Integrating ChatGPT into Medical Education: A Combined SEM-ML Approach

Salloum, Said; Shaalan, Khaled; Alfaisal, Raghad; Salloum, Ayham; Gaber, Tarek

Abstract

The educational realm has undergone profound transformations due to technological advancements, evolving from conventional classrooms to digital platforms, such as online learning modules and virtual simulations. Within this context, ChatGPT, an innovation in artificial intelligence, stands out for its capacity to enhance and personalize learning experiences in medical education. While the potential of tools like ChatGPT is acknowledged, there is a need to understand the determinants of their acceptance, especially in the backdrop of dynamic medical curricula. Drawing on The Technology Acceptance Model (TAM) and focusing on perceived value, we collected 563 questionnaires across multiple academic institutions. We then analyzed this data using partial least squares-structural equation modeling (PLS-SEM), and machine learning (ML) algorithms. Findings highlighted ChatGPT's pronounced influence on user acceptance, with perceived value emerging as a primary driver. Interestingly, task-technology congruence did not show significant predictive power. Notably, the J48 classifier showcased superior predictive capacity over other models for the dependent variable. This study offers invaluable insights for stakeholders in medical education, suggesting the importance of aligning AI tools like ChatGPT with user perceptions and needs to ensure successful adoption and integration into the learning landscape.

Citation

Salloum, S., Shaalan, K., Alfaisal, R., Salloum, A., & Gaber, T. (2024). Integrating ChatGPT into Medical Education: A Combined SEM-ML Approach. #Journal not on list, https://doi.org/10.1109/assic60049.2024.10507994

• Journal Article Type: Article
• Acceptance Date: Jan 7, 2024
• Publication Date: Apr 30, 2024
• Deposit Date: Aug 1, 2024
• Journal: 2024 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/assic60049.2024.10507994