文献速递牙体牙髓病

患者、牙位与治疗层面因素与根管治疗失败的关系:一项回顾性纵向与机器学习研究

Association between patient-, tooth- and treatment-level factors and root canal treatment failure: A retrospective longitudinal and machine learning study.
PubMed 文献 · J Dent · 2021-12-20

研究纳入2016至2020年在一所大型大学医院接受根管治疗且随访≥6个月的591颗恒牙(458例患者),总体成功率为79.5%。逻辑回归显示牙位层面因素与失败强相关,患者层面仅吸烟与失败风险显著相关;各机器学习模型的预测能力均有限。

要点

  • 牙槽骨丧失66-100%(OR 6.48)与根尖周指数评分≥4(OR 4.59)与根管治疗失败强相关。
  • 再治疗(OR 1.77)与吸烟(OR 2.05)亦与失败风险显著相关。
  • 各模型预测失败的ROC AUC有限(逻辑回归0.63,梯度提升机0.59,随机森林0.59,极端梯度提升0.60)。

核心结论

  • 根管治疗失败主要与牙位层面因素相关。
  • 即使使用更复杂的机器学习,预测失败也仅有限可能。

研究设计与样本

  • 回顾性纵向研究,纳入2016至2020年在一所大型大学医院接受根管治疗、随访≥6个月的591颗恒牙(458例患者,女/男47.2%/52.8%)。
  • 采用逻辑回归分析全数据集中的关联,并用逻辑回归、随机森林、梯度提升机和极端梯度提升进行预测建模,在独立测试集上以ROC AUC评估。

主要发现

  • 总体成功率为79.5%。
  • 逻辑回归中牙位层面因素与失败强相关:牙槽骨丧失66-100%(OR 6.48,95%CI [2.86, 14.89],p<0.001);根尖周指数评分≥4(OR 4.59,95%CI [2.44, 8.79],p<0.001);牙槽骨丧失33-66%(OR 2.59,95%CI [1.49, 4.49],p<0.001);根尖周指数评分=3(OR 2.45,95%CI [1.43, 4.34],p<0.01);治疗类型为再治疗(OR 1.77,95%CI [1.01, 2.86],p<0.01)。
  • 患者层面仅吸烟与失败风险显著相关(OR 2.05,95%CI [1.18, 3.53],p<0.05)。
  • 预测建模中所有模型预测能力有限:逻辑回归ROC AUC 0.63(95%CI [0.53, 0.73]);梯度提升机0.59(95%CI [0.50, 0.68]);随机森林0.59(95%CI [0.50, 0.68]);极端梯度提升0.60(95%CI [0.50, 0.70])。

临床怎么用

  • 识别根管治疗失败的具体风险因素并预测治疗结局,对治疗计划和知情共同决策具有相关性。
  • 本研究显示牙位层面因素与失败相关,但预测失败仅有限可能。

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

OBJECTIVES: We aimed to assess patient-, tooth- and treatment-level covariates on the failure of root canal treatments (RT) and to predict failure using machine learning (ML). METHODS: Teeth receiving RT at one large university hospital from 2016 to 2020 with a minimum follow-up of ≥6 months were included. Failure compromised absent radiographic healing and/or the presence of clinical symptoms. Covariates were selected on tooth-, treatment- and patient-level. We used logistic regression (logR) to determine associations in the full dataset, and logR as well as more advanced ML (random forests (RF), gradient boosting machine (GBM) and extremely gradient boosting (XGB)) for predictive modeling (area-under-the-receiver operating characteristic-curve (ROCAUC)) and testing on a separate test dataset. RESULTS: 458 patients (female/male 47.2/52.8%) with 591 permanent teeth were included (overall success rate 79.5%). In logR, tooth-level covariates showed strong associations with failure: Alveolar bone loss 66-100% (ABL, OR 6.48, 95% CI [2.86, 14.89], p<0.001); Periapical index (PAI) score≥4 (OR 4.59, [2.44, 8.79], p<0.001); ABL 33-66% (OR 2.59 [1.49, 4.49], p<0.001); PAI=3 (OR 2.45, [1.43, 4.34], p<0.01); Treatment type "retreatment" (OR 1.77, [1.01, 2.86], p<0.01). On patient level only smoking (OR 2.05, [1.18, 3.53], p<0.05) was significantly associated with risk of failure. For predictive modeling, the predictive power of all models was limited (ROCAUC: logR 0.63, [0.53, 0.73]; GBM 0.59, [0.50, 0.68]; RF 0.59, [0.50, 0.68]; XGB 0.60, [0.50, 0.70]). CONCLUSIONS: Failure of RT was associated mainly with tooth-level covariates. Predicting failure was only limitedly possible, also with more complex ML. CLINICAL SIGNIFICANCE: Identifying specific risk factors for failure of RT and predicting the outcome of RT is relevant for treatment planning and informed shared decision-making. The present study found tooth-level factors to be associated with failure. Notably, predicting failure was only limitedly possible.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Herbst CS, Schwendicke F, Krois J, et al. Association between patient-, tooth- and treatment-level factors and root canal treatment failure: A retrospective longitudinal and machine learning study. J Dent. 2021. PMID: 34942278. doi:10.1016/j.jdent.2021.103937

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。