文献速递牙周病

人工智能检测牙周骨丧失及牙周病分类效能系统综述

Efficacy of artificial intelligence in the detection of periodontal bone loss and classification of periodontal diseases: A systematic review.
PubMed 文献 · J Am Dent Assoc · 2023-07-14

本系统综述检索 PubMed、Scopus 与 Web of Science 截至 2022 年 8 月的文献,评估人工智能模型检测影像学牙周骨丧失(PBL)及分类牙周病变的效能。13 篇文献中 6 项研究符合纳入标准,涵盖全景与口内放射影像及多种算法,结局指标包括敏感度、特异度、准确率与像素准确率。部分研究报告 AI 与临床医生表现无实质差异,另一些显示 AI 更优;证据确定性低,作者建议临床谨慎使用。

要点

  • AI 在牙周骨丧失检测上具潜力,但研究间算法与影像模态不一致。
  • 部分研究显示 AI 不劣于或优于临床医生,结论尚不统一。
  • 证据等级低,临床应用前需标准化算法并验证临床效用。

核心结论

  • 证据提示人工智能有潜力辅助牙周骨丧失检测与牙周病分类。
  • AI 与临床医生表现的关系尚不一致,部分研究无实质差异、部分显示 AI 更优。
  • 因证据等级低且算法表现不一致,诊断牙周骨丧失时应谨慎考虑使用 AI 模型。

研究设计与样本

  • 系统综述,电子检索 PubMed、Scopus 与 Web of Science 截至 2022 年 8 月的文献。
  • 电子检索识别 13 篇文章,其中 6 项研究符合纳入标准。
  • 纳入研究采用多种 AI 算法与不同影像模态,包括全景与口内放射影像。
  • 采用诊断准确性研究质量评价工具(QUADAS)评估文献,并用 GRADE 评价证据确定性。
  • 综述已在 PROSPERO 注册(CRD42022364600)。

主要发现

  • 测量的结局包括敏感度、特异度、准确率与像素准确率。
  • 部分研究发现 AI 与牙科临床医生表现之间无实质差异。
  • 其他研究显示 AI 在检测牙周骨丧失方面具有优越性。

临床怎么用

  • AI 在牙周病检测与分类中可能带来一定益处,但现有证据等级低。
  • 鉴于算法表现不一致,临床用于诊断牙周骨丧失前应保持谨慎。

局限性

  • 证据水平低。
  • AI 算法表现不一致,需进一步研究以标准化算法并验证其临床实用性。

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

BACKGROUND: Artificial intelligence (AI) can aid in the diagnosis and treatment planning of periodontal disease by means of reducing subjectivity. This systematic review aimed to evaluate the efficacy of AI models in detecting radiographic periodontal bone loss (PBL) and accuracy in classifying lesions. TYPES OF STUDIES REVIEWED: The authors conducted an electronic search of PubMed, Scopus, and Web of Science for articles published through August 2022. Articles evaluating the efficacy of AI in determining PBL were included. The authors assessed the articles using the Quality Assessment for Studies of Diagnostic Accuracy tool. They used the Grading of Recommendations Assessment, Development and Evaluation criteria to evaluate the certainty of evidence. RESULTS: Of the 13 articles identified through electronic search, 6 studies met the inclusion criteria, using a variety of AI algorithms and different modalities, including panoramic and intraoral radiographs. Sensitivity, specificity, accuracy, and pixel accuracy were the outcomes measured. Although some studies found no substantial difference between AI and dental clinicians' performance, others showed AI's superiority in detecting PBL. Evidence suggests that AI has the potential to aid in the detection of PBL and classification of periodontal diseases. However, further research is needed to standardize AI algorithms and validate their clinical usefulness. PRACTICAL IMPLICATIONS: Although the use of AI may offer some benefits in the detection and classification of periodontal diseases, the low level of evidence and the inconsistent performance of AI algorithms suggest that caution should be exercised when considering the use of AI models in diagnosing PBL. This review was registered at PROSPERO (CRD42022364600).

来源:J Am Dent Assoc,查看原文。版权归原作者所有。

引用

  1. Patil S, Joda T, Soffe B, et al. Efficacy of artificial intelligence in the detection of periodontal bone loss and classification of periodontal diseases: A systematic review. J Am Dent Assoc. 2023. PMID: 37452813. doi:10.1016/j.adaj.2023.05.010

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。