Polizzi Alessandro, Serra Sara, Leonardi Rosalia, Isola Gaetano
Department of General Surgery and Medical-Surgical Specialities, University of Catania, 95124 Catania, Italy.
Medicina (Kaunas). 2025 Jun 25;61(7):1141. doi: 10.3390/medicina61071141.
: To systematically map and evaluate the current literature on the application of artificial intelligence (AI) in teleorthodontics, focusing on clinical use, technological approaches, outcomes, and limitations. : A scoping review was conducted following a formal and recognized methodological framework. Three databases (PubMed, Scopus, Web of Science) were searched until 30 April 2025. Studies were included if they reported original data on AI applications in orthodontic remote monitoring or virtual care. Data extraction focused on study design, type of AI, clinical setting, reported outcomes, and main findings. : Nine studies met the inclusion criteria. Most research focused on the use of the Dental Monitoring™ (DM) system, which employs deep learning algorithms to analyze intraoral scans captured via smartphones. Reported benefits included reduced in-office visits (up to 33%), accurate 3D tracking of tooth movement, improved hygiene compliance, and high patient engagement. However, significant variability was observed in the repeatability and precision of AI decisions, especially in GO/NO-GO aligner progression instructions. One study explored an alternative system, StrojCHECK™, based on a decision tree algorithm, showing improved compliance with personalized feedback. : AI-powered teleorthodontic systems show potential to enhance treatment efficiency and patient engagement, particularly in aligner therapy. However, their current clinical application remains narrowly focused on commercial monitoring platforms, with limited validation and transparency. This review highlights the early stage of real-world AI integration in orthodontics, underlining the need for independent validation, broader applications beyond monitoring, and robust ethical frameworks. In this context, AI should be used as a complementary tool, never a substitute, for clinical judgment.
系统梳理和评估当前关于人工智能(AI)在远程正畸学中应用的文献,重点关注临床应用、技术方法、结果和局限性。
按照正式且公认的方法框架进行范围综述。检索了三个数据库(PubMed、Scopus、Web of Science)直至2025年4月30日。如果研究报告了关于AI在正畸远程监测或虚拟护理中应用的原始数据,则纳入研究。数据提取集中在研究设计、AI类型、临床环境、报告的结果和主要发现。
九项研究符合纳入标准。大多数研究集中在Dental Monitoring™(DM)系统的使用上,该系统采用深度学习算法来分析通过智能手机捕获的口腔内扫描图像。报告的益处包括减少面诊次数(高达33%)、对牙齿移动进行精确的三维跟踪、提高口腔卫生依从性以及患者参与度高。然而,在AI决策的可重复性和精确性方面观察到显著差异,尤其是在隐形矫治器进展的通过/不通过指示方面。一项研究探索了基于决策树算法的替代系统StrojCHECK™,显示出个性化反馈下依从性有所提高。
人工智能驱动的远程正畸系统显示出提高治疗效率和患者参与度的潜力,特别是在隐形矫治治疗中。然而,它们目前的临床应用仍然狭窄地集中在商业监测平台上,验证和透明度有限。本综述强调了正畸学中真实世界AI整合尚处于早期阶段,强调需要独立验证、监测之外的更广泛应用以及健全的伦理框架。在此背景下,AI应作为临床判断的辅助工具,而非替代品。