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

James Kleshinski, Sadik A. Khuder, Joseph I. Shapiro, Jeffrey P. Gold

Research output: Contribution to journalArticle

37 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)69-78
Number of pages10
JournalAdvances in Health Sciences Education
Volume14
Issue number1
DOIs
StatePublished - Mar 1 2009

Fingerprint

Licensure
neural network
Linear Models
examination
College Admission Test
performance
Neural Networks (Computer)
Biological Science Disciplines
Medical Schools
applicant
regression
Regression Analysis
science
regression analysis
ability
school

Keywords

  • Medical school admissions
  • Neural network
  • USMLE

ASJC Scopus subject areas

  • Education

Cite this

Impact of preadmission variables on USMLE step 1 and step 2 performance. / Kleshinski, James; Khuder, Sadik A.; Shapiro, Joseph I.; Gold, Jeffrey P.

In: Advances in Health Sciences Education, Vol. 14, No. 1, 01.03.2009, p. 69-78.

Research output: Contribution to journalArticle

Kleshinski, James ; Khuder, Sadik A. ; Shapiro, Joseph I. ; Gold, Jeffrey P. / Impact of preadmission variables on USMLE step 1 and step 2 performance. In: Advances in Health Sciences Education. 2009 ; Vol. 14, No. 1. pp. 69-78.
@article{83678654874b4024968e72bd44eb4f6f,
title = "Impact of preadmission variables on USMLE step 1 and step 2 performance",
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 admissions, Neural network, USMLE",
author = "James Kleshinski and Khuder, {Sadik A.} and Shapiro, {Joseph I.} and Gold, {Jeffrey P.}",
year = "2009",
month = "3",
day = "1",
doi = "10.1007/s10459-007-9087-x",
language = "English (US)",
volume = "14",
pages = "69--78",
journal = "Advances in Health Sciences Education",
issn = "1382-4996",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Impact of preadmission variables on USMLE step 1 and step 2 performance

AU - Kleshinski, James

AU - Khuder, Sadik A.

AU - Shapiro, Joseph I.

AU - Gold, Jeffrey P.

PY - 2009/3/1

Y1 - 2009/3/1

N2 - 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.

AB - 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.

KW - Medical school admissions

KW - Neural network

KW - USMLE

UR - http://www.scopus.com/inward/record.url?scp=60449087126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60449087126&partnerID=8YFLogxK

U2 - 10.1007/s10459-007-9087-x

DO - 10.1007/s10459-007-9087-x

M3 - Article

C2 - 17987399

AN - SCOPUS:60449087126

VL - 14

SP - 69

EP - 78

JO - Advances in Health Sciences Education

JF - Advances in Health Sciences Education

SN - 1382-4996

IS - 1

ER -