文献速递牙体牙髓病

当代牙髓显微手术预后预测的临床影像机器学习模型:一项回顾性研究

Clinical-imaging Model for Predicting Prognosis in Contemporary Endodontic Microsurgery: A Retrospective Machine Learning-based Study.
PubMed 文献 · J Endod · 2026-02-20

本研究回顾性分析213颗患牙(180例患者)的临床与断层影像数据,采用合成少数类过采样技术处理类别不平衡,训练并验证多种机器学习算法预测牙髓显微手术预后。随机森林分类器表现最佳(准确率91%、灵敏度91%、特异度85%、AUC 0.97),并识别出8个不良预后关键预测因素。

要点

  • 随机森林模型在内部验证中预测牙髓显微手术预后准确率达91%,AUC为0.97。
  • 不良预后关键预测因素包括未使用引导组织再生技术、根尖充填质量差、使用旋转式骨切开术等8项。
  • 模型基于小样本及合成过采样数据,结果可能偏乐观,需外部验证后再用于临床决策。

核心结论

  • 随机森林模型在内部验证中表现出较强的牙髓显微手术预后预测性能,但受限于小样本及合成过采样数据,结果可能偏乐观,需外部验证。

研究设计与样本

  • 回顾性分析纳入180例患者的213颗患牙,临床与断层影像数据经二分类化及合成少数类过采样技术处理。
  • 采用SelectKbest、卡方检验、互信息及集成分类器进行特征选择,训练逻辑回归、随机森林、支持向量机、K近邻、简单决策树和朴素贝叶斯等分类器。
  • 数据按80:20拆分训练与验证,通过准确率、灵敏度、特异度、精确率、F1分数和ROC曲线下面积评估性能,并应用SHAP技术解释模型与评估特征重要性。

主要发现

  • 随机森林分类器预测性能最高:准确率91%、灵敏度91%、特异度85%、ROC曲线下面积0.97。
  • 识别出8个不良预后关键预测因素:未使用引导组织再生技术、根尖充填质量差、使用旋转式骨切开术、病变大小≤6.29 mm、患者年龄>52.50岁、根尖切除质量差、根尖切除斜面过陡、冠部修复欠佳。

临床怎么用

  • SHAP衍生的预测因素具有临床合理性,但仅代表模型关联,不能作为因果推断依据。
  • 在获得外部验证前,该模型不宜直接用于临床预后判断或治疗决策。

局限性

  • 数据集样本量小且经合成少数类过采样技术扩充,可能导致结果偏乐观。
  • 仅采用单次训练-测试拆分,未进行交叉验证或外部验证。
  • SHAP衍生的预测因素仅反映模型关联,需外部验证后方可得出明确临床结论。

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: Predictive tools for endodontic microsurgery outcomes remain limited. This study evaluated the performance of various machine learning algorithms in forecasting endodontic microsurgery prognosis using patient-, tooth-, and procedure-related variables. METHODS: A retrospective analysis was conducted on 213 teeth from 180 patients. Clinical and tomographic data were dichotomized and processed using synthetic minority oversampling technique to address class imbalance. Feature selection used SelectKbest, chi-square, mutual information, and ensemble classifiers. Several classifiers including logistic regression, random forest, support vector machine, k-nearest neighbors, simple decision tree, and naïve Bayes were trained and validated on an 80:20 split, with performance assessed via accuracy, sensitivity, specificity, precision, F1-score, and area under the receiver operating characteristic curve. To interpret the model and assess feature importance, the SHapley Additive exPlanations technique was applied. RESULTS: The random forest classifier achieved the highest predictive performance (accuracy: 91%, sensitivity: 91%, specificity: 85%, area under the receiver operating characteristic curve: 0.97). Eight key predictors of poor prognosis were identified: lack of guided tissue regeneration techniques, poor root-end filling quality, use of rotary osteotomy, lesion size ≤6.29 mm, patient age >52.50 years, poor root-end resection quality, steep root-end resection bevel, and suboptimal coronal restoration. CONCLUSION: This study demonstrates that the random forest model showed strong internal performance, but results may be optimistic given the small, synthetic minority oversampling technique-augmented dataset and single train-test split. SHapley Additive exPlanations-derived predictors are clinically plausible yet represent model associations, underscoring the need for external validation before drawing firm clinical conclusions.

来源:J Endod,查看原文。版权归原作者所有。

引用

  1. Tobón-Arroyave SI, Restrepo-Restrepo FA, Marín-Cardona N, et al. Clinical-imaging Model for Predicting Prognosis in Contemporary Endodontic Microsurgery: A Retrospective Machine Learning-based Study. J Endod. 2026. PMID: 41724212. doi:10.1016/j.joen.2026.02.011

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。