Actionable companion · Accessibility & inclusion

Learning with agency: Leveraging machine learning in nursing: innovations, challenges, and ethical insights

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paper Search paper agent CC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Age / stage not established. Health-professions learning must be distinguished from K–12 instruction.

Original authors’ abstract, reproduced under the linked source license:

Abstract Aim/objective This review aims to provide a comprehensive analysis of the integration of machine learning (ML) (1) in nursing by exploring its implications on patient care, nursing practices, and healthcare delivery. It highlights current applications, challenges, ethical considerations, and the potential future developments of ML in nursing. Background With the advent of ML in healthcare, the nursing profession stands on the cusp of a transformative era. Despite the technological advancements, discussions on the utilization of ML in nursing, which are crucial for advancing the profession, are lacking. This review seeks to fill this gap by examining the balance between technological innovation and the human-centric nature of nursing. Design This narrative review employs a detailed search strategy across several databases, including PubMed, Embase, MEDLINE, Scopus, and Web of Science. It focuses on articles that were published from January 2019 to December 2023. Moreover, this review aims to illustrate the current use, challenges, and future potential of ML applications in nursing. Methods Inclusion criteria targeted articles that focus on ML application in nursing, challenges, ethical considerations, and future directions. Exclusion criteria omitted opinion pieces and nonrelevant studies. Articles were categorized into themes, such as patient care, nursing education, operational efficiency, ethical considerations, and future potential, thus facilitating a structured analysis. Results Findings demonstrate that ML has significantly enhanced patient monitoring, predictive analytics, and preventive care. For example, the COMPOSER deep learning model for early sepsis prediction was associated with a 1.9% absolute reduction (17% relative decrease) in in-hospital sepsis mortality and a 5.0% absolute increase (10% relative increase) in sepsis bundle compliance. In nursing education, ML has improved simulation-based training by facilitating adaptive learning experiences that support continual skill development. Furthermore, ML contributes to operational efficiency through automated staffing optimization and administrative task automation, thus reducing nurse workload and enhancing patient care outcomes. However, key challenges include ethical considerations, such as data privacy, algorithmic bias, and patient autonomy, which necessitate ongoing research and regulatory oversight. Conclusions ML in nursing offers transformative potential across patient care, education, and operational efficiency, which is balanced by significant challenges and ethical considerations. Future directions include expanding clinical and community applications, integrating emerging technologies, and enhancing nursing education. Continuous research, ethical oversight, and interdisciplinary collaboration are essential for harnessing ML's full potential in nursing to ensure that its advancements improve patient outcomes and support nursing professionals without compromising core nursing values. Keywords: machine learning, artificial intelligence, digital health, predictive analytics, ethical considerations, interdisciplinary collaboration

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Evidence synthesis

Stage: Age / stage not established. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

This narrative review comprehensively illustrates the current use of ML applications in nursing, the challenges and ethical considerations, and potential future advancements. A detailed search strategy was employed by utilizing a range of keywords that are associated with ML and its applications within various sectors of healthcare, including “machine learning,” “artificial intelligence,” “nursing,” “healthcare,” “clinical,” “education,” “training,” and “management.” The databases PubMed, Embase, MEDLINE, Scopus, and Web of Science were systematically searched. Given the vast number of publications that are related to ML in nursing, the inclusion of all available studies across all periods was neither feasible nor methodologically appropriate. Instead, a targeted approach was adopted to ensure the inclusion of highly relevant and recent studies that align with current advancements and practical applications in nursing. PubMed, MEDLINE, Embase, Scopus, and Web of Science were selected for their comprehensive coverage of healthcare, clinical, and interdisciplinary AI research. PubMed and MEDLINE focus on nursing and clinical studies. Embase provides pharmaceutical and European research insights. Scopus offers broad scientific coverage, while Web of Science enables citation tracking to identify influential works. Studies were prioritized based on recency, impact, and direct applicability to nursing practice to maintain relevance and methodological rigor. Meanwhile, older foundational papers were included selectively if they provided critical background knowledge. This approach balances breadth and depth, thus ensuring that the review remains focused, up to date, and practically relevant to nursing professionals and researchers. The scope of the search was narrowed to English full-text articles that were published between January 2019 and December 2024.

Limitations and uncertainty · source passage

This narrative review has several limitations. First, the search strategy was not exhaustive. Although we aimed to capture a broad representation of ML applications in nursing, the inclusion of articles was not based on a systematic review protocol. As such publication bias or omission of relevant studies may have occurred. Second, the categorization of included studies into thematic domains was conducted inductively and may be subject to interpretation bias. Third, many of the articles cited describe theoretical applications or early-stage developments rather than empirically validated interventions. Thus, some proposed potentials of ML remain speculative. Fourth, given the rapidly evolving nature of AI and ML technologies, the literature may quickly become outdated. Emerging developments, such as large language models, may not yet be fully captured in peer-reviewed research. Finally, while we attempted to include global perspectives, the literature predominantly reflects research from high-resource settings, thus limiting the generalizability of findings to low- and middle-income countries.

Design the system before the pilot

Document the learner model, mastery rule, hint sequence and adaptation signal. Compare adaptive routing with the same content in a non-adaptive sequence. Check whether early errors lead to persistent low-expectation pathways.

Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
Days 16–30 · Design. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. Name an accountable owner and set the baseline, success threshold and budget before implementation.
Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
Days 61–90 · Decide. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Sophie So Wan Yip; Sheng Ning; Niki Yan Ki Wong; Jeffrey Chan; Kei Shing Ng; Bernadette Oi Ting Kwok; Robert L Anders; Simon Ching Lam. Leveraging machine learning in nursing: innovations, challenges, and ethical insights. Frontiers in Digital Health (2025-05-23). https://doi.org/10.3389/fdgth.2025.1514133

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.