Abstract
BACKGROUND AND OBJECTIVE: Pulmonary nodules are commonly identified in clinical practice, frequently as incidental findings during imaging performed for unrelated indications. Their management poses significant clinical challenges, as accurate risk stratification and timely diagnosis are essential to distinguish benign from malignant lesions. However, variability in clinician expertise often results in inconsistent decision-making. Artificial intelligence (AI) offers promising solutions for standardizing pulmonary nodule assessment and enhancing clinician training. This narrative review systematically compiles the current status and research progress of the application of AI technology in the field of medical education, especially in the teaching of pulmonary nodule management, and further discusses its future development trend. METHODS: A narrative literature review was conducted using electronic databases, including PubMed and Google Scholar, to identify relevant peer-reviewed studies published in recent years. Literature retrieval was conducted in major research areas such as AI, medical education, pulmonary nodules, and clinical decision support. Articles were selected based on their relevance to AI-based educational tools, decision support systems, and diagnostic applications in pulmonary nodule evaluation. KEY CONTENT AND FINDINGS: The review reveals a growing integration of AI technologies in medical education and clinical training related to pulmonary nodule management. AI-driven educational platforms, including virtual simulation environments and intelligent tutoring systems, have demonstrated effectiveness in improving learners' skills in imaging interpretation and clinical risk assessment. Moreover, AI-enhanced decision support tools have the capacity to reduce diagnostic variability, particularly among trainees and early-career clinicians. In view of this, the medical education system urgently needs to introduce AI-related courses and build an interdisciplinary talent cultivation framework to promote the teaching of lung nodule management towards intelligence and precision. CONCLUSIONS: AI is the link between medical education and the clinical management of lung nodules, and is a transformative force driving its development. Its integration into training programs can facilitate more interactive, personalized, and effective learning experiences, ultimately contributing to improved diagnostic precision and patient outcomes. Future research should focus on validating AI-assisted educational interventions, addressing challenges in implementation, and ensuring their ethical and equitable use across diverse healthcare settings. Broader adoption of such technologies may significantly advance both clinician preparedness and the quality of care delivered to patients with pulmonary nodules.