# Exploring the role of AI in dental education: a mixed-method experimental study from Pakistan

## TL;DR

This study explores how AI can support dental education in Pakistan, finding that AI and human facilitation produce similar learning outcomes but with different strengths.

## Contribution

The study introduces AI as a scalable facilitator in dental case-based learning and identifies a hybrid model as optimal.

## Key findings

- AI and human facilitation led to similar post-test score improvements in dental students.
- AI provided structured feedback and factual recall, while humans enhanced emotional engagement and clinical reasoning.
- Students preferred a blended approach combining AI and human facilitation.

## Abstract

Case-based learning (CBL) is a cornerstone of dental education, fostering critical thinking and clinical reasoning. In Pakistan, challenges like low facilitator-to-student ratios and faculty shortages hinder CBL effectiveness. Artificial intelligence (AI) offers potential solutions through scalable, structured facilitation, yet its role in dental CBL remains underexplored.

The objective of this study was to evaluate the effectiveness and acceptability of artificial intelligence (AI) as a facilitator in case-based learning (CBL) for dental education. It aimed to compare learning outcomes between AI- and human-facilitated sessions using a randomized crossover design, and to explore students’ perceptions and experiences of AI-mediated learning through focus group discussions.

A sequential mixed-methods design (QUAN → QUAL) was employed with 16 final-year BDS students in a randomized two-period crossover trial. Phase 1 compared AI-facilitated (via ChatGPT-3.5) and human-facilitated CBL using pre- and post-test MCQs, analyzed with Wilcoxon signed-rank and Mann-Whitney U tests. Phase 2 explored student experiences through focus group discussions (FGDs), analyzed thematically using Braun and Clarke’s framework. Ethical approvals were obtained (ERC #2023-6789-12345, IRB-789/LCMD/2023).

Both AI- and human-facilitated groups showed significant post-test score improvements (p < 0.012), with no significant inter-group differences (p ≥ 0.130). AI excelled in factual recall and structured feedback, while human facilitation enhanced emotional engagement and clinical reasoning. FGDs revealed themes of AI’s consistency but limited emotional depth, with students favoring a hybrid model.

AI-facilitated CBL yields comparable academic outcomes to human facilitation, offering scalability in resource-limited settings. However, human facilitators remain vital for emotional and adaptive learning. A blended approach, integrating AI’s structure with human mentorship, is recommended for optimal dental education.