Baxmann Martin, Kárpáti Krisztina, Baráth Zoltán
Department of Orthodontics, Faculty of Education and Research, DTMD University, Wiltz, 9516, Luxembourg.
Department of Orthodontics and Pediatric Dentistry, Faculty of Dentistry, University of Szeged, Szeged, 6720, Hungary.
BMC Oral Health. 2025 Jun 3;25(1):905. doi: 10.1186/s12903-025-06070-7.
Generative AI technologies offer significant opportunities to enhance orthodontic education by improving knowledge retention, clinical decision-making, and skills training. This systematic review aimed to evaluate the impact of generative AI tools in orthodontic education, focusing on knowledge retention, decision-making, and practical skills.
A comprehensive literature search was conducted across PubMed, Cochrane Library, ERIC, CINAHL, and IEEE Xplore from January 2010 to December 2023. Studies evaluating the integration of generative AI in dental and orthodontic education were included. Seventeen studies met the inclusion criteria. Risk of bias was assessed using the Cochrane Risk of Bias Tool and the Newcastle-Ottawa Scale, with the GRADE approach used to evaluate evidence quality.
Generative AI improved knowledge retention and clinical decision-making through adaptive learning pathways and real-time feedback. Barriers included limited faculty training, technical infrastructure deficits, and educator resistance.
Generative AI holds transformative potential for orthodontic education but requires addressing practical and ethical challenges. Future research should focus on longitudinal studies to validate long-term impact and explore integration strategies.
生成式人工智能技术通过提高知识保留、临床决策和技能培训,为正畸教育提供了重大机遇。本系统评价旨在评估生成式人工智能工具在正畸教育中的影响,重点关注知识保留、决策和实践技能。
于2010年1月至2023年12月在PubMed、Cochrane图书馆、教育资源信息中心(ERIC)、护理学与健康领域数据库(CINAHL)和电气与电子工程师协会数据库(IEEE Xplore)中进行了全面的文献检索。纳入了评估生成式人工智能在牙科和正畸教育中整合情况的研究。17项研究符合纳入标准。使用Cochrane偏倚风险工具和纽卡斯尔-渥太华量表评估偏倚风险,并采用GRADE方法评估证据质量。
生成式人工智能通过适应性学习路径和实时反馈提高了知识保留和临床决策能力。障碍包括教师培训有限、技术基础设施不足以及教育工作者的抵触情绪。
生成式人工智能对正畸教育具有变革潜力,但需要应对实际和伦理挑战。未来的研究应侧重于纵向研究,以验证长期影响并探索整合策略。