Department of Prosthodontics & Oral Rehabilitation, Tokushima University Graduate School of Biomedical Sciences, Japan.
J Prosthodont Res. 2022 Jan 11;66(1):19-28. doi: 10.2186/jpr.JPR_D_20_00139. Epub 2021 Jan 14.
The purpose of this study was to comprehensively review the literature regarding the application of artificial intelligence (AI) in the dental field, focusing on the evaluation criteria and architecture types.
Electronic databases (PubMed, Cochrane Library, Scopus) were searched. Full-text articles describing the clinical application of AI for the detection, diagnosis, and treatment of lesions and the AI method/architecture were included.
The primary search presented 422 studies from 1996 to 2019, and 58 studies were finally selected. Regarding the year of publication, the oldest study, which was reported in 1996, focused on "oral and maxillofacial surgery." Machine-learning architectures were employed in the selected studies, while approximately half of them (29/58) employed neural networks. Regarding the evaluation criteria, eight studies compared the results obtained by AI with the diagnoses formulated by dentists, while several studies compared two or more architectures in terms of performance. The following parameters were employed for evaluating the AI performance: accuracy, sensitivity, specificity, mean absolute error, root mean squared error, and area under the receiver operating characteristic curve.
Application of AI in the dental field has progressed; however, the criteria for evaluating the efficacy of AI have not been clarified. It is necessary to obtain better quality data for machine learning to achieve the effective diagnosis of lesions and suitable treatment planning.
本研究旨在全面回顾人工智能（AI）在口腔医学领域的应用文献，重点关注评估标准和架构类型。
电子数据库（PubMed、Cochrane Library、Scopus）进行检索。纳入描述 AI 用于检测、诊断和治疗病变的临床应用以及 AI 方法/架构的全文文章。
初步检索出 1996 年至 2019 年的 422 篇研究，最终选择了 58 篇研究。就发表年份而言，最早的研究报告于 1996 年，涉及“口腔颌面外科”。所选研究中采用了机器学习架构，其中约一半（29/58）采用了神经网络。就评估标准而言，有 8 项研究将 AI 得出的结果与牙医制定的诊断进行了比较，而一些研究则比较了两种或更多架构的性能。用于评估 AI 性能的参数包括：准确性、灵敏度、特异性、平均绝对误差、均方根误差和接收器工作特征曲线下的面积。
AI 在口腔医学领域的应用已经取得进展；然而，AI 疗效的评估标准尚未明确。需要获得更好质量的数据用于机器学习，以实现对病变的有效诊断和合适的治疗计划。
