Evaluation of nursing MCQs by ChatGPT and human educators highlights differences in quality and inclusivity.
This study aimed to compare the quality of 100 multiple-choice questions (MCQs), 50 generated by ChatGPT and 50 by experienced human educators, for nursing graduate exams. A panel of 25 international nursing educators evaluated the questions based on domains such as cognitive level, scenario relevance, distractor plausibility, bias, inclusivity, and alignment with Bloom's taxonomy using a 5-point Likert scale (0 = not at all reflective; 5 = fully reflective). The MCQs generated by ChatGPT were evaluated as higher in relevance and cognitive level and lower in bias and inclusivity than those generated by humans.
No takes yet. Share an insight, caveat, or question.
Alnomasy et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: