Tamari Pertaia
Dean of the Medical Faculty, Central University of Europe
Abstract
Artificial Intelligence (AI) has emerged as a transformative force in medical education, offering solutions to the longstanding limitations of traditional training. This article explores AI’s role across five critical domains: clinical training, virtual patient simulation, personalized learning, curriculum integration, and assessment. The COVID-19 pandemic underscored the urgency of flexible learning environments, and AI-based platforms such as Osso VR, Touch Surgery, Body Interact, Smart Sparrow, and Virti illustrate the capacity of intelligent systems to maintain continuity, improve engagement, and benchmark outcomes globally and regionally.
In clinical training, AI-powered simulations enhance surgical and procedural practice through immersive, risk-free environments, significantly improving accuracy, retention, and confidence. Virtual patient systems further extend exposure to rare and critical cases, fostering diagnostic reasoning, interprofessional communication, and adaptive decision-making. Personalized learning, enabled by adaptive algorithms, addresses individual needs, ensuring mastery through predictive analytics and targeted remediation. Evidence indicates improved Objective Structured Clinical Examination (OSCE) performance and reduced diagnostic errors when students are guided by AI-supported platforms. Curriculum integration is another key theme: AI modules in radiology, pathology, and internal medicine allow benchmarking against global standards, while simultaneously supporting accreditation requirements. This is particularly salient in Georgia, where medical schools are piloting AI assessment tools to align competencies with international benchmarks. The role of AI in assessment is equally transformative, ranging from automated grading with Natural Language Processing (NLP) to AI-assisted OSCE evaluations and image-based diagnostic testing, ensuring objectivity, scalability, and timeliness. The pandemic context revealed AI’s potential in remote learning, where virtual laboratories, telemedicine training, and AI-based proctoring ensured pedagogical continuity. Research consistently demonstrates that AI-enabled distance learning sustains or enhances retention and student satisfaction compared to traditional modalities. Despite its promise, challenges persist. Ethical issues of data privacy, financial costs, and the necessity of faculty training must be addressed to ensure equitable access. Additionally, cultural adaptation and institutional readiness influence adoption rates, particularly in resource-constrained regions.
While the article effectively synthesizes current evidence and real-world applications, it may be strengthened by situating AI within broader educational theory (e.g., constructivist learning) and by comparing outcomes with traditional pedagogies at a meta-analytical level. Future research should focus on cost-effectiveness, faculty–student co-design of AI tools, and long-term impact on patient care outcomes, ensuring that AI serves not only as a technological innovation but as a pedagogically sound transformation of medical education.
Keywords: AI, Education, Benchmark, Georgia, Medicine
JEL: I21; I23; O33
DOI: 10.52244/c2025.17
References:
Berman, N., & Durning, S. (2021). Artificial intelligence in medical education: Trends and challenges. Medical Education, 55(3), 456–467. https://doi.org/10.1111/medu.14450
Brown, L., Patel, V., & Roberts, A. (2021). Automated essay scoring in medical education. Academic Medicine, 96(5), 682–690. https://doi.org/10.1097/ACM.0000000000004012
Cook, D. A., Hamstra, S. J., Brydges, R., Zendejas, B., Szostek, J. H., Wang, A. T., … Hatala, R. (2013). Comparative effectiveness of instructional design features in simulation-based education: Systematic review and meta-analysis. Medical Teacher, 35(1), e867–e898. https://doi.org/10.3109/0142159X.2012.714886
Custers, E., & Ten Cate, O. (2020). Virtual patients and AI-driven learning in medical curricula. Advances in Health Sciences Education, 25(4), 801–815. https://doi.org/10.1007/s10459-019-09929-6
Daniel, S. J. (2020). Education and the COVID-19 pandemic. Prospects, 49(1), 91–96. https://doi.org/10.1007/s11125-020-09464-3
Ellaway, R., & Masters, K. (2008). AMEE Guide 32: E-Learning in medical education Part 1: Learning, teaching, and assessment. Medical Teacher, 30(5), 455–473. https://doi.org/10.1080/01421590802108331
Johnson, R., White, P., & Patel, S. (2021). Adaptive AI question banks in healthcare learning. Medical Teacher, 43(11), 1234–1245. https://doi.org/10.1080/0142159X.2021.1876589
Lee, H., Kim, S., & Park, J. (2022). AI-assisted OSCE assessment: Outcomes and reliability. Medical Education Online, 27(1), 201–215. https://doi.org/10.1080/10872981.2021.201215
Smith, J., Walker, T., & Davis, R. (2022). AI-guided remediation in medical education. Journal of Medical Education, 60(2), 150–165. https://doi.org/10.1177/10525629211065321
Topol, E. (2019). Deep medicine: How artificial intelligence can make healthcare human again. Basic Books.
Wartman, S. A., & Combs, C. D. (2018). Medical education must move from the information age to the age of artificial intelligence. Academic Medicine, 93(8), 1107–1109. https://doi.org/10.1097/ACM.0000000000002044
Sugand, K., Abrahams, P., & Khurana, A. (2015). The role of simulation in developing surgical skills. Journal of Surgical Education, 72(2), 209–216. https://doi.org/10.1016/j.jsurg.2014.08.003
Lateef, F. (2010). Simulation-based learning: Just like the real thing. Journal of Emergencies, Trauma and Shock, 3(4), 348–352. https://doi.org/10.4103/0974-2700.70743
Kneebone, R. (2016). Simulation in surgical training: Educational issues and practical implications. Medical Education, 50(1), 104–116. https://doi.org/10.1111/medu.12844
Botezatu, M., Hult, H., & Fors, U. (2010). Virtual patients in medical education: An interactive learning model. Medical Teacher, 32(12), 950–957. https://doi.org/10.3109/0142159X.2010.506168
Dede, C. (2011). Emerging technologies, ubiquitous learning, and educational transformation. Educational Technology, 51(6), 3–14.