Educational data mining in medical education: a scoping review

Background & Objective: The increasing complexity and volume of data in medical education highlight the importance of using advanced analytical techniques, such as data mining, to analyze educational data.This review aims to identify and assess the applications of educational data mining in medical education. Materials & Methods:This research is a scoping review conducted based on the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR).Data was collected on January 8, 2025, utilizing search strategies specifically tailored for the Scopus, Web of Science (WOS), and PubMed databases.The inclusion criteria consisted of research articles related to medical education and data mining.In contrast, the exclusion criteria included non-research articles, articles written in languages other than English, and articles that had been retracted.The screening of articles was performed in three stages: titles, abstracts, and full texts.Finally, the selected articles were reviewed and reported based on data mining tools, algorithms, software, and results. Results:The data mining applications identified were categorized into four main themes: predicting students' performance, identifying at-risk students, analyzing student interactions in online learning, and evaluating the quality of exams.Algorithms that are commonly used include Artificial Neural Networks (ANN), Naive Bayes, and K-means clustering. Conclusion:Data mining is a powerful tool for analyzing educational data, particularly for planners in medical sciences.It can help improve the quality of educational systems and enhance student academic success through its various techniques.The intentional use of data mining can also support strategic decision-making within educational systems, leading to improved teaching quality and a reduction in socio-economic disparities among students.