AI Integration in MCQ Development: Assessing Quality in Medical Education: A Systematic Review

Abstract

This systematic review focuses on examining how artificial intelligence is included in multiple-choice questions
and how this affects the efficacy and quality of assessments used in education. Several papers investigating the
application of artificial intelligence in multiple-choice question creation have been found through a thorough
literature analysis. The present study employed a systematic literature review to comprehensively analyze the
existing literature and underscore the effects of incorporating artificial intelligence into creating multiplechoice
questions on the standard and efficacy of assessments used in education. Between January 2019 and
January 2024, we examined papers from credible publications, concentrating on sixteen chosen articles for indepth examination. The results show how artificial intelligence can revolutionize traditional evaluation
methods in education by improving the accuracy, efficiency, and diversity of multiple-choice questions. While
artificial intelligence models like ChatGPT, Bard, and Bing have shown encouraging results in creating multiplechoice questions, issues with validity, complexity, and reasoning ability still need to be addressed.
Notwithstanding its drawbacks, artificial intelligence-driven multiple-choice question holds great potential for
enhancing evaluation processes and enhancing educational opportunities in a variety of subject areas. This
Systematic review highlights the necessity of further research and advancement to fully utilize artificial
intelligence in creating multiple-choice questions and its incorporation into frameworks for educational
assessments.