文献速递口腔正畸

AI增强正畸治疗计划:基于证据的临床应用范围综述及商用软件概览

AI-enhanced orthodontic treatment planning - a scoping review on evidence-based clinical application with commercial software overview.
PubMed 文献 · J Dent · 2025-09-18

本范围综述检索截至2025年2月的四个数据库,纳入17项关于AI正畸治疗计划工具的研究,发现AI方法报告准确率72%至95%,并识别出7款商用AI工具;学术验证工具多依赖临床医生文本输入,商用系统可处理原始临床数据但普遍缺乏发表验证,二者存在不匹配。

要点

  • AI正畸治疗计划工具报告准确率72%至95%,主要集中于拔牙决策与设计。
  • 学术验证工具多依赖临床医生文本输入,商用系统可处理口内扫描等原始数据。
  • 商用AI工具普遍缺乏发表验证,学术与商用系统间存在不匹配。

核心结论

  • 综述纳入的研究主要涉及关键治疗计划决策或广泛治疗建议。
  • 学术验证工具通常依赖临床医生提供的文本输入,而商用AI解决方案可处理口内扫描等原始临床数据。
  • 学术验证工具与商用系统之间存在不匹配,商用系统普遍缺乏发表验证,需验证以确保有效临床整合。

研究设计与样本

  • 范围综述,检索PubMed、Embase、Web of Science和Cochrane至2025年2月的英文文献。
  • 从307项研究中纳入17项符合标准的研究,包括8项评估研究、3项验证研究、2项准确性研究和3项比较研究。

主要发现

  • 纳入研究最集中于AI驱动的正畸拔牙决策与设计。
  • 其他研究探索深覆合计划及混合牙列扩弓的自动化。
  • 若干研究评估大语言模型(LLMs)回答正畸问题。
  • AI方法包括机器学习、深度学习和LLMs,报告准确率从72%到95%。
  • 识别出7款用于正畸治疗计划的商用AI工具。

关键数值与推荐

  • AI方法报告准确率范围为72%至95%。
  • 纳入17项研究,其中评估研究8项、验证研究3项、准确性研究2项、比较研究3项。
  • 识别出7款商用AI正畸治疗计划工具。

临床怎么用

  • AI正畸治疗计划工具可能提升临床效率并促进决策一致性。
  • 学术与商用解决方案均显示作为决策支持系统的显著潜力,强化而非替代正畸专业人员的专业知识。

局限性

  • 商用AI系统普遍缺乏发表验证,学术验证工具与商用系统之间存在不匹配。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: This scoping review aimed to identify evidence-based research papers on AI-enhanced treatment planning tools for orthodontics. The clinical relevance and applicability of academically validated AI tools were examined and complemented by an assessment of commercially available software. DATA SOURCES: PubMed, Embase, Web of Science, and Cochrane were searched up to February 2025 for English-language studies on AI-based orthodontic treatment planning tools. STUDY SELECTION: Included studies were validation, accuracy, evaluation research papers; were available in full text; published in English; and focused on digital orthodontic treatment planning. RESULTS: Of 307 studies identified, 17 met inclusion criteria. The most focused on AI-driven decision-making for orthodontic extractions and design. Others explored automation for deep-bite planning and expansion in mixed dentition. Several studies evaluated large language models (LLMs) for answering orthodontic questions. Included were eight evaluation studies, three validation studies, two accuracy studies, and three comparative studies. AI methods included machine learning, deep learning, and LLMs, with reported accuracies from 72% to 95%. Seven commercial AI tools for orthodontic treatment planning were identified. CONCLUSIONS: The reviewed studies primarily addressed key treatment planning decisions or broader treatment recommendations. Academically validated tools typically rely on clinician-provided text inputs, whereas commercial AI solutions can process raw clinical data, such as intraoral scans. There is a mismatch between academically validated tools and commercially available systems, which generally lack published validation. This gap highlights the need for validation of commercial tools to ensure effective clinical integration. CLINICAL SIGNIFICANCE: AI-based tools for orthodontic treatment planning might enhance clinical efficiency and promote consistency in decision-making. Both academic and commercial solutions demonstrate significant potential as decision-support systems, reinforcing - rather than replacing - the expertise of orthodontic professionals.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Preda F, Elshazly N, Jacobs R, et al. AI-enhanced orthodontic treatment planning - a scoping review on evidence-based clinical application with commercial software overview. J Dent. 2025. PMID: 40975160. doi:10.1016/j.jdent.2025.106112

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。