Computer-Assisted Decision Support for Student Admissions Based on Their Predicted Academic Performance.

Journal: American journal of pharmaceutical education
PMID:

Abstract

To develop predictive computational models forecasting the academic performance of students in the didactic-rich portion of a doctor of pharmacy (PharmD) curriculum as admission-assisting tools. All PharmD candidates over three admission cycles were divided into two groups: those who completed the PharmD program with a GPA ≥ 3; and the remaining candidates. Random Forest machine learning technique was used to develop a binary classification model based on 11 pre-admission parameters. Robust and externally predictive models were developed that had particularly high overall accuracy of 77% for candidates with high or low academic performance. These multivariate models were highly accurate in predicting these groups to those obtained using undergraduate GPA and composite PCAT scores only. The models developed in this study can be used to improve the admission process as preliminary filters and thus quickly identify candidates who are likely to be successful in the PharmD curriculum.

Authors

  • Eugene Muratov
    Laboratory for Molecular Modeling, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, NC, USA.
  • Margaret Lewis
    UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.
  • Denis Fourches
    Bioinformatics Research Center, North Carolina State University, Raleigh, North Carolina.
  • Alexander Tropsha
    Laboratory for Molecular Modeling, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, NC, USA.
  • Wendy C Cox
    UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina.