机器学习模型预测初次非手术根管治疗后根尖周愈合
本研究回顾性纳入276例由牙髓专科医生完成的单牙初次非手术根管治疗,随访12-18个月判定根尖周愈合为有利或不利,并开发逻辑回归、随机森林和径向基支持向量机模型。结果显示随机森林在默认阈值下区分度最高(PR-AUC_UNF=0.359;ROC-AUC=0.724),但敏感性仅27.3%;经不平衡处理和阈值调整后敏感性可提高至90.9%,但特异性降至48.9%。结论认为仅用准确率可能掩盖临床相关失败,阈值调整可增加失败检出但代价是假阳性警报。
要点
- 随机森林在默认阈值下区分度最高(PR-AUC_UNF=0.359;ROC-AUC=0.724),但敏感性仅27.3%。
- 经不平衡处理和阈值调整后,失败检出敏感性可提高至90.9%,但特异性降至48.9%。
- 牙位和基线病变大小对随机森林特征重要性贡献最大。
核心结论
- 在类别不平衡数据集中,仅用准确率可能掩盖临床相关失败。
- 阈值调整可提高不利愈合检出,但代价是假阳性警报增加。
- 这些内部评估结果属初步发现,临床使用前需外部验证。
研究设计与样本
- 回顾性研究纳入276例由牙髓专科医生完成的单牙初次非手术根管治疗。
- 临床-影像学结局在12-18个月后判定。
- 开发逻辑回归、随机森林和径向基支持向量机模型,采用分层80/20训练-测试拆分和分层5折交叉验证。
- 类别不平衡通过随机过采样和合成少数类过采样仅应用于训练数据。
- 以不利愈合为正类,评估ROC-AUC和不利愈合的精确率-召回率曲线下面积(PR-AUC_UNF)。
主要发现
- 不利愈合发生率为18.8%。
- 多数类基线准确率达80.4%,但不利愈合敏感性为0%。
- 默认阈值下随机森林区分度最高(PR-AUC_UNF=0.359;ROC-AUC=0.724),敏感性仅27.3%。
- 经不平衡处理,SVM-RBF的PR-AUC_UNF最高达0.535,敏感性最高达54.5%。
- 阈值调整后敏感性增至90.9%,但特异性降至48.9%,阳性预测值降至30.3%。
关键数值与推荐
- 不利愈合定义为根尖周愈合分类为不利(UNF)。
- 性能评估采用ROC-AUC和PR-AUC_UNF,并探索阈值调整的不利愈合警报策略。
临床怎么用
- 临床应用中需注意仅用准确率可能低估失败风险。
- 阈值调整可提高失败检出,但需权衡假阳性警报的增加。
- 当前模型属初步内部评估,临床使用前需外部验证。
局限性
- 研究为回顾性设计。
- 模型仅进行内部评估,未进行外部验证。
- 样本量有限(276例治疗)。
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 train and internally evaluate machine learning models to classify periapical healing as favorable (FAV) or unfavorable (UNF) after primary nonsurgical endodontic treatment, emphasizing failure-oriented evaluation. METHODS: This retrospective study included 276 single-tooth treatments performed by endodontists, with clinical-radiographic outcomes adjudicated after 12-18 months. Logistic regression, random forest (RF), and radial-basis-function support vector machine (SVM-RBF) models were developed using Scikit-learn pipelines. Validation used a stratified 80/20 train-test split and stratified 5-fold cross-validation. Class imbalance was addressed by random oversampling and synthetic minority oversampling applied only to training data. UNF healing was the positive class. Performance was assessed using ROC-AUC and precision-recall area under the curve for UNF healing (PR-AUC_UNF); a threshold-adjusted UNF-alert strategy was explored. RESULTS: UNF healing occurred in 18.8% of cases. A majority-class baseline achieved 80.4% accuracy but 0% UNF sensitivity. At default thresholds, RF showed the highest discrimination (PR-AUC_UNF = 0.359; ROC-AUC = 0.724) but only 27.3% sensitivity. With imbalance handling, SVM-RBF achieved PR-AUC_UNF up to 0.535 and sensitivity up to 54.5%. Threshold adjustment increased sensitivity to 90.9% while reducing specificity to 48.9% and positive predictive value to 30.3%. Tooth type and baseline lesion size had the highest aggregated RF feature-importance scores. CONCLUSIONS: Accuracy alone may obscure clinically relevant failures in imbalanced datasets. Threshold adjustment increased UNF detection at the cost of false-positive alerts. These internally evaluated findings are preliminary and require external validation before clinical use.
引用
- Dufey-Portilla N, Peña-Bengoa F, Abarca J, et al. Machine Learning Models for Predicting Periapical Healing after Primary Nonsurgical Endodontic Treatment. J Endod. 2026. PMID: 42946040. doi:10.1016/j.joen.2026.10.007
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。