Can We Predict Your Performance? Assessing the Relationship of Admissions Data to Academic Performance in Gross Anatomy of First-Year Medical Students

Abstract

Introduction and Objective: Educational data mining and predictive analytics in medical education have been justified to assist admissions committees and to help identify at-risk students for purposeful interventions. This study's purpose is to see if medical school entry metrics could predict first semester anatomy performance. Methods: Block entry multiple regression analysis was used with pre-admissions data from one cohort of 133 students on their anatomy lab practical scores. Results: The results showed that Cumulative Science GPA and MCAT scores are each positive, statistically significant predictors of anatomy performance, while first-generation status are significant negative predictors of academic performance on the lab practicals. Significance and Implications: The long-term goal is to utilize the formulated regression model to encourage practitioners within medical education to consider programs and activities that assist in student development of at-risk students.