Comparing ChatGPT and Dental Students' Performance in an Introduction to Dental Anatomy Examination: A Cross-Sectional Study

Objectives This article compares the knowledge and interpretation ability of Chat Generative Pre-Trained Transformer (ChatGPT), with undergraduate dental students by administering a dental anatomy multiple-choice question-based examination. Materials and Methods This analytical cross-sectional study determined ChatGPT's justification for each response to evaluate its suitability as an e-learning tool. The frequency and percentage of students and ChatGPT were calculated to obtain the correct answers for a multiple-choice examination. Statistical Analysis The data analysis was performed through Statistical Package for Social Sciences (SPSS) by IBM (Version 20) and Microsoft Excel by Microsoft Corporation. The frequency and percentage of students and the ChatGPT were calculated for the correct answers. The p-value of the Shapiro-Wilk test was 0.001, therefore, the Kolmogorov test was applied to check the hypothesis for the distribution of the average ChatGPT explanation score given by the experts. Results The results revealed that students performed better in the introductory dental anatomy examination. The average score of students was 74.28%, while that of ChatGPT was 60%. A good agreement was observed between the experts regarding the grading of the explanation. Conclusion ChatGPT possesses a foundational understanding of basic dental anatomy, sufficient to achieve a passing grade on an undergraduate examination, its performance exhibits limitations in accuracy and reliability, therefore, it cannot be recommended as a sole learning resource.