CONCEPTUAL APPROACHES TO THE INTEGRATION OF GENERATIVE ARTIFICIAL INTELLIGENCE INTO SIMULATION-BASED TRAINING FOR MEDICAL STUDENTS

Abstract

The rapid expansion of generative artificial intelligence (GenAI) is transforming medical education by creating new opportunities for simulation-based learning, clinical reasoning development, and personalized educational support. Despite increasing adoption of large language models in health professions education, their integration into simulation remains fragmented, with limited methodological guidance and a lack of standardized pedagogical frameworks. To develop a conceptual model for integrating GenAI into simulation-based medical education and to define methodological principles for its safe, pedagogically sound, and evidence-based implementation. A narrative analysis of contemporary literature, international recommendations, and methodological documents published between 2023 and 2026 was conducted. Current evidence regarding the educational applications, benefits, limitations, ethical considerations, and implementation strategies of GenAI in medical education and healthcare simulation was synthesized. Based on these findings, a conceptual framework and methodological principles for GenAI integration into simulation-based learning were developed. The proposed framework integrates GenAI across all stages of simulation-based education, including scenario design, educational content generation, adaptive virtual patient interactions, clinical reasoning support, formative feedback, debriefing assistance, and reflective learning. Eight methodological principles were identified: pedagogical appropriateness, prioritization of clinical reasoning, human-in-the-loop supervision, evidence-based clinical content, comprehensive integration throughout the simulation process, academic integrity, ethics and data privacy, and continuous educational evaluation. The model emphasizes that GenAI should augment rather than replace educators, with faculty maintaining responsibility for instructional design, expert validation of AI-generated content, learner assessment, and educational debriefing. GenAI has considerable potential to enhance simulation-based medical education by improving educational efficiency, adaptability, and learner engagement. However, its successful implementation requires standardized pedagogical frameworks, continuous human oversight, adherence to evidence-based medicine, academic integrity, ethical principles, and data protection. The proposed conceptual model provides a methodological foundation for the responsible integration of GenAI into undergraduate medical education and may support future research evaluating its educational effectiveness and impact on competency development