joel Moore , Debra Kiegaldie

Aim

This project leverages AI-driven simulation to create immersive, culturally rich learning experiences that foster students’ development of cultural competence and interprofessional collaboration skills.

Background

Cultural competence and interprofessional collaboration are essential skills for future clinicians, yet traditional teaching methods often fall short in providing immersive, patient-centred learning experiences. AI-driven simulations offer a promising way to bridge this gap by creating realistic, interactive scenarios that engage students in meaningful, culturally nuanced clinical encounters.

Design/Methods

This project introduced Aalia, an AI-driven simulation featuring a 32 year-old Middle Eastern woman navigating the Italian healthcare system, delivered via a platform called ATLAS. Conducted in a synchronous 45-minute Zoom session, the simulation engaged over 130 health professions students and 20 educators from four countries. Working in interprofessional teams across ten breakout rooms, students interacted with Aalia through over 350 conversations and received automated feedback via ATLAS to support reflection and skill development.

Results

Evaluation results showed strong student agreement on the simulation’s value, with 94 % expressing interest in future AI simulations and 91 % reporting improved understanding of empathy in care. Simulate effectiveness was highly rated, notably, 89 % found the simulation realistic and engaging, 90 % engaging and 88 % felt it increased their confidence in providing culturally responsive healthcare. Interestingly, 67 % appreciated AI-generated feedback as more tolerable compared to teacher-given feedback.

Conclusions

Aalia’s narrative provided a high-quality and authentic virtual environment for practising culturally responsive, collaborative care. This AI-driven simulation reinforced teamwork as essential in professional practice. Educators found it effective and easy to use, with significant potential for wider application.

该项目利用人工智能驱动的模拟来创造身临其境的、文化丰富的学习体验，培养学生的文化能力和跨专业协作技能。文化能力和跨专业合作是未来临床医生的基本技能，然而传统的教学方法往往无法提供身临其境的、以患者为中心的学习体验。人工智能驱动的模拟为弥合这一差距提供了一种很有希望的方式，通过创造现实的、互动的场景，让学生参与到有意义的、文化上细微差别的临床接触中。设计/方法该项目引入了Aalia，这是一个人工智能驱动的模拟，通过ATLAS平台交付，描述了一名32岁的中东妇女在意大利医疗系统中的导航。模拟在同步45分钟的Zoom会议中进行，来自四个国家的130多名卫生专业学生和20名教育工作者参与了模拟。学生们在10个分组讨论室的跨专业团队中与Aalia进行了350多次对话，并通过ATLAS获得了自动反馈，以支持反思和技能发展。结果评估结果显示，学生对模拟的价值有强烈的认同，94% %的学生表示对未来的人工智能模拟感兴趣，91% %的学生表示对护理中的同理心有了更好的理解。模拟的有效性被高度评价，值得注意的是，89% %的人认为模拟是真实的和引人入胜的，90% %的人引人入胜，88% %的人认为它增加了他们提供文化响应性医疗保健的信心。有趣的是，67% %的人认为人工智能生成的反馈比老师给出的反馈更容易接受。结论saalia的叙事为实践文化响应、协作式护理提供了高质量、真实的虚拟环境。这种人工智能驱动的模拟强化了团队合作在专业实践中的重要性。教育工作者发现它有效且易于使用，具有广泛应用的巨大潜力。

{"title":"Leveraging AI simulations for enhancing cultural responsiveness and interprofessional collaboration in health professions education","authors":"Zahra Aziz , Amna C. Mazeh , Dragan Ilic , Melissa Ciardulli , Safae Nour El Hadi , Alberto Camuccio , Joel Moore , Debra Kiegaldie","doi":"10.1016/j.nepr.2026.104711","DOIUrl":"10.1016/j.nepr.2026.104711","url":null,"abstract":"<div><h3>Aim</h3><div>This project leverages AI-driven simulation to create immersive, culturally rich learning experiences that foster students’ development of cultural competence and interprofessional collaboration skills.</div></div><div><h3>Background</h3><div>Cultural competence and interprofessional collaboration are essential skills for future clinicians, yet traditional teaching methods often fall short in providing immersive, patient-centred learning experiences. AI-driven simulations offer a promising way to bridge this gap by creating realistic, interactive scenarios that engage students in meaningful, culturally nuanced clinical encounters.</div></div><div><h3>Design/Methods</h3><div>This project introduced <em>Aalia,</em> an AI-driven simulation featuring a 32 year-old Middle Eastern woman navigating the Italian healthcare system, delivered via a platform called ATLAS. Conducted in a synchronous 45-minute Zoom session, the simulation engaged over 130 health professions students and 20 educators from four countries. Working in interprofessional teams across ten breakout rooms, students interacted with <em>Aalia</em> through over 350 conversations and received automated feedback via ATLAS to support reflection and skill development.</div></div><div><h3>Results</h3><div>Evaluation results showed strong student agreement on the simulation’s value, with 94 % expressing interest in future AI simulations and 91 % reporting improved understanding of empathy in care. Simulate effectiveness was highly rated, notably, 89 % found the simulation realistic and engaging, 90 % engaging and 88 % felt it increased their confidence in providing culturally responsive healthcare. Interestingly, 67 % appreciated AI-generated feedback as more tolerable compared to teacher-given feedback.</div></div><div><h3>Conclusions</h3><div><em>Aalia’s</em> narrative provided a high-quality and authentic virtual environment for practising culturally responsive, collaborative care. This AI-driven simulation reinforced teamwork as essential in professional practice. Educators found it effective and easy to use, with significant potential for wider application.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104711"},"PeriodicalIF":4.0,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Critical reflections from a transdisciplinary team on deploying an AI-enabled robot in long-term care 一个跨学科团队对在长期护理中部署人工智能机器人的批判性思考

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-06 DOI: 10.1016/j.nepr.2026.104709

Julia Banco, Albin Soni, Karen Lok Yi Wong, Lily Haopu Ren, Rachel Xia, Shambhavi Arora, Lillian Hung

Aim

This study presents our reflections as student researchers working within a transdisciplinary, intergenerational team that implemented Aether, an AI-enabled care robot, in a long-term care (LTC) facility for older adults. We examine our roles and contributions to the project’s transdisciplinary and intergenerational research process.

Background

Transdisciplinary and intergenerational collaboration have been proven beneficial for implementing AI-driven technologies in LTC. Few studies have explored students’ roles in transdisciplinary or intergenerational collaboration and their opportunities for mutual learning experiences and ethically grounded innovations.

Design

This critical reflection paper is part of a larger study examining the deployment of Aether. Our research design focuses on capturing our experiences as a team of student researchers through reflective inquiry, emphasizing our role in the implementation and deployment process.

Methods

Reflections were gathered through individual and group sessions using Rolfe’s (2001) Critical Reflection Framework. Reflexive thematic analysis, combining inductive and deductive coding, was used to identify key themes from our experiences.

Results

Three reflexive themes emerged: (1) The transformative role of transdisciplinary collaboration in addressing real-world challenges; (2) The importance of intergenerational collaboration with industry; and (3) The value of field-based experience in bridging theory and practice.

Conclusions

This study proposes a framework of practical tips, “SHINE,” to support future technology implementations in LTC through intergenerational and transdisciplinary collaboration. This framework highlights the value of student engagement in hands-on, collaborative research settings and encourages future research to focus on the critical role of student engagement in complex care environments.

本研究提出了我们作为学生研究人员在一个跨学科、跨代团队中工作的思考，该团队在老年人长期护理（LTC）设施中实施了支持人工智能的护理机器人以太。我们审视我们在项目的跨学科和代际研究过程中的角色和贡献。跨学科和代际协作已被证明有利于在LTC中实施人工智能驱动技术。很少有研究探讨学生在跨学科或代际合作中的角色，以及他们相互学习经验和道德创新的机会。这篇重要的反思论文是研究以太部署的大型研究的一部分。我们的研究设计侧重于通过反思性调查来捕捉我们作为一个学生研究团队的经验，强调我们在实施和部署过程中的作用。方法采用罗尔夫（2001）批判性反思框架，通过个人和小组会议收集反思。反身性主题分析，结合归纳和演绎编码，从我们的经验中确定关键主题。三个反思性主题浮现出来：(1)跨学科合作在应对现实挑战中的变革作用；(2)与产业的代际合作的重要性；(3)实地经验在衔接理论与实践方面的价值。本研究提出了一个实用技巧框架“SHINE”，通过代际和跨学科合作，支持LTC中未来的技术实施。该框架强调了学生参与实践、合作研究环境的价值，并鼓励未来的研究关注学生参与在复杂护理环境中的关键作用。

{"title":"Critical reflections from a transdisciplinary team on deploying an AI-enabled robot in long-term care","authors":"Julia Banco, Albin Soni, Karen Lok Yi Wong, Lily Haopu Ren, Rachel Xia, Shambhavi Arora, Lillian Hung","doi":"10.1016/j.nepr.2026.104709","DOIUrl":"10.1016/j.nepr.2026.104709","url":null,"abstract":"<div><h3>Aim</h3><div>This study presents our reflections as student researchers working within a transdisciplinary, intergenerational team that implemented Aether, an AI-enabled care robot, in a long-term care (LTC) facility for older adults. We examine our roles and contributions to the project’s transdisciplinary and intergenerational research process.</div></div><div><h3>Background</h3><div>Transdisciplinary and intergenerational collaboration have been proven beneficial for implementing AI-driven technologies in LTC. Few studies have explored students’ roles in transdisciplinary or intergenerational collaboration and their opportunities for mutual learning experiences and ethically grounded innovations.</div></div><div><h3>Design</h3><div>This critical reflection paper is part of a larger study examining the deployment of Aether. Our research design focuses on capturing our experiences as a team of student researchers through reflective inquiry, emphasizing our role in the implementation and deployment process.</div></div><div><h3>Methods</h3><div>Reflections were gathered through individual and group sessions using Rolfe’s (2001) Critical Reflection Framework. Reflexive thematic analysis, combining inductive and deductive coding, was used to identify key themes from our experiences.</div></div><div><h3>Results</h3><div>Three reflexive themes emerged: (1) The transformative role of transdisciplinary collaboration in addressing real-world challenges; (2) The importance of intergenerational collaboration with industry; and (3) The value of field-based experience in bridging theory and practice.</div></div><div><h3>Conclusions</h3><div>This study proposes a framework of practical tips, “SHINE,” to support future technology implementations in LTC through intergenerational and transdisciplinary collaboration. This framework highlights the value of student engagement in hands-on, collaborative research settings and encourages future research to focus on the critical role of student engagement in complex care environments.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104709"},"PeriodicalIF":4.0,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Feasibility and acceptability of immersive virtual reality for end-of-life care education among nurses in high-context cultures 沉浸式虚拟现实在高情境文化中护士临终关怀教育的可行性和可接受性。

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-06 DOI: 10.1016/j.nepr.2026.104712

Cheng-Pei Lin , Lu-Yen Anny Chen , Yu-Chi Chen , Jou-Chun Lin , Ding-Han Wang , Heng-Hsin Tung

Aim

to explore the feasibility and acceptability of implementing an immersive virtual reality (IVR) end-of-life care training program among nursing staff in a high-context culture.

Background

End-of-life nursing education is limited in high-context cultures where discussing death and dying is emotionally challenging. IVR offers an innovative possibility to enhance nurses’ knowledge and empathy and guide patients’ medical decision-making. However, the feasibility and acceptability of this approach in end-of-life care training for nursing staff remain underexplored.

Design

A mixed-methods pre- and post-intervention design supplemented with free-text qualitative feedback.

Methods

Nursing staff with at least 3 months of clinical experience participated in a IVR-based simulation. Pre- and post-intervention knowledge, learning experience, satisfaction and qualitative responses were collected. Data were analysed using descriptive statistics, paired t-tests and content analysis of open-ended responses.

Results

Fifty nurses were recruited (mostly 21–29 years old females with a college degree). Post-intervention knowledge score improved significantly (pre: M 9.18 SD 0.66; post: M 9.58 SD 0.58, Z = -3.780, p < .001). Overall, participants reported high satisfaction (mean: 27.26/30) with positive feedback on the usefulness of VR (M = 87.50/100), the appropriateness of the content in the module (M = 28.32/30) and minimal physical discomfort (M = 2.44/8). IVR was rated more favourably than traditional training (M = 90.60/100), but was viewed as a complementary tool.

Conclusion

IVR-based end-of-life care training is feasible and well-received by nursing staff in high-context cultures, enhancing knowledge and motivation. While promising, IVR should be integrated as a supplementary strategy alongside conventional training to preserve contextual depth in palliative care education.

目的：探讨在高情境文化中，护理人员实施沉浸式虚拟现实（IVR）临终关怀培训计划的可行性和可接受性。背景：临终护理教育在高语境文化中是有限的，在那里讨论死亡和临终是情感上的挑战。IVR提供了一种创新的可能性，可以提高护士的知识和同理心，指导患者的医疗决策。然而，这种方法在护理人员临终关怀培训中的可行性和可接受性仍未得到充分探讨。设计：干预前后混合方法设计，辅以自由文本定性反馈。方法：具有3个月以上临床经验的护理人员参与基于ivr的模拟。收集干预前和干预后的知识、学习经验、满意度和定性反应。数据分析采用描述性统计、配对t检验和开放式回答的内容分析。结果：共招募护士50人，年龄以21 ~ 29岁女性为主，大专以上学历。干预后知识得分显著提高（干预前：M 9.18 SD 0.66；干预后：M 9.58 SD 0.58, Z = -3.780,p ）结论：基于ivr的临终关怀培训在高情境文化下是可行的，并且受到护理人员的欢迎，提高了知识和积极性。IVR虽然很有前途，但应该与传统培训一起作为补充策略进行整合，以保持姑息治疗教育的情境深度。

{"title":"Feasibility and acceptability of immersive virtual reality for end-of-life care education among nurses in high-context cultures","authors":"Cheng-Pei Lin , Lu-Yen Anny Chen , Yu-Chi Chen , Jou-Chun Lin , Ding-Han Wang , Heng-Hsin Tung","doi":"10.1016/j.nepr.2026.104712","DOIUrl":"10.1016/j.nepr.2026.104712","url":null,"abstract":"<div><h3>Aim</h3><div>to explore the feasibility and acceptability of implementing an immersive virtual reality (IVR) end-of-life care training program among nursing staff in a high-context culture.</div></div><div><h3>Background</h3><div>End-of-life nursing education is limited in high-context cultures where discussing death and dying is emotionally challenging. IVR offers an innovative possibility to enhance nurses’ knowledge and empathy and guide patients’ medical decision-making. However, the feasibility and acceptability of this approach in end-of-life care training for nursing staff remain underexplored.</div></div><div><h3>Design</h3><div>A mixed-methods pre- and post-intervention design supplemented with free-text qualitative feedback.</div></div><div><h3>Methods</h3><div>Nursing staff with at least 3 months of clinical experience participated in a IVR-based simulation. Pre- and post-intervention knowledge, learning experience, satisfaction and qualitative responses were collected. Data were analysed using descriptive statistics, paired t-tests and content analysis of open-ended responses.</div></div><div><h3>Results</h3><div>Fifty nurses were recruited (mostly 21–29 years old females with a college degree). Post-intervention knowledge score improved significantly (pre: M 9.18 SD 0.66; post: M 9.58 SD 0.58, Z = -3.780, p < .001). Overall, participants reported high satisfaction (mean: 27.26/30) with positive feedback on the usefulness of VR (M = 87.50/100), the appropriateness of the content in the module (M = 28.32/30) and minimal physical discomfort (M = 2.44/8). IVR was rated more favourably than traditional training (M = 90.60/100), but was viewed as a complementary tool.</div></div><div><h3>Conclusion</h3><div>IVR-based end-of-life care training is feasible and well-received by nursing staff in high-context cultures, enhancing knowledge and motivation. While promising, IVR should be integrated as a supplementary strategy alongside conventional training to preserve contextual depth in palliative care education.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104712"},"PeriodicalIF":4.0,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145918876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of responses to comprehensive nursing exam questions by large language models: A comparison of ChatGPT, DeepSeek and students 基于大语言模型的综合护理考试试题回答分析：ChatGPT、DeepSeek和学生的比较

IF 4 3区医学 Q1 NURSING

Nurse Education in Practice

Pub Date : 2026-01-04 DOI: 10.1016/j.nepr.2025.104691

Li Ma , Qiankun Liu , Pengyao Li , Juju Huang , Yang Xu , Jiaxue Pang , Hui Xie

Objective

This study aimed to evaluate the potential of large language models (LLMs) in nursing education and practice by comparing their performance with that of baccalaureate nursing graduates on a comprehensive nursing examination.

Background

The digital transformation of nursing education is underway and LLMs, with their advanced natural language processing capabilities, show significant potential in this field.

Design

This study employed a cross-sectional design.

Methods

This study compared the graduation exam performance of 221 Chinese nursing undergraduates with two LLMs (ChatGPT, DeepSeek), analyzing answer accuracy and scores via descriptive statistics and chi-square tests.

Results

On questions assessing higher-order thinking skills, students demonstrated superior clinical evaluation and application abilities compared with both ChatGPT and DeepSeek. Conversely, students' clinical analysis ability was significantly lower than that of both AI models (74.77 % vs. 88.24 % vs. 94.12 %, p < 0.05). No statistically significant difference was found in memory ability among the three groups (p > 0.05). For comprehension ability, DeepSeek's performance was superior to that of the students (81.82 % vs. 68.91 %).

Conclusions

This comparative study revealed that LLMs and nursing students demonstrated distinct patterns of strengths and limitations when answering comprehensive exam questions, indicating a potential complementarity. These findings provide preliminary evidence for future exploration of human-AI collaborative models in nursing education. Subsequent research should further investigate specific applications of LLMs in teaching and learning scenarios.

目的通过比较大语言模型（LLMs）与护理本科毕业生在综合护理考试中的表现，评估LLMs在护理教育和实践中的潜力。护理教育的数字化转型正在进行中，法学硕士以其先进的自然语言处理能力，在这一领域显示出巨大的潜力。本研究采用横断面设计。方法采用描述性统计和卡方检验的方法，对221名中国护理本科生（ChatGPT、DeepSeek）的毕业考试成绩进行比较。结果在评估高阶思维能力的问题上，学生的临床评估能力和应用能力均优于ChatGPT和DeepSeek。相反，学生的临床分析能力明显低于两种AI模型（74.77 % vs. 88.24 % vs. 94.12 %,p <； 0.05）。三组患者的记忆能力差异无统计学意义（p >； 0.05）。在理解能力方面，DeepSeek的表现优于学生（81.82 % vs. 68.91 %）。结论本比较研究显示，法学硕士和护理专业学生在回答综合试题时表现出明显的优势和局限性，具有潜在的互补性。这些发现为未来探索护理教育中人类-人工智能协同模式提供了初步依据。后续研究应进一步探讨法学硕士在教学和学习场景中的具体应用。

{"title":"Analysis of responses to comprehensive nursing exam questions by large language models: A comparison of ChatGPT, DeepSeek and students","authors":"Li Ma , Qiankun Liu , Pengyao Li , Juju Huang , Yang Xu , Jiaxue Pang , Hui Xie","doi":"10.1016/j.nepr.2025.104691","DOIUrl":"10.1016/j.nepr.2025.104691","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to evaluate the potential of large language models (LLMs) in nursing education and practice by comparing their performance with that of baccalaureate nursing graduates on a comprehensive nursing examination.</div></div><div><h3>Background</h3><div>The digital transformation of nursing education is underway and LLMs, with their advanced natural language processing capabilities, show significant potential in this field.</div></div><div><h3>Design</h3><div>This study employed a cross-sectional design.</div></div><div><h3>Methods</h3><div>This study compared the graduation exam performance of 221 Chinese nursing undergraduates with two LLMs (ChatGPT, DeepSeek), analyzing answer accuracy and scores via descriptive statistics and chi-square tests.</div></div><div><h3>Results</h3><div>On questions assessing higher-order thinking skills, students demonstrated superior clinical evaluation and application abilities compared with both ChatGPT and DeepSeek. Conversely, students' clinical analysis ability was significantly lower than that of both AI models (74.77 % vs. 88.24 % vs. 94.12 %, p < 0.05). No statistically significant difference was found in memory ability among the three groups (p > 0.05). For comprehension ability, DeepSeek's performance was superior to that of the students (81.82 % vs. 68.91 %).</div></div><div><h3>Conclusions</h3><div>This comparative study revealed that LLMs and nursing students demonstrated distinct patterns of strengths and limitations when answering comprehensive exam questions, indicating a potential complementarity. These findings provide preliminary evidence for future exploration of human-AI collaborative models in nursing education. Subsequent research should further investigate specific applications of LLMs in teaching and learning scenarios.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"91 ","pages":"Article 104691"},"PeriodicalIF":4.0,"publicationDate":"2026-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0