使用机器学习技术诊断根管治疗后牙齿的体内垂直根折
本回顾性研究纳入887例患者共941颗接受根管外科手术的牙齿,利用临床因素和锥形束CT骨缺损信息构建机器学习模型诊断垂直根折。941颗牙齿中112颗(11.9%)确诊垂直根折。XGBoost和LightGBM表现优异,曲线下面积分别为0.98[0.96,0.99],特异性0.978和0.983,敏感性0.883和0.803,精确率0.846和0.865。Shapley加法解释显示舌侧/颊侧骨缺损、根尖上方骨缺损高度与缺损总高度之比、骨缺损宽度和年龄是前5位贡献因素。
要点
- 机器学习模型利用年龄、性别、牙位、根管充填质量和骨丧失位置、高度、宽度、深度诊断垂直根折。
- XGBoost和LightGBM曲线下面积均为0.98[0.96,0.99],特异性分别为0.978和0.983,敏感性分别为0.883和0.803。
- 舌侧/颊侧骨缺损、根尖上方骨缺损高度与缺损总高度之比、骨缺损宽度和年龄是前5位贡献因素。
核心结论
- 使用年龄、性别、牙位、根管充填质量和骨丧失位置、高度、宽度、深度的机器学习模型对根管治疗后垂直根折的诊断具有临床决策价值。
研究设计与样本
- 回顾性研究纳入887例患者共941颗接受根管外科手术的牙齿。
- 测量并记录临床因素和锥形束CT检测的骨缺损。
- 采用线性机器学习模型(逻辑回归)和非线性模型(XGBoost、LightGBM、CatBoost)诊断垂直根折。
- 使用5折交叉验证评估模型性能,指标包括曲线下面积、敏感性、特异性、精确率和F分数。
- 通过Shapley加法解释可视化模型解释。
主要发现
- 941颗牙齿中112颗(11.9%)在根管外科手术中或拔牙后确诊垂直根折。
- XGBoost曲线下面积0.98[0.96,0.99],特异性0.978,敏感性0.883,精确率0.846。
- LightGBM曲线下面积0.98[0.96,0.99],特异性0.983,敏感性0.803,精确率0.865。
- Shapley加法解释值显示舌侧/颊侧骨缺损、根尖上方骨缺损高度与缺损总高度之比、骨缺损宽度和年龄是前5位贡献因素。
关键数值与推荐
- 垂直根折诊断金标准为根管外科手术中或拔牙后确认。
- XGBoost和LightGBM曲线下面积均为0.98[0.96,0.99]。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
INTRODUCTION: This study aimed to diagnose vertical root fracture (VRF) of endodontically treated teeth using clinical features and bone loss information from cone beam computed tomography with machine learning models. METHODS: A total of 887 patients with 941 teeth undergoing endodontic surgery were included in this retrospective study. The clinical factors and bone defects detected via cone beam computed tomography were measured and recorded. Linear machine learning models, logistic regression model and nonlinear models, including XGBoost, LightGBM, and CatBoost were used to diagnose VRF. Model performance was evaluated using 5-fold cross-validation and based on various performance parameters, including the area under the curve, sensitivity, specificity, precision, and F score. Model interpretations were visualized by Shapley Additive Explanations. RESULTS: Of the 941 teeth, 112 VRF teeth (11.9%) were identified during endodontic surgery or after tooth extraction. XGBoost and LightGBM showed excellent performance with area under the curves of 0.98 [0.96, 0.99], specificity of 0.978 and 0.983, sensitivity of 0.883 and 0.803, and precision of 0.846 and 0.865, respectively. Shapley Additive Explanations values showed that lingual/buccal bone defect, the ratio of bone defect height above the root apex to the defect total height, width of bone defect and age were the top 5 contributors. CONCLUSIONS: Machine learning models for the diagnosis of VRF using age, sex, tooth type, the quality of root canal filling and bone loss position, height, width, and depth are valuable for clinical decision making after root canal treatment.
引用
- Ran S, Wang Q, Wang J, et al. Diagnosis of In Vivo Vertical Root Fracture in Endodontically Treated Teeth Using Machine Learning Techniques. J Endod. 2025. PMID: 40374035. doi:10.1016/j.joen.2025.05.004
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。