Graduate student, Graduate Mathematics, School of Mathematical Sciences, Peking University, Beijing, PR China.
Resident, Graduate Prosthodontics, Center of Digital Dentistry, Peking University School and Hospital of Stomatology, Beijing, PR China; Resident, Department of Prosthodontics, Peking University School and Hospital of Stomatology, Beijing, PR China; Resident, National Engineering Laboratory for Digital and Material Technology of Stomatology, Peking University, Beijing, PR China; Resident, NHC Key Laboratory of Digital Technology of Stomatology, Peking University, Beijing, PR China; Resident, Beijing Key Laboratory of Digital Stomatology, Peking University, Beijing, PR China; Resident, National Clinical Research Center for Oral Diseases, Peking University, Beijing, PR China.
J Prosthet Dent. 2021 Jul;126(1):83-90. doi: 10.1016/j.prosdent.2020.04.010. Epub 2020 Jul 20.
Tooth extraction therapy serves as a key initial step in many prosthodontic treatment plans. Dentists must make an appropriate decision on the tooth extraction therapy considering multiple determinants and whether a clinical decision support (CDS) model might help.
The purpose of this retrospective records study was to construct a CDS model to predict tooth extraction therapy in clinical situations by using electronic dental records (EDRs).
The cohort involved 4135 deidentified EDRs of 3559 patients from the database of a prosthodontics department. Knowledge-based algorithms were first proposed to convert raw data from EDRs into structured data for feature extraction. Redundant features were filtered by a recursive feature-elimination method. The tooth extraction problem was then modeled alternatively as a binary or triple classification problem to be solved by 5 machine learning algorithms. Five machine learning algorithms within each model were compared, as well as the efficiency between 2 models. In addition, the proposed CDS was verified by 2 prosthodontists.
The triple classification model outperformed the binary model with the F1 score of the Extreme Gradient Boost (XGBoost) algorithm as 0.856 and 0.847, respectively. The XGBoost outperformed the other 4 algorithms. The accuracy, precision, and recall of the XGBoost algorithm were 0.962, 0.865, and 0.830 in the binary classification and 0.924, 0.879, and 0.836 in the triple classification, respectively. The performance of the 2 prosthodontists was inferior to the models.
The CDS model for tooth extraction therapy achieved high performance in terms of decision-making derived from EDRs.
拔牙治疗是许多修复治疗计划的关键初始步骤。牙医必须考虑多种决定因素，并考虑临床决策支持（CDS）模型是否可能有帮助，从而对拔牙治疗做出适当的决策。
本回顾性记录研究的目的是构建一个 CDS 模型，通过使用电子牙科记录（EDR）来预测临床情况下的拔牙治疗。
该队列包括来自一个修复科数据库的 3559 名患者的 4135 份匿名 EDR。首先提出基于知识的算法将 EDR 中的原始数据转换为用于特征提取的结构化数据。通过递归特征消除方法过滤冗余特征。然后，将拔牙问题建模为二进制或三分类问题，由 5 种机器学习算法解决。在每个模型中比较了 5 种机器学习算法，以及两种模型之间的效率。此外，由两位修复科医生对提出的 CDS 进行验证。
三分类模型的 F1 评分优于二进制模型，极端梯度提升（XGBoost）算法的 F1 评分分别为 0.856 和 0.847。XGBoost 优于其他 4 种算法。XGBoost 算法在二进制分类中的准确率、精确率和召回率分别为 0.962、0.865 和 0.830，在三分类中的准确率、精确率和召回率分别为 0.924、0.879 和 0.836。两位修复科医生的表现不如模型。
基于 EDR 的决策的拔牙治疗 CDS 模型具有较高的性能。
