Impact of preadmission variables on USMLE step 1 and step 2 performance
- 1k Downloads
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.
KeywordsMedical school admissions Neural network USMLE
The authors would like to thank Adam Jacob for his assistance in preparation of the manuscript.
- Adolmaleki, P., Buadu, L. D., Murayama, S., Murakami, J., Hashiguchi, N., Yabuuchi, H., & Masuda, K. (1997). Neural network analysis of breast cancer from MRI findings. Radiation Medicine, 15, 283–293.Google Scholar
- Blue, A. V., Gilbert, G. E., Elam, C. L., & Basco, W. T. (2000). Does institutional selectivity aid in the prediction of medical school performance? Academic Medicine, 75, 31–33.Google Scholar
- Case, S. M., Becker, D. F., & Swanson, D. B. (1993). Performances of men and women on NBME Part I and Part II: The more things change... Academic Medicine, 68, 25–27.Google Scholar
- Johnson, D. G., Lloyd, S. M., Jones, R. F., & Anderson, J. (1986). Predicting academic performance at a predominantly black medical school. Journal of Medical Education, 61, 629–639.Google Scholar
- Jones, R. F., & Thomae-Forgues, M. (1984). Validity of the MCAT in predicting performance in the first two years of medical school. Journal of Medical Education, 59, 455–464.Google Scholar
- Mosier, P. D., & Jurs, P. C. (2002). QSAR/QSPR studies using probabilistic neural networks and generalized regression neural networks. Journal of Chemical Information and Computer Science, 42, 1460–1470.Google Scholar
- Oram F. A. (Ed.) (2005). Peterson’s four-year colleges 2006. Lawrenceville, NJ: Thomson/Peterson’s.Google Scholar
- Roth, K. S., Riley, W. T., Brandt, R. B., & Seibel, H. R. (1996). Prediction of students’ USMLE step 2 performances based on premedical credentials related to verbal skills. Academic Medicine, 71, 176–180.Google Scholar
- Xu, G., Veloski, J. J., Hojat, M., Gonnella, J. S., & Bacharach, B. (1993). Longitudinal comparison ofthe academic performances of Asian–American and white medical students. Academic Medicine, 68, 82–86.Google Scholar
- Zeleznik C., Hojat, M., & Veloski, J. (1983). Baccalaureate preparation for medical school: Does type of degree make a difference? Journal of Medical Education, 58, 26–33.Google Scholar