Ploywarong Rueangket ^1* Juraluck Taebunphakul ^2* Boonsub Sakboonyarat ^2* Akara Prayote ^3*

• ¹ Department of obstetrics and gynecology, Phramongkutklao Hospital, Bangkok, Thailand
• ² Phramongkutklao Hospital, Bangkok, Thailand
• ³ Department of Computer and Information Science, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand

Objectives: Medical student education plays a vital role in enabling graduated doctors to contribute significantly to patient healthcare and the national public health system. This study aimed to identify influential factors on student academic success (Honors level or High-grade group) using data mining techniques for multidimensional educational data.A retrospective cohort study was conducted using a standardized questionnaire administered to 145 medical students. Thirteen factors attributed to four domains; academic activity, demographics, environment, and psychology or learning style were examined. Analysis of prevalence ratio (PR) and adjusted prevalence ratio (APR) was performed using multivariate logistic regression. Unsupervised learning techniques, including cluster analysis and association rules, were used to identify hidden patterns.Visualization techniques, such as heatmaps and centroid plots, based on cluster analysis, were employed to illustrate data relationships and enhance the interpretation of key trends. Internal validation was evaluated.Results: Of the 13 factors analyzed, logistic regression identified pre-med GPAX ≥ 3.75 and an interest in internal medicine as statistically significant predictors of high academic performance, with adjusted prevalence ratios (APRs) of 1.73 (95% CI, 1.02-2.91, p = 0.040) and 1.52 (95% CI, 1.14-2.03, p = 0.005), respectively. Cluster analysis revealed typical characteristics of highgrade students, including a metropolis residence, a very high pre-med GPAX, and a preference for kinesthetic and reading learning styles. Association rules analysis further emphasized the importance of environmental factors, identifying transportation time to school and access to learning resources as influential in supporting academic success.Educational Data Mining (EDM) visually highlighted essential factors in medical student success. Logistic regression identified pre-med GPAX and interest in internal medicine as key predictors; cluster analysis uncovered learning style patterns associated with performance; and association rules emphasized environmental factors, such as proximity to school and access to resources. Together, these methods provide a comprehensive, visual framework to support a holistic, data-driven approach in educational planning, potentially offering new insights for addressing broader medical challenges and advancing clinical practice.