Artificial Intelligence in Personalized Medical Education: A Systematic Review of Applications, Benefits, and Challenges

نویسندگان
doi
10.22062/sdme.2025.201058.1551
چکیده

Background:  Medical education, due to its increasing complexity, requires innovative and effective approaches, with artificial intelligence (AI) emerging as a leading tool. AI facilitates the personalisation of learning by adapting educational processes to individual student needs.Objectives: This study aims to systematically examine the role of artificial intelligence in personalising medical education by identifying its main applications, pedagogical benefits, and implementation challenges, and by proposing evidence-based recommendations for optimising AI-driven instructional strategies.Methods: A systematic review was conducted by searching five major databases PubMed, Scopus, IEEE, Web of Science, and Google Scholar up to March 2025. Relevant keywords included “artificial intelligence,” “personalized learning,” “adaptive learning,” “machine learning,” “deep learning,” “natural language processing,” and “medical education.” In total, 70 articles were initially identified, and after screening and applying inclusion and exclusion criteria, 32 studies focusing on the application of artificial intelligence in medical education were selected for analysis.Results: Findings indicated that AI enhances learning quality through personalized feedback, adaptive learning pathways, and interactive educational simulations. AI can also assess students' strengths and weaknesses, recommend appropriate educational resources, and promote self-directed learning. However, challenges such as implementation costs, data security concerns, and user resistance to adopting new technologies were identified as major barriers.Conclusion: AI holds significant potential for enhancing the quality of medical education and personalizing the learning experience. To fully harness this technology, it is crucial to address existing challenges and develop human-AI hybrid models. Future research should focus on improving technical infrastructure and increasing user acceptance.