Mapping randomized evidence on artificial intelligence-based educational interventions and learning outcomes in nursing students: a scoping review
Artificial intelligence (AI) is increasingly being incorporated into nursing education through generative AI tools, chatbots, intelligent tutoring systems, simulation, and AI-assisted feedback. This scoping review aimed to map randomized evidence on AI-based educational interventions and reported learning outcomes among nursing students. A scoping review was conducted using the Arksey and O’Malley framework. PubMed, Scopus, Web of Science, and the Cochrane Central Register of Controlled Trials (CENTRAL) were searched between July 20 and August 3, 2026, for peer-reviewed, English-language randomized studies evaluating AI-based educational interventions among nursing students. The review protocol was not prospectively registered. Study characteristics, interventions, comparators, outcomes, and reported findings were synthesized descriptively, and risk of bias was assessed using the Cochrane Risk of Bias 2 tool. Thirty-one randomized studies published between 2023 and 2026 met the eligibility criteria. Interventions included generative AI applications, chatbots, intelligent tutoring systems, AI-supported simulation, virtual reality, and AI-assisted assessment and feedback. Outcomes included knowledge and academic performance, clinical performance and reasoning, communication and empathy, higher-order thinking, self-confidence, satisfaction, attitudes toward AI, psychological outcomes, and educational-material quality. Favorable findings were reported across several outcome domains, but results varied according to the intervention, comparator, educational context, and outcome assessed, with conventional or human-supported approaches showing comparable or superior outcomes in some studies. Twenty-eight studies had some concerns regarding risk of bias and three were rated as high risk; none were rated as low risk overall. Longer-term follow-up was uncommon. AI-supported educational approaches may benefit selected learning outcomes in nursing students, but current randomized evidence does not show a consistent advantage over established teaching methods. Heterogeneity in interventions, comparators, outcome measures, follow-up periods, and risk of bias limits firm conclusions. More rigorous randomized studies with longer follow-up are needed.
Authors
- Mohammad Saeed Mirzaee (ORCID: https://orcid.org/0000-0003-0372-1383)
- Cirruse Salehnasab (ORCID: https://orcid.org/0000-0002-5615-9307)
- Naeem Abdi (ORCID: https://orcid.org/0000-0002-5881-8572)
- Salar Dasdar (ORCID: https://orcid.org/0000-0001-5136-2210)
- Alireza Mehrayin
Institutions
- Yasuj University of Medical Sciences (IR)
- Tehran University of Medical Sciences (IR)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1186/s12909-026-10834-2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00