Human versus Artificial Intelligence: ChatGPT-4 Outperforming Bing, Bard, ChatGPT-3.5, and Humans in Clinical Chemistry Multiple-Choice Questions

Abstract

AbstractThe advances in large language models (LLMs) are evolving rapidly. Artificial intelligence (AI) chatbots based on LLMs excel in language understanding and generation, with potential utility to transform healthcare education and practice. However, it is important to assess the performance of such AI models in various topics to highlight its strengths and possible limitations. Therefore, this study aimed to evaluate the performance of ChatGPT (GPT-3.5 and GPT-4), Bing, and Bard compared to human students at a postgraduate master’s (MSc) level in Medical Laboratory Sciences. The study design was based on the METRICS checklist for the design and reporting of AI-based studies in healthcare. The study utilized a dataset of 60 Clinical Chemistry multiple-choice questions (MCQs) initially conceived for assessment of 20 MSc students. The revised Bloom’s taxonomy was used as the framework for classifying the MCQs into four cognitive categories: Remember, Understand, Analyze, and Apply. A modified version of the CLEAR tool was used for assessment of the quality of AI-generated content, with Cohen’s κ for inter-rater agreement. Compared to the mean students’ score which was 40/60 (66.8%), GPT-4 scored 54/60 (90.0%), followed by Bing (46/60, 76.7%), GPT-3.5 (44/60, 73.3%), and Bard (40/60, 66.7%). Statistically significant better performance was noted in lower cognitive domains (Remember and Understand) in GPT-3.5, GPT-4, and Bard. The CLEAR scores indicated that ChatGPT-4 performance was “Excellent” compared to “Above average” performance of ChatGPT-3.5, Bing, and Bard. The findings indicated that ChatGPT-4 excelled in the Clinical Chemistry exam, while ChatGPT-3.5, Bing, and Bard were above-average. Given that the MCQs were directed to postgraduate students with a high degree of specialization, the performance of these AI chatbots was remarkable. Due to the risks of academic dishonesty and possible dependence on these AI models, the appropriateness of MCQs as an assessment tool in higher education should be re-evaluated.