Advances in Health Sciences Education

, Volume 14, Issue 1, pp 69–78

Impact of preadmission variables on USMLE step 1 and step 2 performance

Authors

    • Department of MedicineThe University of Toledo College of Medicine
  • Sadik A. Khuder
    • Department of MedicineThe University of Toledo College of Medicine
  • Joseph I. Shapiro
    • Department of MedicineThe University of Toledo College of Medicine
  • Jeffrey P. Gold
    • College of Medicine, The University of Toledo
Original Article

DOI: 10.1007/s10459-007-9087-x

Cite this article as:
Kleshinski, J., Khuder, S.A., Shapiro, J.I. et al. Adv in Health Sci Educ (2009) 14: 69. doi:10.1007/s10459-007-9087-x

Abstract

Purpose To examine the predictive ability of preadmission variables on United States Medical Licensing Examinations (USMLE) step 1 and step 2 performance, incorporating the use of a neural network model. Method Preadmission data were collected on matriculants from 1998 to 2004. Linear regression analysis was first used to identify predictors of performance on step 1 and step 2. A generalized regression neural network (GRNN) as well as a feed forward neural network (FFNN) was then developed in an effort to more accurately predict step 1 and step 2 scores from these preadmission data. Results Statistically significant predictors for step 1 and step 2 included science grade point average (SGPA), the biologic science (BS) section of the Medical College Admissions Test (MCAT), college selectivity, race, and age of the applicant. Neural networks were found to predict a significant portion of the variance, and the FFNN demonstrated some superiority over that obtained with linear regression models as well as the GRNN. Conclusions The results have implications that could impact the selection of applicants to medical school and the neural networks that we developed could be used in a prospective manner.

Keywords

Medical school admissionsNeural networkUSMLE

Copyright information

© Springer Science+Business Media B.V. 2007