Automated Item Generation: The Future of Medical Education Assessment?

*Kenneth D. Royal,1,2 Mari-Wells Hedgpeth,1 Tae Jeon,3 Cristin M. Colford4

1. Department of Clinical Sciences, College of Veterinary Medicine, North Carolina State University, Raleigh, North Carolina, USA
2. Department of Family Medicine, School of Medicine, University of North Carolina, Chapel Hill, North Carolina, USA
3. Educational Support Services, College of Veterinary Medicine, North Carolina State University, Raleigh, North Carolina, USA
4. Department of Medicine, University of North Carolina, Chapel Hill, North Carolina, USA
*Correspondence to: kdroyal2@ncsu.edu

Disclosure: The authors have declared no conflicts of interest.
Received: 19.07.17 Accepted: 13.12.17
Citation: EMJ Innov. 2018;2[1]:88-93.

Abstract

A major innovation in psychometric science, termed automated item generation (AIG), holds the potential to revolutionise assessment in medical education. In short, AIG involves leveraging the expertise of content specialists, item templates, and computer algorithms to create a variety of item permutations, often resulting in hundreds or thousands of new items based on a single item model. AIG may significantly improve item writing capabilities, reduce human error, streamline efficiencies, and reduce costs for individuals in the medical and health professions. Thus, the purpose of this work is to provide readers with a current overview of AIG and discuss its potential advantages, future possibilities, and current limitations.

This article is made available under the terms of theĀ Creative Commons Attribution-Non Commercial 4.0 License.

Download (PDF, 86KB)

Comments are closed.