文献速递牙周病

系统比较机器学习算法以开发并验证牙周炎预测模型

Systematic comparison of machine learning algorithms to develop and validate predictive models for periodontitis.
PubMed 文献 · J Clin Periodontol · 2022-07-28

本研究利用台湾(n=3453)与美国(n=3685)全国调查数据,训练10种机器学习算法构建牙周炎预测模型,并进行内部(bootstrap抽样)与外部(另一国家数据集)验证。结果显示内部验证中许多算法表现极强(AUC>0.95,准确率>95%),但外部验证中所有算法预测性能急剧下降。结论认为机器学习需更大样本量和更复杂的牙周炎预测因子才能充分发挥潜力。

要点

  • 内部验证中许多算法AUC>0.95、准确率>95%,但外部验证性能急剧下降。
  • 预测性能因数据预处理方法和训练队列不同而异。
  • 机器学习需更大样本量和更复杂预测因子才能充分发挥潜力。

核心结论

  • 机器学习需更大样本量和更复杂的牙周炎预测因子才能充分发挥其潜力。

研究设计与样本

  • 利用台湾全国调查数据(n=3453)和美国数据集(n=3685),提取牙周炎预测因子并预处理,训练10种机器学习算法构建预测模型。
  • 模型进行内部验证(bootstrap抽样)和外部验证(另一国家数据集)。
  • 比较六项性能指标(AUC、准确率、敏感度、特异度、阳性预测值、阴性预测值)和两种数据预处理方法(基于机器学习的特征选择、降维为主成分)。

主要发现

  • 内部验证中许多算法表现极强(AUC>0.95,准确率>95%)。
  • 外部验证中所有算法的预测性能急剧下降,内部验证结果未能复现。
  • 预测性能因数据预处理方法和训练队列不同而异。

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

AIM: The aim of this study was to compare the validity of different machine learning algorithms to develop and validate predictive models for periodontitis. MATERIALS AND METHODS: Using national survey data from Taiwan (n = 3453) and the United States (n = 3685), predictors of periodontitis were extracted from the datasets and pre-processed, and then 10 machine learning algorithms were trained to develop predictive models. The models were validated both internally (bootstrap sampling) and externally (alternative country's dataset). The algorithms were compared across six performance metrics ([i] area under the curve for the receiver operating characteristic [AUC], [ii] accuracy, [iii] sensitivity, [iv] specificity, [v] positive predictive value, and [vi] negative predictive value) and two methods of data pre-processing ([i] machine-learning-based feature selection and [ii] dimensionality reduction into principal components). RESULTS: Many algorithms showed extremely strong performance during internal validation (AUC > 0.95, accuracy > 95%). However, this was not replicated in external validation, where predictive performance of all algorithms dropped off drastically. Furthermore, predictive performance differed according to data pre-processing methodology and the cohort on which they were trained. CONCLUSIONS: Larger sample sizes and more complex predictors of periodontitis are required before machine learning can be leveraged to its full potential.

来源:J Clin Periodontol,查看原文。版权归原作者所有。

引用

  1. Bashir NZ, Rahman Z, Chen SL, et al. Systematic comparison of machine learning algorithms to develop and validate predictive models for periodontitis. J Clin Periodontol. 2022. PMID: 35781722. doi:10.1111/jcpe.13692

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。