Implementation of an artificial intelligence-powered training platform in oral medicine and pathology education
A comparative study
Bibliographic Data
| ID | 22425124 |
|---|---|
| Authors | Bernadette Quah, Nicole Wan Chyan Chia (Ministry of Health), Mai Khanh Ha Huynh (Otherlab), Intekhab Islam (0000-0002-7754-0609, National University of Singapore) |
| Year | 2026 |
| Volume | 26 |
| Issue | 1 |
| Publication date | 2026-02-14 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | BMC Medical Education (JOURNAL) |
| Journal identifiers | ISSN: 1472-6920 • E-ISSN: 1472-6920 |
| Publisher | Springer Science and Business Media LLC (PUBLISHER) |
| DOI | 10.1186/s12909-026-08815-6 |
| PMID | 41691269 |
| OpenAlex | W7128918163 |
| Language | EN |
| References cited | 20 |
BACKGROUND: This study aimed to evaluate the levels of student acceptance and effectiveness of an AI-powered chatbot platform as a teaching tool in the undergraduate oral medicine and pathology curriculum compared to traditional teaching methods. METHODS: Oral medicine and pathology case scenarios were developed with prompt engineering techniques on the GPT-4-powered CognitusAI web-based platform (Med2Lab), which utilised both a virtual patient and a virtual preceptor in conducting each case. The first phase of the study involved pilot testing to assess 50 students’ levels of acceptance of the platform and gather suggestions for improvement. The second phase was a comparative study, with 40 students in the intervention group undergoing case-based learning on the CognitusAI platform, and 40 in the control group undergoing a traditional tutorial of the same scenarios. The students took pre- and post-intervention assessments to evaluate knowledge levels. RESULTS: 92% of students felt confident to apply the knowledge gained on the platform, and 86% stated that it encouraged them to understand. Over 80% of students were more aware of their progress and areas for improvement after the module, and over 90% were interested in similar learning opportunities in the future. Students felt that the platform’s advantages included its strong clinical relevance, facilitation of active recall, personalised and non-judgemental feedback, and good engagement and interactiveness. In the comparative study, students in both the intervention and control groups showed significant score improvements after the teaching session (p < 0.001 for both). Although the difference in score improvements between the intervention and control group was not statistically significant (p = 0.062), the intervention group had significantly higher post-intervention test scores (p = 0.041) and a higher proportion of students with improved scores (p < 0.001). CONCLUSION: AI-powered chatbot platforms are well-received teaching tools and are equally effective and potentially superior to traditional teaching methods in enhancing students’ knowledge and understanding in oral medicine and pathology.
Curriculum · Oral medicine · Preceptor · Teaching method · Virtual reality · AI in Service Interactions · Artificial Intelligence in Healthcare and Education · Dental Research and COVID-19
| Highly cited | No |
|---|