Prediction of USMLE Step 1 Performance Based on Matriculation Characteristics Using Machine Learning Methods

• In Event: Admissions and Enrollment Management in Health Professions Education

Abstract

One of the many goals of a medical school admissions process is to matriculate students
who will successfully complete a medical school curriculum. The purpose of this study is to examine the predictive ability of preadmission variables on United States Medical Licensing Examinations (USMLE) step 1 performance using different machine learning regression methods and identify the best predictive model for USMLE Step 1 results.

Authors

• Ling Wang, Michigan State University

• Heather Laird-Fick, Michigan State University

• Carol Parker, Michigan State University