Issue #9 Week of Oct 19, 2026 – Nov 02, 2026
29Papers
This issue at a glance
This issue is dominated by nursing education, with student AI literacy and use patterns studied across China, Korea, Egypt, Saudi Arabia, and Mediterranean universities. Several papers examine how students actually use generative AI, from distinct usage personas to links between AI dependence and lower achievement motivation. Others test education tools directly, comparing GenAI-assisted debriefing to facilitator-led methods and AI-simulated patients to traditional practice. A smaller set of papers builds machine learning prediction models for frailty, delirium, and haemorrhage, and tests LLMs for detecting spiritual pain and screening curriculum content, generally finding good accuracy but a continued need for human review and external validation.
Papers nearly tripled to 29 this issue (+17), with Workforce & Education remaining the leading topic and growing its share, now 20 of 29 papers compared to 4 last issue. NLP & Generative AI's share fell even though its paper count rose slightly, as it was outpaced by the education surge. Clinical Decision Support continued as a thread, covering frailty, delirium, haemorrhage, and pressure injury prediction, though with different applications than last issue's participatory design and missed-care focus. AI Ethics & Governance returned with one paper after being absent, while EHR & Workflows and Patient-Facing AI, present last issue, do not appear this time.
Student AI literacy, use patterns, and dependence 8AI tools in nursing education and simulation 9Machine learning prediction models for clinical risk 6LLMs analyzing clinical and patient-generated text 2
Compared withIssue #8
Papers29 ▲ 17
Leading topicWorkforce & Education (unchanged)
Rising▲ Workforce & Education
Cooling▼ NLP & Generative AI
Flagged11 ▲ 7
How this digest is made: Papers retrieved bi-weekly from the community-configured sources (PubMed, arXiv, medRxiv, and/or CINAHL — see Digest Settings for this issue's exact sources) using search terms agreed at AINurse-26. Results are restricted to English-language papers; both title and abstract are checked independently, and either being predominantly non-English excludes the paper. Papers are then classified against the community's chosen topics — anything that doesn't clearly match is left out of the issue rather than shown as "Other." Summaries are generated by Claude Sonnet, constrained to report only what the abstract states, with no speculation or inference. The "At a Glance" section above is written under the same constraints — the model synthesizes themes only from the summaries included in this issue, and every number in it (counts, changes since the previous issue) is computed directly from the archive, not by the model. Flagged items indicate incomplete abstracts or unverified peer-review status.
All (29)Clinical Decision Support (5)NLP & Generative AI (3)AI Ethics & Governance (1)Workforce & Education (20) Flagged (11)
Clinical Decision Support5 papers
Clinical Decision Support
Development and Internal Validation of an Electronic Medical Record-Based Machine Learning Model for Frailty Prediction in Hospitalized Patients: Retrospective Cohort Study.
JMIR medical informatics · Oct 2026
Researchers used electronic medical record data from the first 72 hours of hospital admission at Royal Adelaide Hospital to predict frailty in 26,824 patients. A machine learning model (XGBoost) identified frail patients with good accuracy, using factors like polypharmacy, lab results, and nursing assessments, though it performed less well for Indigenous patients. This approach could help hospitals spot frailty early and plan care, while highlighting the need for equity checks in predictive tools.
Clinical Decision Support
Development and validation of a machine learning-based prediction model for postoperative delirium after glioma surgery.
The International journal of neuroscience · Nov 2026
Researchers used retrospective data from 316 adults having glioma surgery at one hospital to build machine-learning models predicting postoperative delirium, using predictors available at different time points. An XGBoost model using perioperative factors plus 24-hour ICU admission status showed the best performance (AUC 0.895) in internal validation. This approach could help nurses identify high-risk patients early, but the authors say external, multicentre, and prospective testing is needed before clinical use.
Clinical Decision Support
Multi-State Modeling of Pressure Injury Staging Transition Trajectories to Inform Next-Generation Clinical Decision Support.
Advances in wound care · Nov 2026
Researchers analyzed EHR data from 29,475 patients with pressure injuries (2015–2023) to track how injury stages changed over time at the coccyx, buttocks, sacrum, and heel. They found stage 2 acts as a 'gateway' to severe stages, and tools like the Braden Scale work better for later transitions than early ones, with some race-based differences also observed. This suggests current risk tools miss time-sensitive changes, highlighting a need for clinical decision support that accounts for how pressure injuries progress over time.
Clinical Decision Support
Improving Haemorrhage Prediction in General Ward Patients by Incorporating Patterns of Change Derived From Routine Ward Measurements.
Journal of Clinical Nursing (John Wiley & Sons, Inc.) · Oct2
Researchers studied over 16,000 general ward patients at three South Korean hospitals to see if tracking changes in routine measurements over time could improve haemorrhage prediction, beyond using only the most recent values. Machine-learning models combining both approaches showed small but statistically supported improvements, with neutrophil count, platelet count, white blood cell count, urine output, and vital signs as key predictors. This suggests routine ward data may hold extra value for nursing surveillance, though prospective testing is needed before clinical use.
NLP & Generative AI3 papers
NLP & Generative AI
Detecting spiritual pain in electronic medical records using large language models.
Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer · Oct 2026
Researchers tested whether large language models (Gemini-2.5-flash and Microsoft Copilot) could detect spiritual pain in nursing records from 109 terminally ill cancer patients at a Japanese palliative care unit. Both models caught all true cases of spiritual pain (sensitivity 1.00) but often flagged unrelated issues like physical decline or delirium as spiritual pain, lowering accuracy. This suggests LLMs may help screen records for spiritual pain, though human review remains needed to catch false positives.
NLP & Generative AI
Characterizing Cancer Symptom Experiences and Related Psychosocial Concerns Through Chinese Social Media Narratives: Computational Text Analysis.
Journal of medical Internet research · Oct 2026
Researchers analyzed 26,086 first-person cancer-related posts from two Chinese social media platforms, using an LLM and topic modeling to identify symptoms and broader concerns. Pain, physical function impairment, and depression were the most common symptoms, while topic modeling also revealed themes like financial burden, existential distress, and health care system interactions not captured by standard symptom tools. This suggests social media narratives could complement structured symptom assessment, though platform differences and nonrepresentative users limit how broadly these findings apply.
Workforce & Education20 papers
Workforce & Education
Preliminary Psychometric Evaluation of the Arabic Version of the NURS-DIAL Questionnaire Among Nursing Students in Saudi Arabia: Cross-Sectional Study.
JMIR nursing · Oct 2026
Researchers translated and culturally adapted the NURS-DIAL, a tool measuring digital and AI literacy, into Arabic and tested it with nursing students at one university in Saudi Arabia. The tool showed strong content validity, preliminary support for its 52-item, 5-factor structure, and good internal consistency. These early results suggest the tool may help assess digital and AI literacy in Arabic-speaking nursing students, but larger multi-institutional studies are needed to confirm its structure and wider use.
Workforce & Education
Generative artificial intelligence use patterns among Chinese nursing graduate students: A qualitative descriptive study.
International journal of nursing studies · Nov 2026
Researchers interviewed 17 nursing graduate students (9 doctoral, 8 master's) from 10 Chinese universities about how they use generative AI in their research. Students showed four distinct usage patterns, ranging from balanced tool use to deep dependency, with doctoral students showing more self-control due to prior research experience. The study suggests nursing programs need stage-specific AI guidance to boost productivity without weakening core research skills.
Workforce & Education
Tailored behavioral personas of large language model use among Chinese nursing students: A qualitative study.
International journal of nursing studies · Nov 2026
Researchers interviewed 22 Chinese nursing students between October and December 2025 to understand how they actually use large language models, not just their attitudes toward them. The study identified four distinct user personas based on cognitive relationships, interaction strategies, verification habits, psychological experiences, and risk perceptions: efficiency-quality trade-off, capability-compensating, prudent-assistance, and cognitive outsourcing. This suggests nursing education interventions should target each persona specifically, pairing critical thinking training with technical and ethical support to reduce cognitive outsourcing risks.
Workforce & Education
Generative AI literacy as a mediator between lifelong learning and AI competence in nursing students: A regression-based cross-sectional study.
Nurse education today · Nov 2026
This cross-sectional study surveyed 533 nursing students at two Mediterranean universities to examine links between lifelong learning tendency, generative AI literacy, and AI usage and competence. Students showed high levels of all three traits, and AI literacy partially explained the link between lifelong learning tendency and AI usage and competence. The authors note findings apply only to education settings, not clinical practice, and call for longitudinal and experimental research to test real-world relevance.
Workforce & Education
Comparing the effects of GenAI-assisted and facilitator-led debriefing on knowledge and non-technical skills in immersive virtual reality simulation in nursing education: A quasi-experimental study.
Nurse education today · Nov 2026
This study compared GenAI-assisted debriefing to facilitator-led debriefing after immersive virtual reality simulation among 178 undergraduate nursing students in Hong Kong with limited clinical experience. Both groups showed significant knowledge gains, with no significant differences between groups in knowledge or self-reported non-technical skills after the intervention. This suggests GenAI-assisted debriefing may offer a scalable option alongside traditional facilitator-led methods, though more research is needed.
Workforce & Education
Nursing students' experiences of interviewing artificial intelligence-simulated patients: A phenomenological study.
Nurse education today · Nov 2026
This phenomenological study interviewed 15 first-year nursing students about their experience practicing interviews with AI-simulated patients. Students described feeling a sense of clinical reality, building reflective communication skills, gaining confidence, developing a professional identity, and feeling more motivated to learn. The findings suggest AI-simulated patients may offer a useful addition to traditional nursing education methods, especially when real clinical practice access is limited.
Workforce & Education
Artificial intelligence literacy of nursing students: A cross-sectional study.
Nurse education today · Nov 2026
This cross-sectional study surveyed 155 sophomore nursing students at a Chinese vocational university to measure AI literacy across awareness, application, evaluation, and ethics. Students showed moderate overall AI literacy, with the strongest scores in the Application dimension; gender and interest in AI independently influenced literacy levels. These findings suggest nursing curricula may need targeted AI training, including extra support for female students and ways to boost AI interest.
Workforce & Education
From awareness to application: Unveiling the interplay between dependence on artificial intelligence and achievement motivation among nursing students: A multicenter study.
Nurse education today · Nov 2026
This multicenter study surveyed 1,412 undergraduate nursing students across five Egyptian universities to examine how AI dependence relates to achievement motivation. Students showed moderate levels of both, with a significant negative correlation between them—higher AI dependence linked to lower motivation, explaining about 20% of the variance. This suggests nursing education programs may need strategies that balance AI use with fostering independent thinking and self-directed learning.
Workforce & Education
Latent profiles of ethical sensitivity and correlates in nursing interns.
Nursing ethics · Nov 2026
Researchers surveyed 458 nursing interns from 32 Chinese medical colleges to identify patterns in ethical sensitivity and how they relate to critical thinking and AI readiness. The study found four distinct profiles, and interns with lower critical thinking scores were more likely to fall into the Balanced-Intermediate or Rights-Privacy Focused groups rather than the High Overall Sensitivity group. This suggests nursing education may need tailored approaches to build ethical sensitivity as healthcare becomes more technology-driven.
Workforce & Education
Association between generative artificial intelligence-related factors and self-directed learning ability among nursing students: a cross-sectional study.
Nurse education today · Nov 2026
This cross-sectional survey of 219 nursing students in South Korea examined how generative AI-related factors relate to self-directed learning ability. Readiness to use generative AI, perceived ease of use, and intention to continue use were all linked to higher self-directed learning ability, along with major satisfaction, together explaining 62.6% of the variance. These findings suggest nursing education strategies could target AI readiness and ease of use to support student learning.
Workforce & Education
An informatics competency model for undergraduate nursing students: A quasi-experimental study.
Nurse education today · Nov 2026
This quasi-experimental study tested a Nursing Informatics Competency Organizational (NICO)-based course with 80 first-year nursing students, comparing project management training plus computer literacy to general computer courses alone. The experimental group showed greater gains in informatics competencies, especially informatics roles, basic computer skills, and wireless device skills, though not in applied computer skills or clinical informatics attitudes, with high reported learner satisfaction. This suggests project-based informatics training may help build some, but not all, competencies in undergraduate nursing education.
Workforce & Education
Distribution and Utilisation of Clinical Placements Across Care Settings: A Four‐Cohort Analysis.
Nursing Forum · 10/2
This retrospective study examined clinical placement records for 331 nursing graduates across four cohorts at a public university in Barcelona, Spain. It found that specialised care settings made up 75%-76% of placement weeks, while primary and transitional care made up much smaller shares, with transitional care underused despite open spots. This points to an imbalance in training exposure that may affect how programs coordinate placements with healthcare providers.
Flagged Papers11
Clinical Decision Support 1 Flagged
Clinical Decision Support
Population unclear
Integrating clinical decision support systems in pediatric oncology: A scoping review of applications, implementation gaps, and management Implications.
International journal of medical informatics · Nov 2026
This scoping review looked at 17 studies on clinical decision support systems (CDSSs) used in pediatric oncology care. Most CDSS tools focused on treatment decisions, with less attention to risk assessment, diagnosis, nursing workflow, or survivorship care, and user interaction and follow-up features need improvement. For nursing informatics, this highlights gaps in CDSS design across the care continuum and a need for multicenter trials to test real-world effectiveness.
NLP & Generative AI 1 Flagged
NLP & Generative AI
Population unclear Setting unclear
Application of large language models in early screening of Alzheimer's disease: a scoping review.
Frontiers in Aging Neuroscience · 2026
This scoping review looked at 25 studies on how large language models (LLMs) are used for early screening of Alzheimer's disease. The studies showed LLMs are mainly used to identify cognitive impairment, augment data, automate cognitive assessment, and support clinical decisions, with newer work exploring multimodal and agent-based approaches. For nursing informatics, this highlights a growing tool area, but the review calls for more real-world testing, multicenter validation, and safety and ethics frameworks before standardized use.
AI Ethics & Governance 1 Flagged
AI Ethics & Governance
Population unclear
When machines explain medicine: Nursing ethics and clinical communication.
Nursing Ethics · Nov2
This article examines, through a non-systematic review of 2022–2025 studies on LLM-assisted radiology and pathology communication, how AI-generated plain-language explanations reshape clinical communication. It finds that interpretive authority becomes spread across clinicians, nurses, patients, and automated systems, while formal accountability stays with professional roles. For nursing informatics, this raises ethical questions about responsibility and how uncertainty gets communicated when explanation is partly automated.
Workforce & Education 8 Flagged
Workforce & Education
Population unclear Setting unclear Abstract incomplete
Strengthening competency-based outcomes in DNP education: Addressing curriculum gaps.
The Nurse practitioner · Nov 2026
This review examines gaps in Doctor of Nursing Practice (DNP) education, including uneven project rigor, limited informatics and AI skills, inconsistent competency-based preparation, and weak scholarly writing. The authors call for standardized competency assessments for DNP projects and stronger faculty development. This matters because it highlights areas where DNP programs may need to improve training to better prepare nurses for informatics-related practice demands.
Workforce & Education
Population unclear Setting unclear
Beyond AI Detection: A Decision-Making Guide for Strategic Assessment Design in Nursing Education.
Nurse educator · 2026
Graduate nursing faculty developed a decision-making guide to help educators judge how vulnerable specific assessments are to inappropriate AI use. The tool scores assessments across two areas—setting and method—and pairs each score with improvement guidance. This helps nursing programs focus assessment redesign on high-stakes areas where AI threatens valid competency evaluation, while keeping flexibility where AI use fits professional practice.
Workforce & Education
Population unclear Setting unclear
Artificial intelligence in nursing education: Balancing innovation and human-centered care.
Nurse education today · Nov 2026
This discussion article examines the growing use of AI tools, such as virtual patient simulations and adaptive learning platforms, in nursing continuing education. It argues that while AI offers efficiency and personalized learning, it risks weakening critical thinking, clinical reasoning, and relational and ethical skills. The author proposes blended learning, AI literacy, and oversight protocols to keep education centered on human and ethical nursing care.
Workforce & Education
Population unclear Setting unclear
Vibe coding in nursing education: From user to creator.
Nurse education today · Nov 2026
This conceptual commentary examines 'vibe coding'—using AI to build digital tools through conversational prompting—as a lens for rethinking nurses' role in educational technology design. The author argues nurses could shift from being users of tools like simulations and learning platforms to becoming co-designers, though this raises concerns about accuracy, bias, privacy, and pedagogical quality. This matters for nursing informatics because it suggests education may need to build critical AI literacy and digital co-design skills, not just basic tool use.
Workforce & Education
Population unclear
Artificial Intelligence Enhanced Content Review for Curriculum Evaluation in Nursing Education: A Pilot Study.
Nurse educator · 2026
Researchers tested a chatbot using retrieval-augmented generation to screen 9 nurse-midwifery lecture sets for health equity content, comparing it to 3 faculty reviewers. The chatbot showed high reliability in repeated ratings (84-91%) but more variable agreement with faculty (56-89%). This suggests AI tools may help scale curriculum review but should assist, not replace, human judgment.
Workforce & Education
Population unclear Setting unclear
Conceptual analysis of Chatbots in nursing education applications.
Nurse education today · Nov 2026
This study used Walker and Avant's concept analysis method to clarify what 'chatbot' means in nursing education, reviewing 24 papers across multiple databases. The authors define a nursing education chatbot as a conversational digital agent built for nursing education that gives automated responses through rule-based, retrieval-based, or AI-based methods, separate from any one technology generation. This clearer definition can help researchers report findings consistently and design better studies, though it does not show that chatbots actually improve learning outcomes.
Workforce & Education
Population unclear Setting unclear
Clinical Narration Competency for Nursing Education and Practice in the Era of Artificial Intelligence.
Journal of Transcultural Nursing · Nov2
This article discusses clinical narration, a new skill where nurses speak their care actions and reasoning aloud so ambient AI tools can create documentation. The authors define this competency as three parts: knowledge, narration skills, and critical review, and propose a teaching framework to build these skills into nursing education. This matters because it highlights a new training need as AI tools become part of everyday nursing practice.
Workforce & Education
Population unclear
Simulation‐Based Education to Support Nurses' Critical Thinking in Delirium Recognition: A Scoping Review.
Journal of Advanced Nursing (John Wiley & Sons, Inc.) · Nov2
This scoping review looked at 14 studies on simulation-based education and how it helps nurses think critically to recognize delirium in patients. The review found that simulation improved skills like spotting subtle cognitive changes, clinical reasoning, and teamwork, with structured debriefing helping nurses reflect on their decisions. This suggests simulation training could help nurses catch delirium earlier and communicate more clearly across care teams.