Artificial intelligence in neurosurgical education – current applications, opportunities and limitations: A narrative review

Abstract

The evolution of artificial intelligence (AI) and large language models (LLMs) is updating medical and neurosurgical education. This narrative review provides an updated synthesis of recent applications of AI in neurosurgical education, with particular emphasis on LLMs, knowledge assessment, simulation-based training, automated competency evaluation, and implementation risks. Through machine learning, deep learning, and virtual reality systems, AI enables personalized, adaptive learning pathways, 24/7 on-demand academic assistance, and objective, data-driven competency evaluations in risk-free environments. In neurosurgery, intelligent surgical simulators and automated 3D spatial planning tools optimize technical execution and track procedural metrics. Generative AI streamlines curriculum design, literature synthesis, and examination drafting. However, the adoption of foundation models introduces critical limitations and risks. These systems remain vulnerable to hallucinations, logic confabulations, and fabricated bibliographic citations, which pose risks in high-stakes clinical contexts. Excessive dependence on AI can cause cognitive fatigue, diminish independent critical thinking, and elevate risks related to academic plagiarism, algorithmic bias, and data privacy. To address these challenges, continuous human verification is required. AI should function as a supportive, transparent assistant of human clinical judgment, ensuring that technological innovation reinforces core values of medical practice and patient safety.