Comparing Human- and ChatGPT-Generated Multiple-Choice Questions in Athletic Training Education

Context Creating well-written multiple-choice questions (MCQs) requires time and attention to detail. Artificial intelligence tools such as ChatGPT have the potential to assist faculty members in creating exam or practice questions. Objective To compare human-generated athletic training–related MCQs with those generated by ChatGPT for quality, clarity, relevance, and difficulty of the questions. Design Cross-sectional study. Patients or Other Participants Ninety-three athletic training faculty teaching in Commission on Accreditation of Athletic Training Education–accredited entry-level athletic training programs completed the survey. Eleven second-year graduate-level athletic training students completed the 20-question quiz. Main Outcome Measure(s) Faculty participants completed a 2-part survey in which they evaluated 10 pairs of MCQs for grammar, clarity, difficulty, terminology, and suitability using a 5-point Likert scale, and indicated which question they preferred. Each pair included a human-generated question and a ChatGPT-generated question on a similar topic. A student quiz was developed to evaluate question quality/difficulty. Second-year master’s students nearing graduation were asked to complete the 20-question quiz using the same questions found in the faculty survey. Results ChatGPT-generated Board of Certification–style questions used in this study have similar values for grammar, stem quality, answer quality, question difficulty, proper use of medical terminology, and suitability for content to human-generated questions for all 5 athletic training domains. Most ChatGPT-generated questions were easy to understand, used appropriate terminology, and had answer options that were similar in style and length. Conclusions ChatGPT is another tool that athletic training faculty may consider using to improve the quality and efficacy of exam question preparation. The data from this study suggest that faculty can effectively use ChatGPT for exam question preparation; however, faculty should understand that ChatGPT, like all tools, has its limitations.

Authors

Institutions

Publication Details

Journal
Journal of Athletic Training Education and Practice
Published
2025-07-01
DOI
https://doi.org/10.4085/1947-380x-24-066
Citations
1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.65
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Comparing Human- and ChatGPT-Generated Multiple-Choice Questions in Athletic Training Education

Christina Davlin-Pater, Lisa S. Jutte
1 citations
Journal of Athletic Training Education and Practice
Artificial Intelligence in Healthcare and Education
0.65
article

Comparing Human- and ChatGPT-Generated Multiple-Choice Questions in Athletic Training Education

Christina Davlin-Pater, Lisa S. Jutte
article en
1 citations

Abstract

Context Creating well-written multiple-choice questions (MCQs) requires time and attention to detail. Artificial intelligence tools such as ChatGPT have the potential to assist faculty members in creating exam or practice questions. Objective To compare human-generated athletic training–related MCQs with those generated by ChatGPT for quality, clarity, relevance, and difficulty of the questions. Design Cross-sectional study. Patients or Other Participants Ninety-three athletic training faculty teaching in Commission on Accreditation of Athletic Training Education–accredited entry-level athletic training programs completed the survey. Eleven second-year graduate-level athletic training students completed the 20-question quiz. Main Outcome Measure(s) Faculty participants completed a 2-part survey in which they evaluated 10 pairs of MCQs for grammar, clarity, difficulty, terminology, and suitability using a 5-point Likert scale, and indicated which question they preferred. Each pair included a human-generated question and a ChatGPT-generated question on a similar topic. A student quiz was developed to evaluate question quality/difficulty. Second-year master’s students nearing graduation were asked to complete the 20-question quiz using the same questions found in the faculty survey. Results ChatGPT-generated Board of Certification–style questions used in this study have similar values for grammar, stem quality, answer quality, question difficulty, proper use of medical terminology, and suitability for content to human-generated questions for all 5 athletic training domains. Most ChatGPT-generated questions were easy to understand, used appropriate terminology, and had answer options that were similar in style and length. Conclusions ChatGPT is another tool that athletic training faculty may consider using to improve the quality and efficacy of exam question preparation. The data from this study suggest that faculty can effectively use ChatGPT for exam question preparation; however, faculty should understand that ChatGPT, like all tools, has its limitations.

Journal of Athletic Training Education and PracticeVol. 21(2)
Xavier University (US)
Openalex Percentile: Top 24%
Artificial Intelligence in Healthcare and Education
0.65
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.