مقالات پذیرفته شده در نهمین کنگره بین المللی زیست پزشکی
Transforming Internal Medicine Education: The Role of Artificial Intelligence in Shaping Teaching and Learning for Medical Students
Transforming Internal Medicine Education: The Role of Artificial Intelligence in Shaping Teaching and Learning for Medical Students
Ali Madadi Mahani,1AmirAli Moodi Ghalibaf,2,*
1. Student Research Committee, School of Medicine, Kerman University of Medical Sciences, Kerman, Iran 2. Student Research Committee, Mashhad University of Medical Sciences, Mashhad, Iran
Introduction: The rapid evolution of artificial intelligence (AI) has introduced new opportunities to reshape medical education, particularly in internal medicine, where the breadth of knowledge and the complexity of patient care demand advanced teaching approaches. Traditional methods of instruction, though effective, often rely on uniform content delivery and limited clinical exposure. AI has the potential to augment these methods by fostering adaptive learning, enhancing clinical reasoning, and supporting individualized learning trajectories. Exploring its role is essential for preparing medical students to meet the challenges of modern internal medicine.
Methods: This study draws upon a narrative synthesis of published literature, educational reports, and case-based applications of AI in medical curricula from 2015 to 2025. Databases including PubMed, Scopus, and Google Scholar were searched using terms such as artificial intelligence, internal medicine education, adaptive learning, clinical reasoning, and personalized learning. Relevant peer-reviewed articles, conference proceedings, and pilot program evaluations were included to capture diverse perspectives. The analysis was structured around three predefined domains: (1) knowledge acquisition, focusing on adaptive learning platforms and intelligent tutoring systems; (2) clinical reasoning, examining AI-supported decision-making tools and simulation-based learning; and (3) personalized education, highlighting predictive analytics and individualized feedback mechanisms. Findings were synthesized qualitatively to identify trends, strengths, limitations, and practical considerations for faculty and learners.
Results: AI applications demonstrated significant benefits across multiple areas of internal medicine education.
Knowledge Acquisition: Adaptive e-learning systems such as AI-driven question banks and intelligent tutoring programs were shown to personalize instruction by identifying gaps in understanding and offering tailored resources. For example, natural language processing (NLP) chatbots were used to explain pathophysiological mechanisms of diseases such as heart failure or diabetes mellitus in a conversational format, allowing students to engage more interactively. Some programs dynamically adjusted difficulty levels in pharmacology or hematology modules, reducing cognitive overload and improving long-term retention.
Clinical Reasoning: AI-powered virtual patient simulations and diagnostic decision-support platforms offered opportunities to practice reasoning in complex scenarios. Simulated cases of pneumonia with atypical presentations, polypharmacy in elderly patients, and overlapping symptoms of autoimmune conditions were employed to test diagnostic skills. These systems provided immediate feedback on diagnostic pathways and therapeutic decisions, highlighting both correct reasoning and potential errors. AI algorithms used in radiology and ECG interpretation training allowed medical students to compare their clinical judgments with machine-generated predictions, encouraging reflection on diagnostic accuracy and limitations.
Personalized Learning: Predictive analytics enabled the early identification of students at risk of underperformance. For example, algorithmic models analyzing engagement patterns and quiz results flagged learners who required additional support, allowing faculty to intervene proactively. AI-based dashboards provided individualized study recommendations, such as revisiting nephrology modules or completing additional practice in cardiovascular case-based learning. This tailoring not only supported struggling learners but also accelerated advanced students toward higher-order skills such as critical appraisal of evidence and management of rare conditions.
Skill Assessment and Feedback: Automated grading of written responses and structured feedback on case presentations offered real-time insights into student progress. Some programs employed AI to evaluate the coherence of clinical notes, the appropriateness of diagnostic plans, and even the clarity of reasoning processes. Such tools reduced faculty workload and allowed educators to focus on higher-value mentorship activities.
Despite these benefits, challenges persisted. Over-reliance on AI-generated solutions risked undermining independent critical thinking. Algorithmic bias—stemming from datasets that may not fully represent diverse patient populations—could inadvertently propagate inequities in training. Ethical issues surrounding data security, confidentiality of patient simulations, and unequal access to high-resource AI tools were also noted. Moreover, successful implementation required significant faculty development, ensuring that instructors could integrate AI into curricula without compromising traditional mentoring, professional identity formation, and empathy-driven care.
Conclusion: AI offers promising opportunities to revolutionize internal medicine education by advancing adaptive learning, strengthening clinical reasoning, and enabling personalized educational experiences. However, these benefits can only be realized if integration is guided by ethical safeguards, pedagogical oversight, and robust faculty engagement. The future of internal medicine training will likely rest on hybrid models that merge AI-driven innovations with the irreplaceable human elements of mentorship, empathy, and professional identity formation. By adopting AI as a supportive partner rather than a substitute for educators, medical schools can cultivate physicians who are both technologically adept and deeply humanistic in practice.