Abstract Background Recent advancements in digital health technologies have led to the accumulation of large volumes of unstructured text data, particularly in electronic health records. Given that nursing documentation frequently includes detailed descriptions of daily living activities and psychosocial contexts, existing medical natural language processing (NLP) tools may not be directly applicable without adaptation. Moreover, the integration of standardized nursing terminologies into NLP systems remains limited. Although NLP has the potential to support risk detection, information management, and care planning, its practical applications in nursing have not yet been systematically mapped. Objective This scoping review aimed to map the practical applications of NLP in nursing practice, with a specific focus on real-world clinical use, particularly for assessment, documentation, and interventions, and to identify the study characteristics, application domains, outcomes, and challenges. Methods Following the Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, a systematic search was conducted across PubMed, CINAHL, the Cochrane Library, Scopus, Embase, and Ichushi-Web in October 2023 and June 2025. The population-concept-context framework (population: nurses; concept: NLP applications; context: clinical settings) was used to guide study selection. Two independent reviewers screened 2889 unique records and reviewed the full texts of 72 studies. Data were descriptively synthesized and thematically classified. Results Six studies met the inclusion criteria, indicating that empirically evaluated applications of NLP in real-world nursing practice remain limited. NLP applications were categorized into three domains: (1) text summarization and generation, (2) information extraction and classification, and (3) real-time detection and screening. NLP was applied across multiple stages of nursing practice, including handovers, assessment, care planning, continuity of care, and patient safety management. Notably, NLP was used as a form of augmented intelligence to complement, rather than replace, nurses’ clinical judgment and to support clinical decision-making. These findings also highlight a substantial gap between rapid technological advances and the limited implementation of NLP in real-world nursing practice. Conclusions This review highlights the substantial gap between rapid technological advances and the limited implementation of NLP in real-world nursing practice. NLP may help reduce manual review workload, support early risk identification, and facilitate individualized care planning in selected nursing contexts. However, direct empirical evidence regarding its effects on nursing workflows, nurses’ clinical decision-making, and patient-level outcomes remains limited. Future research should prioritize real-world implementation studies and evaluate nurses’ acceptance, adoption barriers, workflow integration, and the influence of NLP on clinical decision-making.
BackgroundClinical handover is the process during which responsibility and accountability for care are transferred between clinicians. AI has the potential to improve the reliability and completeness of clinical handover by helping clinicians detect predefined content areas that have been communicated, identify explicit information gaps, and prompt clarification before responsibility is transferred. ObjectiveThis study evaluated the performance of several large language models and prompt optimization strategies for structured information extraction of synthetic nursing handover transcripts. MethodsTwo registered nurses independently annotated a dataset of 203 synthetic handover transcripts to produce consensus labels for information extraction tasks. Tasks included (1) labeling spans of text into SBAR (Situation, Background, Assessment, Recommendation) categories, (2) content detection to determine if specific pieces of information were communicated, and (3) labeling spans of text that communicated information using uncertain terms that included a subtask for identifying unknown facts. Baseline and Genetic-Pareto (GEPA)–optimized prompts were compared for the GPT-5.2, GPT-5-nano, and MedGemma 27B large language models. Additionally, the LangExtract framework was evaluated for span-extraction tasks. ResultsThe GPT-5.2–optimized model achieved a micro–F1-score of 0.85 (95% CI 0.83‐0.88) for content detection, an absolute improvement of +0.08 compared with the matched baseline. GPT-5-nano also performed better after optimization for content detection (micro–F1-score 0.81, 95% CI 0.78‐0.84), suggesting that this structured task was not limited to the highest-capacity model. For SBAR span extraction, GPT-5.2 with prompt optimization achieved a micro–F1-score of 0.76 (95% CI 0.72‐0.79), improving by +0.24 compared with baseline and exceeding LangExtract; GPT-5-nano also improved to a micro–F1-score of 0.69 (95% CI 0.66‐0.72). Broad uncertainty-span extraction remained comparatively weak despite prompt optimization (micro–F1-score 0.41, 95% CI 0.33‐0.48; absolute improvement +0.06). In contrast, explicit unknown-fact extraction was more accurate with GPT-5.2 (micro–F1-score 0.84, 95% CI 0.63‐1.00), GPT-5-nano (micro–F1-score, 0.84 95% CI 0.63‐1.00), and MedGemma 27B (micro–F1-score 0.80, 95% CI 0.63‐1.00). Genetic-Pareto–optimized prompts outperformed the LangExtract approach across each span-extraction task. ConclusionsPrompt optimization improved matched-model point estimates, with the highest performance observed for predefined content detection and SBAR span extraction. Broad uncertainty extraction remained less accurate than the narrower unknown-fact task. These technical results do not establish clinical effectiveness, safety, or readiness for real-time use. Validation using authentic nursing handover communication and prospective evaluation in clinical workflows are required before clinical application.
BackgroundAI is rapidly transforming clinical nursing, promising administrative relief and decision support. However, the frontline reality presents a double-edged sword effect, where technological empowerment is frequently offset by novel occupational burdens and technostress. ObjectiveThis study aims to theoretically deconstruct the bidirectional impacts of AI application among clinical nurses and identify buffering conditions, using the Job Demands-Resources (JD-R) theoretical framework. MethodsA descriptive qualitative study was conducted across multiple general hospitals in mainland China. Using maximum variation and purposive sampling, semistructured in-depth interviews were conducted with registered nurses who actively use clinical AI systems. Data were analyzed using directed qualitative content analysis guided by predefined JD-R constructs. ResultsThe analysis revealed 3 overarching domains comprising 9 main themes and 24 subthemes. On the gain path (job resources), AI empowered nurses through a workflow efficiency leap, clinical cognitive empowerment, and professional capital appreciation. Conversely, along the drain path (job demands), hidden costs were exposed, conceptualized as cognitive impediment, relational attrition, and digital involution driven by performance inflation and competitive perfectionism. The interplay between these pathways was perceived to be buffered by contextual mechanisms, specifically nurses’ proactive coping strategies, professional boundary demarcation, and the provision of a cohesive organizational support architecture. ConclusionsThe impact of AI integration in nursing is not technologically deterministic. While AI provides valuable cognitive and operational support, it concurrently generates novel digital demands. To prevent AI from devolving into an occupational hazard, health care administrators must establish multidimensional life cycle AI governance, cultivate comprehensive AI literacy, and safeguard the irreplaceable humanistic core of clinical care.
Abstract Background Technologies such as virtual reality (VR) and augmented reality (AR) have been increasingly incorporated into nursing education to support the development of cognitive, psychomotor, and behavioral competencies. In midwifery, immersive environments offer opportunities to simulate high-risk or low-frequency clinical scenarios, strengthening students’ confidence and preparedness for professional practice. However, there is still significant variability in how VR and AR are pedagogically implemented, with limited understanding of their theoretical grounding, instructional design, and educational outcomes. Objective This systematic review aimed to synthesize and critically evaluate the characteristics of educational programs using VR and AR to develop competencies among nursing and midwifery students and professionals. Methods This review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 and Synthesis Without Meta-Analysis (SWiM) guidelines and was registered in PROSPERO (International Prospective Register of Systematic Reviews). A comprehensive search was conducted in August 2024 across PubMed, Web of Science, Scopus, and Cumulative Index to Nursing and Allied Health Literature (CINAHL) databases. Eligible studies were experimental, quasi-experimental, or observational, and involved undergraduate or postgraduate students in nursing, obstetric nursing, or midwifery, as well as certified midwives or nurse-midwives. Two independent reviewers conducted screening, data extraction, and quality appraisal using Joanna Briggs Institute (JBI) tools and the Medical Education Research Study Quality Instrument (MERSQI) scale. Data were synthesized narratively according to predefined thematic categories. Results Four studies published between 2021 and 2024 met the inclusion criteria, encompassing 634 participants (360 midwifery students and 274 midwives or nurse-midwives). Two randomized controlled trials and 2 quasi-experimental studies were included. Interventions used VR in 3 studies and AR in one, simulating scenarios such as normal and complicated childbirth, neonatal resuscitation, and emergency obstetric procedures. Most interventions focused on developing technical competencies, while one also addressed teamwork and communication. Only 2 studies explicitly reported theoretical or pedagogical frameworks, and 2 mentioned alignment with the INACSL Healthcare Simulation Standards of Best Practice. Structured briefing or debriefing was rarely described. All studies assessed learning outcomes (Kirkpatrick level 2), and 3 included participants’ satisfaction (level 1). Methodological quality, measured by MERSQI, ranged from 10.0 to 14.5, with a mean score of 12.9 (SD 2.0), indicating moderate to high quality. Conclusions Evidence suggests that VR and AR can enhance learning in obstetric nursing and midwifery education by providing safe, experiential, and interactive learning environments. However, the limited use of theoretical frameworks and structured instructional design highlights the need for more pedagogically grounded interventions. Future research should prioritize the integration of learning theories, validated assessment tools, and best-practice simulation standards to strengthen the educational impact and curricular integration of immersive technologies in nursing and midwifery education.
