ChatGPT for assessment writing

Bibliographic Data

ID21447985
AuthorsMatthew Zuckerman (0000-0001-9576-4203, University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA, corresponding author), Ryan Flood (University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA), Rachael J B Tan (0009-0001-4841-2042, University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA), Nicole C Kelp (0000-0001-8462-5689, University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA), David J Ecker (0000-0002-1530-0079, University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA), Jonathan Menke (University of Colorado Anschutz Medical Campus School of Medicine, Aurora, CO, USA), Tai Lockspeiser (0000-0002-1633-4860, Children's Hospital Colorado)
Year2023
Volume45
Issue11
Pages1224-1227
Publication date2023-11-02
Peer ReviewedYes
Open AccessNo
TypeARTICLE
VenueMedical Teacher (JOURNAL)
Journal identifiersISSN: 0142-159X • E-ISSN: 1466-187X
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/0142159x.2023.2249239
PMID37789636
OpenAlexW4387327237
LanguageEN
Citations received18
References cited3

What is the educational challenge?Medical schools invest significant resources into the creation of multiple-choice items for assessments. This process is costly and requires faculty training. Recently ChatGPT has been used in various areas to improve content creation efficiency, and it has otherwise been used to answer USMLE-style assessment items.What are the proposed solutions?We proposed the use of ChatGPT to create initial drafts of multiple-choice items.What are the potential benefits to a wider global audience?The use of ChatGPT to generate assessment items can decrease resources required, allowing for the creation of more items, and freeing-up faculty time to perform higher level assessment activities. ChatGPT is also able to consistently produce items using a standard format while adhering to item writing guidelines, which can be very challenging for faculty teams.What are the next steps?We plan to pilot ChatGPT drafted questions and compare item statistics for those written by ChatGPT with those written by our content experts. We also plan to further identify the types of questions that ChatGPT is most appropriate for, and incorporate media into assessment items (e.g. images, videos)

Class (philosophy) · Curriculum · Medical education · Multiple choice · Pedagogy · Plan (archaeology) · Political science · Process (computing) · Quality (philosophy) · Reading (process) · Work (physics) · Artificial Intelligence in Healthcare and Education · Clinical Reasoning and Diagnostic Skills · Computer Science · Innovations in Medical Education · Medicine · Psychology

Tools

Open DOI