Jul 2026· Journal of Advanced Nursing· 0 citations· 44 references
Medicine
TL;DR
A theoretically grounded synthesis of research gaps and implementation priorities for AI development aligned with nursing clinical judgement is provided, identifying research gaps and implementation priorities for AI development aligned with nursing clinical judgement.
Abstract
Aim
To map and analyse how artificial intelligence technologies interact with and support clinical judgement processes in nursing across practice and educational contexts.
Design
Scoping review.
Methods
JBI methodology for scoping reviews.
DATA SOURCES
An electronic search was conducted on 1 July 2025 across MEDLINE, CINAHL, Scopus, Web of Science, and IEEE Xplore to identify studies published since January 2015. Additional sources of grey literature included ProQuest Dissertations & Theses Global, preprint servers (medRxiv and arXiv), and websites of relevant organisations.
Results
Eleven studies were included. Mapped against Tanner's Clinical Judgement Model, AI applications predominantly supported early cognitive phases (noticing and interpreting) through predictive models and decision support systems, while responding and reflecting phases received minimal attention.
Conclusion
Current AI research in nursing concentrates on computational pattern recognition, with the reflective processes central to expertise development remaining largely unexamined. Future research should examine how AI influences nurses' cognitive and interpretative processes across all phases of clinical judgement, with primary studies in nursing education representing a particularly underdeveloped priority.
IMPLICATIONS FOR THE PROFESSION AND/OR PATIENT CARE
The integration of artificial intelligence into nursing practice should be guided by a clear understanding of how these technologies support clinical judgement. Artificial intelligence-enabled tools must be rigorously developed, implemented, and evaluated to enhance nurses' reasoning processes while safeguarding patient safety, professional autonomy, and quality of care.
IMPACT
Research on artificial intelligence in nursing rarely employs theoretical frameworks of clinical judgement, limiting understanding of how these technologies interact with cognitive processes central to professional expertise. This review provides a theoretically grounded synthesis, identifying research gaps and implementation priorities for AI development aligned with nursing clinical judgement.
REPORTING
Method
PRISMA-ScR.
PATIENT OR PUBLIC CONTRIBUTION
This study did not include patient or public involvement in its design, conduct or reporting.
TRIAL REGISTRATION
Protocol registered in Open Science Framework (https://osf.io; DOI: https://doi.org/10.17605/OSF.IO/UH7RA), and subsequently published in a peer-reviewed journal, DOI: https://doi.org/10.62741/ahrj.v2i4.73.
OBJECTIVE
This scoping review will map the scope and nature of the available evidence on the use of artificial intelligence-based clinical decision support systems (AI-CDSSs) for undergraduate nursing students.
INTRODUCTION
AI is increasingly integrated into nursing education to support students' clinical reasoning and decision-making. Yet the literature on AI-CDSSs remains fragmented and heterogeneous, with variability in technologies, educational applications, and reported outcomes, as well as concerns regarding bias and ethical implications. To date, no comprehensive synthesis has mapped the evidence on AI-CDSS use for undergraduate nursing students.
ELIGIBILITY CRITERIA
This review will map empirical research involving undergraduate nursing students using AI-based tools to support clinical reasoning, diagnostic reasoning, prioritization, or the nursing process. It will consider sources published in English, Spanish, French, Italian, or Chinese, provided that the title and abstract are in English and the record is considered relevant. Searches will be limited to sources published from 2017 onward, aligning with the rapid evolution and only recent widespread availability of modern generative AI tools.
METHODS
This review will follow the JBI methodology for scoping reviews. Searches will be conducted in PubMed, Scopus, CINAHL (EBSCOhost), the Cochrane Library, ERIC (EBSCOhost), and Web of Science Core Collection, while gray literature will be retrieved from ProQuest Dissertations and Theses Global (ProQuest), OpenAlex, Google Scholar, and professional body and regulatory sources. Screening will be performed independently by 2 reviewers, and data will be synthesized descriptively and thematically. Reporting will be documented according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews.
REVIEW REGISTRATION
OSF https://osf.io/eh9bt/.
Francesco Scerbo, G. Caggianelli, Simone Ciucciarelli et al.· JBI Evidence Synthesis· 0 citations
INTRODUCTION
Objective Structured Clinical Examinations (OSCEs) are widely used to assess clinical competence, but face challenges related to examiner workload, scoring variability, delayed feedback, and resource demands. Although AI may address these constraints and support precision medical education, the evidence remains fragmented. This scoping review maps AI applications in OSCEs.
METHODS
We followed PRISMA-ScR. We searched MEDLINE, Scopus, Embase, Web of Science, ERIC, LILACS, and IEEE Xplore from inception to June 2025. Eligible studies examined AI within any phase of an OSCE in health professions education. Data charting captured AI form, technology, OSCE phase, competencies, outcomes, faculty and resource implications, and ethical/governance issues. Synthesis used a hybrid approach: deductive coding with FACETS, SAMR, and operationalized P4 properties, plus inductive coding for emergent themes. Findings were stratified by evidence maturity rather than formal quality scoring.
RESULTS
Of 421 records screened, 22 studies were included. AI was used for learner preparation, station/material construction, scoring/evaluation, and operational delivery. Benefits were strongest for grading, feedback speed, and consistency in structured tasks, but weaker for relational competencies. Most applications reflected SAMR Augmentation or Modification. Personalization dominated P4 alignment. Ethical concerns centered on privacy, bias, accuracy, transparency, access, and human oversight.
DISCUSSION AND CONCLUSION
AI currently augments rather than transforms OSCE assessment, performing best in structured, observable tasks and least well in relational, situated, and culturally mediated competencies. Claims that AI delivers precision medical education through OSCEs are not yet supported by evidence; alignment with P4 is partial and conditional. Realizing the potential of AI in OSCEs will require human-in-the-loop governance with concrete safeguards and equity-focused implementation in resource-limited settings.
Sergio Andrés León-Ariza, María Camila Orobio-Pinzón, Héctor Miguel Ibáñez-Gutiérrez et al.· Medical Teacher· 0 citations
Nursing academics appear to adopt AI selectively, prioritising preservation of core professional values while embracing applications perceived to enhance, rather than replace, educational practice, providing evidence for nursing education programs globally regarding faculty development, institutional policy frameworks, and curriculum design strategies integrating technological advancement whilst maintaining person-centred values.
Natasha Hawkins, Anthea Fagan, Yumiko Coffey et al.· Journal of Advanced Nursing· 0 citations
BACKGROUND
Artificial intelligence (AI) is reshaping clinical decision support systems (CDSSs). In acute and critical care, nurses provide continuous surveillance, recognise deterioration, coordinate escalation and translate protocols into bedside action. AI-CDSS may be particularly relevant when they support rather than replace clinical judgement.
AIM
To examine whether nurse-used AI-CDSS improve patient-important outcomes in acute and critical care contexts and summarise effects on care processes and nurse-reported outcomes.
STUDY DESIGN
Following PRISMA 2020 and a preregistered protocol, we searched eight databases and major trial registries for English-language studies from 1 January 2010 to 1 January 2026. Searches were conducted on 1 January 2026. We included randomised, quasi-experimental and adjusted cohort studies in which registered nurses or nursing teams were primary users of AI-CDSS generating patient-specific predictions or recommendations. Mortality was pooled using a random effects model; other outcomes were synthesised narratively.
RESULTS
Seven studies involving about 75 000 patients were included. Most evidence came from acute wards, intensive care units, sepsis, deterioration and delirium-prevention contexts, with additional home and palliative care evidence. Three mortality studies were pooled. Nurse-facing AI-CDSS were associated with lower hospital mortality (RR 0.68, 95% CI 0.53-0.87; I2 = 24%), although the prediction interval included possible no effect. Length of stay and protocol adherence generally improved when tools were embedded in nursing workflows. Nurse-reported outcomes were sparse.
CONCLUSION
Nurse-facing AI-CDSS may strengthen acute and critical care nursing by improving surveillance, escalation and protocol delivery for patients at risk of deterioration. Evidence is promising but limited by small study numbers, heterogeneous interventions and sparse nurse-reported outcomes. Critical care implementation should prioritise nurse-centred design, alert burden, equity, safety monitoring and rigorous evaluation before scale-up.
RELEVANCE TO CLINICAL PRACTICE
Nurse-used AI-CDSS show potential to improve patient outcomes and care processes, but evidence remains limited and context dependent.
W. Almagharbeh, S. Alkubati, A. A. Alasmari et al.· Nursing Critical Care· 0 citations
BackgroundArtificial intelligence (AI) is transforming healthcare by influencing clinical decision-making, service delivery, and professional roles. Healthcare professionals' perceptions of AI are critical to its successful implementation and integration into clinical practice. Understanding research trends in this field can support future scientific and policy developments.ObjectiveThis study aimed to examine the scientific structure, research trends, and thematic development of the literature on healthcare professionals' perceptions of artificial intelligence through bibliometric analysis.MethodsA bibliometric analysis was conducted using publications indexed in the Scopus database between 2015 and 2025. The dataset included English-language, peer-reviewed journal articles in medicine, nursing, and health sciences. A total of 644 publications met the inclusion criteria. Publication trends, productive countries, authors, subject areas, and citation patterns were analyzed. Network visualization and keyword co-occurrence analyses were performed using VOSviewer.ResultsPublications increased markedly after 2020, indicating growing scientific interest in the topic. Three major thematic clusters were identified: clinical and technological integration of AI in healthcare, AI in health education and professional practice, and ethical, psychological, and attitudinal aspects of AI. The findings also revealed a shift toward human-centered research emphasizing healthcare professionals' competencies, acceptance, and concerns regarding AI.ConclusionsThis study provides a comprehensive overview of the intellectual landscape of research on healthcare professionals' perceptions of AI. The findings may inform future research, evidence-based policymaking, and strategies to support the effective integration of AI into healthcare systems.
Objective To map the evidence on artificial intelligence (AI)-generated diabetes-related patient education materials and patient-facing health information, with particular attention to AI models, prompting approaches, evaluation methods, and information-quality outcomes. Methods This scoping review was conducted in accordance with the JBI methodology for scoping reviews and reported following the PRISMA-ScR checklist. The review was registered on the Open Science Framework (doi: 10.17605/OSF.IO/U4FAE) PubMed, Web of Science, Embase, Scopus, Cochrane CENTRAL, CNKI, WanFang Data, and SinoMed were searched from inception to May 1, 2026. Chinese- and English-language literature was searched. Two reviewers independently screened studies, charted data, and mapped reported outcomes to Wang and Strong's information quality framework. Outcomes not adequately represented by the framework were retained as additional dimensions. Descriptive statistics and narrative synthesis were used. Results Of 6,049 records identified, 24 studies from 11 countries or regions were included. All studies evaluated ChatGPT or another GPT-family model; 21 used zero-shot or direct prompting, three used role prompting, and two implemented retrieval-augmented generation. Eleven indicators were mapped to the information quality framework, with ease of understanding (n = 14), accuracy (n = 13), and believability (n = 9) assessed most frequently. Six additional outcomes were identified: clinical safety (n = 5), actionability (n = 3), response efficiency (n = 1), personalization (n = 1), transparency (n = 1), and empathy (n = 1). Most studies reported reading demands above those generally recommended for patient education, although findings varied by language, material type, and assessment method. Study-specific instruments were used in 17 studies (70.8%), whereas 10 (41.7%) used structured or established tools. Only six studies reported full source or model blinding, 10 reported quantitative inter-rater agreement, and three involved patients or members of the public. Conclusion Research on AI-generated diabetes education is expanding, but substantial heterogeneity in prompts, evaluators, tools, and outcome definitions limits comparison across studies. Future research should prioritize validated, multilingual, and patient-centered evaluation tools that integrate conventional information-quality attributes with clinically relevant dimensions such as safety, actionability, personalization, transparency, empathy, and response efficiency.
Jingwen Song, Norafisyah Makhdzir, Zarina Haron et al.· Frontiers in Public Health· 0 citations