Artificial Intelligence in Nursing Practice Education: A Systematic Review and Meta-Analysis

To systematically evaluate the application effect of artificial intelligence (AI) technology in nursing practice courses and to provide evidence-based guidance for the intelligent reform of nursing education.

Computerized searches were performed in PubMed, Web of Science, Embase, the Cochrane Library, CNKI, WanFang, CBM, and VIP databases for randomized controlled trials and quasi-experimental studies on the educational effectiveness of AI in nursing practice courses. The retrieval period was from the establishment of each database to February 2026. Data extraction, quality evaluation, and literature screening were carried out separately by two researchers. RevMan 5.4 was used to conduct the meta-analysis. The PROSPERO registration number for this review protocol is CRD420261403298. The PRISMA 2020 guidelines are followed in this systematic review.

A total of 16 studies with a sample size of 1647 participants were included, including 7 randomized controlled trials and 9 quasi-experimental studies. The results of this meta-analysis indicate that incorporating AI into nursing practical training programs may enhance students' learning outcomes in a variety of ways, with beneficial facilitative effects noted in knowledge level (SMD = 0.72, 95% CI [0.20-1.24], p = 0.007), practical ability (SMD = 1.25, 95% CI [0.50-2.00], p = 0.001), critical thinking and clinical reasoning abilities (SMD = 0.43, 95% CI [0.21-0.65], p < 0.001), learning satisfaction (SMD = 0.38, 95% CI [0.16-0.59], p = 0.0005), and ethical awareness and decision-making capacity (SMD = 0.50, 95% CI [0.29-0.71], p < 0.001). However, high heterogeneity was observed for knowledge level (I² = 91%) and practical ability (I² = 95%), while the remaining outcomes showed low to mild heterogeneity (I² < 50%). The overall methodological quality of the included studies was moderate to high.

There are encouraging advantages to using AI in practical nursing courses. According to preliminary data, it may have positive benefits on a variety of learning parameters. These results are still preliminary and need to be confirmed by future high-quality research due to significant variation, especially in knowledge level and practical abilities, as well as limitations in the quantity and design of included studies.

Nursing education management can gain multifaceted practical insights from the use of AI in practical training courses: (1) Institutions shall actively adopt mechanisms for the implementation, evaluation, and continuous improvement of AI-assisted teaching; allocate resources in a coordinated manner; and advance the intelligent upgrading of practical courses to ease the shortage of clinical practice resources. (2) To improve nursing educators' competence in AI instructional design and ethical standards, a tiered and categorized training system will be implemented. To promote educational innovation, corresponding reward and assessment schemes should be developed. (3) Teaching management must incorporate a multifaceted evaluation system for AI teaching outcomes. Formative assessment using platform data can be used to continuously monitor and enhance the quality of instruction. (4) The goals of nursing talent training should include AI digital literacy. To avoid an over-reliance on technology, instructors must cultivate students' critical thinking and autonomous judgment while enhancing their practical skills. (5) To standardize educational data management, a strong ethical and safety framework for AI application must be refined. This ensures a uniform and long-lasting intelligent change of nursing education by striking a balance between humanistic care and technology empowerment.